summaryrefslogtreecommitdiff
path: root/mm/memory.c
diff options
context:
space:
mode:
authorAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>2017-02-24 14:59:13 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-02-24 17:46:56 -0800
commitcee216a696b2004017a5ecb583366093d90b1568 (patch)
tree4270e8e8e17a7450395e374b3a10391818d08d45 /mm/memory.c
parent3f472cc978ea019c7b09cc03f90b8ed6034efdf8 (diff)
mm/autonuma: don't use set_pte_at when updating protnone ptes
Architectures like ppc64, use privilege access bit to mark pte non accessible. This implies that kernel can do a copy_to_user to an address marked for numa fault. This also implies that there can be a parallel hardware update for the pte. set_pte_at cannot be used in such scenarios. Hence switch the pte update to use ptep_get_and_clear and set_pte_at combination. [akpm@linux-foundation.org: remove unwanted ppc change, per Aneesh] Link: http://lkml.kernel.org/r/1486400776-28114-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memory.c')
-rw-r--r--mm/memory.c18
1 files changed, 9 insertions, 9 deletions
diff --git a/mm/memory.c b/mm/memory.c
index bfad9fe316c1..0c759ba122e1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3400,32 +3400,32 @@ static int do_numa_page(struct vm_fault *vmf)
int last_cpupid;
int target_nid;
bool migrated = false;
- pte_t pte = vmf->orig_pte;
- bool was_writable = pte_write(pte);
+ pte_t pte;
+ bool was_writable = pte_write(vmf->orig_pte);
int flags = 0;
/*
* The "pte" at this point cannot be used safely without
* validation through pte_unmap_same(). It's of NUMA type but
* the pfn may be screwed if the read is non atomic.
- *
- * We can safely just do a "set_pte_at()", because the old
- * page table entry is not accessible, so there would be no
- * concurrent hardware modifications to the PTE.
*/
vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd);
spin_lock(vmf->ptl);
- if (unlikely(!pte_same(*vmf->pte, pte))) {
+ if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) {
pte_unmap_unlock(vmf->pte, vmf->ptl);
goto out;
}
- /* Make it present again */
+ /*
+ * Make it present again, Depending on how arch implementes non
+ * accessible ptes, some can allow access by kernel mode.
+ */
+ pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte);
pte = pte_modify(pte, vma->vm_page_prot);
pte = pte_mkyoung(pte);
if (was_writable)
pte = pte_mkwrite(pte);
- set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
+ ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte);
update_mmu_cache(vma, vmf->address, vmf->pte);
page = vm_normal_page(vma, vmf->address, pte);