Blktests test cases nvme/014, 057 and 058 fail occasionally due to a
lockdep WARN. As reported in the Closes tag URL, the WARN indicates that
a deadlock can happen due to the dependency among disk->open_mutex,
kblockd workqueue completion and partition_scan_work completion.
To avoid the lockdep WARN and the potential deadlock, cut the dependency
by running the partition_scan_work not by kblockd workqueue but by
nvme_wq.
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAHj4cs8mJ+R_GmQm9R8ebResKAWUE8kF5+_WVg0v8zndmqd6BQ@mail.gmail.com/
Link: https://lore.kernel.org/linux-block/oeyzci6ffshpukpfqgztsdeke5ost5hzsuz4rrsjfmvpqcevax@5nhnwbkzbrpa/
Fixes: 1f021341eef4 ("nvme-multipath: defer partition scanning")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
For queue-depth I/O policy, this patch fixes unbalanced I/Os across
nvme multipaths.
Issue Description:
The RETRY disposition incorrectly increments ns->ctrl->nr_active
counter and reinitializes iostat start-time. In such cases nr_active
counter never goes back to zero until that path disconnects and
reconnects.
Such a path is not chosen for new I/Os if multiple RETRY cases on a given
a path cause its queue-depth counter to be artificially higher compared
to other paths. This leads to unbalanced I/Os across paths.
The patch skips incrementing nr_active if NVME_MPATH_CNT_ACTIVE is already
set. And it skips restarting io stats if NVME_MPATH_IO_STATS is already set.
base-commit: e989a3da2d371a4b6597ee8dee5c72e407b4db7a
Fixes: d4d957b53d91eeb ("nvme-multipath: support io stats on the mpath device")
Signed-off-by: Amit Chaudhary <achaudhary@purestorage.com>
Reviewed-by: Randy Jennings <randyj@purestorage.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Pull block fixes from Jens Axboe:
- NVMe fixes via Christoph:
- fix incorrect cdw15 value in passthru error logging (Alok Tiwari)
- fix memory leak of bio integrity in nvmet (Dmitry Bogdanov)
- refresh visible attrs after being checked (Eugen Hristev)
- fix suspicious RCU usage warning in the multipath code (Geliang Tang)
- correctly account for namespace head reference counter (Nilay Shroff)
- Fix for a regression introduced in ublk in this cycle, where it would
attempt to queue a canceled request.
- brd RCU sleeping fix, also introduced in this cycle. Bare bones fix,
should be improved upon for the next release.
* tag 'block-6.16-20250704' of git://git.kernel.dk/linux:
brd: fix sleeping function called from invalid context in brd_insert_page()
ublk: don't queue request if the associated uring_cmd is canceled
nvme-multipath: fix suspicious RCU usage warning
nvme-pci: refresh visible attrs after being checked
nvmet: fix memory leak of bio integrity
nvme: correctly account for namespace head reference counter
nvme: Fix incorrect cdw15 value in passthru error logging
When I run the NVME over TCP test in virtme-ng, I get the following
"suspicious RCU usage" warning in nvme_mpath_add_sysfs_link():
'''
[ 5.024557][ T44] nvmet: Created nvm controller 1 for subsystem nqn.2025-06.org.nvmexpress.mptcp for NQN nqn.2014-08.org.nvmexpress:uuid:f7f6b5e0-ff97-4894-98ac-c85309e0bc77.
[ 5.027401][ T183] nvme nvme0: creating 2 I/O queues.
[ 5.029017][ T183] nvme nvme0: mapped 2/0/0 default/read/poll queues.
[ 5.032587][ T183] nvme nvme0: new ctrl: NQN "nqn.2025-06.org.nvmexpress.mptcp", addr 127.0.0.1:4420, hostnqn: nqn.2014-08.org.nvmexpress:uuid:f7f6b5e0-ff97-4894-98ac-c85309e0bc77
[ 5.042214][ T25]
[ 5.042440][ T25] =============================
[ 5.042579][ T25] WARNING: suspicious RCU usage
[ 5.042705][ T25] 6.16.0-rc3+ #23 Not tainted
[ 5.042812][ T25] -----------------------------
[ 5.042934][ T25] drivers/nvme/host/multipath.c:1203 RCU-list traversed in non-reader section!!
[ 5.043111][ T25]
[ 5.043111][ T25] other info that might help us debug this:
[ 5.043111][ T25]
[ 5.043341][ T25]
[ 5.043341][ T25] rcu_scheduler_active = 2, debug_locks = 1
[ 5.043502][ T25] 3 locks held by kworker/u9:0/25:
[ 5.043615][ T25] #0: ffff888008730948 ((wq_completion)async){+.+.}-{0:0}, at: process_one_work+0x7ed/0x1350
[ 5.043830][ T25] #1: ffffc900001afd40 ((work_completion)(&entry->work)){+.+.}-{0:0}, at: process_one_work+0xcf3/0x1350
[ 5.044084][ T25] #2: ffff888013ee0020 (&head->srcu){.+.+}-{0:0}, at: nvme_mpath_add_sysfs_link.part.0+0xb4/0x3a0
[ 5.044300][ T25]
[ 5.044300][ T25] stack backtrace:
[ 5.044439][ T25] CPU: 0 UID: 0 PID: 25 Comm: kworker/u9:0 Not tainted 6.16.0-rc3+ #23 PREEMPT(full)
[ 5.044441][ T25] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[ 5.044442][ T25] Workqueue: async async_run_entry_fn
[ 5.044445][ T25] Call Trace:
[ 5.044446][ T25] <TASK>
[ 5.044449][ T25] dump_stack_lvl+0x6f/0xb0
[ 5.044453][ T25] lockdep_rcu_suspicious.cold+0x4f/0xb1
[ 5.044457][ T25] nvme_mpath_add_sysfs_link.part.0+0x2fb/0x3a0
[ 5.044459][ T25] ? queue_work_on+0x90/0xf0
[ 5.044461][ T25] ? lockdep_hardirqs_on+0x78/0x110
[ 5.044466][ T25] nvme_mpath_set_live+0x1e9/0x4f0
[ 5.044470][ T25] nvme_mpath_add_disk+0x240/0x2f0
[ 5.044472][ T25] ? __pfx_nvme_mpath_add_disk+0x10/0x10
[ 5.044475][ T25] ? add_disk_fwnode+0x361/0x580
[ 5.044480][ T25] nvme_alloc_ns+0x81c/0x17c0
[ 5.044483][ T25] ? kasan_quarantine_put+0x104/0x240
[ 5.044487][ T25] ? __pfx_nvme_alloc_ns+0x10/0x10
[ 5.044495][ T25] ? __pfx_nvme_find_get_ns+0x10/0x10
[ 5.044496][ T25] ? rcu_read_lock_any_held+0x45/0xa0
[ 5.044498][ T25] ? validate_chain+0x232/0x4f0
[ 5.044503][ T25] nvme_scan_ns+0x4c8/0x810
[ 5.044506][ T25] ? __pfx_nvme_scan_ns+0x10/0x10
[ 5.044508][ T25] ? find_held_lock+0x2b/0x80
[ 5.044512][ T25] ? ktime_get+0x16d/0x220
[ 5.044517][ T25] ? kvm_clock_get_cycles+0x18/0x30
[ 5.044520][ T25] ? __pfx_nvme_scan_ns_async+0x10/0x10
[ 5.044522][ T25] async_run_entry_fn+0x97/0x560
[ 5.044523][ T25] ? rcu_is_watching+0x12/0xc0
[ 5.044526][ T25] process_one_work+0xd3c/0x1350
[ 5.044532][ T25] ? __pfx_process_one_work+0x10/0x10
[ 5.044536][ T25] ? assign_work+0x16c/0x240
[ 5.044539][ T25] worker_thread+0x4da/0xd50
[ 5.044545][ T25] ? __pfx_worker_thread+0x10/0x10
[ 5.044546][ T25] kthread+0x356/0x5c0
[ 5.044548][ T25] ? __pfx_kthread+0x10/0x10
[ 5.044549][ T25] ? ret_from_fork+0x1b/0x2e0
[ 5.044552][ T25] ? __lock_release.isra.0+0x5d/0x180
[ 5.044553][ T25] ? ret_from_fork+0x1b/0x2e0
[ 5.044555][ T25] ? rcu_is_watching+0x12/0xc0
[ 5.044557][ T25] ? __pfx_kthread+0x10/0x10
[ 5.044559][ T25] ret_from_fork+0x218/0x2e0
[ 5.044561][ T25] ? __pfx_kthread+0x10/0x10
[ 5.044562][ T25] ret_from_fork_asm+0x1a/0x30
[ 5.044570][ T25] </TASK>
'''
This patch uses sleepable RCU version of helper list_for_each_entry_srcu()
instead of list_for_each_entry_rcu() to fix it.
Fixes: 4dbd2b2ebe4c ("nvme-multipath: Add visibility for round-robin io-policy")
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The blktests nvme/058 manifests an issue where the NVMe subsystem
kobject entry remains stale in sysfs, causing a failure during
subsequent NVMe module reloads[1]. Specifically, when attempting to
register a new NVMe subsystem, the driver encounters a kobejct name
collision because a stale kobject still exists. Though, please note
that nvme/058 doesn't report any failure and test case passes and
it's only during subsequent NVMe module reloads, the stale nvme sub-
system kobject entry in sysfs causes the observed symptom[1].
This issue stems from an imbalance in the get/put usage of the namespace
head (nshead) reference counter. The nshead holds a reference to the
associated NVMe subsystem. If the nshead reference is not properly
released, it prevents the cleanup of the subsystem's kobject, leaving
nvme subsystem stale entry behind in sysfs.
During the failure case, the last namespace path referencing a nshead
is removed, but the nshead reference was not released. This occurs
because the release logic currently only puts the nshead reference
when its state is LIVE. However, in configurations where ANA (Asymmetric
Namespace Access) is enabled, a namespace may be associated with an ANA
state that is neither optimized nor non-optimized. In this case, the
nshead may never transition to LIVE, and the corresponding nshead
reference is then never dropped. In fact nvme/058 associates some of
nvme namespaces to an inaccessible ANA state and with that nshead is
created but it's state is not transitioned to LIVE. So the current
logic would then causes nshead reference to be leaked for non-LIVE
states.
Another scenario, during namespace allocation, the driver first
allocates a nshead and then issues an Identify Namespace command. If
this command fails — which can happen in tests like nvme/058 that
rapidly enables and disables namespaces — we must release the reference
to the newly allocated nshead. However this reference release is
currently missing in the failure, causing a nshead reference leak.
To fix this, we now unconditionally release the nshead reference when
the last nvme path referencing to the nshead is removed, regardless of
the head’s state. Also during identify namespace failure case we now
properly release the nshead reference. So this ensures proper cleanup
of the nshead, and consequently, the NVMe subsystem and its associated
kobject.
This change prevents stale kobject entries from lingering in sysfs and
eliminates the module reload failures observed just after running
nvme/058.
[1] https://lore.kernel.org/all/CAHj4cs8fOBS-eSjsd5LUBzy7faKXJtgLkCN+mDy_-ezCLLLq+Q@mail.gmail.com/
Reported-by: yi.zhang@redhat.com
Closes: https://lore.kernel.org/all/CAHj4cs8fOBS-eSjsd5LUBzy7faKXJtgLkCN+mDy_-ezCLLLq+Q@mail.gmail.com/
Fixes: 62188639ec16 ("nvme-multipath: introduce delayed removal of the multipath head node")
Tested-by: yi.zhang@redhat.com
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Pull block fixes from Jens Axboe:
- Fixes for ublk:
- fix C++ narrowing warnings in the uapi header
- update/improve UBLK_F_SUPPORT_ZERO_COPY comment in uapi header
- fix for the ublk ->queue_rqs() implementation, limiting a batch
to just the specific task AND ring
- ublk_get_data() error handling fix
- sanity check more arguments in ublk_ctrl_add_dev()
- selftest addition
- NVMe pull request via Christoph:
- reset delayed remove_work after reconnect
- fix atomic write size validation
- Fix for a warning introduced in bdev_count_inflight_rw() in this
merge window
* tag 'block-6.16-20250626' of git://git.kernel.dk/linux:
block: fix false warning in bdev_count_inflight_rw()
ublk: sanity check add_dev input for underflow
nvme: fix atomic write size validation
nvme: refactor the atomic write unit detection
nvme: reset delayed remove_work after reconnect
ublk: setup ublk_io correctly in case of ublk_get_data() failure
ublk: update UBLK_F_SUPPORT_ZERO_COPY comment in UAPI header
ublk: fix narrowing warnings in UAPI header
selftests: ublk: don't take same backing file for more than one ublk devices
ublk: build batch from IOs in same io_ring_ctx and io task
The remove_work will proceed with permanently disconnecting on the initial final path failure if the head shows no paths after the delay. If a new path connects while the remove_work is pending, and if that new path happens to disconnect before that remove_work executes, the delayed removal should reset based on the most recent path disconnect time, but queue_delayed_work() won't do anything if the work is already pending. Attempt to cancel the delayed work when a new path connects, and use mod_delayed_work() in case the remove_work remains pending anyway. Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Nilay Shroff <nilay@linux.ibm.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Move this API to the canonical timer_*() namespace. [ tglx: Redone against pre rc1 ] Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/all/aB2X0jCKQO56WdMt@gmail.com
Fix various spelling errors in comments. Signed-off-by: Yi Zhang <yi.zhang@redhat.com> Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
Pull block updates from Jens Axboe:
- ublk updates:
- Add support for updating the size of a ublk instance
- Zero-copy improvements
- Auto-registering of buffers for zero-copy
- Series simplifying and improving GET_DATA and request lookup
- Series adding quiesce support
- Lots of selftests additions
- Various cleanups
- NVMe updates via Christoph:
- add per-node DMA pools and use them for PRP/SGL allocations
(Caleb Sander Mateos, Keith Busch)
- nvme-fcloop refcounting fixes (Daniel Wagner)
- support delayed removal of the multipath node and optionally
support the multipath node for private namespaces (Nilay Shroff)
- support shared CQs in the PCI endpoint target code (Wilfred
Mallawa)
- support admin-queue only authentication (Hannes Reinecke)
- use the crc32c library instead of the crypto API (Eric Biggers)
- misc cleanups (Christoph Hellwig, Marcelo Moreira, Hannes
Reinecke, Leon Romanovsky, Gustavo A. R. Silva)
- MD updates via Yu:
- Fix that normal IO can be starved by sync IO, found by mkfs on
newly created large raid5, with some clean up patches for bdev
inflight counters
- Clean up brd, getting rid of atomic kmaps and bvec poking
- Add loop driver specifically for zoned IO testing
- Eliminate blk-rq-qos calls with a static key, if not enabled
- Improve hctx locking for when a plug has IO for multiple queues
pending
- Remove block layer bouncing support, which in turn means we can
remove the per-node bounce stat as well
- Improve blk-throttle support
- Improve delay support for blk-throttle
- Improve brd discard support
- Unify IO scheduler switching. This should also fix a bunch of lockdep
warnings we've been seeing, after enabling lockdep support for queue
freezing/unfreezeing
- Add support for block write streams via FDP (flexible data placement)
on NVMe
- Add a bunch of block helpers, facilitating the removal of a bunch of
duplicated boilerplate code
- Remove obsolete BLK_MQ pci and virtio Kconfig options
- Add atomic/untorn write support to blktrace
- Various little cleanups and fixes
* tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux: (186 commits)
selftests: ublk: add test for UBLK_F_QUIESCE
ublk: add feature UBLK_F_QUIESCE
selftests: ublk: add test case for UBLK_U_CMD_UPDATE_SIZE
traceevent/block: Add REQ_ATOMIC flag to block trace events
ublk: run auto buf unregisgering in same io_ring_ctx with registering
io_uring: add helper io_uring_cmd_ctx_handle()
ublk: remove io argument from ublk_auto_buf_reg_fallback()
ublk: handle ublk_set_auto_buf_reg() failure correctly in ublk_fetch()
selftests: ublk: add test for covering UBLK_AUTO_BUF_REG_FALLBACK
selftests: ublk: support UBLK_F_AUTO_BUF_REG
ublk: support UBLK_AUTO_BUF_REG_FALLBACK
ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG
ublk: prepare for supporting to register request buffer automatically
ublk: convert to refcount_t
selftests: ublk: make IO & device removal test more stressful
nvme: rename nvme_mpath_shutdown_disk to nvme_mpath_remove_disk
nvme: introduce multipath_always_on module param
nvme-multipath: introduce delayed removal of the multipath head node
nvme-pci: derive and better document max segments limits
nvme-pci: use struct_size for allocation struct nvme_dev
...