summaryrefslogtreecommitdiffstats
path: root/mm/mmap.c
diff options
context:
space:
mode:
authorHugh Dickins <hugh@veritas.com>2005-10-29 18:16:29 -0700
committerLinus Torvalds <torvalds@g5.osdl.org>2005-10-29 21:40:40 -0700
commit8f4f8c164cb4af1432cc25eda82928ea4519ba72 (patch)
tree49cd3c62069df1f8d6c863b9806923de16c10e8b /mm/mmap.c
parent663b97f7efd001b0c56bd5fce059c5272725b86f (diff)
[PATCH] mm: unlink vma before pagetables
In most places the descent from pgd to pud to pmd to pte holds mmap_sem (exclusively or not), which ensures that free_pgtables cannot be freeing page tables from any level at the same time. But truncation and reverse mapping descend without mmap_sem. No problem: just make sure that a vma is unlinked from its prio_tree (or nonlinear list) and from its anon_vma list, after zapping the vma, but before freeing its page tables. Then neither vmtruncate nor rmap can reach that vma whose page tables are now volatile (nor do they need to reach it, since all its page entries have been zapped by this stage). The i_mmap_lock and anon_vma->lock already serialize this correctly; but the locking hierarchy is such that we cannot take them while holding page_table_lock. Well, we're trying to push that down anyway. So in this patch, move anon_vma_unlink and unlink_file_vma into free_pgtables, at the same time as moving page_table_lock around calls to unmap_vmas. tlb_gather_mmu and tlb_finish_mmu then fall outside the page_table_lock, but we made them preempt_disable and preempt_enable earlier; and a long source audit of all the architectures has shown no problem with removing page_table_lock from them. free_pgtables doesn't need page_table_lock for itself, nor for what it calls; tlb->mm->nr_ptes is usually protected by page_table_lock, but partly by non-exclusive mmap_sem - here it's decremented with exclusive mmap_sem, or mm_users 0. update_hiwater_rss and vm_unacct_memory don't need page_table_lock either. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm/mmap.c')
-rw-r--r--mm/mmap.c23
1 files changed, 6 insertions, 17 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index d931d7e49ac..fa35323a3c5 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -203,14 +203,6 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
{
struct vm_area_struct *next = vma->vm_next;
- /*
- * Hide vma from rmap and vmtruncate before freeing page tables:
- * to be moved into free_pgtables once page_table_lock is lifted
- * from it, but until then lock ordering forbids that move.
- */
- anon_vma_unlink(vma);
- unlink_file_vma(vma);
-
might_sleep();
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
@@ -1679,15 +1671,15 @@ static void unmap_region(struct mm_struct *mm,
unsigned long nr_accounted = 0;
lru_add_drain();
- spin_lock(&mm->page_table_lock);
tlb = tlb_gather_mmu(mm, 0);
update_hiwater_rss(mm);
+ spin_lock(&mm->page_table_lock);
unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL);
+ spin_unlock(&mm->page_table_lock);
vm_unacct_memory(nr_accounted);
free_pgtables(&tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
next? next->vm_start: 0);
tlb_finish_mmu(tlb, start, end);
- spin_unlock(&mm->page_table_lock);
}
/*
@@ -1962,23 +1954,20 @@ void exit_mmap(struct mm_struct *mm)
unsigned long end;
lru_add_drain();
-
- spin_lock(&mm->page_table_lock);
-
flush_cache_mm(mm);
tlb = tlb_gather_mmu(mm, 1);
/* Don't update_hiwater_rss(mm) here, do_exit already did */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
+ spin_lock(&mm->page_table_lock);
end = unmap_vmas(&tlb, mm, vma, 0, -1, &nr_accounted, NULL);
+ spin_unlock(&mm->page_table_lock);
vm_unacct_memory(nr_accounted);
free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
tlb_finish_mmu(tlb, 0, end);
- spin_unlock(&mm->page_table_lock);
-
/*
- * Walk the list again, actually closing and freeing it
- * without holding any MM locks.
+ * Walk the list again, actually closing and freeing it,
+ * with preemption enabled, without holding any MM locks.
*/
while (vma)
vma = remove_vma(vma);