From da8cf4bd458722d090a788c6e581eeb72695c62f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:36 +0100 Subject: [PATCH 01/12] netfs: Fix hang due to missing case in final DIO read result collection When doing a DIO read, if the subrequests we issue fail and cause the request PAUSE flag to be set to put a pause on subrequest generation, we may complete collection of the subrequests (possibly discarding them) prior to the ALL_QUEUED flags being set. In such a case, netfs_read_collection() doesn't see ALL_QUEUED being set after netfs_collect_read_results() returns and will just return to the app (the collector can be seen unpausing the generator in the trace log). The subrequest generator can then set ALL_QUEUED and the app thread reaches netfs_wait_for_request(). This causes netfs_collect_in_app() to be called to see if we're done yet, but there's missing case here. netfs_collect_in_app() will see that a thread is active and set inactive to false, but won't see any subrequests in the read stream, and so won't set need_collect to true. The function will then just return 0, indicating that the caller should just sleep until further activity (which won't be forthcoming) occurs. Fix this by making netfs_collect_in_app() check to see if an active thread is complete - i.e. that ALL_QUEUED is set and the subrequests list is empty - and to skip the sleep return path. The collector will then be called which will clear the request IN_PROGRESS flag, allowing the app to progress. Fixes: 2b1424cd131c ("netfs: Fix wait/wake to be consistent about the waitqueue used") Reported-by: Steve French Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-2-dhowells@redhat.com Tested-by: Steve French Reviewed-by: Paulo Alcantara cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/misc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 43b67a28a8fa..0a54b1203486 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -381,7 +381,7 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq, static int netfs_collect_in_app(struct netfs_io_request *rreq, bool (*collector)(struct netfs_io_request *rreq)) { - bool need_collect = false, inactive = true; + bool need_collect = false, inactive = true, done = true; for (int i = 0; i < NR_IO_STREAMS; i++) { struct netfs_io_subrequest *subreq; @@ -400,9 +400,11 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq, need_collect = true; break; } + if (subreq || !test_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags)) + done = false; } - if (!need_collect && !inactive) + if (!need_collect && !inactive && !done) return 0; /* Sleep */ __set_current_state(TASK_RUNNING); From 9df7b5ebead649b00bf9a53a798e4bf83a1318fd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:37 +0100 Subject: [PATCH 02/12] netfs: Fix double put of request If a netfs request finishes during the pause loop, it will have the ref that belongs to the IN_PROGRESS flag removed at that point - however, if it then goes to the final wait loop, that will *also* put the ref because it sees that the IN_PROGRESS flag is clear and incorrectly assumes that this happened when it called the collector. In fact, since IN_PROGRESS is clear, we shouldn't call the collector again since it's done all the cleanup, such as calling ->ki_complete(). Fix this by making netfs_collect_in_app() just return, indicating that we're done if IN_PROGRESS is removed. Fixes: 2b1424cd131c ("netfs: Fix wait/wake to be consistent about the waitqueue used") Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-3-dhowells@redhat.com Tested-by: Steve French Reviewed-by: Paulo Alcantara cc: Steve French cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-cifs@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/misc.c | 5 +++++ include/trace/events/netfs.h | 1 + 2 files changed, 6 insertions(+) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 0a54b1203486..8cf73b237269 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -383,6 +383,11 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq, { bool need_collect = false, inactive = true, done = true; + if (!netfs_check_rreq_in_progress(rreq)) { + trace_netfs_rreq(rreq, netfs_rreq_trace_recollect); + return 1; /* Done */ + } + for (int i = 0; i < NR_IO_STREAMS; i++) { struct netfs_io_subrequest *subreq; struct netfs_io_stream *stream = &rreq->io_streams[i]; diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 333d2e38dd2c..ba35dc66e986 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -56,6 +56,7 @@ EM(netfs_rreq_trace_dirty, "DIRTY ") \ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_abandon, "S-ABNDN") \ From 1a6d45fec33a03ca681eee125ea96987742a893f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:38 +0100 Subject: [PATCH 03/12] netfs: Provide helpers to perform NETFS_RREQ_IN_PROGRESS flag wangling Provide helpers to clear and test the NETFS_RREQ_IN_PROGRESS and to insert the appropriate barrierage. Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-4-dhowells@redhat.com Tested-by: Steve French Reviewed-by: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/internal.h | 18 ++++++++++++++++++ fs/netfs/misc.c | 10 +++++----- fs/netfs/read_collect.c | 4 ++-- fs/netfs/write_collect.c | 4 ++-- 4 files changed, 27 insertions(+), 9 deletions(-) diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index e2ee9183392b..d6656d2b54ab 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -274,6 +274,24 @@ static inline void netfs_wake_rreq_flag(struct netfs_io_request *rreq, } } +/* + * Test the NETFS_RREQ_IN_PROGRESS flag, inserting an appropriate barrier. + */ +static inline bool netfs_check_rreq_in_progress(const struct netfs_io_request *rreq) +{ + /* Order read of flags before read of anything else, such as error. */ + return test_bit_acquire(NETFS_RREQ_IN_PROGRESS, &rreq->flags); +} + +/* + * Test the NETFS_SREQ_IN_PROGRESS flag, inserting an appropriate barrier. + */ +static inline bool netfs_check_subreq_in_progress(const struct netfs_io_subrequest *subreq) +{ + /* Order read of flags before read of anything else, such as error. */ + return test_bit_acquire(NETFS_SREQ_IN_PROGRESS, &subreq->flags); +} + /* * fscache-cache.c */ diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 8cf73b237269..7f31c3cbfe01 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -356,14 +356,14 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq, DEFINE_WAIT(myself); list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + if (!netfs_check_subreq_in_progress(subreq)) continue; trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); for (;;) { prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); - if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + if (!netfs_check_subreq_in_progress(subreq)) break; trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for); @@ -400,7 +400,7 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq, struct netfs_io_subrequest, rreq_link); if (subreq && - (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) || + (!netfs_check_subreq_in_progress(subreq) || test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) { need_collect = true; break; @@ -451,7 +451,7 @@ static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq, } } - if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) + if (!netfs_check_rreq_in_progress(rreq)) break; schedule(); @@ -518,7 +518,7 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq, } } - if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) || + if (!netfs_check_rreq_in_progress(rreq) || !test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) break; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 96ee18af28ef..cceed9d629c6 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -218,7 +218,7 @@ reassess: stream->collected_to = front->start; } - if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) + if (netfs_check_subreq_in_progress(front)) notes |= HIT_PENDING; smp_rmb(); /* Read counters after IN_PROGRESS flag. */ transferred = READ_ONCE(front->transferred); @@ -445,7 +445,7 @@ void netfs_read_collection_worker(struct work_struct *work) struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); netfs_see_request(rreq, netfs_rreq_trace_see_work); - if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) { + if (netfs_check_rreq_in_progress(rreq)) { if (netfs_read_collection(rreq)) /* Drop the ref from the IN_PROGRESS flag. */ netfs_put_request(rreq, netfs_rreq_trace_put_work_ip); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index e2b102ffb768..2ac85a819b71 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -240,7 +240,7 @@ reassess_streams: } /* Stall if the front is still undergoing I/O. */ - if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) { + if (netfs_check_subreq_in_progress(front)) { notes |= HIT_PENDING; break; } @@ -434,7 +434,7 @@ void netfs_write_collection_worker(struct work_struct *work) struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); netfs_see_request(rreq, netfs_rreq_trace_see_work); - if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) { + if (netfs_check_rreq_in_progress(rreq)) { if (netfs_write_collection(rreq)) /* Drop the ref from the IN_PROGRESS flag. */ netfs_put_request(rreq, netfs_rreq_trace_put_work_ip); From 09623e3a14c1c5465124350cd227457c2b0fb017 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:39 +0100 Subject: [PATCH 04/12] netfs: Fix looping in wait functions netfs_wait_for_request() and netfs_wait_for_pause() can loop forever if netfs_collect_in_app() returns 2, indicating that it wants to repeat because the ALL_QUEUED flag isn't yet set and there are no subreqs left that haven't been collected. The problem is that, unless collection is offloaded (OFFLOAD_COLLECTION), we have to return to the application thread to continue and eventually set ALL_QUEUED after pausing to deal with a retry - but we never get there. Fix this by inserting checks for the IN_PROGRESS and PAUSE flags as appropriate before cycling round - and add cond_resched() for good measure. Fixes: 2b1424cd131c ("netfs: Fix wait/wake to be consistent about the waitqueue used") Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-5-dhowells@redhat.com Tested-by: Steve French Reviewed-by: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/misc.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 7f31c3cbfe01..127a269938bb 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -430,8 +430,8 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq, /* * Wait for a request to complete, successfully or otherwise. */ -static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq, - bool (*collector)(struct netfs_io_request *rreq)) +static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq, + bool (*collector)(struct netfs_io_request *rreq)) { DEFINE_WAIT(myself); ssize_t ret; @@ -447,6 +447,9 @@ static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq, case 1: goto all_collected; case 2: + if (!netfs_check_rreq_in_progress(rreq)) + break; + cond_resched(); continue; } } @@ -485,12 +488,12 @@ all_collected: ssize_t netfs_wait_for_read(struct netfs_io_request *rreq) { - return netfs_wait_for_request(rreq, netfs_read_collection); + return netfs_wait_for_in_progress(rreq, netfs_read_collection); } ssize_t netfs_wait_for_write(struct netfs_io_request *rreq) { - return netfs_wait_for_request(rreq, netfs_write_collection); + return netfs_wait_for_in_progress(rreq, netfs_write_collection); } /* @@ -514,6 +517,10 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq, case 1: goto all_collected; case 2: + if (!netfs_check_rreq_in_progress(rreq) || + !test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + break; + cond_resched(); continue; } } From 97d8e8e52cb8ab3d7675880a92626d9a4332f7a6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:40 +0100 Subject: [PATCH 05/12] netfs: Fix ref leak on inserted extra subreq in write retry The write-retry algorithm will insert extra subrequests into the list if it can't get sufficient capacity to split the range that needs to be retried into the sequence of subrequests it currently has (for instance, if the cifs credit pool has fewer credits available than it did when the range was originally divided). However, the allocator furnishes each new subreq with 2 refs and then another is added for resubmission, causing one to be leaked. Fix this by replacing the ref-getting line with a neutral trace line. Fixes: 288ace2f57c9 ("netfs: New writeback implementation") Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-6-dhowells@redhat.com Tested-by: Steve French Reviewed-by: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/write_retry.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index 9d1d8a8bab72..7158657061e9 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -153,7 +153,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), netfs_sreq_trace_new); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + trace_netfs_sreq(subreq, netfs_sreq_trace_split); list_add(&subreq->rreq_link, &to->rreq_link); to = list_next_entry(to, rreq_link); From e67e75edeb88022c04f8e0a173e1ff6dc688f155 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 1 Jul 2025 17:38:41 +0100 Subject: [PATCH 06/12] smb: client: set missing retry flag in smb2_writev_callback() Set NETFS_SREQ_NEED_RETRY flag to tell netfslib that the subreq needs to be retried. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Signed-off-by: Paulo Alcantara (Red Hat) Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-7-dhowells@redhat.com Tested-by: Steve French Cc: linux-cifs@vger.kernel.org Cc: netfs@lists.linux.dev Signed-off-by: Christian Brauner --- fs/smb/client/smb2pdu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index a717be1626a3..084ee66e73fd 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4862,6 +4862,7 @@ smb2_writev_callback(struct mid_q_entry *mid) break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: + __set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags); result = -EAGAIN; break; case MID_RESPONSE_MALFORMED: From 0e60bae24ad28ab06a485698077d3c626f1e54ab Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 1 Jul 2025 17:38:42 +0100 Subject: [PATCH 07/12] smb: client: set missing retry flag in cifs_readv_callback() Set NETFS_SREQ_NEED_RETRY flag to tell netfslib that the subreq needs to be retried. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Signed-off-by: Paulo Alcantara (Red Hat) Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-8-dhowells@redhat.com Tested-by: Steve French Cc: linux-cifs@vger.kernel.org Cc: netfs@lists.linux.dev Signed-off-by: Christian Brauner --- fs/smb/client/cifssmb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 7216fcec79e8..f9ccae5de5b8 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1335,6 +1335,7 @@ cifs_readv_callback(struct mid_q_entry *mid) break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: + __set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags); rdata->result = -EAGAIN; if (server->sign && rdata->got_bytes) /* reset bytes number since we can not check a sign */ From 74ee76bea4b445c023d04806e0bcd78a912fd30b Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 1 Jul 2025 17:38:43 +0100 Subject: [PATCH 08/12] smb: client: set missing retry flag in cifs_writev_callback() Set NETFS_SREQ_NEED_RETRY flag to tell netfslib that the subreq needs to be retried. Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading") Signed-off-by: Paulo Alcantara (Red Hat) Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-9-dhowells@redhat.com Tested-by: Steve French Cc: linux-cifs@vger.kernel.org Cc: netfs@lists.linux.dev Signed-off-by: Christian Brauner --- fs/smb/client/cifssmb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index f9ccae5de5b8..0e509a0433fb 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1715,6 +1715,7 @@ cifs_writev_callback(struct mid_q_entry *mid) break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: + __set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags); result = -EAGAIN; break; default: From 2e0658940d90a3dc130bb3b7f75bae9f4100e01f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:45 +0100 Subject: [PATCH 09/12] netfs: Fix i_size updating Fix the updating of i_size, particularly in regard to the completion of DIO writes and especially async DIO writes by using a lock. The bug is triggered occasionally by the generic/207 xfstest as it chucks a bunch of AIO DIO writes at the filesystem and then checks that fstat() returns a reasonable st_size as each completes. The problem is that netfs is trying to do "if new_size > inode->i_size, update inode->i_size" sort of thing but without a lock around it. This can be seen with cifs, but shouldn't be seen with kafs because kafs serialises modification ops on the client whereas cifs sends the requests to the server as they're generated and lets the server order them. Fixes: 153a9961b551 ("netfs: Implement unbuffered/DIO write support") Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-11-dhowells@redhat.com Reviewed-by: Paulo Alcantara (Red Hat) cc: Steve French cc: Paulo Alcantara cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/buffered_write.c | 2 ++ fs/netfs/direct_write.c | 8 ++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 72a3e6db2524..b87ef3fe4ea4 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -64,6 +64,7 @@ static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode, return; } + spin_lock(&inode->i_lock); i_size_write(inode, pos); #if IS_ENABLED(CONFIG_FSCACHE) fscache_update_cookie(ctx->cache, NULL, &pos); @@ -77,6 +78,7 @@ static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode, DIV_ROUND_UP(pos, SECTOR_SIZE), inode->i_blocks + add); } + spin_unlock(&inode->i_lock); } /** diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index fa9a5bf3c6d5..3efa5894b2c0 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -14,13 +14,17 @@ static void netfs_cleanup_dio_write(struct netfs_io_request *wreq) struct inode *inode = wreq->inode; unsigned long long end = wreq->start + wreq->transferred; - if (!wreq->error && - i_size_read(inode) < end) { + if (wreq->error || end <= i_size_read(inode)) + return; + + spin_lock(&inode->i_lock); + if (end > i_size_read(inode)) { if (wreq->netfs_ops->update_i_size) wreq->netfs_ops->update_i_size(inode, end); else i_size_write(inode, end); } + spin_unlock(&inode->i_lock); } /* From 5e1e6ec2e346c0850f304c31abdef4158007474e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:46 +0100 Subject: [PATCH 10/12] netfs: Merge i_size update functions Netfslib has two functions for updating the i_size after a write: one for buffered writes into the pagecache and one for direct/unbuffered writes. However, what needs to be done is much the same in both cases, so merge them together. This does raise one question, though: should updating the i_size after a direct write do the same estimated update of i_blocks as is done for buffered writes. Also get rid of the cleanup function pointer from netfs_io_request as it's only used for direct write to update i_size; instead do the i_size setting directly from write collection. Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-12-dhowells@redhat.com cc: Steve French cc: Paulo Alcantara cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/buffered_write.c | 36 +++++++++++++++++++++--------------- fs/netfs/direct_write.c | 19 ------------------- fs/netfs/internal.h | 6 ++++++ fs/netfs/write_collect.c | 6 ++++-- include/linux/netfs.h | 1 - 5 files changed, 31 insertions(+), 37 deletions(-) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index b87ef3fe4ea4..f27ea5099a68 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -53,30 +53,38 @@ static struct folio *netfs_grab_folio_for_write(struct address_space *mapping, * data written into the pagecache until we can find out from the server what * the values actually are. */ -static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode, - loff_t i_size, loff_t pos, size_t copied) +void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode, + loff_t pos, size_t copied) { + loff_t i_size, end = pos + copied; blkcnt_t add; size_t gap; + if (end <= i_size_read(inode)) + return; + if (ctx->ops->update_i_size) { - ctx->ops->update_i_size(inode, pos); + ctx->ops->update_i_size(inode, end); return; } spin_lock(&inode->i_lock); - i_size_write(inode, pos); + + i_size = i_size_read(inode); + if (end > i_size) { + i_size_write(inode, end); #if IS_ENABLED(CONFIG_FSCACHE) - fscache_update_cookie(ctx->cache, NULL, &pos); + fscache_update_cookie(ctx->cache, NULL, &end); #endif - gap = SECTOR_SIZE - (i_size & (SECTOR_SIZE - 1)); - if (copied > gap) { - add = DIV_ROUND_UP(copied - gap, SECTOR_SIZE); + gap = SECTOR_SIZE - (i_size & (SECTOR_SIZE - 1)); + if (copied > gap) { + add = DIV_ROUND_UP(copied - gap, SECTOR_SIZE); - inode->i_blocks = min_t(blkcnt_t, - DIV_ROUND_UP(pos, SECTOR_SIZE), - inode->i_blocks + add); + inode->i_blocks = min_t(blkcnt_t, + DIV_ROUND_UP(end, SECTOR_SIZE), + inode->i_blocks + add); + } } spin_unlock(&inode->i_lock); } @@ -113,7 +121,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct folio *folio = NULL, *writethrough = NULL; unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; - loff_t i_size, pos = iocb->ki_pos; + loff_t pos = iocb->ki_pos; size_t max_chunk = mapping_max_folio_size(mapping); bool maybe_trouble = false; @@ -346,10 +354,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, flush_dcache_folio(folio); /* Update the inode size if we moved the EOF marker */ + netfs_update_i_size(ctx, inode, pos, copied); pos += copied; - i_size = i_size_read(inode); - if (pos > i_size) - netfs_update_i_size(ctx, inode, i_size, pos, copied); written += copied; if (likely(!wreq)) { diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 3efa5894b2c0..dcf2b096cc4e 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -9,24 +9,6 @@ #include #include "internal.h" -static void netfs_cleanup_dio_write(struct netfs_io_request *wreq) -{ - struct inode *inode = wreq->inode; - unsigned long long end = wreq->start + wreq->transferred; - - if (wreq->error || end <= i_size_read(inode)) - return; - - spin_lock(&inode->i_lock); - if (end > i_size_read(inode)) { - if (wreq->netfs_ops->update_i_size) - wreq->netfs_ops->update_i_size(inode, end); - else - i_size_write(inode, end); - } - spin_unlock(&inode->i_lock); -} - /* * Perform an unbuffered write where we may have to do an RMW operation on an * encrypted file. This can also be used for direct I/O writes. @@ -102,7 +84,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * if (async) wreq->iocb = iocb; wreq->len = iov_iter_count(&wreq->buffer.iter); - wreq->cleanup = netfs_cleanup_dio_write; ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len); if (ret < 0) { _debug("begin = %zd", ret); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index d6656d2b54ab..f9bb9464a147 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -27,6 +27,12 @@ void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); +/* + * buffered_write.c + */ +void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode, + loff_t pos, size_t copied); + /* * main.c */ diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 2ac85a819b71..33a93258f36e 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -393,8 +393,10 @@ bool netfs_write_collection(struct netfs_io_request *wreq) ictx->ops->invalidate_cache(wreq); } - if (wreq->cleanup) - wreq->cleanup(wreq); + if ((wreq->origin == NETFS_UNBUFFERED_WRITE || + wreq->origin == NETFS_DIO_WRITE) && + !wreq->error) + netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); if (wreq->origin == NETFS_DIO_WRITE && wreq->mapping->nrpages) { diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 065c17385e53..d8186b90fb38 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -279,7 +279,6 @@ struct netfs_io_request { #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; - void (*cleanup)(struct netfs_io_request *req); }; /* From 4e32541076833f5ce2e23523c9faa25f7b2cc96f Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:47 +0100 Subject: [PATCH 11/12] netfs: Renumber the NETFS_RREQ_* flags to make traces easier to read Renumber the NETFS_RREQ_* flags to put the most useful status bits in the bottom nibble - and therefore the last hex digit in the trace output - making it easier to grasp the state at a glance. In particular, put the IN_PROGRESS flag in bit 0 and ALL_QUEUED at bit 1. Also make the flags field in /proc/fs/netfs/requests larger to accommodate all the flags. Also make the flags field in the netfs_sreq tracepoint larger to accommodate all the NETFS_SREQ_* flags. Signed-off-by: David Howells Link: https://lore.kernel.org/20250701163852.2171681-13-dhowells@redhat.com Reviewed-by: Paulo Alcantara cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/main.c | 6 +++--- include/linux/netfs.h | 20 ++++++++++---------- include/trace/events/netfs.h | 2 +- 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 3db401d269e7..73da6c9f5777 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -58,15 +58,15 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v) if (v == &netfs_io_requests) { seq_puts(m, - "REQUEST OR REF FL ERR OPS COVERAGE\n" - "======== == === == ==== === =========\n" + "REQUEST OR REF FLAG ERR OPS COVERAGE\n" + "======== == === ==== ==== === =========\n" ); return 0; } rreq = list_entry(v, struct netfs_io_request, proc_link); seq_printf(m, - "%08x %s %3d %2lx %4ld %3d @%04llx %llx/%llx", + "%08x %s %3d %4lx %4ld %3d @%04llx %llx/%llx", rreq->debug_id, netfs_origins[rreq->origin], refcount_read(&rreq->ref), diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d8186b90fb38..f43f075852c0 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -265,17 +265,17 @@ struct netfs_io_request { bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_OFFLOAD_COLLECTION 0 /* Offload collection to workqueue */ -#define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ -#define NETFS_RREQ_FAILED 4 /* The request failed */ -#define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes (has ref) */ -#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 6 /* Copy current folio to cache from read */ -#define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ -#define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ +#define NETFS_RREQ_IN_PROGRESS 0 /* Unlocked when the request completes (has ref) */ +#define NETFS_RREQ_ALL_QUEUED 1 /* All subreqs are now queued */ +#define NETFS_RREQ_PAUSE 2 /* Pause subrequest generation */ +#define NETFS_RREQ_FAILED 3 /* The request failed */ +#define NETFS_RREQ_RETRYING 4 /* Set if we're in the retry path */ +#define NETFS_RREQ_SHORT_TRANSFER 5 /* Set if we have a short transfer */ +#define NETFS_RREQ_OFFLOAD_COLLECTION 8 /* Offload collection to workqueue */ +#define NETFS_RREQ_NO_UNLOCK_FOLIO 9 /* Don't unlock no_unlock_folio on completion */ +#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 10 /* Copy current folio to cache from read */ +#define NETFS_RREQ_UPLOAD_TO_SERVER 11 /* Need to write to the server */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ -#define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ -#define NETFS_RREQ_RETRYING 14 /* Set if we're in the retry path */ -#define NETFS_RREQ_SHORT_TRANSFER 15 /* Set if we have a short transfer */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index ba35dc66e986..c2d581429a7b 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -367,7 +367,7 @@ TRACE_EVENT(netfs_sreq, __entry->slot = sreq->io_iter.folioq_slot; ), - TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx s=%u e=%d", + TP_printk("R=%08x[%x] %s %s f=%03x s=%llx %zx/%zx s=%u e=%d", __entry->rreq, __entry->index, __print_symbolic(__entry->source, netfs_sreq_sources), __print_symbolic(__entry->what, netfs_sreq_traces), From 90b3ccf514578ca3a6ac25db51a29a48e34e0f1b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 1 Jul 2025 17:38:48 +0100 Subject: [PATCH 12/12] netfs: Update tracepoints in a number of ways Make a number of updates to the netfs tracepoints: (1) Remove a duplicate trace from netfs_unbuffered_write_iter_locked(). (2) Move the trace in netfs_wake_rreq_flag() to after the flag is cleared so that the change appears in the trace. (3) Differentiate the use of netfs_rreq_trace_wait/woke_queue symbols. (4) Don't do so many trace emissions in the wait functions as some of them are redundant. (5) In netfs_collect_read_results(), differentiate a subreq that's being abandoned vs one that has been consumed in a regular way. (6) Add a tracepoint to indicate the call to ->ki_complete(). (7) Don't double-increment the subreq_counter when retrying a write. (8) Move the netfs_sreq_trace_io_progress tracepoint within cifs code to just MID_RESPONSE_RECEIVED and add different tracepoints for other MID states and note check failure. Signed-off-by: David Howells Co-developed-by: Paulo Alcantara Signed-off-by: Paulo Alcantara Link: https://lore.kernel.org/20250701163852.2171681-14-dhowells@redhat.com cc: Steve French cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-cifs@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/direct_write.c | 1 - fs/netfs/internal.h | 2 +- fs/netfs/misc.c | 14 ++++++-------- fs/netfs/read_collect.c | 12 +++++++++--- fs/netfs/write_collect.c | 4 +++- fs/netfs/write_retry.c | 1 - fs/smb/client/cifssmb.c | 24 ++++++++++++++++++++++-- fs/smb/client/smb2pdu.c | 28 +++++++++++++++++++++++----- include/trace/events/netfs.h | 26 ++++++++++++++++++-------- 9 files changed, 82 insertions(+), 30 deletions(-) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index dcf2b096cc4e..a16660ab7f83 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -91,7 +91,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * } if (!async) { - trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); ret = netfs_wait_for_write(wreq); if (ret > 0) iocb->ki_pos += ret; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index f9bb9464a147..d4f16fefd965 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -273,9 +273,9 @@ static inline void netfs_wake_rreq_flag(struct netfs_io_request *rreq, enum netfs_rreq_trace trace) { if (test_bit(rreq_flag, &rreq->flags)) { - trace_netfs_rreq(rreq, trace); clear_bit_unlock(rreq_flag, &rreq->flags); smp_mb__after_atomic(); /* Set flag before task state */ + trace_netfs_rreq(rreq, trace); wake_up(&rreq->waitq); } } diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 127a269938bb..20748bcfbf59 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -359,7 +359,7 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq, if (!netfs_check_subreq_in_progress(subreq)) continue; - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_quiesce); for (;;) { prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); @@ -368,10 +368,10 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq, trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for); schedule(); - trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); } } + trace_netfs_rreq(rreq, netfs_rreq_trace_waited_quiesce); finish_wait(&rreq->waitq, &myself); } @@ -437,7 +437,6 @@ static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq, ssize_t ret; for (;;) { - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { @@ -457,11 +456,12 @@ static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq, if (!netfs_check_rreq_in_progress(rreq)) break; + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip); schedule(); - trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); } all_collected: + trace_netfs_rreq(rreq, netfs_rreq_trace_waited_ip); finish_wait(&rreq->waitq, &myself); ret = rreq->error; @@ -504,10 +504,8 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq, { DEFINE_WAIT(myself); - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause); - for (;;) { - trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause); prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { @@ -530,10 +528,10 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq, break; schedule(); - trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); } all_collected: + trace_netfs_rreq(rreq, netfs_rreq_trace_waited_pause); finish_wait(&rreq->waitq, &myself); } diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index cceed9d629c6..3e804da1e1eb 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -293,7 +293,9 @@ reassess: spin_lock(&rreq->lock); remove = front; - trace_netfs_sreq(front, netfs_sreq_trace_discard); + trace_netfs_sreq(front, + notes & ABANDON_SREQ ? + netfs_sreq_trace_abandoned : netfs_sreq_trace_consumed); list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); @@ -353,9 +355,11 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq) if (rreq->iocb) { rreq->iocb->ki_pos += rreq->transferred; - if (rreq->iocb->ki_complete) + if (rreq->iocb->ki_complete) { + trace_netfs_rreq(rreq, netfs_rreq_trace_ki_complete); rreq->iocb->ki_complete( rreq->iocb, rreq->error ? rreq->error : rreq->transferred); + } } if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); @@ -379,9 +383,11 @@ static void netfs_rreq_assess_single(struct netfs_io_request *rreq) if (rreq->iocb) { rreq->iocb->ki_pos += rreq->transferred; - if (rreq->iocb->ki_complete) + if (rreq->iocb->ki_complete) { + trace_netfs_rreq(rreq, netfs_rreq_trace_ki_complete); rreq->iocb->ki_complete( rreq->iocb, rreq->error ? rreq->error : rreq->transferred); + } } if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 33a93258f36e..0f3a36852a4d 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -421,9 +421,11 @@ bool netfs_write_collection(struct netfs_io_request *wreq) if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); wreq->iocb->ki_pos += written; - if (wreq->iocb->ki_complete) + if (wreq->iocb->ki_complete) { + trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete); wreq->iocb->ki_complete( wreq->iocb, wreq->error ? wreq->error : written); + } wreq->iocb = VFS_PTR_POISON; } diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index 7158657061e9..fc9c3e0d34d8 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -146,7 +146,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq = netfs_alloc_subrequest(wreq); subreq->source = to->source; subreq->start = start; - subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); subreq->stream_nr = to->stream_nr; subreq->retry_count = 1; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 0e509a0433fb..75142f49d65d 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1334,7 +1334,11 @@ cifs_readv_callback(struct mid_q_entry *mid) cifs_stats_bytes_read(tcon, rdata->got_bytes); break; case MID_REQUEST_SUBMITTED: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_req_submitted); + goto do_retry; case MID_RETRY_NEEDED: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_retry_needed); +do_retry: __set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags); rdata->result = -EAGAIN; if (server->sign && rdata->got_bytes) @@ -1344,8 +1348,14 @@ cifs_readv_callback(struct mid_q_entry *mid) task_io_account_read(rdata->got_bytes); cifs_stats_bytes_read(tcon, rdata->got_bytes); break; - default: + case MID_RESPONSE_MALFORMED: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_malformed); rdata->result = -EIO; + break; + default: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_unknown); + rdata->result = -EIO; + break; } if (rdata->result == -ENODATA) { @@ -1714,11 +1724,21 @@ cifs_writev_callback(struct mid_q_entry *mid) } break; case MID_REQUEST_SUBMITTED: - case MID_RETRY_NEEDED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_req_submitted); __set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags); result = -EAGAIN; break; + case MID_RETRY_NEEDED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_retry_needed); + __set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags); + result = -EAGAIN; + break; + case MID_RESPONSE_MALFORMED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_malformed); + result = -EIO; + break; default: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_unknown); result = -EIO; break; } diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 084ee66e73fd..7f6186c2e60d 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4567,7 +4567,11 @@ smb2_readv_callback(struct mid_q_entry *mid) cifs_stats_bytes_read(tcon, rdata->got_bytes); break; case MID_REQUEST_SUBMITTED: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_req_submitted); + goto do_retry; case MID_RETRY_NEEDED: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_retry_needed); +do_retry: __set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags); rdata->result = -EAGAIN; if (server->sign && rdata->got_bytes) @@ -4578,11 +4582,15 @@ smb2_readv_callback(struct mid_q_entry *mid) cifs_stats_bytes_read(tcon, rdata->got_bytes); break; case MID_RESPONSE_MALFORMED: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_malformed); credits.value = le16_to_cpu(shdr->CreditRequest); credits.instance = server->reconnect_instance; - fallthrough; - default: rdata->result = -EIO; + break; + default: + trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_unknown); + rdata->result = -EIO; + break; } #ifdef CONFIG_CIFS_SMB_DIRECT /* @@ -4835,11 +4843,14 @@ smb2_writev_callback(struct mid_q_entry *mid) switch (mid->mid_state) { case MID_RESPONSE_RECEIVED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress); credits.value = le16_to_cpu(rsp->hdr.CreditRequest); credits.instance = server->reconnect_instance; result = smb2_check_receive(mid, server, 0); - if (result != 0) + if (result != 0) { + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_bad); break; + } written = le32_to_cpu(rsp->DataLength); /* @@ -4861,15 +4872,23 @@ smb2_writev_callback(struct mid_q_entry *mid) } break; case MID_REQUEST_SUBMITTED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_req_submitted); + __set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags); + result = -EAGAIN; + break; case MID_RETRY_NEEDED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_retry_needed); __set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags); result = -EAGAIN; break; case MID_RESPONSE_MALFORMED: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_malformed); credits.value = le16_to_cpu(rsp->hdr.CreditRequest); credits.instance = server->reconnect_instance; - fallthrough; + result = -EIO; + break; default: + trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_unknown); result = -EIO; break; } @@ -4909,7 +4928,6 @@ smb2_writev_callback(struct mid_q_entry *mid) server->credits, server->in_flight, 0, cifs_trace_rw_credits_write_response_clear); wdata->credits.value = 0; - trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress); cifs_write_subrequest_terminated(wdata, result ?: written); release_mid(mid); trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index c2d581429a7b..73e96ccbe830 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -50,12 +50,13 @@ #define netfs_rreq_traces \ EM(netfs_rreq_trace_assess, "ASSESS ") \ - EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_collect, "COLLECT") \ EM(netfs_rreq_trace_complete, "COMPLET") \ + EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_dirty, "DIRTY ") \ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ @@ -64,13 +65,15 @@ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ + EM(netfs_rreq_trace_unpause, "UNPAUSE") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ - EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ - EM(netfs_rreq_trace_wait_queue, "WAIT-Q ") \ + EM(netfs_rreq_trace_wait_pause, "--PAUSED--") \ + EM(netfs_rreq_trace_wait_quiesce, "WAIT-QUIESCE") \ + EM(netfs_rreq_trace_waited_ip, "DONE-IP") \ + EM(netfs_rreq_trace_waited_pause, "--UNPAUSED--") \ + EM(netfs_rreq_trace_waited_quiesce, "DONE-QUIESCE") \ EM(netfs_rreq_trace_wake_ip, "WAKE-IP") \ EM(netfs_rreq_trace_wake_queue, "WAKE-Q ") \ - EM(netfs_rreq_trace_woke_queue, "WOKE-Q ") \ - EM(netfs_rreq_trace_unpause, "UNPAUSE") \ E_(netfs_rreq_trace_write_done, "WR-DONE") #define netfs_sreq_sources \ @@ -83,6 +86,7 @@ E_(NETFS_WRITE_TO_CACHE, "WRIT") #define netfs_sreq_traces \ + EM(netfs_sreq_trace_abandoned, "ABNDN") \ EM(netfs_sreq_trace_add_donations, "+DON ") \ EM(netfs_sreq_trace_added, "ADD ") \ EM(netfs_sreq_trace_cache_nowrite, "CA-NW") \ @@ -90,6 +94,7 @@ EM(netfs_sreq_trace_cache_write, "CA-WR") \ EM(netfs_sreq_trace_cancel, "CANCL") \ EM(netfs_sreq_trace_clear, "CLEAR") \ + EM(netfs_sreq_trace_consumed, "CONSM") \ EM(netfs_sreq_trace_discard, "DSCRD") \ EM(netfs_sreq_trace_donate_to_prev, "DON-P") \ EM(netfs_sreq_trace_donate_to_next, "DON-N") \ @@ -97,7 +102,12 @@ EM(netfs_sreq_trace_fail, "FAIL ") \ EM(netfs_sreq_trace_free, "FREE ") \ EM(netfs_sreq_trace_hit_eof, "EOF ") \ - EM(netfs_sreq_trace_io_progress, "IO ") \ + EM(netfs_sreq_trace_io_bad, "I-BAD") \ + EM(netfs_sreq_trace_io_malformed, "I-MLF") \ + EM(netfs_sreq_trace_io_unknown, "I-UNK") \ + EM(netfs_sreq_trace_io_progress, "I-OK ") \ + EM(netfs_sreq_trace_io_req_submitted, "I-RSB") \ + EM(netfs_sreq_trace_io_retry_needed, "I-RTR") \ EM(netfs_sreq_trace_limited, "LIMIT") \ EM(netfs_sreq_trace_need_clear, "N-CLR") \ EM(netfs_sreq_trace_partial_read, "PARTR") \ @@ -143,8 +153,8 @@ #define netfs_sreq_ref_traces \ EM(netfs_sreq_trace_get_copy_to_cache, "GET COPY2C ") \ - EM(netfs_sreq_trace_get_resubmit, "GET RESUBMIT") \ - EM(netfs_sreq_trace_get_submit, "GET SUBMIT") \ + EM(netfs_sreq_trace_get_resubmit, "GET RESUBMT") \ + EM(netfs_sreq_trace_get_submit, "GET SUBMIT ") \ EM(netfs_sreq_trace_get_short_read, "GET SHORTRD") \ EM(netfs_sreq_trace_new, "NEW ") \ EM(netfs_sreq_trace_put_abandon, "PUT ABANDON") \