September 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] x86/sev: Guard sev_evict_cache() with CONFIG_AMD_MEM_ENCRYPT" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-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-6.1.y git checkout FETCH_HEAD git cherry-pick -x 7f830e126dc357fc086905ce9730140fd4528d66 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092126-fabulous-despair-ac21@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7f830e126dc357fc086905ce9730140fd4528d66 Mon Sep 17 00:00:00 2001 From: Tom Lendacky <thomas.lendacky(a)amd.com> Date: Mon, 15 Sep 2025 11:04:12 -0500 Subject: [PATCH] x86/sev: Guard sev_evict_cache() with CONFIG_AMD_MEM_ENCRYPT The sev_evict_cache() is guest-related code and should be guarded by CONFIG_AMD_MEM_ENCRYPT, not CONFIG_KVM_AMD_SEV. CONFIG_AMD_MEM_ENCRYPT=y is required for a guest to run properly as an SEV-SNP guest, but a guest kernel built with CONFIG_KVM_AMD_SEV=n would get the stub function of sev_evict_cache() instead of the version that performs the actual eviction. Move the function declarations under the appropriate #ifdef. Fixes: 7b306dfa326f ("x86/sev: Evict cache lines during SNP memory validation") Signed-off-by: Tom Lendacky <thomas.lendacky(a)amd.com> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: stable(a)kernel.org # 6.16.x Link: https://lore.kernel.org/r/70e38f2c4a549063de54052c9f64929705313526.17577089… diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 02236962fdb1..465b19fd1a2d 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -562,6 +562,24 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, extern struct ghcb *boot_ghcb; +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define snp_vmpl 0 @@ -605,6 +623,7 @@ static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, static inline int snp_svsm_vtpm_send_command(u8 *buffer) { return -ENODEV; } static inline void __init snp_secure_tsc_prepare(void) { } static inline void __init snp_secure_tsc_init(void) { } +static inline void sev_evict_cache(void *va, int npages) {} #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -619,24 +638,6 @@ int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); void snp_fixup_e820_tables(void); - -static inline void sev_evict_cache(void *va, int npages) -{ - volatile u8 val __always_unused; - u8 *bytes = va; - int page_idx; - - /* - * For SEV guests, a read from the first/last cache-lines of a 4K page - * using the guest key is sufficient to cause a flush of all cache-lines - * associated with that 4K page without incurring all the overhead of a - * full CLFLUSH sequence. - */ - for (page_idx = 0; page_idx < npages; page_idx++) { - val = bytes[page_idx * PAGE_SIZE]; - val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; - } -} #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_rmptable_init(void) { return -ENOSYS; } @@ -652,7 +653,6 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } static inline void snp_fixup_e820_tables(void) {} -static inline void sev_evict_cache(void *va, int npages) {} #endif #endif

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] btrfs: tree-checker: fix the incorrect inode ref size check" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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-5.4.y git checkout FETCH_HEAD git cherry-pick -x 96fa515e70f3e4b98685ef8cac9d737fc62f10e1 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092135-breeding-chrome-585a@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 96fa515e70f3e4b98685ef8cac9d737fc62f10e1 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Tue, 16 Sep 2025 07:54:06 +0930 Subject: [PATCH] btrfs: tree-checker: fix the incorrect inode ref size check [BUG] Inside check_inode_ref(), we need to make sure every structure, including the btrfs_inode_extref header, is covered by the item. But our code is incorrectly using "sizeof(iref)", where @iref is just a pointer. This means "sizeof(iref)" will always be "sizeof(void *)", which is much smaller than "sizeof(struct btrfs_inode_extref)". This will allow some bad inode extrefs to sneak in, defeating tree-checker. [FIX] Fix the typo by calling "sizeof(*iref)", which is the same as "sizeof(struct btrfs_inode_extref)", and will be the correct behavior we want. Fixes: 71bf92a9b877 ("btrfs: tree-checker: Add check for INODE_REF") CC: stable(a)vger.kernel.org # 6.1+ Reviewed-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 0f556f4de3f9..a997c7cc35a2 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1756,10 +1756,10 @@ static int check_inode_ref(struct extent_buffer *leaf, while (ptr < end) { u16 namelen; - if (unlikely(ptr + sizeof(iref) > end)) { + if (unlikely(ptr + sizeof(*iref) > end)) { inode_ref_err(leaf, slot, "inode ref overflow, ptr %lu end %lu inode_ref_size %zu", - ptr, end, sizeof(iref)); + ptr, end, sizeof(*iref)); return -EUCLEAN; }

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] iommu/amd/pgtbl: Fix possible race while increase page table" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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-5.4.y git checkout FETCH_HEAD git cherry-pick -x 1e56310b40fd2e7e0b9493da9ff488af145bdd0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092105-gawk-armful-317b@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1e56310b40fd2e7e0b9493da9ff488af145bdd0c Mon Sep 17 00:00:00 2001 From: Vasant Hegde <vasant.hegde(a)amd.com> Date: Sat, 13 Sep 2025 06:26:57 +0000 Subject: [PATCH] iommu/amd/pgtbl: Fix possible race while increase page table level The AMD IOMMU host page table implementation supports dynamic page table levels (up to 6 levels), starting with a 3-level configuration that expands based on IOVA address. The kernel maintains a root pointer and current page table level to enable proper page table walks in alloc_pte()/fetch_pte() operations. The IOMMU IOVA allocator initially starts with 32-bit address and onces its exhuasted it switches to 64-bit address (max address is determined based on IOMMU and device DMA capability). To support larger IOVA, AMD IOMMU driver increases page table level. But in unmap path (iommu_v1_unmap_pages()), fetch_pte() reads pgtable->[root/mode] without lock. So its possible that in exteme corner case, when increase_address_space() is updating pgtable->[root/mode], fetch_pte() reads wrong page table level (pgtable->mode). It does compare the value with level encoded in page table and returns NULL. This will result is iommu_unmap ops to fail and upper layer may retry/log WARN_ON. CPU 0 CPU 1 ------ ------ map pages unmap pages alloc_pte() -> increase_address_space() iommu_v1_unmap_pages() -> fetch_pte() pgtable->root = pte (new root value) READ pgtable->[mode/root] Reads new root, old mode Updates mode (pgtable->mode += 1) Since Page table level updates are infrequent and already synchronized with a spinlock, implement seqcount to enable lock-free read operations on the read path. Fixes: 754265bcab7 ("iommu/amd: Fix race in increase_address_space()") Reported-by: Alejandro Jimenez <alejandro.j.jimenez(a)oracle.com> Cc: stable(a)vger.kernel.org Cc: Joao Martins <joao.m.martins(a)oracle.com> Cc: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> Signed-off-by: Vasant Hegde <vasant.hegde(a)amd.com> Signed-off-by: Joerg Roedel <joerg.roedel(a)amd.com> diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5219d7ddfdaa..95f63c5f6159 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -555,6 +555,7 @@ struct gcr3_tbl_info { }; struct amd_io_pgtable { + seqcount_t seqcount; /* Protects root/mode update */ struct io_pgtable pgtbl; int mode; u64 *root; diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index a91e71f981ef..70c2f5b1631b 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> +#include <linux/seqlock.h> #include <asm/barrier.h> @@ -130,8 +131,11 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, *pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root)); + write_seqcount_begin(&pgtable->seqcount); pgtable->root = pte; pgtable->mode += 1; + write_seqcount_end(&pgtable->seqcount); + amd_iommu_update_and_flush_device_table(domain); pte = NULL; @@ -153,6 +157,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, { unsigned long last_addr = address + (page_size - 1); struct io_pgtable_cfg *cfg = &pgtable->pgtbl.cfg; + unsigned int seqcount; int level, end_lvl; u64 *pte, *page; @@ -170,8 +175,14 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, } - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + + address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -249,6 +260,7 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, unsigned long *page_size) { int level; + unsigned int seqcount; u64 *pte; *page_size = 0; @@ -256,8 +268,12 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, if (address > PM_LEVEL_SIZE(pgtable->mode)) return NULL; - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -541,6 +557,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; + seqcount_init(&pgtable->seqcount); cfg->pgsize_bitmap = amd_iommu_pgsize_bitmap; cfg->ias = IOMMU_IN_ADDR_BIT_SIZE;

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] iommu/amd/pgtbl: Fix possible race while increase page table" 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 1e56310b40fd2e7e0b9493da9ff488af145bdd0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092104-flashcard-deepness-5002@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1e56310b40fd2e7e0b9493da9ff488af145bdd0c Mon Sep 17 00:00:00 2001 From: Vasant Hegde <vasant.hegde(a)amd.com> Date: Sat, 13 Sep 2025 06:26:57 +0000 Subject: [PATCH] iommu/amd/pgtbl: Fix possible race while increase page table level The AMD IOMMU host page table implementation supports dynamic page table levels (up to 6 levels), starting with a 3-level configuration that expands based on IOVA address. The kernel maintains a root pointer and current page table level to enable proper page table walks in alloc_pte()/fetch_pte() operations. The IOMMU IOVA allocator initially starts with 32-bit address and onces its exhuasted it switches to 64-bit address (max address is determined based on IOMMU and device DMA capability). To support larger IOVA, AMD IOMMU driver increases page table level. But in unmap path (iommu_v1_unmap_pages()), fetch_pte() reads pgtable->[root/mode] without lock. So its possible that in exteme corner case, when increase_address_space() is updating pgtable->[root/mode], fetch_pte() reads wrong page table level (pgtable->mode). It does compare the value with level encoded in page table and returns NULL. This will result is iommu_unmap ops to fail and upper layer may retry/log WARN_ON. CPU 0 CPU 1 ------ ------ map pages unmap pages alloc_pte() -> increase_address_space() iommu_v1_unmap_pages() -> fetch_pte() pgtable->root = pte (new root value) READ pgtable->[mode/root] Reads new root, old mode Updates mode (pgtable->mode += 1) Since Page table level updates are infrequent and already synchronized with a spinlock, implement seqcount to enable lock-free read operations on the read path. Fixes: 754265bcab7 ("iommu/amd: Fix race in increase_address_space()") Reported-by: Alejandro Jimenez <alejandro.j.jimenez(a)oracle.com> Cc: stable(a)vger.kernel.org Cc: Joao Martins <joao.m.martins(a)oracle.com> Cc: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> Signed-off-by: Vasant Hegde <vasant.hegde(a)amd.com> Signed-off-by: Joerg Roedel <joerg.roedel(a)amd.com> diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5219d7ddfdaa..95f63c5f6159 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -555,6 +555,7 @@ struct gcr3_tbl_info { }; struct amd_io_pgtable { + seqcount_t seqcount; /* Protects root/mode update */ struct io_pgtable pgtbl; int mode; u64 *root; diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index a91e71f981ef..70c2f5b1631b 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> +#include <linux/seqlock.h> #include <asm/barrier.h> @@ -130,8 +131,11 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, *pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root)); + write_seqcount_begin(&pgtable->seqcount); pgtable->root = pte; pgtable->mode += 1; + write_seqcount_end(&pgtable->seqcount); + amd_iommu_update_and_flush_device_table(domain); pte = NULL; @@ -153,6 +157,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, { unsigned long last_addr = address + (page_size - 1); struct io_pgtable_cfg *cfg = &pgtable->pgtbl.cfg; + unsigned int seqcount; int level, end_lvl; u64 *pte, *page; @@ -170,8 +175,14 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, } - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + + address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -249,6 +260,7 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, unsigned long *page_size) { int level; + unsigned int seqcount; u64 *pte; *page_size = 0; @@ -256,8 +268,12 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, if (address > PM_LEVEL_SIZE(pgtable->mode)) return NULL; - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -541,6 +557,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; + seqcount_init(&pgtable->seqcount); cfg->pgsize_bitmap = amd_iommu_pgsize_bitmap; cfg->ias = IOMMU_IN_ADDR_BIT_SIZE;

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] iommu/amd/pgtbl: Fix possible race while increase page table" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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-5.15.y git checkout FETCH_HEAD git cherry-pick -x 1e56310b40fd2e7e0b9493da9ff488af145bdd0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092103-skilled-expand-23a8@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1e56310b40fd2e7e0b9493da9ff488af145bdd0c Mon Sep 17 00:00:00 2001 From: Vasant Hegde <vasant.hegde(a)amd.com> Date: Sat, 13 Sep 2025 06:26:57 +0000 Subject: [PATCH] iommu/amd/pgtbl: Fix possible race while increase page table level The AMD IOMMU host page table implementation supports dynamic page table levels (up to 6 levels), starting with a 3-level configuration that expands based on IOVA address. The kernel maintains a root pointer and current page table level to enable proper page table walks in alloc_pte()/fetch_pte() operations. The IOMMU IOVA allocator initially starts with 32-bit address and onces its exhuasted it switches to 64-bit address (max address is determined based on IOMMU and device DMA capability). To support larger IOVA, AMD IOMMU driver increases page table level. But in unmap path (iommu_v1_unmap_pages()), fetch_pte() reads pgtable->[root/mode] without lock. So its possible that in exteme corner case, when increase_address_space() is updating pgtable->[root/mode], fetch_pte() reads wrong page table level (pgtable->mode). It does compare the value with level encoded in page table and returns NULL. This will result is iommu_unmap ops to fail and upper layer may retry/log WARN_ON. CPU 0 CPU 1 ------ ------ map pages unmap pages alloc_pte() -> increase_address_space() iommu_v1_unmap_pages() -> fetch_pte() pgtable->root = pte (new root value) READ pgtable->[mode/root] Reads new root, old mode Updates mode (pgtable->mode += 1) Since Page table level updates are infrequent and already synchronized with a spinlock, implement seqcount to enable lock-free read operations on the read path. Fixes: 754265bcab7 ("iommu/amd: Fix race in increase_address_space()") Reported-by: Alejandro Jimenez <alejandro.j.jimenez(a)oracle.com> Cc: stable(a)vger.kernel.org Cc: Joao Martins <joao.m.martins(a)oracle.com> Cc: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> Signed-off-by: Vasant Hegde <vasant.hegde(a)amd.com> Signed-off-by: Joerg Roedel <joerg.roedel(a)amd.com> diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5219d7ddfdaa..95f63c5f6159 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -555,6 +555,7 @@ struct gcr3_tbl_info { }; struct amd_io_pgtable { + seqcount_t seqcount; /* Protects root/mode update */ struct io_pgtable pgtbl; int mode; u64 *root; diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index a91e71f981ef..70c2f5b1631b 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> +#include <linux/seqlock.h> #include <asm/barrier.h> @@ -130,8 +131,11 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, *pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root)); + write_seqcount_begin(&pgtable->seqcount); pgtable->root = pte; pgtable->mode += 1; + write_seqcount_end(&pgtable->seqcount); + amd_iommu_update_and_flush_device_table(domain); pte = NULL; @@ -153,6 +157,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, { unsigned long last_addr = address + (page_size - 1); struct io_pgtable_cfg *cfg = &pgtable->pgtbl.cfg; + unsigned int seqcount; int level, end_lvl; u64 *pte, *page; @@ -170,8 +175,14 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, } - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + + address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -249,6 +260,7 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, unsigned long *page_size) { int level; + unsigned int seqcount; u64 *pte; *page_size = 0; @@ -256,8 +268,12 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, if (address > PM_LEVEL_SIZE(pgtable->mode)) return NULL; - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -541,6 +557,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; + seqcount_init(&pgtable->seqcount); cfg->pgsize_bitmap = amd_iommu_pgsize_bitmap; cfg->ias = IOMMU_IN_ADDR_BIT_SIZE;

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] iommu/amd/pgtbl: Fix possible race while increase page table" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-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-6.1.y git checkout FETCH_HEAD git cherry-pick -x 1e56310b40fd2e7e0b9493da9ff488af145bdd0c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092102-landfill-panorama-3049@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1e56310b40fd2e7e0b9493da9ff488af145bdd0c Mon Sep 17 00:00:00 2001 From: Vasant Hegde <vasant.hegde(a)amd.com> Date: Sat, 13 Sep 2025 06:26:57 +0000 Subject: [PATCH] iommu/amd/pgtbl: Fix possible race while increase page table level The AMD IOMMU host page table implementation supports dynamic page table levels (up to 6 levels), starting with a 3-level configuration that expands based on IOVA address. The kernel maintains a root pointer and current page table level to enable proper page table walks in alloc_pte()/fetch_pte() operations. The IOMMU IOVA allocator initially starts with 32-bit address and onces its exhuasted it switches to 64-bit address (max address is determined based on IOMMU and device DMA capability). To support larger IOVA, AMD IOMMU driver increases page table level. But in unmap path (iommu_v1_unmap_pages()), fetch_pte() reads pgtable->[root/mode] without lock. So its possible that in exteme corner case, when increase_address_space() is updating pgtable->[root/mode], fetch_pte() reads wrong page table level (pgtable->mode). It does compare the value with level encoded in page table and returns NULL. This will result is iommu_unmap ops to fail and upper layer may retry/log WARN_ON. CPU 0 CPU 1 ------ ------ map pages unmap pages alloc_pte() -> increase_address_space() iommu_v1_unmap_pages() -> fetch_pte() pgtable->root = pte (new root value) READ pgtable->[mode/root] Reads new root, old mode Updates mode (pgtable->mode += 1) Since Page table level updates are infrequent and already synchronized with a spinlock, implement seqcount to enable lock-free read operations on the read path. Fixes: 754265bcab7 ("iommu/amd: Fix race in increase_address_space()") Reported-by: Alejandro Jimenez <alejandro.j.jimenez(a)oracle.com> Cc: stable(a)vger.kernel.org Cc: Joao Martins <joao.m.martins(a)oracle.com> Cc: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> Signed-off-by: Vasant Hegde <vasant.hegde(a)amd.com> Signed-off-by: Joerg Roedel <joerg.roedel(a)amd.com> diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 5219d7ddfdaa..95f63c5f6159 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -555,6 +555,7 @@ struct gcr3_tbl_info { }; struct amd_io_pgtable { + seqcount_t seqcount; /* Protects root/mode update */ struct io_pgtable pgtbl; int mode; u64 *root; diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index a91e71f981ef..70c2f5b1631b 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/dma-mapping.h> +#include <linux/seqlock.h> #include <asm/barrier.h> @@ -130,8 +131,11 @@ static bool increase_address_space(struct amd_io_pgtable *pgtable, *pte = PM_LEVEL_PDE(pgtable->mode, iommu_virt_to_phys(pgtable->root)); + write_seqcount_begin(&pgtable->seqcount); pgtable->root = pte; pgtable->mode += 1; + write_seqcount_end(&pgtable->seqcount); + amd_iommu_update_and_flush_device_table(domain); pte = NULL; @@ -153,6 +157,7 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, { unsigned long last_addr = address + (page_size - 1); struct io_pgtable_cfg *cfg = &pgtable->pgtbl.cfg; + unsigned int seqcount; int level, end_lvl; u64 *pte, *page; @@ -170,8 +175,14 @@ static u64 *alloc_pte(struct amd_io_pgtable *pgtable, } - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + + address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -249,6 +260,7 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, unsigned long *page_size) { int level; + unsigned int seqcount; u64 *pte; *page_size = 0; @@ -256,8 +268,12 @@ static u64 *fetch_pte(struct amd_io_pgtable *pgtable, if (address > PM_LEVEL_SIZE(pgtable->mode)) return NULL; - level = pgtable->mode - 1; - pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + do { + seqcount = read_seqcount_begin(&pgtable->seqcount); + level = pgtable->mode - 1; + pte = &pgtable->root[PM_LEVEL_INDEX(level, address)]; + } while (read_seqcount_retry(&pgtable->seqcount, seqcount)); + *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -541,6 +557,7 @@ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (!pgtable->root) return NULL; pgtable->mode = PAGE_MODE_3_LEVEL; + seqcount_init(&pgtable->seqcount); cfg->pgsize_bitmap = amd_iommu_pgsize_bitmap; cfg->ias = IOMMU_IN_ADDR_BIT_SIZE;

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] samples/damon/prcl: avoid starting DAMON before" failed to apply to 6.16-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.16-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-6.16.y git checkout FETCH_HEAD git cherry-pick -x e6b733ca2f99e968d696c2e812c8eb8e090bf37b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092121-boned-marbles-55ea@gregkh' --subject-prefix 'PATCH 6.16.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e6b733ca2f99e968d696c2e812c8eb8e090bf37b Mon Sep 17 00:00:00 2001 From: SeongJae Park <sj(a)kernel.org> Date: Mon, 8 Sep 2025 19:22:37 -0700 Subject: [PATCH] samples/damon/prcl: avoid starting DAMON before initialization Commit 2780505ec2b4 ("samples/damon/prcl: fix boot time enable crash") is somehow incompletely applying the origin patch [1]. It is missing the part that avoids starting DAMON before module initialization. Probably a mistake during a merge has happened. Fix it by applying the missed part again. Link: https://lkml.kernel.org/r/20250909022238.2989-3-sj@kernel.org Link: https://lore.kernel.org/20250706193207.39810-3-sj@kernel.org [1] Fixes: 2780505ec2b4 ("samples/damon/prcl: fix boot time enable crash") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c index 1b839c06a612..0226652f94d5 100644 --- a/samples/damon/prcl.c +++ b/samples/damon/prcl.c @@ -137,6 +137,9 @@ static int damon_sample_prcl_enable_store( if (enabled == is_enabled) return 0; + if (!init_called) + return 0; + if (enabled) { err = damon_sample_prcl_start(); if (err)

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: folio_may_be_lru_cached() unless folio_test_large()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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-5.4.y git checkout FETCH_HEAD git cherry-pick -x 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092147-truck-ceremony-311d@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins <hughd(a)google.com> Date: Mon, 8 Sep 2025 15:23:15 -0700 Subject: [PATCH] mm: folio_may_be_lru_cached() unless folio_test_large() mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as a large folio is added: so collect_longterm_unpinnable_folios() just wastes effort when calling lru_add_drain[_all]() on a large folio. But although there is good reason not to batch up PMD-sized folios, we might well benefit from batching a small number of low-order mTHPs (though unclear how that "small number" limitation will be implemented). So ask if folio_may_be_lru_cached() rather than !folio_test_large(), to insulate those particular checks from future change. Name preferred to "folio_is_batchable" because large folios can well be put on a batch: it's just the per-CPU LRU caches, drained much later, which need care. Marked for stable, to counter the increase in lru_add_drain_all()s from "mm/gup: check ref_count instead of lru before migration". Link: https://lkml.kernel.org/r/57d2eaf8-3607-f318-e0c5-be02dce61ad0@google.com Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region") Signed-off-by: Hugh Dickins <hughd(a)google.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Keir Fraser <keirf(a)google.com> Cc: Konstantin Khlebnikov <koct9i(a)gmail.com> Cc: Li Zhe <lizhe.67(a)bytedance.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Shivank Garg <shivankg(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Wei Xu <weixugc(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: yangge <yangge1116(a)126.com> Cc: Yuanchu Xie <yuanchu(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/mm/gup.c b/mm/gup.c index b47066a54f52..0bc4d140fc07 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2307,13 +2307,13 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } - if (drained == 0 && + if (drained == 0 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain(); drained = 1; } - if (drained == 1 && + if (drained == 1 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); diff --git a/mm/mlock.c b/mm/mlock.c index a1d93ad33c6d..bb0776f5ef7c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } diff --git a/mm/swap.c b/mm/swap.c index 6ae2d5680574..b74ebe865dd9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq)

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: folio_may_be_lru_cached() unless folio_test_large()" 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 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092146-exhume-krypton-1383@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins <hughd(a)google.com> Date: Mon, 8 Sep 2025 15:23:15 -0700 Subject: [PATCH] mm: folio_may_be_lru_cached() unless folio_test_large() mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as a large folio is added: so collect_longterm_unpinnable_folios() just wastes effort when calling lru_add_drain[_all]() on a large folio. But although there is good reason not to batch up PMD-sized folios, we might well benefit from batching a small number of low-order mTHPs (though unclear how that "small number" limitation will be implemented). So ask if folio_may_be_lru_cached() rather than !folio_test_large(), to insulate those particular checks from future change. Name preferred to "folio_is_batchable" because large folios can well be put on a batch: it's just the per-CPU LRU caches, drained much later, which need care. Marked for stable, to counter the increase in lru_add_drain_all()s from "mm/gup: check ref_count instead of lru before migration". Link: https://lkml.kernel.org/r/57d2eaf8-3607-f318-e0c5-be02dce61ad0@google.com Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region") Signed-off-by: Hugh Dickins <hughd(a)google.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Keir Fraser <keirf(a)google.com> Cc: Konstantin Khlebnikov <koct9i(a)gmail.com> Cc: Li Zhe <lizhe.67(a)bytedance.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Shivank Garg <shivankg(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Wei Xu <weixugc(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: yangge <yangge1116(a)126.com> Cc: Yuanchu Xie <yuanchu(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/mm/gup.c b/mm/gup.c index b47066a54f52..0bc4d140fc07 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2307,13 +2307,13 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } - if (drained == 0 && + if (drained == 0 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain(); drained = 1; } - if (drained == 1 && + if (drained == 1 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); diff --git a/mm/mlock.c b/mm/mlock.c index a1d93ad33c6d..bb0776f5ef7c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } diff --git a/mm/swap.c b/mm/swap.c index 6ae2d5680574..b74ebe865dd9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq)

1 month, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: folio_may_be_lru_cached() unless folio_test_large()" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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-5.15.y git checkout FETCH_HEAD git cherry-pick -x 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025092145-system-superjet-a0fb@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins <hughd(a)google.com> Date: Mon, 8 Sep 2025 15:23:15 -0700 Subject: [PATCH] mm: folio_may_be_lru_cached() unless folio_test_large() mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as a large folio is added: so collect_longterm_unpinnable_folios() just wastes effort when calling lru_add_drain[_all]() on a large folio. But although there is good reason not to batch up PMD-sized folios, we might well benefit from batching a small number of low-order mTHPs (though unclear how that "small number" limitation will be implemented). So ask if folio_may_be_lru_cached() rather than !folio_test_large(), to insulate those particular checks from future change. Name preferred to "folio_is_batchable" because large folios can well be put on a batch: it's just the per-CPU LRU caches, drained much later, which need care. Marked for stable, to counter the increase in lru_add_drain_all()s from "mm/gup: check ref_count instead of lru before migration". Link: https://lkml.kernel.org/r/57d2eaf8-3607-f318-e0c5-be02dce61ad0@google.com Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region") Signed-off-by: Hugh Dickins <hughd(a)google.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Keir Fraser <keirf(a)google.com> Cc: Konstantin Khlebnikov <koct9i(a)gmail.com> Cc: Li Zhe <lizhe.67(a)bytedance.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Shivank Garg <shivankg(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Wei Xu <weixugc(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: yangge <yangge1116(a)126.com> Cc: Yuanchu Xie <yuanchu(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/mm/gup.c b/mm/gup.c index b47066a54f52..0bc4d140fc07 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2307,13 +2307,13 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } - if (drained == 0 && + if (drained == 0 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain(); drained = 1; } - if (drained == 1 && + if (drained == 1 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); diff --git a/mm/mlock.c b/mm/mlock.c index a1d93ad33c6d..bb0776f5ef7c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } diff --git a/mm/swap.c b/mm/swap.c index 6ae2d5680574..b74ebe865dd9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq)

1 month, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2025