October 2023 - Linux-stable-mirror

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" 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 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100427-urban-cognition-691b@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" 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 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100424-koala-ivory-c2e4@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" 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 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100422-twistable-umbrella-a71d@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and" 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 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100420-grafting-raft-1e1b@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 24526268f4e38c9ec0c4a30de4f37ad2a2a84e47 Mon Sep 17 00:00:00 2001 From: Yang Shi <yang(a)os.amperecomputing.com> Date: Wed, 20 Sep 2023 15:32:42 -0700 Subject: [PATCH] mm: mempolicy: keep VMA walk if both MPOL_MF_STRICT and MPOL_MF_MOVE are specified When calling mbind() with MPOL_MF_{MOVE|MOVEALL} | MPOL_MF_STRICT, kernel should attempt to migrate all existing pages, and return -EIO if there is misplaced or unmovable page. Then commit 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()") messed up the return value and didn't break VMA scan early ianymore when MPOL_MF_STRICT alone. The return value problem was fixed by commit a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"), but it broke the VMA walk early if unmovable page is met, it may cause some pages are not migrated as expected. The code should conceptually do: if (MPOL_MF_MOVE|MOVEALL) scan all vmas try to migrate the existing pages return success else if (MPOL_MF_MOVE* | MPOL_MF_STRICT) scan all vmas try to migrate the existing pages return -EIO if unmovable or migration failed else /* MPOL_MF_STRICT alone */ break early if meets unmovable and don't call mbind_range() at all else /* none of those flags */ check the ranges in test_walk, EFAULT without mbind_range() if discontig. Fixed the behavior. Link: https://lkml.kernel.org/r/20230920223242.3425775-1-yang@os.amperecomputing.… Fixes: a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified") Signed-off-by: Yang Shi <yang(a)os.amperecomputing.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Rafael Aquini <aquini(a)redhat.com> Cc: Kirill A. Shutemov <kirill(a)shutemov.name> Cc: David Rientjes <rientjes(a)google.com> Cc: <stable(a)vger.kernel.org> [4.9+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 42b5567e3773..f1b00d6ac7ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -426,6 +426,7 @@ struct queue_pages { unsigned long start; unsigned long end; struct vm_area_struct *first; + bool has_unmovable; }; /* @@ -446,9 +447,8 @@ static inline bool queue_folio_required(struct folio *folio, /* * queue_folios_pmd() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. huge zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing folio was already on a node that does not follow the * policy. @@ -479,7 +479,7 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_folio_add(folio, qp->pagelist, flags)) { - ret = 1; + qp->has_unmovable = true; goto unlock; } } else @@ -495,9 +495,8 @@ static int queue_folios_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * * queue_folios_pte_range() has three possible return values: * 0 - folios are placed on the right node or queued successfully, or - * special page is met, i.e. zero page. - * 1 - there is unmovable folio, and MPOL_MF_MOVE* & MPOL_MF_STRICT were - * specified. + * special page is met, i.e. zero page, or unmovable page is found + * but continue walking (indicated by queue_pages.has_unmovable). * -EIO - only MPOL_MF_STRICT was specified and an existing folio was already * on a node that does not follow the policy. */ @@ -508,7 +507,6 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - bool has_unmovable = false; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; @@ -538,11 +536,12 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_folio_required(folio, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - /* MPOL_MF_STRICT must be specified if we get here */ - if (!vma_migratable(vma)) { - has_unmovable = true; - break; - } + /* + * MPOL_MF_STRICT must be specified if we get here. + * Continue walking vmas due to MPOL_MF_MOVE* flags. + */ + if (!vma_migratable(vma)) + qp->has_unmovable = true; /* * Do not abort immediately since there may be @@ -550,16 +549,13 @@ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, * need migrate other LRU pages. */ if (migrate_folio_add(folio, qp->pagelist, flags)) - has_unmovable = true; + qp->has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); - if (has_unmovable) - return 1; - return addr != end ? -EIO : 0; } @@ -599,7 +595,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Detecting misplaced folio but allow migrating folios which * have been queued. */ - ret = 1; + qp->has_unmovable = true; goto unlock; } @@ -620,7 +616,7 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Failed to isolate folio but allow migrating pages * which have been queued. */ - ret = 1; + qp->has_unmovable = true; } unlock: spin_unlock(ptl); @@ -756,12 +752,15 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, .start = start, .end = end, .first = NULL, + .has_unmovable = false, }; const struct mm_walk_ops *ops = lock_vma ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); + if (qp.has_unmovable) + err = 1; if (!qp.first) /* whole range in hole */ err = -EFAULT; @@ -1358,7 +1357,7 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) + if (((ret > 0) || nr_failed) && (flags & MPOL_MF_STRICT)) err = -EIO; } else { up_out:

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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-4.14.y git checkout FETCH_HEAD git cherry-pick -x 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100409-shorten-demanding-15d2@gregkh' --subject-prefix 'PATCH 4.14.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer <Ben.Wolsieffer(a)hefring.com> Date: Thu, 14 Sep 2023 12:30:20 -0400 Subject: [PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock The no-MMU implementation of /proc/<pid>/map doesn't normally release the mmap read lock, because it uses !IS_ERR_OR_NULL(_vml) to determine whether to release the lock. Since _vml is NULL when the end of the mappings is reached, the lock is not released. Reading /proc/1/maps twice doesn't cause a hang because it only takes the read lock, which can be taken multiple times and therefore doesn't show any problem if the lock isn't released. Instead, you need to perform some operation that attempts to take the write lock after reading /proc/<pid>/maps. To actually reproduce the bug, compile the following code as 'proc_maps_bug': #include <stdio.h> #include <unistd.h> #include <sys/mman.h> int main(int argc, char *argv[]) { void *buf; sleep(1); buf = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); puts("mmap returned"); return 0; } Then, run: ./proc_maps_bug &; cat /proc/$!/maps; fg Without this patch, mmap() will hang and the command will never complete. This code was incorrectly adapted from the MMU implementation, which at the time released the lock in m_next() before returning the last entry. The MMU implementation has diverged further from the no-MMU version since then, so this patch brings their locking and error handling into sync, fixing the bug and hopefully avoiding similar issues in the future. Link: https://lkml.kernel.org/r/20230914163019.4050530-2-ben.wolsieffer@hefring.c… Fixes: 47fecca15c09 ("fs/proc/task_nommu.c: don't use priv->task->mm") Signed-off-by: Ben Wolsieffer <ben.wolsieffer(a)hefring.com> Acked-by: Oleg Nesterov <oleg(a)redhat.com> Cc: Giulio Benetti <giulio.benetti(a)benettiengineering.com> Cc: Greg Ungerer <gerg(a)uclinux.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a8ac0dd8041e..bc2e843f4810 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -192,11 +192,16 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } @@ -205,23 +210,21 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (vma) return vma; - mmap_read_unlock(mm); - mmput(mm); return NULL; } -static void m_stop(struct seq_file *m, void *_vml) +static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(_vml)) { - mmap_read_unlock(priv->mm); - mmput(priv->mm); - } - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } static void *m_next(struct seq_file *m, void *_p, loff_t *pos)

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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-4.19.y git checkout FETCH_HEAD git cherry-pick -x 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100408-swab-depict-d818@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer <Ben.Wolsieffer(a)hefring.com> Date: Thu, 14 Sep 2023 12:30:20 -0400 Subject: [PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock The no-MMU implementation of /proc/<pid>/map doesn't normally release the mmap read lock, because it uses !IS_ERR_OR_NULL(_vml) to determine whether to release the lock. Since _vml is NULL when the end of the mappings is reached, the lock is not released. Reading /proc/1/maps twice doesn't cause a hang because it only takes the read lock, which can be taken multiple times and therefore doesn't show any problem if the lock isn't released. Instead, you need to perform some operation that attempts to take the write lock after reading /proc/<pid>/maps. To actually reproduce the bug, compile the following code as 'proc_maps_bug': #include <stdio.h> #include <unistd.h> #include <sys/mman.h> int main(int argc, char *argv[]) { void *buf; sleep(1); buf = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); puts("mmap returned"); return 0; } Then, run: ./proc_maps_bug &; cat /proc/$!/maps; fg Without this patch, mmap() will hang and the command will never complete. This code was incorrectly adapted from the MMU implementation, which at the time released the lock in m_next() before returning the last entry. The MMU implementation has diverged further from the no-MMU version since then, so this patch brings their locking and error handling into sync, fixing the bug and hopefully avoiding similar issues in the future. Link: https://lkml.kernel.org/r/20230914163019.4050530-2-ben.wolsieffer@hefring.c… Fixes: 47fecca15c09 ("fs/proc/task_nommu.c: don't use priv->task->mm") Signed-off-by: Ben Wolsieffer <ben.wolsieffer(a)hefring.com> Acked-by: Oleg Nesterov <oleg(a)redhat.com> Cc: Giulio Benetti <giulio.benetti(a)benettiengineering.com> Cc: Greg Ungerer <gerg(a)uclinux.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a8ac0dd8041e..bc2e843f4810 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -192,11 +192,16 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } @@ -205,23 +210,21 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (vma) return vma; - mmap_read_unlock(mm); - mmput(mm); return NULL; } -static void m_stop(struct seq_file *m, void *_vml) +static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(_vml)) { - mmap_read_unlock(priv->mm); - mmput(priv->mm); - } - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } static void *m_next(struct seq_file *m, void *_p, loff_t *pos)

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock" 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 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100406-component-isolating-b700@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 578d7699e5c2add8c2e9549d9d75dfb56c460cb3 Mon Sep 17 00:00:00 2001 From: Ben Wolsieffer <Ben.Wolsieffer(a)hefring.com> Date: Thu, 14 Sep 2023 12:30:20 -0400 Subject: [PATCH] proc: nommu: /proc/<pid>/maps: release mmap read lock The no-MMU implementation of /proc/<pid>/map doesn't normally release the mmap read lock, because it uses !IS_ERR_OR_NULL(_vml) to determine whether to release the lock. Since _vml is NULL when the end of the mappings is reached, the lock is not released. Reading /proc/1/maps twice doesn't cause a hang because it only takes the read lock, which can be taken multiple times and therefore doesn't show any problem if the lock isn't released. Instead, you need to perform some operation that attempts to take the write lock after reading /proc/<pid>/maps. To actually reproduce the bug, compile the following code as 'proc_maps_bug': #include <stdio.h> #include <unistd.h> #include <sys/mman.h> int main(int argc, char *argv[]) { void *buf; sleep(1); buf = mmap(NULL, 4096, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); puts("mmap returned"); return 0; } Then, run: ./proc_maps_bug &; cat /proc/$!/maps; fg Without this patch, mmap() will hang and the command will never complete. This code was incorrectly adapted from the MMU implementation, which at the time released the lock in m_next() before returning the last entry. The MMU implementation has diverged further from the no-MMU version since then, so this patch brings their locking and error handling into sync, fixing the bug and hopefully avoiding similar issues in the future. Link: https://lkml.kernel.org/r/20230914163019.4050530-2-ben.wolsieffer@hefring.c… Fixes: 47fecca15c09 ("fs/proc/task_nommu.c: don't use priv->task->mm") Signed-off-by: Ben Wolsieffer <ben.wolsieffer(a)hefring.com> Acked-by: Oleg Nesterov <oleg(a)redhat.com> Cc: Giulio Benetti <giulio.benetti(a)benettiengineering.com> Cc: Greg Ungerer <gerg(a)uclinux.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index a8ac0dd8041e..bc2e843f4810 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -192,11 +192,16 @@ static void *m_start(struct seq_file *m, loff_t *pos) return ERR_PTR(-ESRCH); mm = priv->mm; - if (!mm || !mmget_not_zero(mm)) + if (!mm || !mmget_not_zero(mm)) { + put_task_struct(priv->task); + priv->task = NULL; return NULL; + } if (mmap_read_lock_killable(mm)) { mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; return ERR_PTR(-EINTR); } @@ -205,23 +210,21 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (vma) return vma; - mmap_read_unlock(mm); - mmput(mm); return NULL; } -static void m_stop(struct seq_file *m, void *_vml) +static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; + struct mm_struct *mm = priv->mm; - if (!IS_ERR_OR_NULL(_vml)) { - mmap_read_unlock(priv->mm); - mmput(priv->mm); - } - if (priv->task) { - put_task_struct(priv->task); - priv->task = NULL; - } + if (!priv->task) + return; + + mmap_read_unlock(mm); + mmput(mm); + put_task_struct(priv->task); + priv->task = NULL; } static void *m_next(struct seq_file *m, void *_p, loff_t *pos)

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] NFSv4: Fix a state manager thread deadlock regression" 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 956fd46f97d238032cb5fa4771cdaccc6e760f9a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100429-stonework-conceal-099d@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 956fd46f97d238032cb5fa4771cdaccc6e760f9a Mon Sep 17 00:00:00 2001 From: Trond Myklebust <trond.myklebust(a)hammerspace.com> Date: Sun, 24 Sep 2023 13:14:15 -0400 Subject: [PATCH] NFSv4: Fix a state manager thread deadlock regression Commit 4dc73c679114 reintroduces the deadlock that was fixed by commit aeabb3c96186 ("NFSv4: Fix a NFSv4 state manager deadlock") because it prevents the setup of new threads to handle reboot recovery, while the older recovery thread is stuck returning delegations. Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Cc: stable(a)vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker(a)Netapp.com> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3508d8238826..7016eaadf555 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10622,7 +10622,9 @@ static void nfs4_disable_swap(struct inode *inode) */ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + wake_up_var(&clp->cl_state); } static const struct inode_operations nfs4_dir_inode_operations = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0bc160fbabec..9a5d911a7edc 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *clnt = clp->cl_rpcclient; + bool swapon = false; - if (clp->cl_rpcclient->cl_shutdown) + if (clnt->cl_shutdown) return; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { - wake_up_var(&clp->cl_state); - return; + + if (atomic_read(&clnt->cl_swapper)) { + swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, + &clp->cl_state); + if (!swapon) { + wake_up_var(&clp->cl_state); + return; + } } - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) __func__, PTR_ERR(task)); if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); + if (swapon) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs4_clear_state_manager_bit(clp); - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2748,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); again: - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); - if (atomic_read(&cl->cl_swapper)) { + + if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) && + !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) { wait_var_event_interruptible(&clp->cl_state, test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)); - if (atomic_read(&cl->cl_swapper) && - test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + if (!atomic_read(&cl->cl_swapper)) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; /* Either no longer a swapper, or were signalled */ + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); } - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); if (refcount_read(&clp->cl_count) > 1 && !signalled() && test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && - !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; nfs_put_client(clp);

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] NFSv4: Fix a state manager thread deadlock regression" 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 956fd46f97d238032cb5fa4771cdaccc6e760f9a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100428-runaround-caliber-aaa3@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 956fd46f97d238032cb5fa4771cdaccc6e760f9a Mon Sep 17 00:00:00 2001 From: Trond Myklebust <trond.myklebust(a)hammerspace.com> Date: Sun, 24 Sep 2023 13:14:15 -0400 Subject: [PATCH] NFSv4: Fix a state manager thread deadlock regression Commit 4dc73c679114 reintroduces the deadlock that was fixed by commit aeabb3c96186 ("NFSv4: Fix a NFSv4 state manager deadlock") because it prevents the setup of new threads to handle reboot recovery, while the older recovery thread is stuck returning delegations. Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Cc: stable(a)vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker(a)Netapp.com> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3508d8238826..7016eaadf555 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10622,7 +10622,9 @@ static void nfs4_disable_swap(struct inode *inode) */ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + wake_up_var(&clp->cl_state); } static const struct inode_operations nfs4_dir_inode_operations = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0bc160fbabec..9a5d911a7edc 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *clnt = clp->cl_rpcclient; + bool swapon = false; - if (clp->cl_rpcclient->cl_shutdown) + if (clnt->cl_shutdown) return; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { - wake_up_var(&clp->cl_state); - return; + + if (atomic_read(&clnt->cl_swapper)) { + swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, + &clp->cl_state); + if (!swapon) { + wake_up_var(&clp->cl_state); + return; + } } - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) __func__, PTR_ERR(task)); if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); + if (swapon) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs4_clear_state_manager_bit(clp); - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2748,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); again: - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); - if (atomic_read(&cl->cl_swapper)) { + + if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) && + !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) { wait_var_event_interruptible(&clp->cl_state, test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)); - if (atomic_read(&cl->cl_swapper) && - test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + if (!atomic_read(&cl->cl_swapper)) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; /* Either no longer a swapper, or were signalled */ + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); } - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); if (refcount_read(&clp->cl_count) > 1 && !signalled() && test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && - !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; nfs_put_client(clp);

2 years, 2 months

1
0
0 0

FAILED: patch "[PATCH] NFSv4: Fix a state manager thread deadlock regression" 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 956fd46f97d238032cb5fa4771cdaccc6e760f9a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100427-labored-staff-0ab4@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 956fd46f97d238032cb5fa4771cdaccc6e760f9a Mon Sep 17 00:00:00 2001 From: Trond Myklebust <trond.myklebust(a)hammerspace.com> Date: Sun, 24 Sep 2023 13:14:15 -0400 Subject: [PATCH] NFSv4: Fix a state manager thread deadlock regression Commit 4dc73c679114 reintroduces the deadlock that was fixed by commit aeabb3c96186 ("NFSv4: Fix a NFSv4 state manager deadlock") because it prevents the setup of new threads to handle reboot recovery, while the older recovery thread is stuck returning delegations. Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Cc: stable(a)vger.kernel.org Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: Anna Schumaker <Anna.Schumaker(a)Netapp.com> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 3508d8238826..7016eaadf555 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10622,7 +10622,9 @@ static void nfs4_disable_swap(struct inode *inode) */ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + wake_up_var(&clp->cl_state); } static const struct inode_operations nfs4_dir_inode_operations = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0bc160fbabec..9a5d911a7edc 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,16 +1209,26 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + struct rpc_clnt *clnt = clp->cl_rpcclient; + bool swapon = false; - if (clp->cl_rpcclient->cl_shutdown) + if (clnt->cl_shutdown) return; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); - if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { - wake_up_var(&clp->cl_state); - return; + + if (atomic_read(&clnt->cl_swapper)) { + swapon = !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, + &clp->cl_state); + if (!swapon) { + wake_up_var(&clp->cl_state); + return; + } } - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); + + if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) + return; + __module_get(THIS_MODULE); refcount_inc(&clp->cl_count); @@ -1235,8 +1245,9 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) __func__, PTR_ERR(task)); if (!nfs_client_init_is_complete(clp)) nfs_mark_client_ready(clp, PTR_ERR(task)); + if (swapon) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs4_clear_state_manager_bit(clp); - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); nfs_put_client(clp); module_put(THIS_MODULE); } @@ -2748,22 +2759,25 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); again: - set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state); nfs4_state_manager(clp); - if (atomic_read(&cl->cl_swapper)) { + + if (test_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) && + !test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) { wait_var_event_interruptible(&clp->cl_state, test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)); - if (atomic_read(&cl->cl_swapper) && - test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + if (!atomic_read(&cl->cl_swapper)) + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); + if (refcount_read(&clp->cl_count) > 1 && !signalled() && + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; /* Either no longer a swapper, or were signalled */ + clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); } - clear_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state); if (refcount_read(&clp->cl_count) > 1 && !signalled() && test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state) && - !test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state)) + !test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state)) goto again; nfs_put_client(clp);

2 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2023