From 4a955bed882e734807024afd8f53213d4c61ff97 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Mon, 14 Nov 2022 22:55:37 +1100 Subject: mm/memory: return vm_fault_t result from migrate_to_ram() callback The migrate_to_ram() callback should always succeed, but in rare cases can fail usually returning VM_FAULT_SIGBUS. Commit 16ce101db85d ("mm/memory.c: fix race when faulting a device private page") incorrectly stopped passing the return code up the stack. Fix this by setting the ret variable, restoring the previous behaviour on migrate_to_ram() failure. Link: https://lkml.kernel.org/r/20221114115537.727371-1-apopple@nvidia.com Fixes: 16ce101db85d ("mm/memory.c: fix race when faulting a device private page") Signed-off-by: Alistair Popple Acked-by: David Hildenbrand Reviewed-by: Felix Kuehling Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Sierra Cc: Ben Skeggs Cc: Lyude Paul Cc: Jason Gunthorpe Cc: Michael Ellerman Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/memory.c') diff --git a/mm/memory.c b/mm/memory.c index f88c351aecd4..8a6d5c823f91 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3763,7 +3763,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); - vmf->page->pgmap->ops->migrate_to_ram(vmf); + ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; -- cgit v1.2.3 From 21b85b09527c28e242db55c1b751f7f7549b830c Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Mon, 14 Nov 2022 15:55:05 -0800 Subject: madvise: use zap_page_range_single for madvise dontneed This series addresses the issue first reported in [1], and fully described in patch 2. Patches 1 and 2 address the user visible issue and are tagged for stable backports. While exploring solutions to this issue, related problems with mmu notification calls were discovered. This is addressed in the patch "hugetlb: remove duplicate mmu notifications:". Since there are no user visible effects, this third is not tagged for stable backports. Previous discussions suggested further cleanup by removing the routine zap_page_range. This is possible because zap_page_range_single is now exported, and all callers of zap_page_range pass ranges entirely within a single vma. This work will be done in a later patch so as not to distract from this bug fix. [1] https://lore.kernel.org/lkml/CAO4mrfdLMXsao9RF4fUE8-Wfde8xmjsKrTNMNC9wjUb6JudD0g@mail.gmail.com/ This patch (of 2): Expose the routine zap_page_range_single to zap a range within a single vma. The madvise routine madvise_dontneed_single_vma can use this routine as it explicitly operates on a single vma. Also, update the mmu notification range in zap_page_range_single to take hugetlb pmd sharing into account. This is required as MADV_DONTNEED supports hugetlb vmas. Link: https://lkml.kernel.org/r/20221114235507.294320-1-mike.kravetz@oracle.com Link: https://lkml.kernel.org/r/20221114235507.294320-2-mike.kravetz@oracle.com Fixes: 90e7e7f5ef3f ("mm: enable MADV_DONTNEED for hugetlb mappings") Signed-off-by: Mike Kravetz Reported-by: Wei Chen Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Mina Almasry Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Peter Xu Cc: Rik van Riel Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 27 +++++++++++++++++++-------- mm/madvise.c | 6 +++--- mm/memory.c | 23 +++++++++++------------ 3 files changed, 33 insertions(+), 23 deletions(-) (limited to 'mm/memory.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8bbcccbc5565..cbfb489d381c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1852,6 +1852,23 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem __show_free_areas(flags, nodemask, MAX_NR_ZONES - 1); } +/* + * Parameter block passed down to zap_pte_range in exceptional cases. + */ +struct zap_details { + struct folio *single_folio; /* Locked folio to be unmapped */ + bool even_cows; /* Zap COWed private pages too? */ + zap_flags_t zap_flags; /* Extra flags for zapping */ +}; + +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) + #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else @@ -1869,6 +1886,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details); void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); @@ -3467,12 +3486,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif -/* - * Whether to drop the pte markers, for example, the uffd-wp information for - * file-backed memory. This should only be specified when we will completely - * drop the page in the mm, either by truncation or unmapping of the vma. By - * default, the flag is not set. - */ -#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) - #endif /* _LINUX_MM_H */ diff --git a/mm/madvise.c b/mm/madvise.c index c7105ec6d08c..b913ba6efc10 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -772,8 +772,8 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The - * zap_page_range call sets things up for shrink_active_list to actually free - * these pages later if no one else has touched them in the meantime, + * zap_page_range_single call sets things up for shrink_active_list to actually + * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * @@ -790,7 +790,7 @@ static int madvise_free_single_vma(struct vm_area_struct *vma, static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - zap_page_range(vma, start, end - start); + zap_page_range_single(vma, start, end - start, NULL); return 0; } diff --git a/mm/memory.c b/mm/memory.c index 8a6d5c823f91..9bc5edc35725 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1341,15 +1341,6 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) return ret; } -/* - * Parameter block passed down to zap_pte_range in exceptional cases. - */ -struct zap_details { - struct folio *single_folio; /* Locked folio to be unmapped */ - bool even_cows; /* Zap COWed private pages too? */ - zap_flags_t zap_flags; /* Extra flags for zapping */ -}; - /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { @@ -1774,19 +1765,27 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * * The range must fit into one VMA. */ -static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, +void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { + const unsigned long end = address + size; struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, address + size); + address, end); + if (is_vm_hugetlb_page(vma)) + adjust_range_if_pmd_sharing_possible(vma, &range.start, + &range.end); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); - unmap_single_vma(&tlb, vma, address, range.end, details); + /* + * unmap 'address-end' not 'range.start-range.end' as range + * could have been expanded for hugetlb pmd sharing. + */ + unmap_single_vma(&tlb, vma, address, end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } -- cgit v1.2.3 From 04ada095dcfc4ae359418053c0be94453bdf1e84 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Mon, 14 Nov 2022 15:55:06 -0800 Subject: hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing madvise(MADV_DONTNEED) ends up calling zap_page_range() to clear page tables associated with the address range. For hugetlb vmas, zap_page_range will call __unmap_hugepage_range_final. However, __unmap_hugepage_range_final assumes the passed vma is about to be removed and deletes the vma_lock to prevent pmd sharing as the vma is on the way out. In the case of madvise(MADV_DONTNEED) the vma remains, but the missing vma_lock prevents pmd sharing and could potentially lead to issues with truncation/fault races. This issue was originally reported here [1] as a BUG triggered in page_try_dup_anon_rmap. Prior to the introduction of the hugetlb vma_lock, __unmap_hugepage_range_final cleared the VM_MAYSHARE flag to prevent pmd sharing. Subsequent faults on this vma were confused as VM_MAYSHARE indicates a sharable vma, but was not set so page_mapping was not set in new pages added to the page table. This resulted in pages that appeared anonymous in a VM_SHARED vma and triggered the BUG. Address issue by adding a new zap flag ZAP_FLAG_UNMAP to indicate an unmap call from unmap_vmas(). This is used to indicate the 'final' unmapping of a hugetlb vma. When called via MADV_DONTNEED, this flag is not set and the vm_lock is not deleted. [1] https://lore.kernel.org/lkml/CAO4mrfdLMXsao9RF4fUE8-Wfde8xmjsKrTNMNC9wjUb6JudD0g@mail.gmail.com/ Link: https://lkml.kernel.org/r/20221114235507.294320-3-mike.kravetz@oracle.com Fixes: 90e7e7f5ef3f ("mm: enable MADV_DONTNEED for hugetlb mappings") Signed-off-by: Mike Kravetz Reported-by: Wei Chen Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Mina Almasry Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Peter Xu Cc: Rik van Riel Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 ++ mm/hugetlb.c | 27 ++++++++++++++++----------- mm/memory.c | 2 +- 3 files changed, 19 insertions(+), 12 deletions(-) (limited to 'mm/memory.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index cbfb489d381c..974ccca609d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1868,6 +1868,8 @@ struct zap_details { * default, the flag is not set. */ #define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) +/* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ +#define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) #ifdef CONFIG_MMU extern bool can_do_mlock(void); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f1385c3b6c96..e36ca75311a5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5206,17 +5206,22 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); - /* - * Unlock and free the vma lock before releasing i_mmap_rwsem. When - * the vma_lock is freed, this makes the vma ineligible for pmd - * sharing. And, i_mmap_rwsem is required to set up pmd sharing. - * This is important as page tables for this unmapped range will - * be asynchrously deleted. If the page tables are shared, there - * will be issues when accessed by someone else. - */ - __hugetlb_vma_unlock_write_free(vma); - - i_mmap_unlock_write(vma->vm_file->f_mapping); + if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ + /* + * Unlock and free the vma lock before releasing i_mmap_rwsem. + * When the vma_lock is freed, this makes the vma ineligible + * for pmd sharing. And, i_mmap_rwsem is required to set up + * pmd sharing. This is important as page tables for this + * unmapped range will be asynchrously deleted. If the page + * tables are shared, there will be issues when accessed by + * someone else. + */ + __hugetlb_vma_unlock_write_free(vma); + i_mmap_unlock_write(vma->vm_file->f_mapping); + } else { + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + } } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, diff --git a/mm/memory.c b/mm/memory.c index 9bc5edc35725..8c8420934d60 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1711,7 +1711,7 @@ void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, { struct mmu_notifier_range range; struct zap_details details = { - .zap_flags = ZAP_FLAG_DROP_MARKER, + .zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP, /* Careful - we need to zap private pages too! */ .even_cows = true, }; -- cgit v1.2.3