We can easily have up to 24 flags with sane
atomicity, _without_ pushing anything out
of the first cacheline of struct block_device.
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQQqUNBr3gm4hGXdBJlZ7Krx/gZQ6wUCZkznRwAKCRBZ7Krx/gZQ
69XpAQDOZCyvYOZ/dlMOKKLf2vAojC/h++E/NjvGt3erbvVN2wEArXMi13ECsoCw
JYJA3MsmvjuY6VNcm24icf2/p4TMIgo=
=JyYi
-----END PGP SIGNATURE-----
Merge tag 'pull-bd_flags-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull bdev flags update from Al Viro:
"Compactifying bdev flags.
We can easily have up to 24 flags with sane atomicity, _without_
pushing anything out of the first cacheline of struct block_device"
* tag 'pull-bd_flags-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
bdev: move ->bd_make_it_fail to ->__bd_flags
bdev: move ->bd_ro_warned to ->__bd_flags
bdev: move ->bd_has_subit_bio to ->__bd_flags
bdev: move ->bd_write_holder into ->__bd_flags
bdev: move ->bd_read_only to ->__bd_flags
bdev: infrastructure for flags
wrapper for access to ->bd_partno
Use bdev_is_paritition() instead of open-coding it
Currently, io_ticks is accounted based on sampling, specifically
update_io_ticks() will always account io_ticks by 1 jiffies from
bdev_start_io_acct()/blk_account_io_start(), and the result can be
inaccurate, for example(HZ is 250):
Test script:
fio -filename=/dev/sda -bs=4k -rw=write -direct=1 -name=test -thinktime=4ms
Test result: util is about 90%, while the disk is really idle.
This behaviour is introduced by commit 5b18b5a737 ("block: delete
part_round_stats and switch to less precise counting"), however, there
was a key point that is missed that this patch also improve performance
a lot:
Before the commit:
part_round_stats:
if (part->stamp != now)
stats |= 1;
part_in_flight()
-> there can be lots of task here in 1 jiffies.
part_round_stats_single()
__part_stat_add()
part->stamp = now;
After the commit:
update_io_ticks:
stamp = part->bd_stamp;
if (time_after(now, stamp))
if (try_cmpxchg())
__part_stat_add()
-> only one task can reach here in 1 jiffies.
Hence in order to account io_ticks precisely, we only need to know if
there are IO inflight at most once in one jiffies. Noted that for
rq-based device, iterating tags should not be used here because
'tags->lock' is grabbed in blk_mq_find_and_get_req(), hence
part_stat_lock_inc/dec() and part_in_flight() is used to trace inflight.
The additional overhead is quite little:
- per cpu add/dec for each IO for rq-based device;
- per cpu sum for each jiffies;
And it's verified by null-blk that there are no performance degration
under heavy IO pressure.
Fixes: 5b18b5a737 ("block: delete part_round_stats and switch to less precise counting")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20240509123717.3223892-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_zone_complete_request() must be called to handle the completion of a
zone write request handled with zone write plugging. This function is
called from blk_complete_request(), blk_update_request() and also in
blk_mq_submit_bio() error path. Improve this by moving this function
call into blk_mq_finish_request() as all requests are processed with
this function when they complete as well as when they are freed without
being executed. This also improves blk_update_request() used by scsi
devices as these may repeatedly call this function to handle partial
completions.
To be consistent with this change, blk_zone_complete_request() is
renamed to blk_zone_finish_request() and
blk_zone_write_plug_complete_request() is renamed to
blk_zone_write_plug_finish_request().
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240501110907.96950-12-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Zone write plugging ignores empty (no data) flush operations but handles
flush BIOs that have data to ensure that the flush machinery generated
write is processed in order. However, the call to
blk_zone_write_plug_attempt_merge() which sets a request
RQF_ZONE_WRITE_PLUGGING flag is called after blk_insert_flush(), thus
missing indicating that a non empty flush request completion needs
handling by zone write plugging.
Fix this by moving the call to blk_zone_write_plug_attempt_merge()
before blk_insert_flush(). And while at it, rename that function as
blk_zone_write_plug_init_request() to be clear that it is not just about
merging plugged BIOs in the request. While at it, also add a WARN_ONCE()
check that the zone write plug for the request is not NULL.
Fixes: dd291d77cc ("block: Introduce zone write plugging")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240501110907.96950-10-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With the block layer zone write plugging being automatically done for
any write operation to a zone of a zoned block device, a regular request
plugging handled through current->plug can only ever see at most a
single write request per zone. In such case, any potential reordering
of the plugged requests will be harmless. We can thus remove the special
casing for write operations to zones and have these requests plugged as
well. This allows removing the function blk_mq_plug and instead directly
using current->plug where needed.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240408014128.205141-29-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The zone append emulation of the scsi disk driver was the only driver
using BLK_STS_ZONE_RESOURCE. With this code removed,
BLK_STS_ZONE_RESOURCE is now unused. Remove this macro definition and
simplify blk_mq_dispatch_rq_list() where this status code was handled.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240408014128.205141-20-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Given that zone write plugging manages all writes to zones of a zoned
block device and tracks the write pointer position of all zones that are
not full nor empty, emulating zone append operations using regular
writes can be implemented generically, without relying on the underlying
device driver to implement such emulation. This is needed for devices
that do not natively support the zone append command (e.g. SMR
hard-disks).
A device may request zone append emulation by setting its
max_zone_append_sectors queue limit to 0. For such device, the function
blk_zone_wplug_prepare_bio() changes zone append BIOs into
non-mergeable regular write BIOs. Modified zone append BIOs are flagged
with the new BIO flag BIO_EMULATES_ZONE_APPEND. This flag is checked
on completion of the BIO in blk_zone_write_plug_bio_endio() to restore
the original REQ_OP_ZONE_APPEND operation code of the BIO.
The block layer internal inline helper function bio_is_zone_append() is
added to test if a BIO is either a native zone append operation
(REQ_OP_ZONE_APPEND operation code) or if it is flagged with
BIO_EMULATES_ZONE_APPEND. Given that both native and emulated zone
append BIO completion handling should be similar, The functions
blk_update_request() and blk_zone_complete_request_bio() are modified to
use bio_is_zone_append() to execute blk_zone_update_request_bio() for
both native and emulated zone append operations.
This commit contains contributions from Christoph Hellwig <hch@lst.de>.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20240408014128.205141-11-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Zone write plugging implements a per-zone "plug" for write operations
to control the submission and execution order of write operations to
sequential write required zones of a zoned block device. Per-zone
plugging guarantees that at any time there is at most only one write
request per zone being executed. This mechanism is intended to replace
zone write locking which implements a similar per-zone write throttling
at the scheduler level, but is implemented only by mq-deadline.
Unlike zone write locking which operates on requests, zone write
plugging operates on BIOs. A zone write plug is simply a BIO list that
is atomically manipulated using a spinlock and a kblockd submission
work. A write BIO to a zone is "plugged" to delay its execution if a
write BIO for the same zone was already issued, that is, if a write
request for the same zone is being executed. The next plugged BIO is
unplugged and issued once the write request completes.
This mechanism allows to:
- Untangle zone write ordering from block IO schedulers. This allows
removing the restriction on using mq-deadline for writing to zoned
block devices. Any block IO scheduler, including "none" can be used.
- Zone write plugging operates on BIOs instead of requests. Plugged
BIOs waiting for execution thus do not hold scheduling tags and thus
are not preventing other BIOs from executing (reads or writes to
other zones). Depending on the workload, this can significantly
improve the device use (higher queue depth operation) and
performance.
- Both blk-mq (request based) zoned devices and BIO-based zoned devices
(e.g. device mapper) can use zone write plugging. It is mandatory
for the former but optional for the latter. BIO-based drivers can
use zone write plugging to implement write ordering guarantees, or
the drivers can implement their own if needed.
- The code is less invasive in the block layer and is mostly limited to
blk-zoned.c with some small changes in blk-mq.c, blk-merge.c and
bio.c.
Zone write plugging is implemented using struct blk_zone_wplug. This
structure includes a spinlock, a BIO list and a work structure to
handle the submission of plugged BIOs. Zone write plugs structures are
managed using a per-disk hash table.
Plugging of zone write BIOs is done using the function
blk_zone_write_plug_bio() which returns false if a BIO execution does
not need to be delayed and true otherwise. This function is called
from blk_mq_submit_bio() after a BIO is split to avoid large BIOs
spanning multiple zones which would cause mishandling of zone write
plugs. This ichange enables by default zone write plugging for any mq
request-based block device. BIO-based device drivers can also use zone
write plugging by expliclty calling blk_zone_write_plug_bio() in their
->submit_bio method. For such devices, the driver must ensure that a
BIO passed to blk_zone_write_plug_bio() is already split and not
straddling zone boundaries.
Only write and write zeroes BIOs are plugged. Zone write plugging does
not introduce any significant overhead for other operations. A BIO that
is being handled through zone write plugging is flagged using the new
BIO flag BIO_ZONE_WRITE_PLUGGING. A request handling a BIO flagged with
this new flag is flagged with the new RQF_ZONE_WRITE_PLUGGING flag.
The completion of BIOs and requests flagged trigger respectively calls
to the functions blk_zone_write_bio_endio() and
blk_zone_write_complete_request(). The latter function is used to
trigger submission of the next plugged BIO using the zone plug work.
blk_zone_write_bio_endio() does the same for BIO-based devices.
This ensures that at any time, at most one request (blk-mq devices) or
one BIO (BIO-based devices) is being executed for any zone. The
handling of zone write plugs using a per-zone plug spinlock maximizes
parallelism and device usage by allowing multiple zones to be writen
simultaneously without lock contention.
Zone write plugging ignores flush BIOs without data. Hovever, any flush
BIO that has data is always plugged so that the write part of the flush
sequence is serialized with other regular writes.
Given that any BIO handled through zone write plugging will be the only
BIO in flight for the target zone when it is executed, the unplugging
and submission of a BIO will have no chance of successfully merging with
plugged requests or requests in the scheduler. To overcome this
potential performance degradation, blk_mq_submit_bio() calls the
function blk_zone_write_plug_attempt_merge() to try to merge other
plugged BIOs with the one just unplugged and submitted. Successful
merging is signaled using blk_zone_write_plug_bio_merged(), called from
bio_attempt_back_merge(). Furthermore, to avoid recalculating the number
of segments of plugged BIOs to attempt merging, the number of segments
of a plugged BIO is saved using the new struct bio field
__bi_nr_segments. To avoid growing the size of struct bio, this field is
added as a union with the bio_cookie field. This is safe to do as
polling is always disabled for plugged BIOs.
When BIOs are plugged in a zone write plug, the device request queue
usage counter is always incremented. This reference is kept and reused
for blk-mq devices when the plugged BIO is unplugged and submitted
again using submit_bio_noacct_nocheck(). For this case, the unplugged
BIO is already flagged with BIO_ZONE_WRITE_PLUGGING and
blk_mq_submit_bio() proceeds directly to allocating a new request for
the BIO, re-using the usage reference count taken when the BIO was
plugged. This extra reference count is dropped in
blk_zone_write_plug_attempt_merge() for any plugged BIO that is
successfully merged. Given that BIO-based devices will not take this
path, the extra reference is dropped after a plugged BIO is unplugged
and submitted.
Zone write plugs are dynamically allocated and managed using a hash
table (an array of struct hlist_head) with RCU protection.
A zone write plug is allocated when a write BIO is received for the
zone and not freed until the zone is fully written, reset or finished.
To detect when a zone write plug can be freed, the write state of each
zone is tracked using a write pointer offset which corresponds to the
offset of a zone write pointer relative to the zone start. Write
operations always increment this write pointer offset. Zone reset
operations set it to 0 and zone finish operations set it to the zone
size.
If a write error happens, the wp_offset value of a zone write plug may
become incorrect and out of sync with the device managed write pointer.
This is handled using the zone write plug flag BLK_ZONE_WPLUG_ERROR.
The function blk_zone_wplug_handle_error() is called from the new disk
zone write plug work when this flag is set. This function executes a
report zone to update the zone write pointer offset to the current
value as indicated by the device. The disk zone write plug work is
scheduled whenever a BIO flagged with BIO_ZONE_WRITE_PLUGGING completes
with an error or when bio_zone_wplug_prepare_bio() detects an unaligned
write. Once scheduled, the disk zone write plugs work keeps running
until all zone errors are handled.
To match the new data structures used for zoned disks, the function
disk_free_zone_bitmaps() is renamed to the more generic
disk_free_zone_resources(). The function disk_init_zone_resources() is
also introduced to initialize zone write plugs resources when a gendisk
is allocated.
In order to guarantee that the user can simultaneously write up to a
number of zones equal to a device max active zone limit or max open zone
limit, zone write plugs are allocated using a mempool sized to the
maximum of these 2 device limits. For a device that does not have
active and open zone limits, 128 is used as the default mempool size.
If a change to the device active and open zone limits is detected, the
disk mempool is resized when blk_revalidate_disk_zones() is executed.
This commit contains contributions from Christoph Hellwig <hch@lst.de>.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240408014128.205141-8-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
On completion of a zone append request, the request sector indicates the
location of the written data. This value must be returned to the user
through the BIO iter sector. This is done in 2 places: in
blk_complete_request() and in blk_update_request(). Introduce the inline
helper function blk_zone_update_request_bio() to avoid duplicating
this BIO update for zone append requests, and to compile out this
helper call when CONFIG_BLK_DEV_ZONED is not enabled.
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240408014128.205141-4-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Moving req_bio_endio() code into its only caller, blk_update_request(),
allows reducing accesses to and tests of bio and request fields. Also,
given that partial completions of zone append operations is not
possible and that zone append operations cannot be merged, the update
of the BIO sector using the request sector for these operations can be
moved directly before the call to bio_endio().
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Tested-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Link: https://lore.kernel.org/r/20240408014128.205141-3-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Kernel parameter of `isolcpus=` or 'nohz_full=' are used to isolate CPUs
for specific task, and it isn't expected to let block IO disturb these CPUs.
blk-mq kworker shouldn't be scheduled on isolated CPUs. Also if isolated
CPUs is run for blk-mq kworker, long block IO latency can be caused.
Kernel workqueue only respects CPU isolation for WQ_UNBOUND, for bound
WQ, the responsibility is on user because CPU is specified as WQ API
parameter, such as mod_delayed_work_on(cpu), queue_delayed_work_on(cpu)
and queue_work_on(cpu).
So not run blk-mq kworker on isolated CPUs by removing isolated CPUs
from hctx->cpumask. Meantime use queue map to check if all CPUs in this
hw queue are offline instead of hctx->cpumask, this way can avoid any
cost in fast IO code path, and is safe since hctx->cpumask are only
used in the two cases.
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Andrew Theurer <atheurer@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Sebastian Jug <sejug@redhat.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Tejun Heo <tj@kernel.org>
Tesed-by: Joe Mario <jmario@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Link: https://lore.kernel.org/r/20240322021244.1056223-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This reverts commit 748dc0b65e.
Partial zone append completions cannot be supported as there is no
guarantees that the fragmented data will be written sequentially in the
same manner as with a full command. Commit 748dc0b65e ("block: fix
partial zone append completion handling in req_bio_endio()") changed
req_bio_endio() to always advance a partially failed BIO by its full
length, but this can lead to incorrect accounting. So revert this
change and let low level device drivers handle this case by always
failing completely zone append operations. With this revert, users will
still see an IO error for a partially completed zone append BIO.
Fixes: 748dc0b65e ("block: fix partial zone append completion handling in req_bio_endio()")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240328004409.594888-2-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZem4UQAKCRCRxhvAZXjc
ouERAQDg63R9s3bKmUgGqngf9cfr//VCTE+WVARwOUTdn2iDbwEA1IME7X1kL/Vz
EdhEjyqO6xom+ao/Vqxe0XIDNz70vgs=
=8RdE
-----END PGP SIGNATURE-----
Merge tag 'vfs-6.9.iomap' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull iomap updates from Christian Brauner:
- Restore read-write hints in struct bio through the bi_write_hint
member for the sake of UFS devices in mobile applications. This can
result in up to 40% lower write amplification in UFS devices. The
patch series that builds on this will be coming in via the SCSI
maintainers (Bart)
- Overhaul the iomap writeback code. Afterwards ->map_blocks() is able
to map multiple blocks at once as long as they're in the same folio.
This reduces CPU usage for buffered write workloads on e.g., xfs on
systems with lots of cores (Christoph)
- Record processed bytes in iomap_iter() trace event (Kassey)
- Extend iomap_writepage_map() trace event after Christoph's
->map_block() changes to map mutliple blocks at once (Zhang)
* tag 'vfs-6.9.iomap' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (22 commits)
iomap: Add processed for iomap_iter
iomap: add pos and dirty_len into trace_iomap_writepage_map
block, fs: Restore the per-bio/request data lifetime fields
fs: Propagate write hints to the struct block_device inode
fs: Move enum rw_hint into a new header file
fs: Split fcntl_rw_hint()
fs: Verify write lifetime constants at compile time
fs: Fix rw_hint validation
iomap: pass the length of the dirty region to ->map_blocks
iomap: map multiple blocks at a time
iomap: submit ioends immediately
iomap: factor out a iomap_writepage_map_block helper
iomap: only call mapping_set_error once for each failed bio
iomap: don't chain bios
iomap: move the iomap_sector sector calculation out of iomap_add_to_ioend
iomap: clean up the iomap_alloc_ioend calling convention
iomap: move all remaining per-folio logic into iomap_writepage_map
iomap: factor out a iomap_writepage_handle_eof helper
iomap: move the PF_MEMALLOC check to iomap_writepages
iomap: move the io_folios field out of struct iomap_ioend
...
For most of ARCHs, 'nr_cpus=1' is passed for kdump kernel, so
nr_hw_queues for each mapping is supposed to be 1 already.
More importantly, this way may cause trouble for driver, because blk-mq and
driver see different queue mapping since driver should setup hardware
queue setting before calling into allocating blk-mq tagset.
So not overriding nr_hw_queues and nr_maps for kdump kernel.
Cc: Wen Xiong <wenxiong@us.ibm.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240228040857.306483-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The logic in blk_mq_complete_need_ipi() assumes SMP systems where all
CPUs have equal compute capacities and only LLC cache can make
a different on perceived performance. But this assumption falls apart on
HMP systems where LLC is shared, but the CPUs have different capacities.
Staying local then can have a big performance impact if the IO request
was done from a CPU with higher capacity but the interrupt is serviced
on a lower capacity CPU.
Use the new cpus_equal_capacity() function to check if we need to send
an IPI.
Without the patch I see the BLOCK softirq always running on little cores
(where the hardirq is serviced). With it I can see it running on all
cores.
This was noticed after the topology change [1] where now on a big.LITTLE
we truly get that the LLC is shared between all cores where as in the
past it was being misrepresented for historical reasons. The logic
exposed a missing dependency on capacities for such systems where there
can be a big performance difference between the CPUs.
This of course introduced a noticeable change in behavior depending on
how the topology is presented. Leading to regressions in some workloads
as the performance of the BLOCK softirq on littles can be noticeably
worse on some platforms.
Worth noting that we could have checked for capacities being greater
than or equal instead for equality. This will lead to favouring higher
performance always. But opted for equality instead to match the
performance of the requester without making an assumption that can lead
to power trade-offs which these systems tend to be sensitive about. If
the requester would like to run faster, it's better to rely on the
scheduler to give the IO requester via some facility to run on a faster
core; and then if the interrupt triggered on a CPU with different
capacity we'll make sure to match the performance the requester is
supposed to run at.
[1] https://lpc.events/event/16/contributions/1342/attachments/962/1883/LPC-2022-Android-MC-Phantom-Domains.pdf
Signed-off-by: Qais Yousef <qyousef@layalina.io>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240223155749.2958009-3-qyousef@layalina.io
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This is the same in two places, and another will be added soon. Create a
helper for it.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20240223155910.3622666-4-kbusch@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pass a queue_limits to blk_mq_alloc_disk and apply it if non-NULL. This
will allow allocating queues with valid queue limits instead of setting
the values one at a time later.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20240213073425.1621680-11-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pass a queue_limits to blk_mq_init_queue and apply it if non-NULL. This
will allow allocating queues with valid queue limits instead of setting
the values one at a time later.
Also rename the function to blk_mq_alloc_queue as that is a much better
name for a function that allocates a queue and always pass the queuedata
argument instead of having a separate version for the extra argument.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20240213073425.1621680-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pass a queue_limits to blk_alloc_queue and apply it after validating and
capping the values using blk_validate_limits. This will allow allocating
queues with valid queue limits instead of setting the values one at a
time later.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20240213073425.1621680-9-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Restore support for passing data lifetime information from filesystems to
block drivers. This patch reverts commit b179c98f76 ("block: Remove
request.write_hint") and commit c75e707fe1 ("block: remove the
per-bio/request write hint").
This patch does not modify the size of struct bio because the new
bi_write_hint member fills a hole in struct bio. pahole reports the
following for struct bio on an x86_64 system with this patch applied:
/* size: 112, cachelines: 2, members: 20 */
/* sum members: 110, holes: 1, sum holes: 2 */
/* last cacheline: 48 bytes */
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20240202203926.2478590-7-bvanassche@acm.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
Convert any user of ktime_get_ns() to use blk_time_get_ns(), and
ktime_get() to blk_time_get(), so we have a unified API for querying the
current time in nanoseconds or as ktime.
No functional changes intended, this patch just wraps ktime_get_ns()
and ktime_get() with a block helper.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Share the main merge / split / integrity preparation code between the
cached request vs newly allocated request cases, and add comments
explaining the cached request handling.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240124092658.2258309-4-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a new helper to check if there is suitable cached request in
blk_mq_submit_bio. This removes open coded logic in blk_mq_submit_bio
and moves some checks that so far are in blk_mq_use_cached_rq to
be performed earlier. This avoids the case where we first do check
with the cached request but then later end up allocating a new one
anyway and need to grab a queue reference.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240124092658.2258309-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_mq_attempt_bio_merge has nothing to do with allocating a new
request, it avoids allocating a new request. Move the call out of
blk_mq_get_new_requests and into the only caller.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20240124092658.2258309-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit 82b74cac28 ("blk-ioprio: Convert from rqos policy to direct
call") pushed setting bio I/O priority down into blk_mq_submit_bio()
-- which is too low within block core's submit_bio() because it
skips setting I/O priority for block drivers that implement
fops->submit_bio() (e.g. DM, MD, etc).
Fix this by moving bio_set_ioprio() up from blk-mq.c to blk-core.c and
call it from submit_bio(). This ensures all block drivers call
bio_set_ioprio() during initial bio submission.
Fixes: a78418e6a0 ("block: Always initialize bio IO priority on submit")
Co-developed-by: Yibin Ding <yibin.ding@unisoc.com>
Signed-off-by: Yibin Ding <yibin.ding@unisoc.com>
Signed-off-by: Hongyu Jin <hongyu.jin@unisoc.com>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Mikulas Patocka <mpatocka@redhat.com>
[snitzer: revised commit header]
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240130202638.62600-2-snitzer@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=DLW9
-----END PGP SIGNATURE-----
Merge tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux
Pull block fixes from Jens Axboe:
- NVMe pull request via Keith:
- tcp, fc, and rdma target fixes (Maurizio, Daniel, Hannes,
Christoph)
- discard fixes and improvements (Christoph)
- timeout debug improvements (Keith, Max)
- various cleanups (Daniel, Max, Giuxen)
- trace event string fixes (Arnd)
- shadow doorbell setup on reset fix (William)
- a write zeroes quirk for SK Hynix (Jim)
- MD pull request via Song:
- Sparse warning since v6.0 (Bart)
- /proc/mdstat regression since v6.7 (Yu Kuai)
- Use symbolic error value (Christian)
- IO Priority documentation update (Christian)
- Fix for accessing queue limits without having entered the queue
(Christoph, me)
- Fix for loop dio support (Christoph)
- Move null_blk off deprecated ida interface (Christophe)
- Ensure nbd initializes full msghdr (Eric)
- Fix for a regression with the folio conversion, which is now easier
to hit because of an unrelated change (Matthew)
- Remove redundant check in virtio-blk (Li)
- Fix for a potential hang in sbitmap (Ming)
- Fix for partial zone appending (Damien)
- Misc changes and fixes (Bart, me, Kemeng, Dmitry)
* tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux: (45 commits)
Documentation: block: ioprio: Update schedulers
loop: fix the the direct I/O support check when used on top of block devices
blk-mq: Remove the hctx 'run' debugfs attribute
nbd: always initialize struct msghdr completely
block: Fix iterating over an empty bio with bio_for_each_folio_all
block: bio-integrity: fix kcalloc() arguments order
virtio_blk: remove duplicate check if queue is broken in virtblk_done
sbitmap: remove stale comment in sbq_calc_wake_batch
block: Correct a documentation comment in blk-cgroup.c
null_blk: Remove usage of the deprecated ida_simple_xx() API
block: ensure we hold a queue reference when using queue limits
blk-mq: rename blk_mq_can_use_cached_rq
block: print symbolic error name instead of error code
blk-mq: fix IO hang from sbitmap wakeup race
nvmet-rdma: avoid circular locking dependency on install_queue()
nvmet-tcp: avoid circular locking dependency on install_queue()
nvme-pci: set doorbell config before unquiescing
block: fix partial zone append completion handling in req_bio_endio()
block/iocost: silence warning on 'last_period' potentially being unused
md/raid1: Use blk_opf_t for read and write operations
...
q_usage_counter is the only thing preventing us from the limits changing
under us in __bio_split_to_limits, but blk_mq_submit_bio doesn't hold
it while calling into it.
Move the splitting inside the region where we know we've got a queue
reference. Ideally this could still remain a shared section of code, but
let's keep the fix simple and defer any refactoring here to later.
Reported-by: Christoph Hellwig <hch@lst.de>
Fixes: 900e080752 ("block: move queue enter logic into blk_mq_submit_bio()")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_mq_can_use_cached_rq doesn't just check if we can use the request,
but also performs the work to actually use it. Remove the _can in the
naming, and improve the comment describing the function.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20240111135705.2155518-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In blk_mq_mark_tag_wait(), __add_wait_queue() may be re-ordered
with the following blk_mq_get_driver_tag() in case of getting driver
tag failure.
Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observe
the added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantime
blk_mq_mark_tag_wait() can't get driver tag successfully.
This issue can be reproduced by running the following test in loop, and
fio hang can be observed in < 30min when running it on my test VM
in laptop.
modprobe -r scsi_debug
modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4
dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`
fio --filename=/dev/"$dev" --direct=1 --rw=randrw --bs=4k --iodepth=1 \
--runtime=100 --numjobs=40 --time_based --name=test \
--ioengine=libaio
Fix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), which
is just fine in case of running out of tag.
Cc: Jan Kara <jack@suse.cz>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Reported-by: Changhui Zhong <czhong@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20240112122626.4181044-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=YAfp
-----END PGP SIGNATURE-----
Merge tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe:
"Pretty quiet round this time around. This contains:
- NVMe updates via Keith:
- nvme fabrics spec updates (Guixin, Max)
- nvme target udpates (Guixin, Evan)
- nvme attribute refactoring (Daniel)
- nvme-fc numa fix (Keith)
- MD updates via Song:
- Fix/Cleanup RCU usage from conf->disks[i].rdev (Yu Kuai)
- Fix raid5 hang issue (Junxiao Bi)
- Add Yu Kuai as Reviewer of the md subsystem
- Remove deprecated flavors (Song Liu)
- raid1 read error check support (Li Nan)
- Better handle events off-by-1 case (Alex Lyakas)
- Efficiency improvements for passthrough (Kundan)
- Support for mapping integrity data directly (Keith)
- Zoned write fix (Damien)
- rnbd fixes (Kees, Santosh, Supriti)
- Default to a sane discard size granularity (Christoph)
- Make the default max transfer size naming less confusing
(Christoph)
- Remove support for deprecated host aware zoned model (Christoph)
- Misc fixes (me, Li, Matthew, Min, Ming, Randy, liyouhong, Daniel,
Bart, Christoph)"
* tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux: (78 commits)
block: Treat sequential write preferred zone type as invalid
block: remove disk_clear_zoned
sd: remove the !ZBC && blk_queue_is_zoned case in sd_read_block_characteristics
drivers/block/xen-blkback/common.h: Fix spelling typo in comment
blk-cgroup: fix rcu lockdep warning in blkg_lookup()
blk-cgroup: don't use removal safe list iterators
block: floor the discard granularity to the physical block size
mtd_blkdevs: use the default discard granularity
bcache: use the default discard granularity
zram: use the default discard granularity
null_blk: use the default discard granularity
nbd: use the default discard granularity
ubd: use the default discard granularity
block: default the discard granularity to sector size
bcache: discard_granularity should not be smaller than a sector
block: remove two comments in bio_split_discard
block: rename and document BLK_DEF_MAX_SECTORS
loop: don't abuse BLK_DEF_MAX_SECTORS
aoe: don't abuse BLK_DEF_MAX_SECTORS
null_blk: don't cap max_hw_sectors to BLK_DEF_MAX_SECTORS
...
Partial completions of zone append request is not allowed but if a zone
append completion indicates a number of completed bytes different from
the original BIO size, only the BIO status is set to error. This leads
to bio_advance() not setting the BIO size to 0 and thus to not call
bio_endio() at the end of req_bio_endio().
Make sure a partially completed zone append is failed and completed
immediately by forcing the completed number of bytes (nbytes) to be
equal to the BIO size, thus ensuring that bio_endio() is called.
Fixes: 297db73184 ("block: fix req_bio_endio append error handling")
Cc: stable@kernel.vger.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20240110092942.442334-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Write-back throttling (WBT) enables QUEUE_FLAG_STATS on the request
queue. But WBT does not make sense for passthrough io, so skip
QUEUE_FLAG_STATS processing.
Also skip rq_qos_issue/done for passthrough io.
Overall, the change gives ~11% hike in peak performance.
Signed-off-by: Kundan Kumar <kundan.kumar@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Link: https://lore.kernel.org/r/20231123190331.7934-1-kundan.kumar@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Request queue quiesce may interrupt flush sequence, and the original request
may have been marked as COMPLETE, but can't get finished because of
queue quiesce.
This way is fine from driver viewpoint, because flush sequence is block
layer concept, and it isn't related with driver.
However, driver(such as dm-rq) can call blk_mq_queue_inflight() to count &
drain inflight requests, then the wait & drain never gets done because
the completed & not-finished flush request is counted as inflight.
Fix this issue by not counting completed flush data request as inflight in
case of quiesce.
Cc: Mike Snitzer <snitzer@kernel.org>
Cc: David Jeffery <djeffery@redhat.com>
Cc: John Pittman <jpittman@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20231201085605.577730-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_integrity_unregister() can come if queue usage counter isn't held
for one bio with integrity prepared, so this request may be completed with
calling profile->complete_fn, then kernel panic.
Another constraint is that bio_integrity_prep() needs to be called
before bio merge.
Fix the issue by:
- call bio_integrity_prep() with one queue usage counter grabbed reliably
- call bio_integrity_prep() before bio merge
Fixes: 900e080752 ("block: move queue enter logic into blk_mq_submit_bio()")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Link: https://lore.kernel.org/r/20231113035231.2708053-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now we update driver tags request table in blk_mq_get_driver_tag(),
so the driver that support queue_rqs() have to update that inflight
table by itself.
Move it to blk_mq_start_request(), which is a better place where
we setup the deadline for request timeout check. And it's just
where the request becomes inflight.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230913151616.3164338-5-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since active requests have been accounted when allocate driver tags,
we can remove this limit now.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230913151616.3164338-4-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Since the previous patch change to only account active requests when
we really allocate the driver tag, the RQF_MQ_INFLIGHT can be removed
and no double account problem.
1. none elevator: flush request will use the first pending request's
driver tag, won't double account.
2. other elevator: flush request will be accounted when allocate driver
tag when issue, and will be unaccounted when it put the driver tag.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230913151616.3164338-3-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is a limit that batched queue_rqs() can't work on shared tags
queue, since the account of active requests can't be done there.
Now we account the active requests only in blk_mq_get_driver_tag(),
which is not the time we get driver tag actually (with none elevator).
To support batched queue_rqs() on shared tags queue, we move the
account of active requests to where we get the driver tag:
1. none elevator: blk_mq_get_tags() and blk_mq_get_tag()
2. other elevator: __blk_mq_alloc_driver_tag()
This is clearer and match with the unaccount side, which just happen
when we put the driver tag.
The other good point is that we don't need RQF_MQ_INFLIGHT trick
anymore, which used to avoid double account of flush request.
Now we only account when actually get the driver tag, so all is good.
We will remove RQF_MQ_INFLIGHT in the next patch.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230913151616.3164338-2-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When nr_hw_queues shrink, we free the excess tags before realloc'ing
hw_ctxs for each queue. During that resize, we may need to access those
tags, like blk_mq_tag_idle(hctx) will access queue shared tags.
This can cause a slab use-after-free, as reported by KASAN. Fix it by
moving the releasing of excess tags to the end.
Fixes: e1dd7bc930 ("blk-mq: fix tags leak when shrink nr_hw_queues")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/all/CAHj4cs_CK63uoDpGBGZ6DN4OCTpzkR3UaVgK=LX8Owr8ej2ieQ@mail.gmail.com/
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20230908005702.2183908-1-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=p1bd
-----END PGP SIGNATURE-----
Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe:
"Pretty quiet round for this release. This contains:
- Add support for zoned storage to ublk (Andreas, Ming)
- Series improving performance for drivers that mark themselves as
needing a blocking context for issue (Bart)
- Cleanup the flush logic (Chengming)
- sed opal keyring support (Greg)
- Fixes and improvements to the integrity support (Jinyoung)
- Add some exports for bcachefs that we can hopefully delete again in
the future (Kent)
- deadline throttling fix (Zhiguo)
- Series allowing building the kernel without buffer_head support
(Christoph)
- Sanitize the bio page adding flow (Christoph)
- Write back cache fixes (Christoph)
- MD updates via Song:
- Fix perf regression for raid0 large sequential writes (Jan)
- Fix split bio iostat for raid0 (David)
- Various raid1 fixes (Heinz, Xueshi)
- raid6test build fixes (WANG)
- Deprecate bitmap file support (Christoph)
- Fix deadlock with md sync thread (Yu)
- Refactor md io accounting (Yu)
- Various non-urgent fixes (Li, Yu, Jack)
- Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li,
Ming, Nitesh, Ruan, Tejun, Thomas, Xu)"
* tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits)
block: use strscpy() to instead of strncpy()
block: sed-opal: keyring support for SED keys
block: sed-opal: Implement IOC_OPAL_REVERT_LSP
block: sed-opal: Implement IOC_OPAL_DISCOVERY
blk-mq: prealloc tags when increase tagset nr_hw_queues
blk-mq: delete redundant tagset map update when fallback
blk-mq: fix tags leak when shrink nr_hw_queues
ublk: zoned: support REQ_OP_ZONE_RESET_ALL
md: raid0: account for split bio in iostat accounting
md/raid0: Fix performance regression for large sequential writes
md/raid0: Factor out helper for mapping and submitting a bio
md raid1: allow writebehind to work on any leg device set WriteMostly
md/raid1: hold the barrier until handle_read_error() finishes
md/raid1: free the r1bio before waiting for blocked rdev
md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io()
blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
drivers/rnbd: restore sysfs interface to rnbd-client
md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
raid6: test: only check for Altivec if building on powerpc hosts
raid6: test: make sure all intermediate and artifact files are .gitignored
...
Just like blk_mq_alloc_tag_set(), it's better to prepare all tags before
using to map to queue ctxs in blk_mq_map_swqueue(), which now have to
consider empty set->tags[].
The good point is that we can fallback easily if increasing nr_hw_queues
fail, instead of just mapping to hctx[0] when fail in blk_mq_map_swqueue().
And the fallback path already has tags free & clean handling, so all
is good.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230821095602.70742-3-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When we increase nr_hw_queues fail, the fallback path will use
blk_mq_update_queue_map() to clear and update all maps.
Obviously, this line of update of HCTX_TYPE_DEFAULT only is not
needed, so delete it.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230821095602.70742-2-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Although we don't need to realloc set->tags[] when shrink nr_hw_queues,
we need to free them. Or these tags will be leaked.
How to reproduce:
1. mount -t configfs configfs /mnt
2. modprobe null_blk nr_devices=0 submit_queues=8
3. mkdir /mnt/nullb/nullb0
4. echo 1 > /mnt/nullb/nullb0/power
5. echo 4 > /mnt/nullb/nullb0/submit_queues
6. rmdir /mnt/nullb/nullb0
In step 4, will alloc 9 tags (8 submit queues and 1 poll queue), then
in step 5, new_nr_hw_queues = 5 (4 submit queues and 1 poll queue).
At last in step 6, only these 5 tags are freed, the other 4 tags leaked.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230821095602.70742-1-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Chuck reported [1] an IO hang problem on NFS exports that reside on SATA
devices and bisected to commit 615939a2ae ("blk-mq: defer to the normal
submission path for post-flush requests").
We analysed the IO hang problem, found there are two postflush requests
waiting for each other.
The first postflush request completed the REQ_FSEQ_DATA sequence, so go to
the REQ_FSEQ_POSTFLUSH sequence and added in the flush pending list, but
failed to blk_kick_flush() because of the second postflush request which
is inflight waiting in scheduler queue.
The second postflush waiting in scheduler queue can't be dispatched because
the first postflush hasn't released scheduler resource even though it has
completed by itself.
Fix it by releasing scheduler resource when the first postflush request
completed, so the second postflush can be dispatched and completed, then
make blk_kick_flush() succeed.
While at it, remove the check for e->ops.finish_request, as all
schedulers set that. Reaffirm this requirement by adding a WARN_ON_ONCE()
at scheduler registration time, just like we do for insert_requests and
dispatch_request.
[1] https://lore.kernel.org/all/7A57C7AE-A51A-4254-888B-FE15CA21F9E9@oracle.com/
Link: https://lore.kernel.org/linux-block/20230819031206.2744005-1-chengming.zhou@linux.dev/
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202308172100.8ce4b853-oliver.sang@intel.com
Fixes: 615939a2ae ("blk-mq: defer to the normal submission path for post-flush requests")
Reported-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Tested-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://lore.kernel.org/r/20230813152325.3017343-1-chengming.zhou@linux.dev
[axboe: folded in incremental fix and added tags]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blk_mq_run_queue() runs the queue asynchronously if BLK_MQ_F_BLOCKING
has been set. This is suboptimal since running the queue asynchronously
is slower than running the queue synchronously. This patch modifies
blk_mq_run_queue() as follows if BLK_MQ_F_BLOCKING has been set:
- Run the queue synchronously if it is allowed to sleep.
- Run the queue asynchronously if it is not allowed to sleep.
Additionally, blk_mq_run_hw_queue(hctx, false) calls are modified into
blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING) if the caller
may be invoked from atomic context.
The following caller chains have been reviewed:
blk_mq_run_hw_queue(hctx, false)
blk_mq_get_tag() /* may sleep, hence the functions it calls may also sleep */
blk_execute_rq() /* may sleep */
blk_mq_run_hw_queues(q, async=false)
blk_freeze_queue_start() /* may sleep */
blk_mq_requeue_work() /* may sleep */
scsi_kick_queue()
scsi_requeue_run_queue() /* may sleep */
scsi_run_host_queues()
scsi_ioctl_reset() /* may sleep */
blk_mq_insert_requests(hctx, ctx, list, run_queue_async=false)
blk_mq_dispatch_plug_list(plug, from_sched=false)
blk_mq_flush_plug_list(plug, from_schedule=false)
__blk_flush_plug(plug, from_schedule=false)
blk_add_rq_to_plug()
blk_mq_submit_bio() /* may sleep if REQ_NOWAIT has not been set */
blk_mq_plug_issue_direct()
blk_mq_flush_plug_list() /* see above */
blk_mq_dispatch_plug_list(plug, from_sched=false)
blk_mq_flush_plug_list() /* see above */
blk_mq_try_issue_directly()
blk_mq_submit_bio() /* may sleep if REQ_NOWAIT has not been set */
blk_mq_try_issue_list_directly(hctx, list)
blk_mq_insert_requests() /* see above */
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230721172731.955724-4-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If request need to be completed remotely, we insert it into percpu llist,
and smp_call_function_single_async() if llist is empty previously.
We don't need to use per-rq csd, percpu csd is enough. And the size of
struct request is decreased by 24 bytes.
This way is cleaner, and looks correct, given block softirq is guaranteed
to be scheduled to consume the list if one new request is added to this
percpu list, either smp_call_function_single_async() returns -EBUSY or 0.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230717040058.3993930-2-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We have seen rare IO stalls as follows:
* blk_mq_plug_issue_direct() is entered with an mq_list containing two
requests.
* For the first request, it sets last == false and enters the driver's
queue_rq callback.
* The driver queue_rq callback indirectly calls schedule() which calls
blk_flush_plug(). This may happen if the driver has the
BLK_MQ_F_BLOCKING flag set and is allowed to sleep in ->queue_rq.
* blk_flush_plug() handles the remaining request in the mq_list. mq_list
is now empty.
* The original call to queue_rq resumes (with last == false).
* The loop in blk_mq_plug_issue_direct() terminates because there are no
remaining requests in mq_list.
The IO is now stalled because the last request submitted to the driver
had last == false and there was no subsequent call to commit_rqs().
Fix this by returning early in blk_mq_flush_plug_list() if rq_count is 0
which it will be in the recursive case, rather than checking if the
mq_list is empty. At the same time, adjust one of the callers to skip
the mq_list empty check as it is not necessary.
Fixes: dc5fc361d8 ("block: attempt direct issue of plug list")
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230714101106.3635611-1-ross.lagerwall@citrix.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The iocost rely on rq start_time_ns and alloc_time_ns to tell saturation
state of the block device. Most of the time request is allocated after
rq_qos_throttle() and its alloc_time_ns or start_time_ns won't be affected.
But for plug batched allocation introduced by the commit 47c122e35d
("block: pre-allocate requests if plug is started and is a batch"), we can
rq_qos_throttle() after the allocation of the request. This is what the
blk_mq_get_cached_request() does.
In this case, the cached request alloc_time_ns or start_time_ns is much
ahead if blocked in any qos ->throttle().
Fix it by setting alloc_time_ns and start_time_ns to now when the allocated
request is actually used.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230710105516.2053478-1-chengming.zhou@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
