From 839f7ad6932d95f4d5ae7267b95c574714ff3d5b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 21 Jan 2011 15:54:57 +0000 Subject: NFS: Fix "kernel BUG at fs/aio.c:554!" Nick Piggin reports: > I'm getting use after frees in aio code in NFS > > [ 2703.396766] Call Trace: > [ 2703.396858] [] ? native_sched_clock+0x27/0x80 > [ 2703.396959] [] ? put_lock_stats+0xe/0x40 > [ 2703.397058] [] ? lock_release_holdtime+0xa8/0x140 > [ 2703.397159] [] lock_acquire+0x95/0x1b0 > [ 2703.397260] [] ? aio_put_req+0x2b/0x60 > [ 2703.397361] [] ? get_parent_ip+0x11/0x50 > [ 2703.397464] [] _raw_spin_lock_irq+0x41/0x80 > [ 2703.397564] [] ? aio_put_req+0x2b/0x60 > [ 2703.397662] [] aio_put_req+0x2b/0x60 > [ 2703.397761] [] do_io_submit+0x2be/0x7c0 > [ 2703.397895] [] sys_io_submit+0xb/0x10 > [ 2703.397995] [] system_call_fastpath+0x16/0x1b > > Adding some tracing, it is due to nfs completing the request then > returning something other than -EIOCBQUEUED, so aio.c > also completes the request. To address this, prevent the NFS direct I/O engine from completing async iocbs when the forward path returns an error without starting any I/O. This fix appears to survive ^C during both "xfstest no. 208" and "fsx -Z." It's likely this bug has existed for a very long while, as we are seeing very similar symptoms in OEL 5. Copying stable. Cc: Stable Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e6ace0d93c71..9943a75bb6d1 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -407,15 +407,18 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + if (put_dreq(dreq)) nfs_direct_complete(dreq); - - if (requested_bytes != 0) - return 0; - - if (result < 0) - return result; - return -EIO; + return 0; } static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, @@ -841,15 +844,18 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + /* + * If no bytes were started, return the error, and let the + * generic layer handle the completion. + */ + if (requested_bytes == 0) { + nfs_direct_req_release(dreq); + return result < 0 ? result : -EIO; + } + if (put_dreq(dreq)) nfs_direct_write_complete(dreq, dreq->inode); - - if (requested_bytes != 0) - return 0; - - if (result < 0) - return result; - return -EIO; + return 0; } static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, -- cgit v1.2.3