From 913fadc5b105c3619d9e8d0fe8899ff1593cc737 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 8 Jul 2020 10:33:40 -0400 Subject: NFS: Fix interrupted slots by sending a solo SEQUENCE operation We used to do this before 3453d5708b33, but this was changed to better handle the NFS4ERR_SEQ_MISORDERED error code. This commit fixed the slot re-use case when the server doesn't receive the interrupted operation, but if the server does receive the operation then it could still end up replying to the client with mis-matched operations from the reply cache. We can fix this by sending a SEQUENCE to the server while recovering from a SEQ_MISORDERED error when we detect that we are in an interrupted slot situation. Fixes: 3453d5708b33 (NFSv4.1: Avoid false retries when RPC calls are interrupted) Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e32717fd1169..2e2dac29a9e9 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -774,6 +774,14 @@ static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, slot->seq_nr_last_acked = seqnr; } +static void nfs4_probe_sequence(struct nfs_client *client, const struct cred *cred, + struct nfs4_slot *slot) +{ + struct rpc_task *task = _nfs41_proc_sequence(client, cred, slot, true); + if (!IS_ERR(task)) + rpc_put_task_async(task); +} + static int nfs41_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) { @@ -790,6 +798,7 @@ static int nfs41_sequence_process(struct rpc_task *task, goto out; session = slot->table->session; + clp = session->clp; trace_nfs4_sequence_done(session, res); @@ -804,7 +813,6 @@ static int nfs41_sequence_process(struct rpc_task *task, nfs4_slot_sequence_acked(slot, slot->seq_nr); /* Update the slot's sequence and clientid lease timer */ slot->seq_done = 1; - clp = session->clp; do_renew_lease(clp, res->sr_timestamp); /* Check sequence flags */ nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags, @@ -852,10 +860,18 @@ static int nfs41_sequence_process(struct rpc_task *task, /* * Were one or more calls using this slot interrupted? * If the server never received the request, then our - * transmitted slot sequence number may be too high. + * transmitted slot sequence number may be too high. However, + * if the server did receive the request then it might + * accidentally give us a reply with a mismatched operation. + * We can sort this out by sending a lone sequence operation + * to the server on the same slot. */ if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) { slot->seq_nr--; + if (task->tk_msg.rpc_proc != &nfs4_procedures[NFSPROC4_CLNT_SEQUENCE]) { + nfs4_probe_sequence(clp, task->tk_msg.rpc_cred, slot); + res->sr_slot = NULL; + } goto retry_nowait; } /* -- cgit v1.2.3 From 65caafd0d2145d1dd02072c4ced540624daeab40 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 15 Jul 2020 13:04:15 -0400 Subject: SUNRPC reverting d03727b248d0 ("NFSv4 fix CLOSE not waiting for direct IO compeletion") Reverting commit d03727b248d0 "NFSv4 fix CLOSE not waiting for direct IO compeletion". This patch made it so that fput() by calling inode_dio_done() in nfs_file_release() would wait uninterruptably for any outstanding directIO to the file (but that wait on IO should be killable). The problem the patch was also trying to address was REMOVE returning ERR_ACCESS because the file is still opened, is supposed to be resolved by server returning ERR_FILE_OPEN and not ERR_ACCESS. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/direct.c | 13 ++++--------- fs/nfs/file.c | 1 - 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'fs') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 3d113cf8908a..1b79dd5cf661 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -267,6 +267,8 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) { struct inode *inode = dreq->inode; + inode_dio_end(inode); + if (dreq->iocb) { long res = (long) dreq->error; if (dreq->count != 0) { @@ -278,10 +280,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) complete(&dreq->completion); - igrab(inode); nfs_direct_req_release(dreq); - inode_dio_end(inode); - iput(inode); } static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) @@ -411,10 +410,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - igrab(inode); - nfs_direct_req_release(dreq); inode_dio_end(inode); - iput(inode); + nfs_direct_req_release(dreq); return result < 0 ? result : -EIO; } @@ -867,10 +864,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * generic layer handle the completion. */ if (requested_bytes == 0) { - igrab(inode); - nfs_direct_req_release(dreq); inode_dio_end(inode); - iput(inode); + nfs_direct_req_release(dreq); return result < 0 ? result : -EIO; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index ccd6c1637b27..f96367a2463e 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -83,7 +83,6 @@ nfs_file_release(struct inode *inode, struct file *filp) dprintk("NFS: release(%pD2)\n", filp); nfs_inc_stats(inode, NFSIOS_VFSRELEASE); - inode_dio_wait(inode); nfs_file_clear_open_context(filp); return 0; } -- cgit v1.2.3