mainline inclusion from mainline-v6.13-rc6 commit 59d9094df3d79443937add8700b2ef1a866b1081 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBBGL0 CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
The folio refcount may be increased unexpectly through try_get_folio() by caller such as split_huge_pages. In huge_pmd_unshare(), we use refcount to check whether a pmd page table is shared. The check is incorrect if the refcount is increased by the above caller, and this can cause the page table leaked:
BUG: Bad page state in process sh pfn:109324 page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x66 pfn:0x109324 flags: 0x17ffff800000000(node=0|zone=2|lastcpupid=0xfffff) page_type: f2(table) raw: 017ffff800000000 0000000000000000 0000000000000000 0000000000000000 raw: 0000000000000066 0000000000000000 00000000f2000000 0000000000000000 page dumped because: nonzero mapcount ... CPU: 31 UID: 0 PID: 7515 Comm: sh Kdump: loaded Tainted: G B 6.13.0-rc2master+ #7 Tainted: [B]=BAD_PAGE Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: show_stack+0x20/0x38 (C) dump_stack_lvl+0x80/0xf8 dump_stack+0x18/0x28 bad_page+0x8c/0x130 free_page_is_bad_report+0xa4/0xb0 free_unref_page+0x3cc/0x620 __folio_put+0xf4/0x158 split_huge_pages_all+0x1e0/0x3e8 split_huge_pages_write+0x25c/0x2d8 full_proxy_write+0x64/0xd8 vfs_write+0xcc/0x280 ksys_write+0x70/0x110 __arm64_sys_write+0x24/0x38 invoke_syscall+0x50/0x120 el0_svc_common.constprop.0+0xc8/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x34/0x128 el0t_64_sync_handler+0xc8/0xd0 el0t_64_sync+0x190/0x198
The issue may be triggered by damon, offline_page, page_idle, etc, which will increase the refcount of page table.
1. The page table itself will be discarded after reporting the "nonzero mapcount".
2. The HugeTLB page mapped by the page table miss freeing since we treat the page table as shared and a shared page table will not be unmapped.
Fix it by introducing independent PMD page table shared count. As described by comment, pt_index/pt_mm/pt_frag_refcount are used for s390 gmap, x86 pgds and powerpc, pt_share_count is used for x86/arm64/riscv pmds, so we can reuse the field as pt_share_count.
Link: https://lkml.kernel.org/r/20241216071147.3984217-1-liushixin2@huawei.com Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Liu Shixin liushixin2@huawei.com Cc: Kefeng Wang wangkefeng.wang@huawei.com Cc: Ken Chen kenneth.w.chen@intel.com Cc: Muchun Song muchun.song@linux.dev Cc: Nanyong Sun sunnanyong@huawei.com Cc: Jane Chu jane.chu@oracle.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Conflicts: include/linux/hugetlb.h include/linux/mm.h include/linux/mm_types.h mm/hugetlb.c mm/rmap.c [ Context conflict with commit ea919671517a and 38ca8a185389. Config conflict with commit 188cac58a8bc. Add missing vma in huge_pmd_unshare() from commit 34ae204f1851. ] Signed-off-by: Liu Shixin liushixin2@huawei.com --- include/linux/hugetlb.h | 7 ++++--- include/linux/mm.h | 1 + include/linux/mm_types.h | 29 +++++++++++++++++++++++++++++ mm/hugetlb.c | 26 +++++++++++++------------- mm/rmap.c | 2 +- 5 files changed, 48 insertions(+), 17 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 86519e714986..303ae0d4ada1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -138,7 +138,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz); pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, @@ -171,8 +172,8 @@ static inline unsigned long hugetlb_total_pages(void) return 0; }
-static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, - pte_t *ptep) +static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { return 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 72532a1d2d20..67e299374ac8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2104,6 +2104,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page) #ifdef CONFIG_TRANSPARENT_HUGEPAGE page->pmd_huge_pte = NULL; #endif + page_pmd_pts_init(page); return ptlock_init(page); }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f2142a5eab6e..2cf5d0aaeb97 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -145,6 +145,9 @@ struct page { union { struct mm_struct *pt_mm; /* x86 pgds only */ atomic_t pt_frag_refcount; /* powerpc */ +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE + atomic_t pt_share_count; +#endif }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; @@ -209,6 +212,32 @@ struct page { #endif } _struct_page_alignment;
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static inline void page_pmd_pts_init(struct page *page) +{ + atomic_set(&page->pt_share_count, 0); +} + +static inline void page_pmd_pts_inc(struct page *page) +{ + atomic_inc(&page->pt_share_count); +} + +static inline void page_pmd_pts_dec(struct page *page) +{ + atomic_dec(&page->pt_share_count); +} + +static inline int page_pmd_pts_count(struct page *page) +{ + return atomic_read(&page->pt_share_count); +} +#else +static inline void page_pmd_pts_init(struct page *page) +{ +} +#endif + #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bde2e7b632db..69dd1e096a48 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5054,7 +5054,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, continue;
ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; @@ -6126,7 +6126,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, &address, ptep)) { pages++; spin_unlock(ptl); shared_pmd = true; @@ -6444,7 +6444,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) spte = huge_pte_offset(svma->vm_mm, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + page_pmd_pts_inc(virt_to_page(spte)); break; } } @@ -6459,7 +6459,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + page_pmd_pts_dec(virt_to_page(spte)); } spin_unlock(ptl); out: @@ -6471,27 +6471,26 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, *addr); p4d_t *p4d = p4d_offset(pgd, *addr); pud_t *pud = pud_offset(p4d, *addr);
- BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!page_pmd_pts_count(virt_to_page(ptep))) return 0;
pud_clear(pud); - put_page(virt_to_page(ptep)); + page_pmd_pts_dec(virt_to_page(ptep)); mm_dec_nr_pmds(mm); *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; @@ -6503,7 +6502,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) return NULL; }
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { return 0; } diff --git a/mm/rmap.c b/mm/rmap.c index bf26f9c8edac..e6724fd0617c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1449,7 +1449,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, address = pvmw.address;
if (PageHuge(page)) { - if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { /* * huge_pmd_unshare unmapped an entire PMD * page. There is no way of knowing exactly