From 8cd44dd1d17a23d5cc8c443c659ca57aa76e2fa5 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Wed, 15 Feb 2023 09:18:02 +0900 Subject: btrfs: zoned: fix zone_unusable accounting on making block group read-write again When btrfs makes a block group read-only, it adds all free regions in the block group to space_info->bytes_readonly. That free space excludes reserved and pinned regions. OTOH, when btrfs makes the block group read-write again, it moves all the unused regions into the block group's zone_unusable. That unused region includes reserved and pinned regions. As a result, it counts too much zone_unusable bytes. Fortunately (or unfortunately), having erroneous zone_unusable does not affect the calculation of space_info->bytes_readonly, because free space (num_bytes in btrfs_dec_block_group_ro) calculation is done based on the erroneous zone_unusable and it reduces the num_bytes just to cancel the error. This behavior can be easily discovered by adding a WARN_ON to check e.g, "bg->pinned > 0" in btrfs_dec_block_group_ro(), and running fstests test case like btrfs/282. Fix it by properly considering pinned and reserved in btrfs_dec_block_group_ro(). Also, add a WARN_ON and introduce btrfs_space_info_update_bytes_zone_unusable() to catch a similar mistake. Fixes: 169e0da91a21 ("btrfs: zoned: track unusable bytes for zones") CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Naohiro Aota Reviewed-by: Josef Bacik Reviewed-by: Johannes Thumshirn Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index eeb56975bee7..de55a555d95b 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2383,6 +2383,14 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned, TP_ARGS(fs_info, sinfo, old, diff) ); +DEFINE_EVENT(btrfs__space_info_update, update_bytes_zone_unusable, + + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), + + TP_ARGS(fs_info, sinfo, old, diff) +); + DECLARE_EVENT_CLASS(btrfs_raid56_bio, TP_PROTO(const struct btrfs_raid_bio *rbio, -- cgit v1.2.3 From b6a66e521a2032f7fcba2af5a9bcbaeaa19b7ca3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Sat, 27 Jul 2024 12:01:23 +0200 Subject: mptcp: sched: check both directions for backup The 'mptcp_subflow_context' structure has two items related to the backup flags: - 'backup': the subflow has been marked as backup by the other peer - 'request_bkup': the backup flag has been set by the host Before this patch, the scheduler was only looking at the 'backup' flag. That can make sense in some cases, but it looks like that's not what we wanted for the general use, because either the path-manager was setting both of them when sending an MP_PRIO, or the receiver was duplicating the 'backup' flag in the subflow request. Note that the use of these two flags in the path-manager are going to be fixed in the next commits, but this change here is needed not to modify the behaviour. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: Paolo Abeni --- include/trace/events/mptcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 09e72215b9f9..085b749cdd97 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -34,7 +34,7 @@ TRACE_EVENT(mptcp_subflow_get_send, struct sock *ssk; __entry->active = mptcp_subflow_active(subflow); - __entry->backup = subflow->backup; + __entry->backup = subflow->backup || subflow->request_bkup; if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock)) __entry->free = sk_stream_memory_free(subflow->tcp_sock); -- cgit v1.2.3 From 8e5ced7804cb9184c4a23f8054551240562a8eda Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 30 Jul 2024 17:01:40 +0100 Subject: netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag" This reverts commit ae678317b95e760607c7b20b97c9cd4ca9ed6e1a. Revert the patch that removes the deprecated use of PG_private_2 in netfslib for the moment as Ceph is actually still using this to track data copied to the cache. Fixes: ae678317b95e ("netfs: Remove deprecated use of PG_private_2 as a second writeback flag") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org https: //lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- include/trace/events/netfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index da23484268df..24ec3434d32e 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -145,6 +145,7 @@ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ -- cgit v1.2.3 From 7b589a9b45ae32aa9d7bece597490e141198d7a6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Aug 2024 19:38:46 +0100 Subject: netfs: Fix handling of USE_PGPRIV2 and WRITE_TO_CACHE flags The NETFS_RREQ_USE_PGPRIV2 and NETFS_RREQ_WRITE_TO_CACHE flags aren't used correctly. The problem is that we try to set them up in the request initialisation, but we the cache may be in the process of setting up still, and so the state may not be correct. Further, we secondarily sample the cache state and make contradictory decisions later. The issue arises because we set up the cache resources, which allows the cache's ->prepare_read() to switch on NETFS_SREQ_COPY_TO_CACHE - which triggers cache writing even if we didn't set the flags when allocating. Fix this in the following way: (1) Drop NETFS_ICTX_USE_PGPRIV2 and instead set NETFS_RREQ_USE_PGPRIV2 in ->init_request() rather than trying to juggle that in netfs_alloc_request(). (2) Repurpose NETFS_RREQ_USE_PGPRIV2 to merely indicate that if caching is to be done, then PG_private_2 is to be used rather than only setting it if we decide to cache and then having netfs_rreq_unlock_folios() set the non-PG_private_2 writeback-to-cache if it wasn't set. (3) Split netfs_rreq_unlock_folios() into two functions, one of which contains the deprecated code for using PG_private_2 to avoid accidentally doing the writeback path - and always use it if USE_PGPRIV2 is set. (4) As NETFS_ICTX_USE_PGPRIV2 is removed, make netfs_write_begin() always wait for PG_private_2. This function is deprecated and only used by ceph anyway, and so label it so. (5) Drop the NETFS_RREQ_WRITE_TO_CACHE flag and use fscache_operation_valid() on the cache_resources instead. This has the advantage of picking up the result of netfs_begin_cache_read() and fscache_begin_write_operation() - which are called after the object is initialised and will wait for the cache to come to a usable state. Just reverting ae678317b95e[1] isn't a sufficient fix, so this need to be applied on top of that. Without this as well, things like: rcu: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { and: WARNING: CPU: 13 PID: 3621 at fs/ceph/caps.c:3386 may happen, along with some UAFs due to PG_private_2 not getting used to wait on writeback completion. Fixes: 2ff1e97587f4 ("netfs: Replace PG_fscache by setting folio->private and marking dirty") Reported-by: Max Kellermann Signed-off-by: David Howells cc: Ilya Dryomov cc: Xiubo Li cc: Hristo Venev cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Link: https://lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk/ [1] Link: https://lore.kernel.org/r/1173209.1723152682@warthog.procyon.org.uk Signed-off-by: Christian Brauner --- include/trace/events/netfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 24ec3434d32e..606b4a0f92da 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -51,6 +51,7 @@ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ -- cgit v1.2.3 From dc0112e6d8b42b39f9d283bab489a757e9d284f0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 12 Aug 2024 11:47:59 -0400 Subject: rpcrdma: Trace connection registration and unregistration These new trace points record xarray indices and the time of endpoint registration and unregistration, to co-ordinate with device removal events. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/trace/events/rpcrdma.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index ba2d6a0e41cc..a96a985c49b3 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -2277,6 +2277,42 @@ DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one); DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_wait_on); DEFINE_CLIENT_DEVICE_EVENT(rpcrdma_client_remove_one_done); +DECLARE_EVENT_CLASS(rpcrdma_client_register_class, + TP_PROTO( + const struct ib_device *device, + const struct rpcrdma_notification *rn + ), + + TP_ARGS(device, rn), + + TP_STRUCT__entry( + __string(name, device->name) + __field(void *, callback) + __field(u32, index) + ), + + TP_fast_assign( + __assign_str(name); + __entry->callback = rn->rn_done; + __entry->index = rn->rn_index; + ), + + TP_printk("device=%s index=%u done callback=%pS\n", + __get_str(name), __entry->index, __entry->callback + ) +); + +#define DEFINE_CLIENT_REGISTER_EVENT(name) \ + DEFINE_EVENT(rpcrdma_client_register_class, name, \ + TP_PROTO( \ + const struct ib_device *device, \ + const struct rpcrdma_notification *rn \ + ), \ + TP_ARGS(device, rn)) + +DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_register); +DEFINE_CLIENT_REGISTER_EVENT(rpcrdma_client_unregister); + #endif /* _TRACE_RPCRDMA_H */ #include -- cgit v1.2.3