From 03db71b7732b6687ec25e64047946a6a0425509f Mon Sep 17 00:00:00 2001 From: AlieZ22 <820460891@qq.com> Date: Fri, 16 Sep 2022 23:31:52 +0800 Subject: [PATCH] mm/page_table_check: check entries at pmd levels mainline inclusion from mainline-v6.0 commit 80110bbfbba6f0078d5a1cbc8df004506db8ffe5 category: feature bugzilla: https://gitee.com/openeuler/open-source-summer/issues/I56FG1?from=project-issue CVE: N/A Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=80110bbfbba6f0078d5a1cbc8df004506db8ffe5 syzbot detected a case where the page table counters were not properly updated. syzkaller login: ------------[ cut here ]------------ kernel BUG at mm/page_table_check.c:162! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 3099 Comm: pasha Not tainted 5.16.0+ #48 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIO4 RIP: 0010:__page_table_check_zero+0x159/0x1a0 Call Trace: free_pcp_prepare+0x3be/0xaa0 free_unref_page+0x1c/0x650 free_compound_page+0xec/0x130 free_transhuge_page+0x1be/0x260 __put_compound_page+0x90/0xd0 release_pages+0x54c/0x1060 __pagevec_release+0x7c/0x110 shmem_undo_range+0x85e/0x1250 ... The repro involved having a huge page that is split due to uprobe event temporarily replacing one of the pages in the huge page. Later the huge page was combined again, but the counters were off, as the PTE level was not properly updated. Make sure that when PMD is cleared and prior to freeing the level the PTEs are updated. Link: https://lkml.kernel.org/r/20220131203249.2832273-5-pasha.tatashin@soleen.com Fixes: df4e817b7108 ("mm: page table check") Signed-off-by: Pasha Tatashin Acked-by: David Rientjes Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Dave Hansen Cc: Greg Thelen Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jiri Slaby Cc: Mike Rapoport Cc: Muchun Song Cc: Paul Turner Cc: Wei Xu Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Zeng Zhimin --- include/linux/page_table_check.h | 19 +++++++++++++++++++ mm/khugepaged.c | 3 +++ mm/page_table_check.c | 20 ++++++++++++++++++++ 3 files changed, 42 insertions(+) diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h index 93960519f743..e387791a04a6 100644 --- a/include/linux/page_table_check.h +++ b/include/linux/page_table_check.h @@ -22,6 +22,9 @@ void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud); +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { @@ -96,6 +99,16 @@ static inline void page_table_check_pud_set(struct mm_struct *mm, __page_table_check_pud_set(mm, addr, pudp, pud); } +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear_range(mm, addr, pmd); +} + #else static inline void page_table_check_alloc(struct page *page, unsigned int order) @@ -139,5 +152,11 @@ static inline void page_table_check_pud_set(struct mm_struct *mm, { } +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ +} + #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 78e9a445e02d..faeae65e4b1a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -1433,10 +1434,12 @@ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *v spinlock_t *ptl; pmd_t pmd; + mmap_assert_write_locked(mm); ptl = pmd_lock(vma->vm_mm, pmdp); pmd = pmdp_collapse_flush(vma, addr, pmdp); spin_unlock(ptl); mm_dec_nr_ptes(mm); + page_table_check_pte_clear_range(mm, addr, pmd); pte_free(mm, pmd_pgtable(pmd)); } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index f0813434c8c2..71d3c59504b5 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -243,3 +243,23 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, } } EXPORT_SYMBOL(__page_table_check_pud_set); + +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (&init_mm == mm) + return; + + if (!pmd_bad(pmd) && !pmd_leaf(pmd)) { + pte_t *ptep = pte_offset_map(&pmd, addr); + unsigned long i; + + pte_unmap(ptep); + for (i = 0; i < PTRS_PER_PTE; i++) { + __page_table_check_pte_clear(mm, addr, *ptep); + addr += PAGE_SIZE; + ptep++; + } + } +} -- GitLab