summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2014-10-02 09:04:11 +1000
committerDave Chinner <david@fromorbit.com>2014-10-02 09:04:11 +1000
commite11bb8052c3f500e66142f33579cc054d691a8fb (patch)
treea0a569a145631d37bd629a9c8a156e49515de626 /fs
parentcf53e99d192171a58791136d33fd3fea5d8bab35 (diff)
downloadop-kernel-dev-e11bb8052c3f500e66142f33579cc054d691a8fb.zip
op-kernel-dev-e11bb8052c3f500e66142f33579cc054d691a8fb.tar.gz
xfs: synchronous buffer IO needs a reference
When synchronous IO runs IO completion work, it does so without an IO reference or a hold reference on the buffer. The IO "hold reference" is owned by the submitter, and released when the submission is complete. The IO reference is released when both the submitter and the bio end_io processing is run, and so if the io completion work is run from IO completion context, it is run without an IO reference. Hence we can get the situation where the submitter can submit the IO, see an error on the buffer and unlock and free the buffer while there is still IO in progress. This leads to use-after-free and memory corruption. Fix this by taking a "sync IO hold" reference that is owned by the IO and not released until after the buffer completion calls are run to wake up synchronous waiters. This means that the buffer will not be freed in any circumstance until all IO processing is completed. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs')
-rw-r--r--fs/xfs/xfs_buf.c51
1 files changed, 42 insertions, 9 deletions
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 9dc4c22..48b1e29 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1019,6 +1019,9 @@ xfs_buf_iodone_work(
else {
ASSERT(read && bp->b_ops);
complete(&bp->b_iowait);
+
+ /* release the !XBF_ASYNC ref now we are done. */
+ xfs_buf_rele(bp);
}
}
@@ -1044,6 +1047,7 @@ xfs_buf_ioend(
} else {
bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);
complete(&bp->b_iowait);
+ xfs_buf_rele(bp);
}
}
@@ -1086,8 +1090,11 @@ xfs_bioerror(
xfs_buf_ioerror(bp, -EIO);
/*
- * We're calling xfs_buf_ioend, so delete XBF_DONE flag.
+ * We're calling xfs_buf_ioend, so delete XBF_DONE flag. For
+ * sync IO, xfs_buf_ioend is going to remove a ref here.
*/
+ if (!(bp->b_flags & XBF_ASYNC))
+ xfs_buf_hold(bp);
XFS_BUF_UNREAD(bp);
XFS_BUF_UNDONE(bp);
xfs_buf_stale(bp);
@@ -1383,22 +1390,48 @@ xfs_buf_iorequest(
if (bp->b_flags & XBF_WRITE)
xfs_buf_wait_unpin(bp);
+
+ /*
+ * Take references to the buffer. For XBF_ASYNC buffers, holding a
+ * reference for as long as submission takes is all that is necessary
+ * here. The IO inherits the lock and hold count from the submitter,
+ * and these are release during IO completion processing. Taking a hold
+ * over submission ensures that the buffer is not freed until we have
+ * completed all processing, regardless of when IO errors occur or are
+ * reported.
+ *
+ * However, for synchronous IO, the IO does not inherit the submitters
+ * reference count, nor the buffer lock. Hence we need to take an extra
+ * reference to the buffer for the for the IO context so that we can
+ * guarantee the buffer is not freed until all IO completion processing
+ * is done. Otherwise the caller can drop their reference while the IO
+ * is still in progress and hence trigger a use-after-free situation.
+ */
xfs_buf_hold(bp);
+ if (!(bp->b_flags & XBF_ASYNC))
+ xfs_buf_hold(bp);
+
/*
- * Set the count to 1 initially, this will stop an I/O
- * completion callout which happens before we have started
- * all the I/O from calling xfs_buf_ioend too early.
+ * Set the count to 1 initially, this will stop an I/O completion
+ * callout which happens before we have started all the I/O from calling
+ * xfs_buf_ioend too early.
*/
atomic_set(&bp->b_io_remaining, 1);
_xfs_buf_ioapply(bp);
+
/*
- * If _xfs_buf_ioapply failed, we'll get back here with
- * only the reference we took above. _xfs_buf_ioend will
- * drop it to zero, so we'd better not queue it for later,
- * or we'll free it before it's done.
+ * If _xfs_buf_ioapply failed or we are doing synchronous IO that
+ * completes extremely quickly, we can get back here with only the IO
+ * reference we took above. _xfs_buf_ioend will drop it to zero. Run
+ * completion processing synchronously so that we don't return to the
+ * caller with completion still pending. This avoids unnecessary context
+ * switches associated with the end_io workqueue.
*/
- _xfs_buf_ioend(bp, bp->b_error ? 0 : 1);
+ if (bp->b_error || !(bp->b_flags & XBF_ASYNC))
+ _xfs_buf_ioend(bp, 0);
+ else
+ _xfs_buf_ioend(bp, 1);
xfs_buf_rele(bp);
}
OpenPOWER on IntegriCloud