The driver core ignores the return value of struct bus_type::remove()
(and so wmi_dev_remove()) because there is only little that can be done.
To simplify the quest to make this function return void, let struct
wmi_driver::remove() return void, too. All implementers of this callback
return 0 already and this way it should be obvious to driver authors
that returning an error code is a bad idea.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Pali Rohár <pali@kernel.org>
Link: https://lore.kernel.org/r/20210301160404.1677064-1-u.kleine-koenig@pengutronix.de
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
The SSAM_DEFINE_SYNC_REQUEST_x() macros are intended to reduce
boiler-plate code for SSAM request definitions by defining a wrapper
function for the specified request. The client device variants of those
macros, i.e. SSAM_DEFINE_SYNC_REQUEST_CL_x() in particular rely on the
multi-device (MD) variants, e.g.:
#define SSAM_DEFINE_SYNC_REQUEST_CL_R(name, rtype, spec...) \
SSAM_DEFINE_SYNC_REQUEST_MD_R(__raw_##name, rtype, spec) \
int name(struct ssam_device *sdev, rtype *ret) \
{ \
return __raw_##name(sdev->ctrl, sdev->uid.target, \
sdev->uid.instance, ret); \
}
This now creates the problem that it is not possible to declare the
generated functions static via
static SSAM_DEFINE_SYNC_REQUEST_CL_R(...)
as this will only apply to the function defined by the multi-device
macro, i.e. SSAM_DEFINE_SYNC_REQUEST_MD_R(). Thus compiling with
`-Wmissing-prototypes' rightfully complains that there is a 'static'
keyword missing.
To solve this, make all SSAM_DEFINE_SYNC_REQUEST_x() macros define
static functions. Non-client-device macros are also changed for
consistency. In general, we expect those functions to be only used
locally in the respective drivers for the corresponding interfaces, so
having to define a wrapper function to be able to export this should be
the odd case out.
Reported-by: kernel test robot <lkp@intel.com>
Fixes: b78b4982d7 ("platform/surface: Add platform profile driver")
Signed-off-by: Maximilian Luz <luzmaximilian@gmail.com>
Link: https://lore.kernel.org/r/20210304190524.1172197-1-luzmaximilian@gmail.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Plantronics Blackwire 3220 Series (047f:c056) sends HID reports twice
for each volume key press. This patch adds a quirk to hid-plantronics
for this product ID, which will ignore the second volume key press if
it happens within 5 ms from the last one that was handled.
The patch was tested on the mentioned model only, it shouldn't affect
other models, however, this quirk might be needed for them too.
Auto-repeat (when a key is held pressed) is not affected, because the
rate is about 3 times per second, which is far less frequent than once
in 5 ms.
Fixes: 81bb773fae ("HID: plantronics: Update to map volume up/down controls")
Signed-off-by: Maxim Mikityanskiy <maxtram95@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
We don't use task file notes anymore, and no need left in indexing
task->io_uring->xa by file, and replace it with ctx. It's better
design-wise, especially since we keep a dangling file, and so have to
keep an eye on not dereferencing it.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains Netfilter fixes for net:
1) Fix incorrect enum type definition in nfnetlink_cthelper UAPI,
from Dmitry V. Levin.
2) Remove extra space in deprecated automatic helper assignment
notice, from Klemen Košir.
3) Drop early socket demux socket after NAT mangling, from
Florian Westphal. Add a test to exercise this bug.
4) Fix bogus invalid packet report in the conntrack TCP tracker,
also from Florian.
5) Fix access to xt[NFPROTO_UNSPEC] list with no mutex
in target/match_revfn(), from Vasily Averin.
6) Disallow updates on the table ownership flag.
7) Fix double hook unregistration of tables with owner.
8) Remove bogus check on the table owner in __nft_release_tables().
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
There's a non-trivial conflict between the parallel TLB flush
framework and the IPI flush debugging code - merge them
manually.
Conflicts:
kernel/smp.c
Signed-off-by: Ingo Molnar <mingo@kernel.org>
To improve TLB shootdown performance, flush the remote and local TLBs
concurrently. Introduce flush_tlb_multi() that does so. Introduce
paravirtual versions of flush_tlb_multi() for KVM, Xen and hyper-v (Xen
and hyper-v are only compile-tested).
While the updated smp infrastructure is capable of running a function on
a single local core, it is not optimized for this case. The multiple
function calls and the indirect branch introduce some overhead, and
might make local TLB flushes slower than they were before the recent
changes.
Before calling the SMP infrastructure, check if only a local TLB flush
is needed to restore the lost performance in this common case. This
requires to check mm_cpumask() one more time, but unless this mask is
updated very frequently, this should impact performance negatively.
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com> # Hyper-v parts
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen and paravirt parts
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20210220231712.2475218-5-namit@vmware.com
Sometimes the PMU internal buffers have to be flushed for per-CPU events
during a context switch, e.g., large PEBS. Otherwise, the perf tool may
report samples in locations that do not belong to the process where the
samples are processed in, because PEBS does not tag samples with PID/TID.
The current code only flush the buffers for a per-task event. It doesn't
check a per-CPU event.
Add a new event state flag, PERF_ATTACH_SCHED_CB, to indicate that the
PMU internal buffers have to be flushed for this event during a context
switch.
Add sched_cb_entry and perf_sched_cb_usages back to track the PMU/cpuctx
which is required to be flushed.
Only need to invoke the sched_task() for per-CPU events in this patch.
The per-task events have been handled in perf_event_context_sched_in/out
already.
Fixes: 9c964efa43 ("perf/x86/intel: Drain the PEBS buffer during context switches")
Reported-by: Gabriel Marin <gmx@google.com>
Originally-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201130193842.10569-1-kan.liang@linux.intel.com
Adds defines for lock state returns from lock_is_held_type() based on
Johannes Berg's suggestions as it make it easier to read and maintain
the lock states. These are defines and a enum to avoid changes to
lock_is_held_type() and lockdep_is_held() return types.
Updates to lock_is_held_type() and __lock_is_held() to use the new
defines.
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/linux-wireless/871rdmu9z9.fsf@codeaurora.org/
Some kernel functions must be called without holding a specific lock.
Add lockdep_assert_not_held() to be used in these functions to detect
incorrect calls while holding a lock.
lockdep_assert_not_held() provides the opposite functionality of
lockdep_assert_held() which is used to assert calls that require
holding a specific lock.
Incorporates suggestions from Peter Zijlstra to avoid misfires when
lockdep_off() is employed.
The need for lockdep_assert_not_held() came up in a discussion on
ath10k patch. ath10k_drain_tx() and i915_vma_pin_ww() are examples
of functions that can use lockdep_assert_not_held().
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/linux-wireless/871rdmu9z9.fsf@codeaurora.org/
Many drivers don't want interrupts enabled automatically via request_irq().
So they are handling this issue by either way of the below two:
(1)
irq_set_status_flags(irq, IRQ_NOAUTOEN);
request_irq(dev, irq...);
(2)
request_irq(dev, irq...);
disable_irq(irq);
The code in the second way is silly and unsafe. In the small time gap
between request_irq() and disable_irq(), interrupts can still come.
The code in the first way is safe though it's subobtimal.
Add a new IRQF_NO_AUTOEN flag which can be handed in by drivers to
request_irq() and request_nmi(). It prevents the automatic enabling of the
requested interrupt/nmi in the same safe way as #1 above. With that the
various usage sites of #1 and #2 above can be simplified and corrected.
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: dmitry.torokhov@gmail.com
Link: https://lore.kernel.org/r/20210302224916.13980-2-song.bao.hua@hisilicon.com
Move the reclaim detection from the timer tick to the task state
tracking machinery using the recently added ONCPU state. And we
also add task psi_flags changes checking in the psi_task_switch()
optimization to update the parents properly.
In terms of performance and cost, this ONCPU task state tracking
is not cheaper than previous timer tick in aggregate. But the code is
simpler and shorter this way, so it's a maintainability win. And
Johannes did some testing with perf bench, the performace and cost
changes would be acceptable for real workloads.
Thanks to Johannes Weiner for pointing out the psi_task_switch()
optimization things and the clearer changelog.
Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20210303034659.91735-3-zhouchengming@bytedance.com
The recent addition of in_serving_softirq() to kconv.h results in
compile failure on PREEMPT_RT because it requires
task_struct::softirq_disable_cnt. This is not available if kconv.h is
included from sched.h.
It is not needed to include kconv.h from sched.h. All but the net/ user
already include the kconv header file.
Move the include of the kconv.h header from sched.h it its users.
Additionally include sched.h from kconv.h to ensure that everything
task_struct related is available.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Andrey Konovalov <andreyknvl@google.com>
Link: https://lkml.kernel.org/r/20210218173124.iy5iyqv3a4oia4vv@linutronix.de
We currently find out about the presence of a HW PMU (or the handling
of that PMU by perf, which amounts to the same thing) in a fairly
roundabout way, by checking the number of counters available to perf.
That's good enough for now, but we will soon need to find about about
that on paths where perf is out of reach (in the world switch).
Instead, let's turn kvm_arm_support_pmu_v3() into a static key.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Link: https://lore.kernel.org/r/20210209114844.3278746-2-maz@kernel.org
Message-Id: <20210305185254.3730990-5-maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull block fixes from Jens Axboe:
- NVMe fixes:
- more device quirks (Julian Einwag, Zoltán Böszörményi, Pascal
Terjan)
- fix a hwmon error return (Daniel Wagner)
- fix the keep alive timeout initialization (Martin George)
- ensure the model_number can't be changed on a used subsystem
(Max Gurtovoy)
- rsxx missing -EFAULT on copy_to_user() failure (Dan)
- rsxx remove unused linux.h include (Tian)
- kill unused RQF_SORTED (Jean)
- updated outdated BFQ comments (Joseph)
- revert work-around commit for bd_size_lock, since we removed the
offending user in this merge window (Damien)
* tag 'block-5.12-2021-03-05' of git://git.kernel.dk/linux-block:
nvmet: model_number must be immutable once set
nvme-fabrics: fix kato initialization
nvme-hwmon: Return error code when registration fails
nvme-pci: add quirks for Lexar 256GB SSD
nvme-pci: mark Kingston SKC2000 as not supporting the deepest power state
nvme-pci: mark Seagate Nytro XM1440 as QUIRK_NO_NS_DESC_LIST.
rsxx: Return -EFAULT if copy_to_user() fails
block/bfq: update comments and default value in docs for fifo_expire
rsxx: remove unused including <linux/version.h>
block: Drop leftover references to RQF_SORTED
block: revert "block: fix bd_size_lock use"
Pull io_uring fixes from Jens Axboe:
"A bit of a mix between fallout from the worker change, cleanups and
reductions now possible from that change, and fixes in general. In
detail:
- Fully serialize manager and worker creation, fixing races due to
that.
- Clean up some naming that had gone stale.
- SQPOLL fixes.
- Fix race condition around task_work rework that went into this
merge window.
- Implement unshare. Used for when the original task does unshare(2)
or setuid/seteuid and friends, drops the original workers and forks
new ones.
- Drop the only remaining piece of state shuffling we had left, which
was cred. Move it into issue instead, and we can drop all of that
code too.
- Kill f_op->flush() usage. That was such a nasty hack that we had
out of necessity, we no longer need it.
- Following from ->flush() removal, we can also drop various bits of
ctx state related to SQPOLL and cancelations.
- Fix an issue with IOPOLL retry, which originally was fallout from a
filemap change (removing iov_iter_revert()), but uncovered an issue
with iovec re-import too late.
- Fix an issue with system suspend.
- Use xchg() for fallback work, instead of cmpxchg().
- Properly destroy io-wq on exec.
- Add create_io_thread() core helper, and use that in io-wq and
io_uring. This allows us to remove various silly completion events
related to thread setup.
- A few error handling fixes.
This should be the grunt of fixes necessary for the new workers, next
week should be quieter. We've got a pending series from Pavel on
cancelations, and how tasks and rings are indexed. Outside of that,
should just be minor fixes. Even with these fixes, we're still killing
a net ~80 lines"
* tag 'io_uring-5.12-2021-03-05' of git://git.kernel.dk/linux-block: (41 commits)
io_uring: don't restrict issue_flags for io_openat
io_uring: make SQPOLL thread parking saner
io-wq: kill hashed waitqueue before manager exits
io_uring: clear IOCB_WAITQ for non -EIOCBQUEUED return
io_uring: don't keep looping for more events if we can't flush overflow
io_uring: move to using create_io_thread()
kernel: provide create_io_thread() helper
io_uring: reliably cancel linked timeouts
io_uring: cancel-match based on flags
io-wq: ensure all pending work is canceled on exit
io_uring: ensure that threads freeze on suspend
io_uring: remove extra in_idle wake up
io_uring: inline __io_queue_async_work()
io_uring: inline io_req_clean_work()
io_uring: choose right tctx->io_wq for try cancel
io_uring: fix -EAGAIN retry with IOPOLL
io-wq: fix error path leak of buffered write hash map
io_uring: remove sqo_task
io_uring: kill sqo_dead and sqo submission halting
io_uring: ignore double poll add on the same waitqueue head
...
Pull ACPI fix from Rafael Wysocki:
"Make the empty stubs of some helper functions used when CONFIG_ACPI is
not set actually match those functions (Andy Shevchenko)"
* tag 'acpi-5.12-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
ACPI: bus: Constify is_acpi_node() and friends (part 2)
Alexei Starovoitov says:
====================
pull-request: bpf 2021-03-04
The following pull-request contains BPF updates for your *net* tree.
We've added 7 non-merge commits during the last 4 day(s) which contain
a total of 9 files changed, 128 insertions(+), 40 deletions(-).
The main changes are:
1) Fix 32-bit cmpxchg, from Brendan.
2) Fix atomic+fetch logic, from Ilya.
3) Fix usage of bpf_csum_diff in selftests, from Yauheni.
====================
Pull tracing fixes from Steven Rostedt:
"Functional fixes:
- Fix big endian conversion for arm64 in recordmcount processing
- Fix timestamp corruption in ring buffer on discarding events
- Fix memory leak in __create_synth_event()
- Skip selftests if tracing is disabled as it will cause them to
fail.
Non-functional fixes:
- Fix help text in Kconfig
- Remove duplicate prototype for trace_empty()
- Fix stale comment about the trace_event_call flags.
Self test update:
- Add more information to the validation output of when a corrupt
timestamp is found in the ring buffer, and also trigger a warning
to make sure that tests catch it"
* tag 'trace-v5.12-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing: Fix comment about the trace_event_call flags
tracing: Skip selftests if tracing is disabled
tracing: Fix memory leak in __create_synth_event()
ring-buffer: Add a little more information and a WARN when time stamp going backwards is detected
ring-buffer: Force before_stamp and write_stamp to be different on discard
tracing: Fix help text of TRACEPOINT_BENCHMARK in Kconfig
tracing: Remove duplicate declaration from trace.h
ftrace: Have recordmcount use w8 to read relp->r_info in arm64_is_fake_mcount
Allow to pass sk_lookup programs to PROG_TEST_RUN. User space
provides the full bpf_sk_lookup struct as context. Since the
context includes a socket pointer that can't be exposed
to user space we define that PROG_TEST_RUN returns the cookie
of the selected socket or zero in place of the socket pointer.
We don't support testing programs that select a reuseport socket,
since this would mean running another (unrelated) BPF program
from the sk_lookup test handler.
Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210303101816.36774-3-lmb@cloudflare.com
These descriptions are present in the man-pages project from the
original submissions around 2015-2016. Import them so that they can be
kept up to date as developers extend the bpf syscall commands.
These descriptions follow the pattern used by scripts/bpf_helpers_doc.py
so that we can take advantage of the parser to generate more up-to-date
man page writing based upon these headers.
Some minor wording adjustments were made to make the descriptions
more consistent for the description / return format.
Signed-off-by: Joe Stringer <joe@cilium.io>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210302171947.2268128-2-joe@cilium.io
Co-authored-by: Alexei Starovoitov <ast@kernel.org>
Co-authored-by: Michael Kerrisk <mtk.manpages@gmail.com>
Provide a generic helper for setting up an io_uring worker. Returns a
task_struct so that the caller can do whatever setup is needed, then call
wake_up_new_task() to kick it into gear.
Add a kernel_clone_args member, io_thread, which tells copy_process() to
mark the task with PF_IO_WORKER.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It may not always be best to complete the IO on same CPU as it was
submitted on. This commit allows userspace to configure it.
This has been useful for vhost-scsi where we have a single thread for
submissions and completions. If we force the completion on the submission
CPU we may be adding conflicts with what the user has setup in the lower
levels with settings like the block layer rq_affinity or the driver's IRQ
or softirq (the network's rps_cpus value) settings.
We may also want to set it up where the vhost thread runs on CPU N and does
its submissions/completions there, and then have LIO do its completion
booking on CPU M, but can't configure the lower levels due to issues like
using dm-multipath with lots of paths (the path selector can throw commands
all over the system because it's only taking into account latency/throughput
at its level).
The new setting is in:
/sys/kernel/config/target/$fabric/$target/param/cmd_completion_affinity
Writing:
-1 -> Gives the current default behavior of completing on the
submission CPU.
-2 -> Completes the cmd on the CPU the lower layers sent it to us from.
> 0 -> Completes on the CPU userspace has specified.
Link: https://lore.kernel.org/r/20210227170006.5077-26-michael.christie@oracle.com
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
target_core_iblock is plugging and unplugging on every command and this is
causing perf issues for drivers that prefer batched cmds. With recent
patches we can now take multiple cmds from a fabric driver queue and then
pass them down the backend drivers in a batch. This patch adds this support
by adding 2 callouts to the backend for plugging and unplugging the
device. Subsequent commits will add support for iblock and tcmu device
plugging.
Link: https://lore.kernel.org/r/20210227170006.5077-22-michael.christie@oracle.com
Reviewed-by: Bodo Stroesser <bostroesser@gmail.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
loop and vhost/scsi do their target cmd submission from driver
workqueues. This allows them to avoid an issue where the backend may block
waiting for resources like tags/requests, mem/locks, etc and that ends up
blocking their entire submission path and for the case of vhost-scsi both
the submission and completion path.
This patch adds a helper drivers can use to submit from a LIO workqueue.
This code will then be extended in the next patches to fix the plugging of
backend devices.
We are only converting vhost/loop initially, but the workqueue based
submission will work for other drivers and have similar benefits where the
main target loops will not end up blocking one some backend resource.
Link: https://lore.kernel.org/r/20210227170006.5077-17-michael.christie@oracle.com
Tested-by: Laurence Oberman <loberman@redhat.com>
Reviewed-by: Bodo Stroesser <bostroesser@gmail.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
tcm_loop could be used like a normal block device, so we can't use
GFP_KERNEL and should use GFP_NOIO. This adds a gfp_t arg to
target_cmd_init_cdb() and converts the users. For every driver but loop
GFP_KERNEL is kept.
This will also be useful in subsequent patches where loop needs to do
target_submit_prep() from interrupt context to get a ref to the se_device,
and so it will need to use GFP_ATOMIC.
Link: https://lore.kernel.org/r/20210227170006.5077-16-michael.christie@oracle.com
Tested-by: Laurence Oberman <loberman@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This breaks up target_submit_cmd_map_sgls() into 3 helpers:
- target_init_cmd(): Do the basic general setup and get a refcount to the
session to make sure the caller can execute the cmd.
- target_submit_prep(): Do the mapping, cdb processing and get a ref to
the LUN.
- target_submit(): Pass the cmd to LIO core for execution.
The above functions must be used by drivers that either:
1. Rely on LIO for session shutdown synchronization by calling
target_stop_session().
2. Need to map sgls.
When the next patches are applied then simple drivers that do not need the
extra functionality above can use target_submit_cmd() and not worry about
failures being returned and how to handle them, since many drivers were
getting this wrong and would have hit refcount bugs.
Also, by breaking target_submit_cmd_map_sgls() up into these 3 helper
functions, we can allow the later patches to do the init/prep from
interrupt context and then do the submission from a workqueue.
Link: https://lore.kernel.org/r/20210227170006.5077-5-michael.christie@oracle.com
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Juergen Gross <jgross@suse.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Nilesh Javali <njavali@marvell.com>
Cc: Michael Cyr <mikecyr@linux.ibm.com>
Cc: Chris Boot <bootc@bootc.net>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Laurence Oberman <loberman@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
SCSI currently uses an atomic variable to track queue depth for each
attached device. The queue depth depends on many factors such as transport
type and device implementation. In addition, the SCSI device queue depth is
not a static entity but changes over time as a result of congestion
management.
While blk-mq currently tracks queue depth for each hctx, it can't easily be
changed to accommodate the SCSI per-device requirement.
The current approach of using an atomic variable doesn't scale well when
there are lots of CPU cores and the disk is very fast. IOPS can be
substantially impacted by the atomic in the hot path.
Replace the atomic variable sdev->device_busy with an sbitmap for tracking
the SCSI device queue depth.
It has been observed that IOPS is improved ~30% by this patchset in the
following test:
1) test machine(32 logical CPU cores)
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 2
NUMA node(s): 2
Model name: Intel(R) Xeon(R) Silver 4110 CPU @ 2.10GHz
2) setup scsi_debug:
modprobe scsi_debug virtual_gb=128 max_luns=1 submit_queues=32 delay=0 max_queue=256
3) fio script:
fio --rw=randread --size=128G --direct=1 --ioengine=libaio --iodepth=2048 \
--numjobs=32 --bs=4k --group_reporting=1 --group_reporting=1 --runtime=60 \
--loops=10000 --name=job1 --filename=/dev/sdN
[mkp: fix device_busy reference in mpt3sas]
Link: https://lore.kernel.org/r/20210122023317.687987-14-ming.lei@redhat.com
Link: https://lore.kernel.org/linux-block/20200119071432.18558-6-ming.lei@redhat.com/
Cc: Omar Sandoval <osandov@fb.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Cc: Ewan D. Milne <emilne@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
