From 045407559c21b1f140316b829f8be9ef320df1f4 Mon Sep 17 00:00:00 2001 From: Brian Geffon Date: Tue, 18 Mar 2025 20:04:30 +0800 Subject: [PATCH 1/2] mm: fix finish_fault() handling for large folios mainline inclusion from mainline-v6.14-rc6 commit 34b82f33cf3f03bc39e9a205a913d790e1520ade category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBRQ5C Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=34b82f33cf3f03bc39e9a205a913d790e1520ade -------------------------------- When handling faults for anon shmem finish_fault() will attempt to install ptes for the entire folio. Unfortunately if it encounters a single non-pte_none entry in that range it will bail, even if the pte that triggered the fault is still pte_none. When this situation happens the fault will be retried endlessly never making forward progress. This patch fixes this behavior and if it detects that a pte in the range is not pte_none it will fall back to setting a single pte. [bgeffon@google.com: tweak whitespace] Link: https://lkml.kernel.org/r/20250227133236.1296853-1-bgeffon@google.com Link: https://lkml.kernel.org/r/20250226162341.915535-1-bgeffon@google.com Fixes: 43e027e41423 ("mm: memory: extend finish_fault() to support large folio") Signed-off-by: Brian Geffon Suggested-by: Baolin Wang Reported-by: Marek Maslanka Cc: Hugh Dickins Cc: David Hildenbrand Cc: Hugh Dickens Cc: Kefeng Wang Cc: Matthew Wilcow (Oracle) Cc: Suren Baghdasaryan Cc: Zi Yan Cc: Signed-off-by: Andrew Morton Signed-off-by: Tong Tiangen --- mm/memory.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index a6d146d684e8..e8daa5a3d369 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4846,7 +4846,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf) bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED); int type, nr_pages; - unsigned long addr = vmf->address; + unsigned long addr; + bool needs_fallback = false; + +fallback: + addr = vmf->address; /* Did we COW the page? */ if (is_cow) @@ -4885,7 +4889,8 @@ vm_fault_t finish_fault(struct vm_fault *vmf) * approach also applies to non-anonymous-shmem faults to avoid * inflating the RSS of the process. */ - if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) { + if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) || + unlikely(needs_fallback)) { nr_pages = 1; } else if (nr_pages > 1) { pgoff_t idx = folio_page_idx(folio, page); @@ -4921,9 +4926,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf) ret = VM_FAULT_NOPAGE; goto unlock; } else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) { - update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages); - ret = VM_FAULT_NOPAGE; - goto unlock; + needs_fallback = true; + pte_unmap_unlock(vmf->pte, vmf->ptl); + goto fallback; } folio_ref_add(folio, nr_pages - 1); -- Gitee From 58f0cc853f6d7556919973d98d81701a7aabdfc4 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Tue, 18 Mar 2025 20:04:31 +0800 Subject: [PATCH 2/2] mm/migrate: fix shmem xarray update during migration mainline inclusion from mainline-v6.14-rc6 commit 60cf233b585cdf1f3c5e52d1225606b86acd08b0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBNJCQ Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=60cf233b585cdf1f3c5e52d1225606b86acd08b0 -------------------------------- A shmem folio can be either in page cache or in swap cache, but not at the same time. Namely, once it is in swap cache, folio->mapping should be NULL, and the folio is no longer in a shmem mapping. In __folio_migrate_mapping(), to determine the number of xarray entries to update, folio_test_swapbacked() is used, but that conflates shmem in page cache case and shmem in swap cache case. It leads to xarray multi-index entry corruption, since it turns a sibling entry to a normal entry during xas_store() (see [1] for a userspace reproduction). Fix it by only using folio_test_swapcache() to determine whether xarray is storing swap cache entries or not to choose the right number of xarray entries to update. [1] https://lore.kernel.org/linux-mm/Z8idPCkaJW1IChjT@casper.infradead.org/ Note: In __split_huge_page(), folio_test_anon() && folio_test_swapcache() is used to get swap_cache address space, but that ignores the shmem folio in swap cache case. It could lead to NULL pointer dereferencing when a in-swap-cache shmem folio is split at __xa_store(), since !folio_test_anon() is true and folio->mapping is NULL. But fortunately, its caller split_huge_page_to_list_to_order() bails out early with EBUSY when folio->mapping is NULL. So no need to take care of it here. Link: https://lkml.kernel.org/r/20250305200403.2822855-1-ziy@nvidia.com Fixes: fc346d0a70a1 ("mm: migrate high-order folios in swap cache correctly") Signed-off-by: Zi Yan Reported-by: Liu Shixin Closes: https://lore.kernel.org/all/28546fb4-5210-bf75-16d6-43e1f8646080@huawei.com/ Suggested-by: Hugh Dickins Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Baolin Wang Cc: Barry Song Cc: Charan Teja Kalla Cc: David Hildenbrand Cc: Hugh Dickins Cc: Kefeng Wang Cc: Lance Yang Cc: Ryan Roberts Cc: Signed-off-by: Andrew Morton Signed-off-by: Tong Tiangen --- mm/migrate.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index ace03cce4e37..1462848ce385 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -449,15 +449,13 @@ static int __folio_migrate_mapping(struct address_space *mapping, if (folio_test_anon(folio) && folio_test_large(folio)) mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); folio_ref_add(newfolio, nr); /* add cache reference */ - if (folio_test_swapbacked(folio)) { + if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); - if (folio_test_swapcache(folio)) { - folio_set_swapcache(newfolio); - newfolio->private = folio_get_private(folio); - } + if (folio_test_swapcache(folio)) { + folio_set_swapcache(newfolio); + newfolio->private = folio_get_private(folio); entries = nr; } else { - VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); entries = 1; } -- Gitee