From: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
If two programs simultaneously try to write to the same part of a file
via direct IO and buffered IO, there's a chance that the post-diowrite
pagecache invalidation will fail on the dirty page. When this happens,
the dio write succeeded, which means that the page cache is no longer
coherent with the disk! Programs are not supposed to mix IO types and
this is a clear case of data corruption, so store an EIO which will be
reflected to userspace during the next fsync. Get rid of the WARN_ON
to assuage the fuzz-tester complaints.
Signed-off-by: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
---
fs/iomap.c | 25 +++++++++++++++++++++++--
1 file changed, 23 insertions(+), 2 deletions(-)
diff --git a/fs/iomap.c b/fs/iomap.c
index 5011a96..9f0e8d4 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -711,6 +711,19 @@ struct iomap_dio {
};
};
+static void iomap_warn_stale_pagecache(struct inode *inode)
+{
+ static DEFINE_RATELIMIT_STATE(_rs,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+
+ errseq_set(&inode->i_mapping->wb_err, -EIO);
+ if (__ratelimit(&_rs)) {
+ pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n");
+ dump_stack_print_info(KERN_CRIT);
+ }
+}
+
static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
@@ -753,7 +766,8 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio)
err = invalidate_inode_pages2_range(inode->i_mapping,
offset >> PAGE_SHIFT,
(offset + dio->size - 1) >> PAGE_SHIFT);
- WARN_ON_ONCE(err);
+ if (err)
+ iomap_warn_stale_pagecache(inode);
}
inode_dio_end(file_inode(iocb->ki_filp));
@@ -1012,9 +1026,16 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (ret)
goto out_free_dio;
+ /*
+ * Try to invalidate cache pages for the range we're direct
+ * writing. If this invalidation fails, tough, the write will
+ * still work, but racing two incompatible write paths is a
+ * pretty crazy thing to do, so we don't support it 100%.
+ */
ret = invalidate_inode_pages2_range(mapping,
start >> PAGE_SHIFT, end >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
+ if (ret)
+ iomap_warn_stale_pagecache(inode);
ret = 0;
if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
