summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2017-05-12 15:46:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-12 15:57:15 -0700
commitcd656375f94632d7b5af57bf67b7b5c0270c591c (patch)
treefb4e1ba316169ebab1f0df21f1ba57db47f45166
parent4636e70bb0a8b871998b6841a2e4b205cf2bc863 (diff)
downloadlinux-cd656375f94632d7b5af57bf67b7b5c0270c591c.tar.bz2
mm: fix data corruption due to stale mmap reads
Currently, we didn't invalidate page tables during invalidate_inode_pages2() for DAX. That could result in e.g. 2MiB zero page being mapped into page tables while there were already underlying blocks allocated and thus data seen through mmap were different from data seen by read(2). The following sequence reproduces the problem: - open an mmap over a 2MiB hole - read from a 2MiB hole, faulting in a 2MiB zero page - write to the hole with write(3p). The write succeeds but we incorrectly leave the 2MiB zero page mapping intact. - via the mmap, read the data that was just written. Since the zero page mapping is still intact we read back zeroes instead of the new data. Fix the problem by unconditionally calling invalidate_inode_pages2_range() in dax_iomap_actor() for new block allocations and by properly invalidating page tables in invalidate_inode_pages2_range() for DAX mappings. Fixes: c6dcf52c23d2d3fb5235cec42d7dd3f786b87d55 Link: http://lkml.kernel.org/r/20170510085419.27601-3-jack@suse.cz Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--fs/dax.c2
-rw-r--r--mm/truncate.c12
2 files changed, 12 insertions, 2 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 38deebb8c86e..123d9903c77d 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1015,7 +1015,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
* into page tables. We have to tear down these mappings so that data
* written by write(2) is visible in mmap.
*/
- if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+ if (iomap->flags & IOMAP_F_NEW) {
invalidate_inode_pages2_range(inode->i_mapping,
pos >> PAGE_SHIFT,
(end - 1) >> PAGE_SHIFT);
diff --git a/mm/truncate.c b/mm/truncate.c
index 706cff171a15..6479ed2afc53 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -686,7 +686,17 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
cond_resched();
index++;
}
-
+ /*
+ * For DAX we invalidate page tables after invalidating radix tree. We
+ * could invalidate page tables while invalidating each entry however
+ * that would be expensive. And doing range unmapping before doesn't
+ * work as we have no cheap way to find whether radix tree entry didn't
+ * get remapped later.
+ */
+ if (dax_mapping(mapping)) {
+ unmap_mapping_range(mapping, (loff_t)start << PAGE_SHIFT,
+ (loff_t)(end - start + 1) << PAGE_SHIFT, 0);
+ }
out:
cleancache_invalidate_inode(mapping);
return ret;