summaryrefslogtreecommitdiffstats
path: root/mm/mprotect.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2014-04-07 15:36:56 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-04-07 16:35:50 -0700
commit1ad9f620c3a22fa800489455ce517c29e576934e (patch)
tree1eb1db0166198b988983e6b59755ced828ad47fe /mm/mprotect.c
parent88a9ab6e3dfb5b10168130c255c6102c925343ab (diff)
downloadtalos-obmc-linux-1ad9f620c3a22fa800489455ce517c29e576934e.tar.gz
talos-obmc-linux-1ad9f620c3a22fa800489455ce517c29e576934e.zip
mm: numa: recheck for transhuge pages under lock during protection changes
Sasha reported the following bug using trinity kernel BUG at mm/mprotect.c:149! invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 20 PID: 26219 Comm: trinity-c216 Tainted: G W 3.14.0-rc5-next-20140305-sasha-00011-ge06f5f3-dirty #105 task: ffff8800b6c80000 ti: ffff880228436000 task.ti: ffff880228436000 RIP: change_protection_range+0x3b3/0x500 Call Trace: change_protection+0x25/0x30 change_prot_numa+0x1b/0x30 task_numa_work+0x279/0x360 task_work_run+0xae/0xf0 do_notify_resume+0x8e/0xe0 retint_signal+0x4d/0x92 The VM_BUG_ON was added in -mm by the patch "mm,numa: reorganize change_pmd_range". The race existed without the patch but was just harder to hit. The problem is that a transhuge check is made without holding the PTL. It's possible at the time of the check that a parallel fault clears the pmd and inserts a new one which then triggers the VM_BUG_ON check. This patch removes the VM_BUG_ON but fixes the race by rechecking transhuge under the PTL when marking page tables for NUMA hinting and bailing if a race occurred. It is not a problem for calls to mprotect() as they hold mmap_sem for write. Signed-off-by: Mel Gorman <mgorman@suse.de> Reported-by: Sasha Levin <sasha.levin@oracle.com> Reviewed-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/mprotect.c')
-rw-r--r--mm/mprotect.c36
1 files changed, 34 insertions, 2 deletions
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 79cb51866e02..2c51c79c8a69 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -36,6 +36,34 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
}
#endif
+/*
+ * For a prot_numa update we only hold mmap_sem for read so there is a
+ * potential race with faulting where a pmd was temporarily none. This
+ * function checks for a transhuge pmd under the appropriate lock. It
+ * returns a pte if it was successfully locked or NULL if it raced with
+ * a transhuge insertion.
+ */
+static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, int prot_numa, spinlock_t **ptl)
+{
+ pte_t *pte;
+ spinlock_t *pmdl;
+
+ /* !prot_numa is protected by mmap_sem held for write */
+ if (!prot_numa)
+ return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+
+ pmdl = pmd_lock(vma->vm_mm, pmd);
+ if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
+ spin_unlock(pmdl);
+ return NULL;
+ }
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+ spin_unlock(pmdl);
+ return pte;
+}
+
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
@@ -45,7 +73,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
spinlock_t *ptl;
unsigned long pages = 0;
- pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+ if (!pte)
+ return 0;
+
arch_enter_lazy_mmu_mode();
do {
oldpte = *pte;
@@ -132,12 +163,13 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
pages += HPAGE_PMD_NR;
nr_huge_updates++;
}
+
+ /* huge pmd was handled */
continue;
}
}
/* fall through, the trans huge pmd just split */
}
- VM_BUG_ON(pmd_trans_huge(*pmd));
this_pages = change_pte_range(vma, pmd, addr, next, newprot,
dirty_accountable, prot_numa);
pages += this_pages;
OpenPOWER on IntegriCloud