The patch titled
Subject: dax: ensure that zero pages are removed from other processes
has been added to the -mm tree. Its filename is
dax-ensure-that-zero-pages-are-removed-from-other-processes.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/dax-ensure-that-zero-pages-are-removed-from-other-processes.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/dax-ensure-that-zero-pages-are-removed-from-other-processes.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Matthew Wilcox <willy@xxxxxxxxxxxxxxx>
Subject: dax: ensure that zero pages are removed from other processes
If the first access to a huge page was a store, there would be no existing
zero pmd in this process's page tables. There could be a zero pmd in
another process's page tables, if it had done a load. We can detect this
case by noticing that the buffer_head returned from the filesystem is New,
and ensure that other processes mapping this huge page have their page
tables flushed.
Signed-off-by: Matthew Wilcox <willy@xxxxxxxxxxxxxxx>
Reported-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/dax.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff -puN fs/dax.c~dax-ensure-that-zero-pages-are-removed-from-other-processes fs/dax.c
--- a/fs/dax.c~dax-ensure-that-zero-pages-are-removed-from-other-processes
+++ a/fs/dax.c
@@ -568,7 +568,11 @@ int __dax_pmd_fault(struct vm_area_struc
if ((pgoff | PG_PMD_COLOUR) >= size)
goto fallback;
- if (is_huge_zero_pmd(*pmd))
+ /*
+ * If we allocated new storage, make sure no process has any
+ * zero pages covering this hole
+ */
+ if (buffer_new(&bh))
unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
_
Patches currently in -mm which might be from willy@xxxxxxxxxxxxxxx are
mm-make-gup-handle-pfn-mapping-unless-foll_get-is-requested.patch
mm-make-gup-handle-pfn-mapping-unless-foll_get-is-requested-fix.patch
dax-move-dax-related-functions-to-a-new-header.patch
dax-revert-userfaultfd-change.patch
thp-prepare-for-dax-huge-pages.patch
thp-prepare-for-dax-huge-pages-fix.patch
mm-add-a-pmd_fault-handler.patch
mm-export-various-functions-for-the-benefit-of-dax.patch
mm-add-vmf_insert_pfn_pmd.patch
dax-add-huge-page-fault-support.patch
ext2-huge-page-fault-support.patch
ext4-huge-page-fault-support.patch
xfs-huge-page-fault-support.patch
ext4-use-ext4_get_block_write-for-dax.patch
thp-change-insert_pfns-return-type-to-void.patch
dax-improve-comment-about-truncate-race.patch
ext4-add-ext4_get_block_dax.patch
ext4-start-transaction-before-calling-into-dax.patch
dax-fix-race-between-simultaneous-faults.patch
thp-decrement-refcount-on-huge-zero-page-if-it-is-split.patch
thp-fix-zap_huge_pmd-for-dax.patch
dax-dont-use-set_huge_zero_page.patch
dax-ensure-that-zero-pages-are-removed-from-other-processes.patch
dax-use-linear_page_index.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
