The ublk selftests mock ublk server kublk supports every data copy mode
except user copy. Add support for user copy to kublk, enabled via the
--user_copy (-u) command line argument. On writes, issue pread() calls
to copy the write data into the ublk_io's buffer before dispatching the
write to the target implementation. On reads, issue pwrite() calls to
copy read data from the ublk_io's buffer before committing the request.
Copy in 2 KB chunks to provide some coverage of the offseting logic.
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The kublk mock ublk server allows multiple data copy mode arguments to
be passed on the command line (--zero_copy, --get_data, and --auto_zc).
The ublk device will be created with all the requested feature flags,
however kublk will only use one of the modes to interact with request
data (arbitrarily preferring auto_zc over zero_copy over get_data). To
clarify the intent of the test, don't allow multiple data copy modes to
be specified. --zero_copy and --auto_zc are allowed together for
--auto_zc_fallback, which uses both copy modes.
Don't set UBLK_F_USER_COPY for zero_copy, as it's a separate feature.
Fix the test cases in test_stress_05 passing --get_data along with
--zero_copy or --auto_zc.
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Refactor ublk_thread to be a thread-local variable instead of storing
it in ublk_dev:
- Remove pthread_t thread field from struct ublk_thread and move it to
struct ublk_thread_info
- Remove struct ublk_thread array from struct ublk_dev, reducing memory
footprint
- Define struct ublk_thread as local variable in __ublk_io_handler_fn()
instead of accessing it from dev->threads[]
- Extract main IO handling logic into __ublk_io_handler_fn() which is
marked as noinline
- Move CPU affinity setup to ublk_io_handler_fn() before calling
__ublk_io_handler_fn()
- Update ublk_thread_set_sched_affinity() to take struct ublk_thread_info *
instead of struct ublk_thread *, and use pthread_setaffinity_np()
instead of sched_setaffinity()
- Reorder struct ublk_thread fields to group related state together
This change makes each thread's ublk_thread structure truly local to
the thread, improving cache locality and reducing memory usage.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Move ublk_thread_set_sched_affinity() call before ublk_thread_init()
to ensure memory allocations during thread initialization occur on
the correct NUMA node. This leverages Linux's first-touch memory
policy for better NUMA locality.
Also convert ublk_thread_set_sched_affinity() to use
pthread_setaffinity_np() instead of sched_setaffinity(), as the
pthread API is the proper interface for setting thread affinity in
multithreaded programs.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull block updates from Jens Axboe:
- NVMe pull request via Keith:
- FC target fixes (Daniel)
- Authentication fixes and updates (Martin, Chris)
- Admin controller handling (Kamaljit)
- Target lockdep assertions (Max)
- Keep-alive updates for discovery (Alastair)
- Suspend quirk (Georg)
- MD pull request via Yu:
- Add support for a lockless bitmap.
A key feature for the new bitmap are that the IO fastpath is
lockless. If a user issues lots of write IO to the same bitmap
bit in a short time, only the first write has additional overhead
to update bitmap bit, no additional overhead for the following
writes.
By supporting only resync or recover written data, means in the
case creating new array or replacing with a new disk, there is no
need to do a full disk resync/recovery.
- Switch ->getgeo() and ->bios_param() to using struct gendisk rather
than struct block_device.
- Rust block changes via Andreas. This series adds configuration via
configfs and remote completion to the rnull driver. The series also
includes a set of changes to the rust block device driver API: a few
cleanup patches, and a few features supporting the rnull changes.
The series removes the raw buffer formatting logic from
`kernel::block` and improves the logic available in `kernel::string`
to support the same use as the removed logic.
- floppy arch cleanups
- Reduce the number of dereferencing needed for ublk commands
- Restrict supported sockets for nbd. Mostly done to eliminate a class
of issues perpetually reported by syzbot, by using nonsensical socket
setups.
- A few s390 dasd block fixes
- Fix a few issues around atomic writes
- Improve DMA interation for integrity requests
- Improve how iovecs are treated with regards to O_DIRECT aligment
constraints.
We used to require each segment to adhere to the constraints, now
only the request as a whole needs to.
- Clean up and improve p2p support, enabling use of p2p for metadata
payloads
- Improve locking of request lookup, using SRCU where appropriate
- Use page references properly for brd, avoiding very long RCU sections
- Fix ordering of recursively submitted IOs
- Clean up and improve updating nr_requests for a live device
- Various fixes and cleanups
* tag 'for-6.18/block-20250929' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (164 commits)
s390/dasd: enforce dma_alignment to ensure proper buffer validation
s390/dasd: Return BLK_STS_INVAL for EINVAL from do_dasd_request
ublk: remove redundant zone op check in ublk_setup_iod()
nvme: Use non zero KATO for persistent discovery connections
nvmet: add safety check for subsys lock
nvme-core: use nvme_is_io_ctrl() for I/O controller check
nvme-core: do ioccsz/iorcsz validation only for I/O controllers
nvme-core: add method to check for an I/O controller
blk-cgroup: fix possible deadlock while configuring policy
blk-mq: fix null-ptr-deref in blk_mq_free_tags() from error path
blk-mq: Fix more tag iteration function documentation
selftests: ublk: fix behavior when fio is not installed
ublk: don't access ublk_queue in ublk_unmap_io()
ublk: pass ublk_io to __ublk_complete_rq()
ublk: don't access ublk_queue in ublk_need_complete_req()
ublk: don't access ublk_queue in ublk_check_commit_and_fetch()
ublk: don't pass ublk_queue to ublk_fetch()
ublk: don't access ublk_queue in ublk_config_io_buf()
ublk: don't access ublk_queue in ublk_check_fetch_buf()
ublk: pass q_id and tag to __ublk_check_and_get_req()
...
When UBLK_F_BUF_REG_OFF_DAEMON was added, we missed updating kublk's
feat_map, which results in the feature being reported as "unknown." Add
UBLK_F_BUF_REG_OFF_DAEMON to feat_map to fix this.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Simplify the definition of feat_map by introducing a helper macro
FEAT_NAME to avoid having to type the feature name twice. As a side
effect, this changes the names in the feature list to be the full macro
name instead of the abbreviated names that were used before, but this is
a good change for clarity.
Using the full feature macro names ruins the alignment of the output, so
change the output format to put each feature's hex value before its
name, as this is easier to align nicely. The output now looks as
follows:
root# ./kublk features
ublk_drv features: 0x7fff
0x1 : UBLK_F_SUPPORT_ZERO_COPY
0x2 : UBLK_F_URING_CMD_COMP_IN_TASK
0x4 : UBLK_F_NEED_GET_DATA
0x8 : UBLK_F_USER_RECOVERY
0x10 : UBLK_F_USER_RECOVERY_REISSUE
0x20 : UBLK_F_UNPRIVILEGED_DEV
0x40 : UBLK_F_CMD_IOCTL_ENCODE
0x80 : UBLK_F_USER_COPY
0x100 : UBLK_F_ZONED
0x200 : UBLK_F_USER_RECOVERY_FAIL_IO
0x400 : UBLK_F_UPDATE_SIZE
0x800 : UBLK_F_AUTO_BUF_REG
0x1000 : UBLK_F_QUIESCE
0x2000 : UBLK_F_PER_IO_DAEMON
0x4000 : unknown
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a new command line option --no_ublk_fixed_fd that excludes the ublk
control device (/dev/ublkcN) from io_uring's registered files array.
When this option is used, only backing files are registered starting
from index 1, while the ublk control device is accessed using its raw
file descriptor.
Add ublk_get_registered_fd() helper function that returns the appropriate
file descriptor for use with io_uring operations.
Key optimizations implemented:
- Cache UBLKS_Q_NO_UBLK_FIXED_FD flag in ublk_queue.flags to avoid
reading dev->no_ublk_fixed_fd in fast path
- Cache ublk char device fd in ublk_queue.ublk_fd for fast access
- Update ublk_get_registered_fd() to use ublk_queue * parameter
- Update io_uring_prep_buf_register/unregister() to use ublk_queue *
- Replace ublk_device * access with ublk_queue * access in fast paths
Also pass --no_ublk_fixed_fd to test_stress_04.sh for covering
plain ublk char device mode.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250827121602.2619736-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use ARRAY_SIZE() macro while calculating size of an array to improve
code readability and reduce potential sizing errors.
Implement this suggestion given by spatch tool by running
coccinelle script - scripts/coccinelle/misc/array_size.cocci
Follow ARRAY_SIZE() macro usage pattern in ublk.c introduced by,
commit ec12009318 ("selftests: ublk: fix ublk_find_tgt()")
wherever appropriate to maintain consistency.
Signed-off-by: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/aKGihYui6/Pcijbk@bhairav-test.ee.iitb.ac.in
Signed-off-by: Jens Axboe <axboe@kernel.dk>
'struct thread' is task local structure, and the related code will become
more readable if we pass it via parameter.
Meantime pass 'ublk_thread *' to ublk_io_alloc_sqes(), and this way is
natural since we use per-thread io_uring for handling IO.
More importantly it helps much for removing the current ubq_daemon or
per-io-task limit.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250713143415.2857561-13-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some failure modes are handled poorly by kublk. For example, if ublk_drv
is built as a module but not currently loaded into the kernel, ./kublk
add ... just hangs forever. This happens because in this case (and a few
others), the worker process does not notify its parent (via a write to
the shared eventfd) that it has tried and failed to initialize, so the
parent hangs forever. Fix this by ensuring that we always notify the
parent process of any initialization failure, and have the parent print
a (not very descriptive) log line when this happens.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250603-ublk_init_fail-v1-1-87c91486230e@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add support in kublk for decoupled ublk_queues and ublk server threads.
kublk now has two modes of operation:
- (preexisting mode) threads and queues are paired 1:1, and each thread
services all the I/Os of one queue
- (new mode) thread and queue counts are independently configurable.
threads service I/Os in a way that balances load across threads even
if load is not balanced over queues.
The default is the preexisting mode. The new mode is activated by
passing the --per_io_tasks flag.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-6-e9d3b119336a@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently, each ublk server I/O handler thread initializes its own
queue. However, as we move towards decoupled ublk_queues and ublk server
threads, this model does not make sense anymore, as there will no longer
be a concept of a thread having "its own" queue. So lift queue
initialization out of the per-thread ublk_io_handler_fn and into a loop
in ublk_start_daemon (which runs once for each device).
There is a part of ublk_queue_init (ring initialization) which does
actually need to happen on the thread that will use the ring; that is
separated into a separate ublk_thread_init which is still called by each
I/O handler thread.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-4-e9d3b119336a@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently have a helper ublk_queue_alloc_sqes which the ublk targets
use to allocate SQEs for their own operations. However, as we move
towards decoupled ublk_queues and ublk server threads, this helper does
not make sense anymore. SQEs are allocated from rings, and we will have
one ring per thread to avoid locking. Change the SQE allocation helper
to ublk_io_alloc_sqes. Currently this still allocates SQEs from the io's
queue's ring, but when we fully decouple threads and queues, it will
allocate from the io's thread's ring instead.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-3-e9d3b119336a@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently, when we process CQEs, we know which ublk_queue we are working
on because we know which ring we are working on, and ublk_queues and
rings are in 1:1 correspondence. However, as we decouple ublk_queues
from ublk server threads, ublk_queues and rings will no longer be in 1:1
correspondence - each ublk server thread will have a ring, and each
thread may issue commands against more than one ublk_queue. So in order
to know which ublk_queue a CQE refers to, plumb that information in the
associated SQE's user_data.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250529-ublk_task_per_io-v8-2-e9d3b119336a@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add test for covering UBLK_AUTO_BUF_REG_FALLBACK:
- pass '--auto_zc_fallback' to null target, which requires both F_AUTO_BUF_REG
and F_SUPPORT_ZERO_COPY for handling UBLK_AUTO_BUF_REG_FALLBACK
- add ->buf_index() method for returning invalid buffer index to trigger
UBLK_AUTO_BUF_REG_FALLBACK
- add generic_09 for running the test
- add --auto_zc_fallback test in stress_03/stress_04/stress_05
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250520045455.515691-7-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Enable UBLK_F_AUTO_BUF_REG support for ublk utility by argument `--auto_zc`,
meantime support this feature in null, loop and stripe target code.
Add function test generic_08 for covering basic UBLK_F_AUTO_BUF_REG feature.
Also cover UBLK_F_AUTO_BUF_REG in stress_03, stress_04 and stress_05 test too.
'fio/t/io_uring -p0 /dev/ublkb0' shows that F_AUTO_BUF_REG can improve
IOPS by 50% compared with F_SUPPORT_ZERO_COPY in my test VM.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250520045455.515691-6-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit 57e13a2e8c ("selftests: ublk: support user recovery") starts to
support UBLK_F_NEED_GET_DATA for covering recovery feature, however the
ublk utility implementation isn't done correctly.
Fix it by supporting UBLK_F_NEED_GET_DATA correctly.
Also add test generic_07 for covering UBLK_F_NEED_GET_DATA.
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Fixes: 57e13a2e8c ("selftests: ublk: support user recovery")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250429022941.1718671-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In NUMA machine, ublk IO performance is very sensitive with queue
pthread's affinity setting.
Retrieve queue's affinity and select the 1st cpu as queue thread's sched
affinity, and it is observed that single cpu task affinity can get
stable & good performance if client application is put on proper cpu.
Dump this info when adding one ublk device. Use shmem to communicate
queue's tid between parent and daemon.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250412023035.2649275-9-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Detach ublk daemon from the starting process completely by double-fork and
clearing its process group, so that `_add_ublk_dev` can return from sub-shell.
Then it is more friendly for writing shell test script for adding/recovering
ublk device.
Prepare for running ublk test in parallel.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250412023035.2649275-5-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are a couple of places in the kublk selftests ublk server which
use the legacy ublk opcodes. These operations fail (with -EOPNOTSUPP) on
a kernel compiled without CONFIG_BLKDEV_UBLK_LEGACY_OPCODES set. We
could easily require it to be set as a prerequisite for these selftests,
but since new applications should not be using the legacy opcodes, use
the ioctl-encoded opcodes everywhere in kublk.
Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250401-ublk_selftests-v1-1-98129c9bc8bb@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add ublk stripe target which can take 1~4 underlying backing files
or block device, with stripe size 4k ~ 512K.
Add two basic tests(write verify & mkfs/mount/umount) over ublk/stripe.
This target is helpful to cover multiple IOs aiming at same
fixed/registered IO kernel buffer.
It is also capable of verifying vectored registered (kernel)buffers
in future for zero copy, so far it isn't supported yet.
Todo: support vectored registered kernel buffer for ublk/zc.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250322093218.431419-9-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
- pass 'truct dev_ctx *ctx' to target init function
- add 'private_data' to 'struct ublk_dev' for storing target specific data
- add 'private_data' to 'struct ublk_io' for storing per-IO data
- add 'tgt_ios' to 'struct ublk_io' for counting how many io_uring ios
for handling the current io command
- add helper ublk_get_io() for supporting stripe target
- add two helpers for simplifying target io handling
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250322093218.431419-6-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Improve ublk_stop_io_daemon() in the following ways:
- don't wait if ->ublksrv_pid becomes -1, which means that the disk
has been stopped
- don't wait if ublk char device doesn't exist any more, so we can
avoid to rely on inoitfy for wait until the char device is closed
And this way may reduce time of delete command a lot.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20250303124324.3563605-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Both ublk driver and userspace heavily depends on io_uring subsystem,
and tools/testing/selftests/ should be the best place for holding this
cross-subsystem tests.
Add basic read/write IO test over this ublk null disk, and make sure ublk
working.
More tests will be added.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250228161919.2869102-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
