summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2012-03-05 14:59:20 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2012-03-12 10:32:56 -0700
commit3ddb5b56f09929992ac6a4e0c0c1f3fb6cbde509 (patch)
treedc0bf19725567c1a02c793f031d287fe54bb26e2
parentb0f1b35e3cf604dcafdeae9ba3b4a1a86df7d9e8 (diff)
mm: thp: fix BUG on mm->nr_ptes
commit 1c641e84719429bbfe62a95ed3545ee7fe24408f upstream. Dave Jones reports a few Fedora users hitting the BUG_ON(mm->nr_ptes...) in exit_mmap() recently. Quoting Hugh's discovery and explanation of the SMP race condition: "mm->nr_ptes had unusual locking: down_read mmap_sem plus page_table_lock when incrementing, down_write mmap_sem (or mm_users 0) when decrementing; whereas THP is careful to increment and decrement it under page_table_lock. Now most of those paths in THP also hold mmap_sem for read or write (with appropriate checks on mm_users), but two do not: when split_huge_page() is called by hwpoison_user_mappings(), and when called by add_to_swap(). It's conceivable that the latter case is responsible for the exit_mmap() BUG_ON mm->nr_ptes that has been reported on Fedora." The simplest way to fix it without having to alter the locking is to make split_huge_page() a noop in nr_ptes terms, so by counting the preallocated pagetables that exists for every mapped hugepage. It was an arbitrary choice not to count them and either way is not wrong or right, because they are not used but they're still allocated. Reported-by: Dave Jones <davej@redhat.com> Reported-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Josh Boyer <jwboyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--mm/huge_memory.c6
1 files changed, 3 insertions, 3 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 78a83e716996..8cc11dda6a74 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -641,6 +641,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
set_pmd_at(mm, haddr, pmd, entry);
prepare_pmd_huge_pte(pgtable, mm);
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
+ mm->nr_ptes++;
spin_unlock(&mm->page_table_lock);
}
@@ -759,6 +760,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd = pmd_mkold(pmd_wrprotect(pmd));
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
prepare_pmd_huge_pte(pgtable, dst_mm);
+ dst_mm->nr_ptes++;
ret = 0;
out_unlock:
@@ -857,7 +859,6 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
}
kfree(pages);
- mm->nr_ptes++;
smp_wmb(); /* make pte visible before pmd */
pmd_populate(mm, pmd, pgtable);
page_remove_rmap(page);
@@ -1016,6 +1017,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
VM_BUG_ON(page_mapcount(page) < 0);
add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
VM_BUG_ON(!PageHead(page));
+ tlb->mm->nr_ptes--;
spin_unlock(&tlb->mm->page_table_lock);
tlb_remove_page(tlb, page);
pte_free(tlb->mm, pgtable);
@@ -1310,7 +1312,6 @@ static int __split_huge_page_map(struct page *page,
pte_unmap(pte);
}
- mm->nr_ptes++;
smp_wmb(); /* make pte visible before pmd */
/*
* Up to this point the pmd is present and huge and
@@ -1925,7 +1926,6 @@ static void collapse_huge_page(struct mm_struct *mm,
set_pmd_at(mm, address, pmd, _pmd);
update_mmu_cache(vma, address, entry);
prepare_pmd_huge_pte(pgtable, mm);
- mm->nr_ptes--;
spin_unlock(&mm->page_table_lock);
#ifndef CONFIG_NUMA