September 2025 - Linux-stable-mirror

[merged mm-hotfixes-stable] mm-revert-mm-gup-clear-the-lru-flag-of-a-page-before-adding-to-lru-batch.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: revert "mm/gup: clear the LRU flag of a page before adding to LRU batch" has been removed from the -mm tree. Its filename was mm-revert-mm-gup-clear-the-lru-flag-of-a-page-before-adding-to-lru-batch.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Hugh Dickins <hughd(a)google.com> Subject: mm: revert "mm/gup: clear the LRU flag of a page before adding to LRU batch" Date: Mon, 8 Sep 2025 15:19:17 -0700 (PDT) This reverts commit 33dfe9204f29: now that collect_longterm_unpinnable_folios() is checking ref_count instead of lru, and mlock/munlock do not participate in the revised LRU flag clearing, those changes are misleading, and enlarge the window during which mlock/munlock may miss an mlock_count update. It is possible (I'd hesitate to claim probable) that the greater likelihood of missed mlock_count updates would explain the "Realtime threads delayed due to kcompactd0" observed on 6.12 in the Link below. If that is the case, this reversion will help; but a complete solution needs also a further patch, beyond the scope of this series. Included some 80-column cleanup around folio_batch_add_and_move(). The role of folio_test_clear_lru() (before taking per-memcg lru_lock) is questionable since 6.13 removed mem_cgroup_move_account() etc; but perhaps there are still some races which need it - not examined here. Link: https://lore.kernel.org/linux-mm/DU0PR01MB10385345F7153F334100981888259A@DU… Link: https://lkml.kernel.org/r/05905d7b-ed14-68b1-79d8-bdec30367eba@google.com Signed-off-by: Hugh Dickins <hughd(a)google.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> --- mm/swap.c | 50 ++++++++++++++++++++++++++------------------------ 1 file changed, 26 insertions(+), 24 deletions(-) --- a/mm/swap.c~mm-revert-mm-gup-clear-the-lru-flag-of-a-page-before-adding-to-lru-batch +++ a/mm/swap.c @@ -164,6 +164,10 @@ static void folio_batch_move_lru(struct for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; + /* block memcg migration while the folio moves between lru */ + if (move_fn != lru_add && !folio_test_clear_lru(folio)) + continue; + folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); @@ -176,14 +180,10 @@ static void folio_batch_move_lru(struct } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, - struct folio *folio, move_fn_t move_fn, - bool on_lru, bool disable_irq) + struct folio *folio, move_fn_t move_fn, bool disable_irq) { unsigned long flags; - if (on_lru && !folio_test_clear_lru(folio)) - return; - folio_get(folio); if (disable_irq) @@ -191,8 +191,8 @@ static void __folio_batch_add_and_move(s else local_lock(&cpu_fbatches.lock); - if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) || - lru_cache_disabled()) + if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || + folio_test_large(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) @@ -201,13 +201,13 @@ static void __folio_batch_add_and_move(s local_unlock(&cpu_fbatches.lock); } -#define folio_batch_add_and_move(folio, op, on_lru) \ - __folio_batch_add_and_move( \ - &cpu_fbatches.op, \ - folio, \ - op, \ - on_lru, \ - offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \ +#define folio_batch_add_and_move(folio, op) \ + __folio_batch_add_and_move( \ + &cpu_fbatches.op, \ + folio, \ + op, \ + offsetof(struct cpu_fbatches, op) >= \ + offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) @@ -231,10 +231,10 @@ static void lru_move_tail(struct lruvec void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || - folio_test_unevictable(folio)) + folio_test_unevictable(folio) || !folio_test_lru(folio)) return; - folio_batch_add_and_move(folio, lru_move_tail, true); + folio_batch_add_and_move(folio, lru_move_tail); } void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file, @@ -328,10 +328,11 @@ static void folio_activate_drain(int cpu void folio_activate(struct folio *folio) { - if (folio_test_active(folio) || folio_test_unevictable(folio)) + if (folio_test_active(folio) || folio_test_unevictable(folio) || + !folio_test_lru(folio)) return; - folio_batch_add_and_move(folio, lru_activate, true); + folio_batch_add_and_move(folio, lru_activate); } #else @@ -507,7 +508,7 @@ void folio_add_lru(struct folio *folio) lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); - folio_batch_add_and_move(folio, lru_add, false); + folio_batch_add_and_move(folio, lru_add); } EXPORT_SYMBOL(folio_add_lru); @@ -685,13 +686,13 @@ void lru_add_drain_cpu(int cpu) void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() && lru_gen_clear_refs(folio)) return; - folio_batch_add_and_move(folio, lru_deactivate_file, true); + folio_batch_add_and_move(folio, lru_deactivate_file); } /* @@ -704,13 +705,13 @@ void deactivate_file_folio(struct folio */ void folio_deactivate(struct folio *folio) { - if (folio_test_unevictable(folio)) + if (folio_test_unevictable(folio) || !folio_test_lru(folio)) return; if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio)) return; - folio_batch_add_and_move(folio, lru_deactivate, true); + folio_batch_add_and_move(folio, lru_deactivate); } /** @@ -723,10 +724,11 @@ void folio_deactivate(struct folio *foli void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || + !folio_test_lru(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; - folio_batch_add_and_move(folio, lru_lazyfree, true); + folio_batch_add_and_move(folio, lru_lazyfree); } void lru_add_drain(void) _ Patches currently in -mm which might be from hughd(a)google.com are mm-lru_add_drain_all-do-local-lru_add_drain-first.patch

1 week, 1 day

1
0
0 0

[merged mm-hotfixes-stable] mm-gup-local-lru_add_drain-to-avoid-lru_add_drain_all.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/gup: local lru_add_drain() to avoid lru_add_drain_all() has been removed from the -mm tree. Its filename was mm-gup-local-lru_add_drain-to-avoid-lru_add_drain_all.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Hugh Dickins <hughd(a)google.com> Subject: mm/gup: local lru_add_drain() to avoid lru_add_drain_all() Date: Mon, 8 Sep 2025 15:16:53 -0700 (PDT) In many cases, if collect_longterm_unpinnable_folios() does need to drain the LRU cache to release a reference, the cache in question is on this same CPU, and much more efficiently drained by a preliminary local lru_add_drain(), than the later cross-CPU lru_add_drain_all(). Marked for stable, to counter the increase in lru_add_drain_all()s from "mm/gup: check ref_count instead of lru before migration". Note for clean backports: can take 6.16 commit a03db236aebf ("gup: optimize longterm pin_user_pages() for large folio") first. Link: https://lkml.kernel.org/r/66f2751f-283e-816d-9530-765db7edc465@google.com Signed-off-by: Hugh Dickins <hughd(a)google.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> --- mm/gup.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) --- a/mm/gup.c~mm-gup-local-lru_add_drain-to-avoid-lru_add_drain_all +++ a/mm/gup.c @@ -2287,8 +2287,8 @@ static unsigned long collect_longterm_un struct pages_or_folios *pofs) { unsigned long collected = 0; - bool drain_allow = true; struct folio *folio; + int drained = 0; long i = 0; for (folio = pofs_get_folio(pofs, i); folio; @@ -2307,10 +2307,17 @@ static unsigned long collect_longterm_un continue; } - if (drain_allow && folio_ref_count(folio) != - folio_expected_ref_count(folio) + 1) { + if (drained == 0 && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { + lru_add_drain(); + drained = 1; + } + if (drained == 1 && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); - drain_allow = false; + drained = 2; } if (!folio_isolate_lru(folio)) _ Patches currently in -mm which might be from hughd(a)google.com are mm-lru_add_drain_all-do-local-lru_add_drain-first.patch

1 week, 1 day

1
0
0 0

[merged mm-hotfixes-stable] mm-gup-check-ref_count-instead-of-lru-before-migration.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/gup: check ref_count instead of lru before migration has been removed from the -mm tree. Its filename was mm-gup-check-ref_count-instead-of-lru-before-migration.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Hugh Dickins <hughd(a)google.com> Subject: mm/gup: check ref_count instead of lru before migration Date: Mon, 8 Sep 2025 15:15:03 -0700 (PDT) Patch series "mm: better GUP pin lru_add_drain_all()", v2. Series of lru_add_drain_all()-related patches, arising from recent mm/gup migration report from Will Deacon. This patch (of 5): Will Deacon reports:- When taking a longterm GUP pin via pin_user_pages(), __gup_longterm_locked() tries to migrate target folios that should not be longterm pinned, for example because they reside in a CMA region or movable zone. This is done by first pinning all of the target folios anyway, collecting all of the longterm-unpinnable target folios into a list, dropping the pins that were just taken and finally handing the list off to migrate_pages() for the actual migration. It is critically important that no unexpected references are held on the folios being migrated, otherwise the migration will fail and pin_user_pages() will return -ENOMEM to its caller. Unfortunately, it is relatively easy to observe migration failures when running pKVM (which uses pin_user_pages() on crosvm's virtual address space to resolve stage-2 page faults from the guest) on a 6.15-based Pixel 6 device and this results in the VM terminating prematurely. In the failure case, 'crosvm' has called mlock(MLOCK_ONFAULT) on its mapping of guest memory prior to the pinning. Subsequently, when pin_user_pages() walks the page-table, the relevant 'pte' is not present and so the faulting logic allocates a new folio, mlocks it with mlock_folio() and maps it in the page-table. Since commit 2fbb0c10d1e8 ("mm/munlock: mlock_page() munlock_page() batch by pagevec"), mlock/munlock operations on a folio (formerly page), are deferred. For example, mlock_folio() takes an additional reference on the target folio before placing it into a per-cpu 'folio_batch' for later processing by mlock_folio_batch(), which drops the refcount once the operation is complete. Processing of the batches is coupled with the LRU batch logic and can be forcefully drained with lru_add_drain_all() but as long as a folio remains unprocessed on the batch, its refcount will be elevated. This deferred batching therefore interacts poorly with the pKVM pinning scenario as we can find ourselves in a situation where the migration code fails to migrate a folio due to the elevated refcount from the pending mlock operation. Hugh Dickins adds:- !folio_test_lru() has never been a very reliable way to tell if an lru_add_drain_all() is worth calling, to remove LRU cache references to make the folio migratable: the LRU flag may be set even while the folio is held with an extra reference in a per-CPU LRU cache. 5.18 commit 2fbb0c10d1e8 may have made it more unreliable. Then 6.11 commit 33dfe9204f29 ("mm/gup: clear the LRU flag of a page before adding to LRU batch") tried to make it reliable, by moving LRU flag clearing; but missed the mlock/munlock batches, so still unreliable as reported. And it turns out to be difficult to extend 33dfe9204f29's LRU flag clearing to the mlock/munlock batches: if they do benefit from batching, mlock/munlock cannot be so effective when easily suppressed while !LRU. Instead, switch to an expected ref_count check, which was more reliable all along: some more false positives (unhelpful drains) than before, and never a guarantee that the folio will prove migratable, but better. Note on PG_private_2: ceph and nfs are still using the deprecated PG_private_2 flag, with the aid of netfs and filemap support functions. Although it is consistently matched by an increment of folio ref_count, folio_expected_ref_count() intentionally does not recognize it, and ceph folio migration currently depends on that for PG_private_2 folios to be rejected. New references to the deprecated flag are discouraged, so do not add it into the collect_longterm_unpinnable_folios() calculation: but longterm pinning of transiently PG_private_2 ceph and nfs folios (an uncommon case) may invoke a redundant lru_add_drain_all(). And this makes easy the backport to earlier releases: up to and including 6.12, btrfs also used PG_private_2, but without a ref_count increment. Note for stable backports: requires 6.16 commit 86ebd50224c0 ("mm: add folio_expected_ref_count() for reference count calculation"). Link: https://lkml.kernel.org/r/41395944-b0e3-c3ac-d648-8ddd70451d28@google.com Link: https://lkml.kernel.org/r/bd1f314a-fca1-8f19-cac0-b936c9614557@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> Reported-by: Will Deacon <will(a)kernel.org> Closes: https://lore.kernel.org/linux-mm/20250815101858.24352-1-will@kernel.org/ Acked-by: Kiryl Shutsemau <kas(a)kernel.org> 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: 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> --- mm/gup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) --- a/mm/gup.c~mm-gup-check-ref_count-instead-of-lru-before-migration +++ a/mm/gup.c @@ -2307,7 +2307,8 @@ static unsigned long collect_longterm_un continue; } - if (!folio_test_lru(folio) && drain_allow) { + if (drain_allow && folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); drain_allow = false; } _ Patches currently in -mm which might be from hughd(a)google.com are mm-lru_add_drain_all-do-local-lru_add_drain-first.patch

1 week, 1 day

1
0
0 0

FAILED: patch "[PATCH] mm/hugetlb: add missing hugetlb_lock in" 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 21cc2b5c5062a256ae9064442d37ebbc23f5aef7 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025091332-pretzel-gating-6744@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 21cc2b5c5062a256ae9064442d37ebbc23f5aef7 Mon Sep 17 00:00:00 2001 From: Jeongjun Park <aha310510(a)gmail.com> Date: Sun, 24 Aug 2025 03:21:15 +0900 Subject: [PATCH] mm/hugetlb: add missing hugetlb_lock in __unmap_hugepage_range() When restoring a reservation for an anonymous page, we need to check to freeing a surplus. However, __unmap_hugepage_range() causes data race because it reads h->surplus_huge_pages without the protection of hugetlb_lock. And adjust_reservation is a boolean variable that indicates whether reservations for anonymous pages in each folio should be restored. Therefore, it should be initialized to false for each round of the loop. However, this variable is not initialized to false except when defining the current adjust_reservation variable. This means that once adjust_reservation is set to true even once within the loop, reservations for anonymous pages will be restored unconditionally in all subsequent rounds, regardless of the folio's state. To fix this, we need to add the missing hugetlb_lock, unlock the page_table_lock earlier so that we don't lock the hugetlb_lock inside the page_table_lock lock, and initialize adjust_reservation to false on each round within the loop. Link: https://lkml.kernel.org/r/20250823182115.1193563-1-aha310510@gmail.com Fixes: df7a6d1f6405 ("mm/hugetlb: restore the reservation if needed") Signed-off-by: Jeongjun Park <aha310510(a)gmail.com> Reported-by: syzbot+417aeb05fd190f3a6da9(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=417aeb05fd190f3a6da9 Reviewed-by: Sidhartha Kumar <sidhartha.kumar(a)oracle.com> Cc: Breno Leitao <leitao(a)debian.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 753f99b4c718..eed59cfb5d21 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5851,7 +5851,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, spinlock_t *ptl; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - bool adjust_reservation = false; + bool adjust_reservation; unsigned long last_addr_mask; bool force_flush = false; @@ -5944,6 +5944,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(folio); + spin_unlock(ptl); /* * Restore the reservation for anonymous page, otherwise the @@ -5951,14 +5952,16 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, * If there we are freeing a surplus, do not set the restore * reservation bit. */ + adjust_reservation = false; + + spin_lock_irq(&hugetlb_lock); if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(folio)) { folio_set_hugetlb_restore_reserve(folio); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } - - spin_unlock(ptl); + spin_unlock_irq(&hugetlb_lock); /* * Adjust the reservation for the region that will have the

1 week, 1 day

2
1
0 0

FAILED: patch "[PATCH] mm/vmalloc, mm/kasan: respect gfp mask in" 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 79357cd06d41d0f5a11b17d7c86176e395d10ef2 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025091303-hush-compactor-2f22@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 79357cd06d41d0f5a11b17d7c86176e395d10ef2 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" <urezki(a)gmail.com> Date: Sun, 31 Aug 2025 14:10:58 +0200 Subject: [PATCH] mm/vmalloc, mm/kasan: respect gfp mask in kasan_populate_vmalloc() kasan_populate_vmalloc() and its helpers ignore the caller's gfp_mask and always allocate memory using the hardcoded GFP_KERNEL flag. This makes them inconsistent with vmalloc(), which was recently extended to support GFP_NOFS and GFP_NOIO allocations. Page table allocations performed during shadow population also ignore the external gfp_mask. To preserve the intended semantics of GFP_NOFS and GFP_NOIO, wrap the apply_to_page_range() calls into the appropriate memalloc scope. xfs calls vmalloc with GFP_NOFS, so this bug could lead to deadlock. There was a report here https://lkml.kernel.org/r/686ea951.050a0220.385921.0016.GAE@google.com This patch: - Extends kasan_populate_vmalloc() and helpers to take gfp_mask; - Passes gfp_mask down to alloc_pages_bulk() and __get_free_page(); - Enforces GFP_NOFS/NOIO semantics with memalloc_*_save()/restore() around apply_to_page_range(); - Updates vmalloc.c and percpu allocator call sites accordingly. Link: https://lkml.kernel.org/r/20250831121058.92971-1-urezki@gmail.com Fixes: 451769ebb7e7 ("mm/vmalloc: alloc GFP_NO{FS,IO} for vmalloc") Signed-off-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com> Reported-by: syzbot+3470c9ffee63e4abafeb(a)syzkaller.appspotmail.com Reviewed-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> Cc: Baoquan He <bhe(a)redhat.com> Cc: Michal Hocko <mhocko(a)kernel.org> Cc: Alexander Potapenko <glider(a)google.com> Cc: Andrey Konovalov <andreyknvl(a)gmail.com> Cc: Dmitry Vyukov <dvyukov(a)google.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> diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 890011071f2b..fe5ce9215821 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { } #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); -int kasan_populate_vmalloc(unsigned long addr, unsigned long size); +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end, @@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } @@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start, static inline void kasan_populate_early_vm_area_shadow(void *start, unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, - unsigned long size) + unsigned long size, gfp_t gfp_mask) { return 0; } diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index e2ceebf737ef..11d472a5c4e8 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -336,13 +336,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages) } } -static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask) { unsigned long nr_populated, nr_total = nr_pages; struct page **page_array = pages; while (nr_pages) { - nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages); if (!nr_populated) { ___free_pages_bulk(page_array, nr_total - nr_pages); return -ENOMEM; @@ -354,25 +354,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages) return 0; } -static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask) { unsigned long nr_pages, nr_total = PFN_UP(end - start); struct vmalloc_populate_data data; + unsigned int flags; int ret = 0; - data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO); if (!data.pages) return -ENOMEM; while (nr_total) { nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); - ret = ___alloc_pages_bulk(data.pages, nr_pages); + ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask); if (ret) break; data.start = start; + + /* + * page tables allocations ignore external gfp mask, enforce it + * by the scope API + */ + if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + flags = memalloc_nofs_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + flags = memalloc_noio_save(); + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, kasan_populate_vmalloc_pte, &data); + + if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + memalloc_nofs_restore(flags); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + memalloc_noio_restore(flags); + ___free_pages_bulk(data.pages, nr_pages); if (ret) break; @@ -386,7 +403,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) return ret; } -int kasan_populate_vmalloc(unsigned long addr, unsigned long size) +int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask) { unsigned long shadow_start, shadow_end; int ret; @@ -415,7 +432,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = __kasan_populate_vmalloc(shadow_start, shadow_end); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask); if (ret) return ret; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6dbcdceecae1..5edd536ba9d2 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2026,6 +2026,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); + /* Only reclaim behaviour flags are relevant. */ + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; might_sleep(); /* @@ -2038,8 +2040,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, */ va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) { - gfp_mask = gfp_mask & GFP_RECLAIM_MASK; - va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); @@ -2089,7 +2089,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); - ret = kasan_populate_vmalloc(addr, size); + ret = kasan_populate_vmalloc(addr, size, gfp_mask); if (ret) { free_vmap_area(va); return ERR_PTR(ret); @@ -4826,7 +4826,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { - if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow; }

1 week, 1 day

2
2
0 0

FAILED: patch "[PATCH] mm/khugepaged: fix the address passed to notifier on testing" 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 394bfac1c7f7b701c2c93834c5761b9c9ceeebcf # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025091344-purist-tattle-13ba@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 394bfac1c7f7b701c2c93834c5761b9c9ceeebcf Mon Sep 17 00:00:00 2001 From: Wei Yang <richard.weiyang(a)gmail.com> Date: Fri, 22 Aug 2025 06:33:18 +0000 Subject: [PATCH] mm/khugepaged: fix the address passed to notifier on testing young Commit 8ee53820edfd ("thp: mmu_notifier_test_young") introduced mmu_notifier_test_young(), but we are passing the wrong address. In xxx_scan_pmd(), the actual iteration address is "_address" not "address". We seem to misuse the variable on the very beginning. Change it to the right one. [akpm(a)linux-foundation.org fix whitespace, per everyone] Link: https://lkml.kernel.org/r/20250822063318.11644-1-richard.weiyang@gmail.com Fixes: 8ee53820edfd ("thp: mmu_notifier_test_young") Signed-off-by: Wei Yang <richard.weiyang(a)gmail.com> Reviewed-by: Dev Jain <dev.jain(a)arm.com> Reviewed-by: Zi Yan <ziy(a)nvidia.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Nico Pache <npache(a)redhat.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Barry Song <baohua(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6b40bdfd224c..b486c1d19b2d 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1417,8 +1417,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || - folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, - address))) + folio_test_referenced(folio) || + mmu_notifier_test_young(vma->vm_mm, _address))) referenced++; } if (!writable) {

1 week, 1 day

2
2
0 0

[tip: core/rseq] rseq: Protect event mask against membarrier IPI

by tip-bot2 for Thomas Gleixner

The following commit has been merged into the core/rseq branch of tip: Commit-ID: 6eb350a2233100a283f882c023e5ad426d0ed63b Gitweb: https://git.kernel.org/tip/6eb350a2233100a283f882c023e5ad426d0ed63b Author: Thomas Gleixner <tglx(a)linutronix.de> AuthorDate: Wed, 13 Aug 2025 17:02:30 +02:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Sat, 13 Sep 2025 19:51:59 +02:00 rseq: Protect event mask against membarrier IPI rseq_need_restart() reads and clears task::rseq_event_mask with preemption disabled to guard against the scheduler. But membarrier() uses an IPI and sets the PREEMPT bit in the event mask from the IPI, which leaves that RMW operation unprotected. Use guard(irq) if CONFIG_MEMBARRIER is enabled to fix that. Fixes: 2a36ab717e8f ("rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ") Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Boqun Feng <boqun.feng(a)gmail.com> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: stable(a)vger.kernel.org --- include/linux/rseq.h | 11 ++++++++--- kernel/rseq.c | 10 +++++----- 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/include/linux/rseq.h b/include/linux/rseq.h index bc8af3e..1fbeb61 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -7,6 +7,12 @@ #include <linux/preempt.h> #include <linux/sched.h> +#ifdef CONFIG_MEMBARRIER +# define RSEQ_EVENT_GUARD irq +#else +# define RSEQ_EVENT_GUARD preempt +#endif + /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. @@ -41,9 +47,8 @@ static inline void rseq_handle_notify_resume(struct ksignal *ksig, static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - preempt_disable(); - __set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask); - preempt_enable(); + scoped_guard(RSEQ_EVENT_GUARD) + __set_bit(RSEQ_EVENT_SIGNAL_BIT, &current->rseq_event_mask); rseq_handle_notify_resume(ksig, regs); } diff --git a/kernel/rseq.c b/kernel/rseq.c index b7a1ec3..2452b73 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -342,12 +342,12 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags) /* * Load and clear event mask atomically with respect to - * scheduler preemption. + * scheduler preemption and membarrier IPIs. */ - preempt_disable(); - event_mask = t->rseq_event_mask; - t->rseq_event_mask = 0; - preempt_enable(); + scoped_guard(RSEQ_EVENT_GUARD) { + event_mask = t->rseq_event_mask; + t->rseq_event_mask = 0; + } return !!event_mask; }

1 week, 1 day

1
0
0 0

[tip: core/rseq] rseq/selftests: Use weak symbol reference, not definition, to link with glibc

by tip-bot2 for Sean Christopherson

The following commit has been merged into the core/rseq branch of tip: Commit-ID: a001cd248ab244633c5fabe4f7c707e13fc1d1cc Gitweb: https://git.kernel.org/tip/a001cd248ab244633c5fabe4f7c707e13fc1d1cc Author: Sean Christopherson <seanjc(a)google.com> AuthorDate: Tue, 19 Aug 2025 15:29:44 -07:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Sat, 13 Sep 2025 19:51:59 +02:00 rseq/selftests: Use weak symbol reference, not definition, to link with glibc Add "extern" to the glibc-defined weak rseq symbols to convert the rseq selftest's usage from weak symbol definitions to weak symbol _references_. Effectively re-defining the glibc symbols wreaks havoc when building with -fno-common, e.g. generates segfaults when running multi-threaded programs, as dynamically linked applications end up with multiple versions of the symbols. Building with -fcommon, which until recently has the been the default for GCC and clang, papers over the bug by allowing the linker to resolve the weak/tentative definition to glibc's "real" definition. Note, the symbol itself (or rather its address), not the value of the symbol, is set to 0/NULL for unresolved weak symbol references, as the symbol doesn't exist and thus can't have a value. Check for a NULL rseq size pointer to handle the scenario where the test is statically linked against a libc that doesn't support rseq in any capacity. Fixes: 3bcbc20942db ("selftests/rseq: Play nice with binaries statically linked against glibc 2.35+") Reported-by: Thomas Gleixner <tglx(a)linutronix.de> Suggested-by: Florian Weimer <fweimer(a)redhat.com> Signed-off-by: Sean Christopherson <seanjc(a)google.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: stable(a)vger.kernel.org Closes: https://lore.kernel.org/all/87frdoybk4.ffs@tglx --- tools/testing/selftests/rseq/rseq.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 663a9ce..dcac5cb 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -40,9 +40,9 @@ * Define weak versions to play nice with binaries that are statically linked * against a libc that doesn't support registering its own rseq. */ -__weak ptrdiff_t __rseq_offset; -__weak unsigned int __rseq_size; -__weak unsigned int __rseq_flags; +extern __weak ptrdiff_t __rseq_offset; +extern __weak unsigned int __rseq_size; +extern __weak unsigned int __rseq_flags; static const ptrdiff_t *libc_rseq_offset_p = &__rseq_offset; static const unsigned int *libc_rseq_size_p = &__rseq_size; @@ -209,7 +209,7 @@ void rseq_init(void) * libc not having registered a restartable sequence. Try to find the * symbols if that's the case. */ - if (!*libc_rseq_size_p) { + if (!libc_rseq_size_p || !*libc_rseq_size_p) { libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");

1 week, 1 day

1
0
0 0

FAILED: patch "[PATCH] mtd: spinand: winbond: Fix oob_layout for W25N01JW" 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 4550d33e18112a11a740424c4eec063cd58e918c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025091343-refund-bullseye-601a@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 4550d33e18112a11a740424c4eec063cd58e918c Mon Sep 17 00:00:00 2001 From: Santhosh Kumar K <s-k6(a)ti.com> Date: Thu, 4 Sep 2025 18:47:41 +0530 Subject: [PATCH] mtd: spinand: winbond: Fix oob_layout for W25N01JW Fix the W25N01JW's oob_layout according to the datasheet [1] [1] https://www.winbond.com/hq/product/code-storage-flash-memory/qspinand-flash… Fixes: 6a804fb72de5 ("mtd: spinand: winbond: add support for serial NAND flash") Cc: Sridharan S N <quic_sridsn(a)quicinc.com> Cc: stable(a)vger.kernel.org Signed-off-by: Santhosh Kumar K <s-k6(a)ti.com> Signed-off-by: Miquel Raynal <miquel.raynal(a)bootlin.com> diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 87053389a1fc..4870b2d5edb2 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -176,6 +176,36 @@ static const struct mtd_ooblayout_ops w25n02kv_ooblayout = { .free = w25n02kv_ooblayout_free, }; +static int w25n01jw_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section) + 12; + region->length = 4; + + return 0; +} + +static int w25n01jw_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section); + region->length = 12; + + /* Extract BBM */ + if (!section) { + region->offset += 2; + region->length -= 2; + } + + return 0; +} + static int w35n01jw_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *region) { @@ -206,6 +236,11 @@ static int w35n01jw_ooblayout_free(struct mtd_info *mtd, int section, return 0; } +static const struct mtd_ooblayout_ops w25n01jw_ooblayout = { + .ecc = w25n01jw_ooblayout_ecc, + .free = w25n01jw_ooblayout_free, +}; + static const struct mtd_ooblayout_ops w35n01jw_ooblayout = { .ecc = w35n01jw_ooblayout_ecc, .free = w35n01jw_ooblayout_free, @@ -394,7 +429,7 @@ static const struct spinand_info winbond_spinand_table[] = { &write_cache_variants, &update_cache_variants), 0, - SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL), + SPINAND_ECCINFO(&w25n01jw_ooblayout, NULL), SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)), SPINAND_INFO("W25N01KV", /* 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xae, 0x21),

1 week, 1 day

2
1
0 0

FAILED: patch "[PATCH] btrfs: fix corruption reading compressed range when block" 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 9786531399a679fc2f4630d2c0a186205282ab2f # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025091345-gloater-dolly-54a5@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 9786531399a679fc2f4630d2c0a186205282ab2f Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Fri, 22 Aug 2025 16:06:13 +0930 Subject: [PATCH] btrfs: fix corruption reading compressed range when block size is smaller than page size [BUG] With 64K page size (aarch64 with 64K page size config) and 4K btrfs block size, the following workload can easily lead to a corrupted read: mkfs.btrfs -f -s 4k $dev > /dev/null mount -o compress $dev $mnt xfs_io -f -c "pwrite -S 0xff 0 64k" $mnt/base > /dev/null echo "correct result:" od -Ad -t x1 $mnt/base xfs_io -f -c "reflink $mnt/base 32k 0 32k" \ -c "reflink $mnt/base 0 32k 32k" \ -c "pwrite -S 0xff 60k 4k" $mnt/new > /dev/null echo "incorrect result:" od -Ad -t x1 $mnt/new umount $mnt This shows the following result: correct result: 0000000 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff * 0065536 incorrect result: 0000000 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff * 0032768 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 * 0061440 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff * 0065536 Notice the zero in the range [32K, 60K), which is incorrect. [CAUSE] With extra trace printk, it shows the following events during od: (some unrelated info removed like CPU and context) od-3457 btrfs_do_readpage: enter r/i=5/258 folio=0(65536) prev_em_start=0000000000000000 The "r/i" is indicating the root and inode number. In our case the file "new" is using ino 258 from fs tree (root 5). Here notice the @prev_em_start pointer is NULL. This means the btrfs_do_readpage() is called from btrfs_read_folio(), not from btrfs_readahead(). od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=0 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=4096 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=8192 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=12288 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=16384 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=20480 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=24576 got em start=0 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=28672 got em start=0 len=32768 These above 32K blocks will be read from the first half of the compressed data extent. od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=32768 got em start=32768 len=32768 Note here there is no btrfs_submit_compressed_read() call. Which is incorrect now. Although both extent maps at 0 and 32K are pointing to the same compressed data, their offsets are different thus can not be merged into the same read. So this means the compressed data read merge check is doing something wrong. od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=36864 got em start=32768 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=40960 got em start=32768 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=45056 got em start=32768 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=49152 got em start=32768 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=53248 got em start=32768 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=57344 got em start=32768 len=32768 od-3457 btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=61440 skip uptodate od-3457 btrfs_submit_compressed_read: cb orig_bio: file off=0 len=61440 The function btrfs_submit_compressed_read() is only called at the end of folio read. The compressed bio will only have an extent map of range [0, 32K), but the original bio passed in is for the whole 64K folio. This will cause the decompression part to only fill the first 32K, leaving the rest untouched (aka, filled with zero). This incorrect compressed read merge leads to the above data corruption. There were similar problems that happened in the past, commit 808f80b46790 ("Btrfs: update fix for read corruption of compressed and shared extents") is doing pretty much the same fix for readahead. But that's back to 2015, where btrfs still only supports bs (block size) == ps (page size) cases. This means btrfs_do_readpage() only needs to handle a folio which contains exactly one block. Only btrfs_readahead() can lead to a read covering multiple blocks. Thus only btrfs_readahead() passes a non-NULL @prev_em_start pointer. With v5.15 kernel btrfs introduced bs < ps support. This breaks the above assumption that a folio can only contain one block. Now btrfs_read_folio() can also read multiple blocks in one go. But btrfs_read_folio() doesn't pass a @prev_em_start pointer, thus the existing bio force submission check will never be triggered. In theory, this can also happen for btrfs with large folios, but since large folio is still experimental, we don't need to bother it, thus only bs < ps support is affected for now. [FIX] Instead of passing @prev_em_start to do the proper compressed extent check, introduce one new member, btrfs_bio_ctrl::last_em_start, so that the existing bio force submission logic will always be triggered. CC: stable(a)vger.kernel.org # 5.15+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c953297aa89a..b21cb72835cc 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -111,6 +111,24 @@ struct btrfs_bio_ctrl { */ unsigned long submit_bitmap; struct readahead_control *ractl; + + /* + * The start offset of the last used extent map by a read operation. + * + * This is for proper compressed read merge. + * U64_MAX means we are starting the read and have made no progress yet. + * + * The current btrfs_bio_is_contig() only uses disk_bytenr as + * the condition to check if the read can be merged with previous + * bio, which is not correct. E.g. two file extents pointing to the + * same extent but with different offset. + * + * So here we need to do extra checks to only merge reads that are + * covered by the same extent map. + * Just extent_map::start will be enough, as they are unique + * inside the same inode. + */ + u64 last_em_start; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) @@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl, * return 0 on success, otherwise return error */ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) + struct btrfs_bio_ctrl *bio_ctrl) { struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); @@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, * non-optimal behavior (submitting 2 bios for the same extent). */ if (compress_type != BTRFS_COMPRESS_NONE && - prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->start) + bio_ctrl->last_em_start != U64_MAX && + bio_ctrl->last_em_start != em->start) force_bio_submit = true; - if (prev_em_start) - *prev_em_start = em->start; + bio_ctrl->last_em_start = em->start; btrfs_free_extent_map(em); em = NULL; @@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio) const u64 start = folio_pos(folio); const u64 end = start + folio_size(folio) - 1; struct extent_state *cached_state = NULL; - struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; + struct btrfs_bio_ctrl bio_ctrl = { + .opf = REQ_OP_READ, + .last_em_start = U64_MAX, + }; struct extent_map *em_cached = NULL; int ret; lock_extents_for_read(inode, start, end, &cached_state); - ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL); + ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); btrfs_free_extent_map(em_cached); @@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD, - .ractl = rac + .ractl = rac, + .last_em_start = U64_MAX, }; struct folio *folio; struct btrfs_inode *inode = BTRFS_I(rac->mapping->host); @@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac) const u64 end = start + readahead_length(rac) - 1; struct extent_state *cached_state = NULL; struct extent_map *em_cached = NULL; - u64 prev_em_start = (u64)-1; lock_extents_for_read(inode, start, end, &cached_state); while ((folio = readahead_folio(rac)) != NULL) - btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start); + btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);

1 week, 1 day

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2025