From 3c226c637b69104f6b9f1c6ec5b08d7b741b3229 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 16 Jun 2017 14:02:34 -0700 Subject: mm: numa: avoid waiting on freed migrated pages In do_huge_pmd_numa_page(), we attempt to handle a migrating thp pmd by waiting until the pmd is unlocked before we return and retry. However, we can race with migrate_misplaced_transhuge_page(): // do_huge_pmd_numa_page // migrate_misplaced_transhuge_page() // Holds 0 refs on page // Holds 2 refs on page vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); /* ... */ if (pmd_trans_migrating(*vmf->pmd)) { page = pmd_page(*vmf->pmd); spin_unlock(vmf->ptl); ptl = pmd_lock(mm, pmd); if (page_count(page) != 2)) { /* roll back */ } /* ... */ mlock_migrate_page(new_page, page); /* ... */ spin_unlock(ptl); put_page(page); put_page(page); // page freed here wait_on_page_locked(page); goto out; } This can result in the freed page having its waiters flag set unexpectedly, which trips the PAGE_FLAGS_CHECK_AT_PREP checks in the page alloc/free functions. This has been observed on arm64 KVM guests. We can avoid this by having do_huge_pmd_numa_page() take a reference on the page before dropping the pmd lock, mirroring what we do in __migration_entry_wait(). When we hit the race, migrate_misplaced_transhuge_page() will see the reference and abort the migration, as it may do today in other cases. Fixes: b8916634b77bffb2 ("mm: Prevent parallel splits during THP migration") Link: http://lkml.kernel.org/r/1497349722-6731-2-git-send-email-will.deacon@arm.com Signed-off-by: Mark Rutland Signed-off-by: Will Deacon Acked-by: Steve Capper Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a84909cf20d3..88c6167f194d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1426,8 +1426,11 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) */ if (unlikely(pmd_trans_migrating(*vmf->pmd))) { page = pmd_page(*vmf->pmd); + if (!get_page_unless_zero(page)) + goto out_unlock; spin_unlock(vmf->ptl); wait_on_page_locked(page); + put_page(page); goto out; } @@ -1459,9 +1462,12 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { + page_nid = -1; + if (!get_page_unless_zero(page)) + goto out_unlock; spin_unlock(vmf->ptl); wait_on_page_locked(page); - page_nid = -1; + put_page(page); goto out; } -- cgit v1.2.3