From: Jann Horn jannh@google.com
stable inclusion from stable-v4.19.270 commit f0700ae26832550ce497a568789c3fceeb44d753 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6DPF8 CVE: NA
--------------------------------
commit 2ba99c5e08812494bc57f319fb562f527d9bacd8 upstream.
Since commit 70cbc3cc78a99 ("mm: gup: fix the fast GUP race against THP collapse"), the lockless_pages_from_mm() fastpath rechecks the pmd_t to ensure that the page table was not removed by khugepaged in between.
However, lockless_pages_from_mm() still requires that the page table is not concurrently freed. Fix it by sending IPIs (if the architecture uses semi-RCU-style page table freeing) before freeing/reusing page tables.
Link: https://lkml.kernel.org/r/20221129154730.2274278-2-jannh@google.com Link: https://lkml.kernel.org/r/20221128180252.1684965-2-jannh@google.com Link: https://lkml.kernel.org/r/20221125213714.4115729-2-jannh@google.com Fixes: ba76149f47d8 ("thp: khugepaged") Signed-off-by: Jann Horn jannh@google.com Reviewed-by: Yang Shi shy828301@gmail.com Acked-by: David Hildenbrand david@redhat.com Cc: John Hubbard jhubbard@nvidia.com Cc: Peter Xu peterx@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org [manual backport: two of the three places in khugepaged that can free ptes were refactored into a common helper between 5.15 and 6.0; TLB flushing was refactored between 5.4 and 5.10; TLB flushing was refactored between 4.19 and 5.4; pmd collapse for PTE-mapped THP was only added in 5.4; ugly hack needed in <=4.19 for s390 and arm] Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
Conflicts: mm/memory.c mm/mmu_gather.c Signed-off-by: Ma Wupeng mawupeng1@huawei.com Reviewed-by: tong tiangen tongtiangen@huawei.com Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com --- include/asm-generic/tlb.h | 6 ++++++ mm/khugepaged.c | 15 +++++++++++++++ mm/memory.c | 1 + mm/mmu_gather.c | 5 +++++ 4 files changed, 27 insertions(+)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index cfc86e3ba460..139bcd821a3c 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -63,6 +63,12 @@ struct mmu_table_batch { extern void tlb_table_flush(struct mmu_gather *tlb); extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+void tlb_remove_table_sync_one(void); + +#else + +static inline void tlb_remove_table_sync_one(void) { } + #endif
/* diff --git a/mm/khugepaged.c b/mm/khugepaged.c index cbf26683898c..83500fe19572 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -23,6 +23,19 @@ #include <asm/pgalloc.h> #include "internal.h"
+/* gross hack for <=4.19 stable */ +#if defined(CONFIG_S390) || defined(CONFIG_ARM) +static void tlb_remove_table_smp_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +static void tlb_remove_table_sync_one(void) +{ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); +} +#endif + enum scan_result { SCAN_FAIL, SCAN_SUCCEED, @@ -1053,6 +1066,7 @@ static void collapse_huge_page(struct mm_struct *mm, _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + tlb_remove_table_sync_one();
spin_lock(pte_ptl); isolated = __collapse_huge_page_isolate(vma, address, pte); @@ -1318,6 +1332,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) _pmd = pmdp_collapse_flush(vma, addr, pmd); spin_unlock(ptl); mm_dec_nr_ptes(mm); + tlb_remove_table_sync_one(); pte_free(mm, pmd_pgtable(_pmd)); } up_write(&mm->mmap_sem); diff --git a/mm/memory.c b/mm/memory.c index 5c573b364bdd..407920bf4b97 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -200,6 +200,7 @@ static void check_sync_rss_stat(struct task_struct *task)
#endif /* SPLIT_RSS_COUNTING */
+ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index c147a5aacfa9..a44cf211ffee 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -177,6 +177,11 @@ static void tlb_remove_table_smp_sync(void *arg) /* Simply deliver the interrupt */ }
+void tlb_remove_table_sync_one(void) +{ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); +} + static void tlb_remove_table_one(void *table) { /*