June 2025 - Linux-stable-mirror

FAILED: patch "[PATCH] x86/its: move its_pages array to struct mod_arch_specific" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x 0b0cae7119a0ec9449d7261b5e672a5fed765068 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062000-reveal-jury-be96@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" <rppt(a)kernel.org> Date: Tue, 3 Jun 2025 14:14:43 +0300 Subject: [PATCH] x86/its: move its_pages array to struct mod_arch_specific The of pages with ITS thunks allocated for modules are tracked by an array in 'struct module'. Since this is very architecture specific data structure, move it to 'struct mod_arch_specific'. No functional changes. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Suggested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..b50fe6ce4655 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_restore_rox(page, PAGE_SIZE); } } @@ -184,11 +184,11 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ @@ -201,14 +201,15 @@ static void *its_alloc(void) #ifdef CONFIG_MODULES if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), + struct its_array *pages = &its_mod->arch.its_pages; + void *tmp = krealloc(pages->pages, + (pages->num+1) * sizeof(void *), GFP_KERNEL); if (!tmp) return NULL; - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + pages->pages = tmp; + pages->pages[pages->num++] = page; execmem_make_temp_rw(page, PAGE_SIZE); } diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..5faa1fb1f4b4 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,11 +586,6 @@ struct module { atomic_t refcnt; #endif -#ifdef CONFIG_MITIGATION_ITS - int its_num_pages; - void **its_page_array; -#endif - #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] x86/its: move its_pages array to struct mod_arch_specific" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-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-6.12.y git checkout FETCH_HEAD git cherry-pick -x 0b0cae7119a0ec9449d7261b5e672a5fed765068 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062059-map-powdering-0ee4@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (Microsoft)" <rppt(a)kernel.org> Date: Tue, 3 Jun 2025 14:14:43 +0300 Subject: [PATCH] x86/its: move its_pages array to struct mod_arch_specific The of pages with ITS thunks allocated for modules are tracked by an array in 'struct module'. Since this is very architecture specific data structure, move it to 'struct mod_arch_specific'. No functional changes. Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches") Suggested-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Mike Rapoport (Microsoft) <rppt(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index e988bac0a4a1..3c2de4ce3b10 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -5,12 +5,20 @@ #include <asm-generic/module.h> #include <asm/orc_types.h> +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + struct mod_arch_specific { #ifdef CONFIG_UNWINDER_ORC unsigned int num_orcs; int *orc_unwind_ip; struct orc_entry *orc_unwind; #endif + struct its_array its_pages; }; #endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ecfe7b497cad..b50fe6ce4655 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod) its_page = NULL; mutex_unlock(&text_mutex); - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_restore_rox(page, PAGE_SIZE); } } @@ -184,11 +184,11 @@ void its_free_mod(struct module *mod) if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) return; - for (int i = 0; i < mod->its_num_pages; i++) { - void *page = mod->its_page_array[i]; + for (int i = 0; i < mod->arch.its_pages.num; i++) { + void *page = mod->arch.its_pages.pages[i]; execmem_free(page); } - kfree(mod->its_page_array); + kfree(mod->arch.its_pages.pages); } #endif /* CONFIG_MODULES */ @@ -201,14 +201,15 @@ static void *its_alloc(void) #ifdef CONFIG_MODULES if (its_mod) { - void *tmp = krealloc(its_mod->its_page_array, - (its_mod->its_num_pages+1) * sizeof(void *), + struct its_array *pages = &its_mod->arch.its_pages; + void *tmp = krealloc(pages->pages, + (pages->num+1) * sizeof(void *), GFP_KERNEL); if (!tmp) return NULL; - its_mod->its_page_array = tmp; - its_mod->its_page_array[its_mod->its_num_pages++] = page; + pages->pages = tmp; + pages->pages[pages->num++] = page; execmem_make_temp_rw(page, PAGE_SIZE); } diff --git a/include/linux/module.h b/include/linux/module.h index 92e1420fccdf..5faa1fb1f4b4 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,11 +586,6 @@ struct module { atomic_t refcnt; #endif -#ifdef CONFIG_MITIGATION_ITS - int its_num_pages; - void **its_page_array; -#endif - #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" 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 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062029-saturday-conical-0eae@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" 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 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062028-richly-basket-a70f@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" 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 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062027-tapestry-uptake-5f29@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" 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 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062026-shrewdly-trough-b30e@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm: close theoretical race where stale TLB entries could" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x 383c4613c67c26e90e8eebb72e3083457d02033f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062025-boogieman-flyable-ee70@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001 From: Ryan Roberts <ryan.roberts(a)arm.com> Date: Fri, 6 Jun 2025 10:28:07 +0100 Subject: [PATCH] mm: close theoretical race where stale TLB entries could linger Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") described a theoretical race as such: """ Nadav Amit identified a theoretical race between page reclaim and mprotect due to TLB flushes being batched outside of the PTL being held. He described the race as follows: CPU0 CPU1 ---- ---- user accesses memory using RW PTE [PTE now cached in TLB] try_to_unmap_one() ==> ptep_get_and_clear() ==> set_tlb_ubc_flush_pending() mprotect(addr, PROT_READ) ==> change_pte_range() ==> [ PTE non-present - no flush ] user writes using cached RW PTE ... try_to_unmap_flush() The same type of race exists for reads when protecting for PROT_NONE and also exists for operations that can leave an old TLB entry behind such as munmap, mremap and madvise. """ The solution was to introduce flush_tlb_batched_pending() and call it under the PTL from mprotect/madvise/munmap/mremap to complete any pending tlb flushes. However, while madvise_free_pte_range() and madvise_cold_or_pageout_pte_range() were both retro-fitted to call flush_tlb_batched_pending() immediately after initially acquiring the PTL, they both temporarily release the PTL to split a large folio if they stumble upon one. In this case, where re-acquiring the PTL flush_tlb_batched_pending() must be called again, but it previously was not. Let's fix that. There are 2 Fixes: tags here: the first is the commit that fixed madvise_free_pte_range(). The second is the commit that added madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the faulty pattern from madvise_free_pte_range(). This is a theoretical bug discovered during code review. Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries") Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD") Signed-off-by: Ryan Roberts <ryan.roberts(a)arm.com> Reviewed-by: Jann Horn <jannh(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mel Gorman <mgorman <mgorman(a)suse.de> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/madvise.c b/mm/madvise.c index 5f7a66a1617e..1d44a35ae85c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -508,6 +508,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0; @@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, start_pte = pte; if (!start_pte) break; + flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); if (!err) nr = 0;

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] net_sched: sch_sfq: reject invalid perturb period" 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 7ca52541c05c832d32b112274f81a985101f9ba8 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062026-stinger-coeditor-bb58@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7ca52541c05c832d32b112274f81a985101f9ba8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet(a)google.com> Date: Wed, 11 Jun 2025 08:35:01 +0000 Subject: [PATCH] net_sched: sch_sfq: reject invalid perturb period Gerrard Tai reported that SFQ perturb_period has no range check yet, and this can be used to trigger a race condition fixed in a separate patch. We want to make sure ctl->perturb_period * HZ will not overflow and is positive. Tested: tc qd add dev lo root sfq perturb -10 # negative value : error Error: sch_sfq: invalid perturb period. tc qd add dev lo root sfq perturb 1000000000 # too big : error Error: sch_sfq: invalid perturb period. tc qd add dev lo root sfq perturb 2000000 # acceptable value tc -s -d qd sh dev lo qdisc sfq 8005: root refcnt 2 limit 127p quantum 64Kb depth 127 flows 128 divisor 1024 perturb 2000000sec Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Gerrard Tai <gerrard.tai(a)starlabs.sg> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: stable(a)vger.kernel.org Link: https://patch.msgid.link/20250611083501.1810459-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 77fa02f2bfcd..a8cca549b5a2 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -656,6 +656,14 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); return -EINVAL; } + + if (ctl->perturb_period < 0 || + ctl->perturb_period > INT_MAX / HZ) { + NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); + return -EINVAL; + } + perturb_period = ctl->perturb_period * HZ; + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; @@ -672,14 +680,12 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, headdrop = q->headdrop; maxdepth = q->maxdepth; maxflows = q->maxflows; - perturb_period = q->perturb_period; quantum = q->quantum; flags = q->flags; /* update and validate configuration */ if (ctl->quantum) quantum = ctl->quantum; - perturb_period = ctl->perturb_period * HZ; if (ctl->flows) maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) {

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] net_sched: sch_sfq: reject invalid perturb period" 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 7ca52541c05c832d32b112274f81a985101f9ba8 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062026-excitable-trunks-92e6@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 7ca52541c05c832d32b112274f81a985101f9ba8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet(a)google.com> Date: Wed, 11 Jun 2025 08:35:01 +0000 Subject: [PATCH] net_sched: sch_sfq: reject invalid perturb period Gerrard Tai reported that SFQ perturb_period has no range check yet, and this can be used to trigger a race condition fixed in a separate patch. We want to make sure ctl->perturb_period * HZ will not overflow and is positive. Tested: tc qd add dev lo root sfq perturb -10 # negative value : error Error: sch_sfq: invalid perturb period. tc qd add dev lo root sfq perturb 1000000000 # too big : error Error: sch_sfq: invalid perturb period. tc qd add dev lo root sfq perturb 2000000 # acceptable value tc -s -d qd sh dev lo qdisc sfq 8005: root refcnt 2 limit 127p quantum 64Kb depth 127 flows 128 divisor 1024 perturb 2000000sec Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Gerrard Tai <gerrard.tai(a)starlabs.sg> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Cc: stable(a)vger.kernel.org Link: https://patch.msgid.link/20250611083501.1810459-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 77fa02f2bfcd..a8cca549b5a2 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -656,6 +656,14 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); return -EINVAL; } + + if (ctl->perturb_period < 0 || + ctl->perturb_period > INT_MAX / HZ) { + NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); + return -EINVAL; + } + perturb_period = ctl->perturb_period * HZ; + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; @@ -672,14 +680,12 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, headdrop = q->headdrop; maxdepth = q->maxdepth; maxflows = q->maxflows; - perturb_period = q->perturb_period; quantum = q->quantum; flags = q->flags; /* update and validate configuration */ if (ctl->quantum) quantum = ctl->quantum; - perturb_period = ctl->perturb_period * HZ; if (ctl->flows) maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) {

2 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] cifs: deal with the channel loading lag while picking" 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 66d590b828b1fd9fa337047ae58fe1c4c6f43609 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025062054-luminance-hacker-c550@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 66d590b828b1fd9fa337047ae58fe1c4c6f43609 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N <sprasad(a)microsoft.com> Date: Mon, 2 Jun 2025 22:37:12 +0530 Subject: [PATCH] cifs: deal with the channel loading lag while picking channels Our current approach to select a channel for sending requests is this: 1. iterate all channels to find the min and max queue depth 2. if min and max are not the same, pick the channel with min depth 3. if min and max are same, round robin, as all channels are equally loaded The problem with this approach is that there's a lag between selecting a channel and sending the request (that increases the queue depth on the channel). While these numbers will eventually catch up, there could be a skew in the channel usage, depending on the application's I/O parallelism and the server's speed of handling requests. With sufficient parallelism, this lag can artificially increase the queue depth, thereby impacting the performance negatively. This change will change the step 1 above to start the iteration from the last selected channel. This is to reduce the skew in channel usage even in the presence of this lag. Fixes: ea90708d3cf3 ("cifs: use the least loaded channel for sending requests") Cc: <stable(a)vger.kernel.org> Signed-off-by: Shyam Prasad N <sprasad(a)microsoft.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 266af17aa7d9..191783f553ce 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -1018,14 +1018,16 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) uint index = 0; unsigned int min_in_flight = UINT_MAX, max_in_flight = 0; struct TCP_Server_Info *server = NULL; - int i; + int i, start, cur; if (!ses) return NULL; spin_lock(&ses->chan_lock); + start = atomic_inc_return(&ses->chan_seq); for (i = 0; i < ses->chan_count; i++) { - server = ses->chans[i].server; + cur = (start + i) % ses->chan_count; + server = ses->chans[cur].server; if (!server || server->terminate) continue; @@ -1042,17 +1044,15 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) */ if (server->in_flight < min_in_flight) { min_in_flight = server->in_flight; - index = i; + index = cur; } if (server->in_flight > max_in_flight) max_in_flight = server->in_flight; } /* if all channels are equally loaded, fall back to round-robin */ - if (min_in_flight == max_in_flight) { - index = (uint)atomic_inc_return(&ses->chan_seq); - index %= ses->chan_count; - } + if (min_in_flight == max_in_flight) + index = (uint)start % ses->chan_count; server = ses->chans[index].server; spin_unlock(&ses->chan_lock);

2 months, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025