Jens Axboe [Wed, 6 Oct 2021 12:34:11 +0000 (06:34 -0600)]
block: pre-allocate requests if plug is started and is a batch
The caller typically has a good (or even exact) idea of how many requests
it needs to submit. We can make the request/tag allocation a lot more
efficient if we just allocate N requests/tags upfront when we queue the
first bio from the batch.
Provide a new plug start helper that allows the caller to specify how many
IOs are expected. This sets plug->nr_ios, and we can use that for smarter
request allocation. The plug provides a holding spot for requests, and
request allocation will check it before calling into the normal request
allocation path.
The blk_finish_plug() is called, check if there are unused requests and
free them. This should not happen in normal operations. The exception is
if we get merging, then we may be left with requests that need freeing
when done.
This raises the per-core performance on my setup from ~5.8M to ~6.1M
IOPS.
Jens Axboe [Wed, 6 Oct 2021 18:01:07 +0000 (12:01 -0600)]
block: bump max plugged deferred size from 16 to 32
Particularly for NVMe with efficient deferred submission for many
requests, there are nice benefits to be seen by bumping the default max
plug count from 16 to 32. This is especially true for virtualized setups,
where the submit part is more expensive. But can be noticed even on
native hardware.
Reduce the multiple queue factor from 4 to 2, since we're changing the
default size.
While changing it, move the defines into the block layer private header.
These aren't values that anyone outside of the block layer uses, or
should use.
Jens Axboe [Tue, 5 Oct 2021 15:23:59 +0000 (09:23 -0600)]
block: inherit request start time from bio for BLK_CGROUP
Doing high IOPS testing with blk-cgroups enabled spends ~15-20% of the
time just doing ktime_get_ns() -> readtsc. We essentially read and
set the start time twice, one for the bio and then again when that bio
is mapped to a request.
Given that the time between the two is very short, inherit the bio
start time instead of reading it again. This cuts 1/3rd of the overhead
of the time keeping.
John Garry [Tue, 5 Oct 2021 10:23:37 +0000 (18:23 +0800)]
blk-mq: Use shared tags for shared sbitmap support
Currently we use separate sbitmap pairs and active_queues atomic_t for
shared sbitmap support.
However a full sets of static requests are used per HW queue, which is
quite wasteful, considering that the total number of requests usable at
any given time across all HW queues is limited by the shared sbitmap depth.
As such, it is considerably more memory efficient in the case of shared
sbitmap to allocate a set of static rqs per tag set or request queue, and
not per HW queue.
So replace the sbitmap pairs and active_queues atomic_t with a shared
tags per tagset and request queue, which will hold a set of shared static
rqs.
Since there is now no valid HW queue index to be passed to the blk_mq_ops
.init and .exit_request callbacks, pass an invalid index token. This
changes the semantics of the APIs, such that the callback would need to
validate the HW queue index before using it. Currently no user of shared
sbitmap actually uses the HW queue index (as would be expected).
John Garry [Tue, 5 Oct 2021 10:23:35 +0000 (18:23 +0800)]
blk-mq: Add blk_mq_alloc_map_and_rqs()
Add a function to combine allocating tags and the associated requests,
and factor out common patterns to use this new function.
Some function only call blk_mq_alloc_map_and_rqs() now, but more
functionality will be added later.
Also make blk_mq_alloc_rq_map() and blk_mq_alloc_rqs() static since they
are only used in blk-mq.c, and finally rename some functions for
conciseness and consistency with other function names:
- __blk_mq_alloc_map_and_{request -> rqs}()
- blk_mq_alloc_{map_and_requests -> set_map_and_rqs}()
John Garry [Tue, 5 Oct 2021 10:23:32 +0000 (18:23 +0800)]
blk-mq: Pass driver tags to blk_mq_clear_rq_mapping()
Function blk_mq_clear_rq_mapping() will be used for shared sbitmap tags
in future, so pass a driver tags pointer instead of the tagset container
and HW queue index.
John Garry [Tue, 5 Oct 2021 10:23:28 +0000 (18:23 +0800)]
blk-mq: Relocate shared sbitmap resize in blk_mq_update_nr_requests()
For shared sbitmap, if the call to blk_mq_tag_update_depth() was
successful for any hctx when hctx->sched_tags is not set, then it would be
successful for all (due to nature in which blk_mq_tag_update_depth()
fails).
As such, there is no need to call blk_mq_tag_resize_shared_sbitmap() for
each hctx. So relocate the call until after the hctx iteration under the
!q->elevator check, which is equivalent (to !hctx->sched_tags).
John Garry [Tue, 5 Oct 2021 10:23:26 +0000 (18:23 +0800)]
blk-mq: Change rqs check in blk_mq_free_rqs()
The original code in commit 24d2f90309b23 ("blk-mq: split out tag
initialization, support shared tags") would check tags->rqs is non-NULL and
then dereference tags->rqs[].
Then in commit 2af8cbe30531 ("blk-mq: split tag ->rqs[] into two"), we
started to dereference tags->static_rqs[], but continued to check non-NULL
tags->rqs.
Check tags->static_rqs as non-NULL instead, which is more logical.
In addition to reverting commit 7b05bf771084 ("Revert "block/mq-deadline:
Prioritize high-priority requests""), this patch uses 'jiffies' instead
of ktime_get() in the code for aging lower priority requests.
This patch has been tested as follows:
Measured QD=1/jobs=1 IOPS for nullb with the mq-deadline scheduler.
Result without and with this patch: 555 K IOPS.
Measured QD=1/jobs=8 IOPS for nullb with the mq-deadline scheduler.
Result without and with this patch: about 380 K IOPS.
Ran the following script:
set -e
scriptdir=$(dirname "$0")
if [ -e /sys/module/scsi_debug ]; then modprobe -r scsi_debug; fi
modprobe scsi_debug ndelay=1000000 max_queue=16
sd=''
while [ -z "$sd" ]; do
sd=$(basename /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*)
done
echo $((100*1000)) > "/sys/block/$sd/queue/iosched/prio_aging_expire"
if [ -e /sys/fs/cgroup/io.prio.class ]; then
cd /sys/fs/cgroup
echo restrict-to-be >io.prio.class
echo +io > cgroup.subtree_control
else
cd /sys/fs/cgroup/blkio/
echo restrict-to-be >blkio.prio.class
fi
echo $$ >cgroup.procs
mkdir -p hipri
cd hipri
if [ -e io.prio.class ]; then
echo none-to-rt >io.prio.class
else
echo none-to-rt >blkio.prio.class
fi
{ "${scriptdir}/max-iops" -a1 -d32 -j1 -e mq-deadline "/dev/$sd" >& ~/low-pri.txt & }
echo $$ >cgroup.procs
"${scriptdir}/max-iops" -a1 -d32 -j1 -e mq-deadline "/dev/$sd" >& ~/hi-pri.txt
Result:
* 11000 IOPS for the high-priority job
* 40 IOPS for the low-priority job
If the prio aging expiry time is changed from 100s into 0, the IOPS results
change into 6712 and 6796 IOPS.
The max-iops script is a script that runs fio with the following arguments:
--bs=4K --gtod_reduce=1 --ioengine=libaio --ioscheduler=${arg_e} --runtime=60
--norandommap --rw=read --thread --buffered=0 --numjobs=${arg_j}
--iodepth=${arg_d} --iodepth_batch_submit=${arg_a}
--iodepth_batch_complete=$((arg_d / 2)) --name=${positional_argument_1}
--filename=${positional_argument_1}
Calculating the sum over all CPUs of per-CPU counters frequently is
inefficient. Hence switch from per-CPU to individual counters. Three
counters are protected by the mq-deadline spinlock since these are
only accessed from contexts that already hold that spinlock. The fourth
counter is atomic because protecting it with the mq-deadline spinlock
would trigger lock contention.
Check a statistics invariant at module unload time. When running
blktests, the invariant is verified every time a request queue is
removed and hence is verified at least once per test.
block/mq-deadline: Improve request accounting further
The scheduler .insert_requests() callback is called when a request is
queued for the first time and also when it is requeued. Only count a
request the first time it is queued. Additionally, since the mq-deadline
scheduler only performs zone locking for requests that have been
inserted, skip the zone unlock code for requests that have not been
inserted into the mq-deadline scheduler.
Except for the features passed to blk_queue_required_elevator_features,
elevator.h is only needed internally to the block layer. Move the
ELEVATOR_F_* definitions to blkdev.h, and the move elevator.h to
block/, dropping all the spurious includes outside of that.
mm: don't include <linux/blk-cgroup.h> in <linux/writeback.h>
blk-cgroup.h pulls in blkdev.h and thus pretty much all the block
headers. Break this dependency chain by turning wbc_blkcg_css into a
macro and dropping the blk-cgroup.h include.
Tejun Heo [Thu, 14 Oct 2021 23:20:22 +0000 (13:20 -1000)]
blk-cgroup: blk_cgroup_bio_start() should use irq-safe operations on blkg->iostat_cpu
c3df5fb57fe8 ("cgroup: rstat: fix A-A deadlock on 32bit around
u64_stats_sync") made u64_stats updates irq-safe to avoid A-A deadlocks.
Unfortunately, the conversion missed one in blk_cgroup_bio_start(). Fix it.
Linus Torvalds [Mon, 18 Oct 2021 05:39:22 +0000 (19:39 -1000)]
Merge tag 'libata-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata
Pull libata fixes from Damien Le Moal:
"Two fixes for this cycle:
- Fix a null pointer dereference in ahci-platform driver (from Hai)
- Fix uninitialized variables in pata_legacy driver (from Dan)"
* tag 'libata-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata:
ata: ahci_platform: fix null-ptr-deref in ahci_platform_enable_regulators()
pata_legacy: fix a couple uninitialized variable bugs
Linus Torvalds [Mon, 18 Oct 2021 05:25:20 +0000 (19:25 -1000)]
Merge tag 'block-5.15-2021-10-17' of git://git.kernel.dk/linux-block
Pull block fixes from Jens Axboe:
"Bigger than usual for this point in time, the majority is fixing some
issues around BDI lifetimes with the move from the request_queue to
the disk in this release. In detail:
- Series on draining fs IO for del_gendisk() (Christoph)
- NVMe pull request via Christoph:
- fix the abort command id (Keith Busch)
- nvme: fix per-namespace chardev deletion (Adam Manzanares)
- brd locking scope fix (Tetsuo)
- BFQ fix (Paolo)"
* tag 'block-5.15-2021-10-17' of git://git.kernel.dk/linux-block:
block, bfq: reset last_bfqq_created on group change
block: warn when putting the final reference on a registered disk
brd: reduce the brd_devices_mutex scope
kyber: avoid q->disk dereferences in trace points
block: keep q_usage_counter in atomic mode after del_gendisk
block: drain file system I/O on del_gendisk
block: split bio_queue_enter from blk_queue_enter
block: factor out a blk_try_enter_queue helper
block: call submit_bio_checks under q_usage_counter
nvme: fix per-namespace chardev deletion
block/rnbd-clt-sysfs: fix a couple uninitialized variable bugs
nvme-pci: Fix abort command id
Linus Torvalds [Mon, 18 Oct 2021 04:17:19 +0000 (18:17 -1000)]
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull virtio fixes from Michael Tsirkin:
"Fixes up some issues in rc5"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
vhost-vdpa: Fix the wrong input in config_cb
VDUSE: fix documentation underline warning
Revert "virtio-blk: Add validation for block size in config space"
vhost_vdpa: unset vq irq before freeing irq
virtio: write back F_VERSION_1 before validate
* tag 'powerpc-5.15-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
KVM: PPC: Book3S HV: Make idle_kvm_start_guest() return 0 if it went to guest
KVM: PPC: Book3S HV: Fix stack handling in idle_kvm_start_guest()
powerpc/xive: Discard disabled interrupts in get_irqchip_state()
Linus Torvalds [Mon, 18 Oct 2021 03:41:39 +0000 (17:41 -1000)]
Merge tag 'objtool_urgent_for_v5.15_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull objtool fixes from Borislav Petkov:
- Update section headers before the respective relocations to not
trigger a safety check in elftoolchain's implementation of libelf
- Do not add garbage data to the .rela.orc_unwind_ip section
* tag 'objtool_urgent_for_v5.15_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
objtool: Update section header before relocations
objtool: Check for gelf_update_rel[a] failures
Linus Torvalds [Mon, 18 Oct 2021 03:30:49 +0000 (17:30 -1000)]
Merge tag 'efi-urgent-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull EFI fixes from Borislav Petkov:
"Forwarded from Ard Biesheuvel through the tip tree. Ard will send
stuff directly in the near future.
Low priority fixes but fixes nonetheless:
- update stub diagnostic print that is no longer accurate
- avoid statically allocated buffer for CPER error record decoding
- avoid sleeping on the efi_runtime semaphore when calling the
ResetSystem EFI runtime service"
* tag 'efi-urgent-for-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
efi: Change down_interruptible() in virt_efi_reset_system() to down_trylock()
efi/cper: use stack buffer for error record decoding
efi/libstub: Simplify "Exiting bootservices" message
Linus Torvalds [Mon, 18 Oct 2021 03:27:22 +0000 (17:27 -1000)]
Merge tag 'x86_urgent_for_v5.15_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fixes from Borislav Petkov:
- Do not enable AMD memory encryption in Kconfig by default due to
shortcomings of some platforms, leading to boot failures.
- Mask out invalid bits in the MXCSR for 32-bit kernels again because
Thomas and I don't know how to mask out bits properly. Third time's
the charm.
* tag 'x86_urgent_for_v5.15_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/fpu: Mask out the invalid MXCSR bits properly
x86/Kconfig: Do not enable AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT automatically
Linus Torvalds [Mon, 18 Oct 2021 03:17:28 +0000 (17:17 -1000)]
Merge tag 'driver-core-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core fixes from Greg KH:
"Here are some small driver core fixes for 5.15-rc6, all of which have
been in linux-next for a while with no reported issues.
They include:
- kernfs negative dentry bugfix
- simple pm bus fixes to resolve reported issues"
* tag 'driver-core-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
drivers: bus: Delete CONFIG_SIMPLE_PM_BUS
drivers: bus: simple-pm-bus: Add support for probing simple bus only devices
driver core: Reject pointless SYNC_STATE_ONLY device links
kernfs: don't create a negative dentry if inactive node exists
Linus Torvalds [Mon, 18 Oct 2021 03:10:00 +0000 (17:10 -1000)]
Merge tag 'staging-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging
Pull staging and IIO driver fixes from Greg KH:
"Here are a number of small IIO and staging driver fixes for 5.15-rc6.
They include:
- vc04_services bugfix for reported problem
- r8188eu array underflow fix
- iio driver fixes for a lot of tiny reported issues.
All of these have been in linux-next for a while with no reported
issues"
* tag 'staging-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
staging: r8188eu: prevent array underflow in rtw_hal_update_ra_mask()
staging: vc04_services: shut up out-of-range warning
iio: light: opt3001: Fixed timeout error when 0 lux
iio: adis16480: fix devices that do not support sleep mode
iio: mtk-auxadc: fix case IIO_CHAN_INFO_PROCESSED
iio: adis16475: fix deadlock on frequency set
iio: ssp_sensors: add more range checking in ssp_parse_dataframe()
iio: ssp_sensors: fix error code in ssp_print_mcu_debug()
iio: adc: ad7793: Fix IRQ flag
iio: adc: ad7780: Fix IRQ flag
iio: adc: ad7192: Add IRQ flag
iio: adc: aspeed: set driver data when adc probe.
iio: adc: rzg2l_adc: add missing clk_disable_unprepare() in rzg2l_adc_pm_runtime_resume()
iio: adc: max1027: Fix the number of max1X31 channels
iio: adc: max1027: Fix wrong shift with 12-bit devices
iio: adc128s052: Fix the error handling path of 'adc128_probe()'
iio: adc: rzg2l_adc: Fix -EBUSY timeout error return
iio: accel: fxls8962af: return IRQ_HANDLED when fifo is flushed
iio: dac: ti-dac5571: fix an error code in probe()
Linus Torvalds [Mon, 18 Oct 2021 03:06:31 +0000 (17:06 -1000)]
Merge tag 'tty-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty
Pull serial driver fix from Greg KH:
"Here is a single 8250 Kconfig fix for 5.15-rc6 that resolves a
regression that showed up in 5.15-rc1. It has been in linux-next for a
while with no reported issues"
* tag 'tty-5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
serial: 8250: allow disabling of Freescale 16550 compile test
Linus Torvalds [Mon, 18 Oct 2021 02:57:06 +0000 (16:57 -1000)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
Pull input fixes from Dmitry Torokhov:
- a new product ID for the xpad joystick driver
- fixes to resistive-adc-touch and snvs_pwrkey drivers
- a change to touchscreen helpers to make clang happier
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: touchscreen - avoid bitwise vs logical OR warning
Input: xpad - add support for another USB ID of Nacon GC-100
Input: resistive-adc-touch - fix division by zero error on z1 == 0
Input: snvs_pwrkey - add clk handling
Paolo Valente [Fri, 15 Oct 2021 14:43:36 +0000 (16:43 +0200)]
block, bfq: reset last_bfqq_created on group change
Since commit 430a67f9d616 ("block, bfq: merge bursts of newly-created
queues"), BFQ maintains a per-group pointer to the last bfq_queue
created. If such a queue, say bfqq, happens to move to a different
group, then bfqq is no more a valid last bfq_queue created for its
previous group. That pointer must then be cleared. Not resetting such
a pointer may also cause UAF, if bfqq happens to also be freed after
being moved to a different group. This commit performs this missing
reset. As such it fixes commit 430a67f9d616 ("block, bfq: merge bursts
of newly-created queues").
Such a missing reset is most likely the cause of the crash reported in [1].
With some analysis, we found that this crash was due to the
above UAF. And such UAF did go away with this commit applied [1].
Anyway, before this commit, that crash happened to be triggered in
conjunction with commit 2d52c58b9c9b ("block, bfq: honor already-setup
queue merges"). The latter was then reverted by commit ebc69e897e17
("Revert "block, bfq: honor already-setup queue merges""). Yet commit 2d52c58b9c9b ("block, bfq: honor already-setup queue merges") contains
no error related with the above UAF, and can then be restored.
block: warn when putting the final reference on a registered disk
Warn when the last reference on a live disk is put without calling
del_gendisk first. There are some BDI related bug reports that look
like a case of this, so make sure we have the proper instrumentation
to catch it.
As with commit 8b52d8be86d72308 ("loop: reorder loop_exit"),
unregister_blkdev() needs to be called first in order to avoid calling
brd_alloc() from brd_probe() after brd_del_one() from brd_exit(). Then,
we can avoid holding global mutex during add_disk()/del_gendisk() as with
commit 1c500ad706383f1a ("loop: reduce the loop_ctl_mutex scope").
Linus Torvalds [Sat, 16 Oct 2021 18:11:07 +0000 (11:11 -0700)]
Merge tag 'perf-tools-fixes-for-v5.15-2021-10-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux
Pull perf tools fixes from Arnaldo Carvalho de Melo:
- Fix 'perf test evsel' build error on !x86 architectures
- Fix libperf's test_stat_cpu mixup of CPU numbers and CPU indexes
- Output offsets for decompressed records, not just useless zeros
* tag 'perf-tools-fixes-for-v5.15-2021-10-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
libperf tests: Fix test_stat_cpu
libperf test evsel: Fix build error on !x86 architectures
perf report: Output non-zero offset for decompressed records
Linus Torvalds [Sat, 16 Oct 2021 17:51:41 +0000 (10:51 -0700)]
Merge tag 'trace-v5.15-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Tracing fixes for 5.15:
- Fix defined but not use warning/error for osnoise function
- Fix memory leak in event probe
- Fix memblock leak in bootconfig
- Fix the API of event probes to be like kprobes
- Added test to check removal of event probe API
- Fix recordmcount.pl for nds32 failed build
* tag 'trace-v5.15-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
nds32/ftrace: Fix Error: invalid operands (*UND* and *UND* sections) for `^'
selftests/ftrace: Update test for more eprobe removal process
tracing: Fix event probe removal from dynamic events
tracing: Fix missing * in comment block
bootconfig: init: Fix memblock leak in xbc_make_cmdline()
tracing: Fix memory leak in eprobe_register()
tracing: Fix missing osnoise tracer on max_latency
Linus Torvalds [Sat, 16 Oct 2021 17:22:08 +0000 (10:22 -0700)]
Merge tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux
Pull clk driver fixes from Stephen Boyd:
"Clk driver fixes for critical issues found in the past few weeks:
- Select gdsc config so qcom sm6350 driver probes
- Fix a register offset in qcom gcc-sm6115 so the correct clk is
controlled
- Fix inverted logic in Renesas RZ/G2L .is_enabled()
- Mark some more clks critical in Renesas clk driver
- Remove a duplicate clk in the agilex driver"
* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
clk: qcom: add select QCOM_GDSC for SM6350
clk: qcom: gcc-sm6115: Fix offset for hlos1_vote_turing_mmu_tbu0_gdsc
clk: socfpga: agilex: fix duplicate s2f_user0_clk
clk: renesas: rzg2l: Fix clk status function
clk: renesas: r9a07g044: Mark IA55_CLK and DMAC_ACLK critical
Linus Torvalds [Sat, 16 Oct 2021 16:14:55 +0000 (09:14 -0700)]
Merge tag 's390-5.15-6' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 fixes from Vasily Gorbik:
- Maintainers and reviewers changes:
* Cornelia decided to free up her time and step down from vfio-ccw
maintainer and s390 kvm reviewer duties
* Add Alexander Gordeev as s390 arch code reviewer
- Fix broken strrchr implementation
* tag 's390-5.15-6' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
s390: add Alexander Gordeev as reviewer
s390: fix strrchr() implementation
vfio-ccw: step down as maintainer
KVM: s390: remove myself as reviewer
Linus Torvalds [Sat, 16 Oct 2021 16:12:18 +0000 (09:12 -0700)]
Merge tag 'csky-for-linus-5.15-rc6' of git://github.com/c-sky/csky-linux
Pull csky fixes from Guo Ren:
"Only 5 fixups:
- Make HAVE_TCM depend on !COMPILE_TEST
- bitops: Remove duplicate __clear_bit define
- Select ARCH_WANT_FRAME_POINTERS only if compiler supports it
- Fixup regs.sr broken in ptrace
- don't let sigreturn play with priveleged bits of status register"
* tag 'csky-for-linus-5.15-rc6' of git://github.com/c-sky/csky-linux:
csky: Make HAVE_TCM depend on !COMPILE_TEST
csky: bitops: Remove duplicate __clear_bit define
csky: Select ARCH_WANT_FRAME_POINTERS only if compiler supports it
csky: Fixup regs.sr broken in ptrace
csky: don't let sigreturn play with priveleged bits of status register
Linus Torvalds [Sat, 16 Oct 2021 16:05:58 +0000 (09:05 -0700)]
Merge tag 'arm-soc-fixes-5.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc
Pull ARM SoC fixes from Arnd Bergmann:
"A small number fixes this time, mostly touching actual code:
- Add platform device for i.MX System Reset Controller (SRC) to
fix a regression caused by fw_devlink change
- A fixup for a boot regression caused by my own rework for the
Qualcomm SCM driver
- Multiple bugfixes for the Arm FFA and optee firmware drivers,
addressing problems when they are built as a loadable module
- Four dts bugfixes for the Broadcom SoC used in Raspberry pi,
addressing VEC (video encoder), MDIO bus controller
#address-cells/#size-cells, SDIO voltage and PCIe host bridge
dtc warnings"
* tag 'arm-soc-fixes-5.15-2' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc:
ARM: imx: register reset controller from a platform driver
iommu/arm: fix ARM_SMMU_QCOM compilation
ARM: dts: bcm2711-rpi-4-b: Fix usb's unit address
ARM: dts: bcm2711-rpi-4-b: Fix pcie0's unit address formatting
tee: optee: Fix missing devices unregister during optee_remove
ARM: dts: bcm2711-rpi-4-b: fix sd_io_1v8_reg regulator states
ARM: dts: bcm2711: fix MDIO #address- and #size-cells
ARM: dts: bcm283x: Fix VEC address for BCM2711
firmware: arm_ffa: Fix __ffa_devices_unregister
firmware: arm_ffa: Add missing remove callback to ffa_bus_type
Input: touchscreen - avoid bitwise vs logical OR warning
A new warning in clang points out a few places in this driver where a
bitwise OR is being used with boolean types:
drivers/input/touchscreen.c:81:17: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical]
data_present = touchscreen_get_prop_u32(dev, "touchscreen-min-x",
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
This use of a bitwise OR is intentional, as bitwise operations do not
short circuit, which allows all the calls to touchscreen_get_prop_u32()
to happen so that the last parameter is initialized while coalescing the
results of the calls to make a decision after they are all evaluated.
To make this clearer to the compiler, use the '|=' operator to assign
the result of each touchscreen_get_prop_u32() call to data_present,
which keeps the meaning of the code the same but makes it obvious that
every one of these calls is expected to happen.
Michael Cullen [Fri, 15 Oct 2021 20:17:50 +0000 (13:17 -0700)]
Input: xpad - add support for another USB ID of Nacon GC-100
The Nacon GX100XF is already mapped, but it seems there is a Nacon
GC-100 (identified as NC5136Wht PCGC-100WHITE though I believe other
colours exist) with a different USB ID when in XInput mode.
On i.MX7S and i.MX8M* (but not i.MX6*) the pwrkey device has an
associated clock. Accessing the registers requires that this clock is
enabled. Binding the driver on at least i.MX7S and i.MX8MP while not
having the clock enabled results in a complete hang of the machine.
(This usually only happens if snvs_pwrkey is built as a module and the
rtc-snvs driver isn't already bound because at bootup the required clk
is on and only gets disabled when the clk framework disables unused clks
late during boot.)
This completes the fix in commit 135be16d3505 ("ARM: dts: imx7s: add
snvs clock to pwrkey").
q->disk becomes invalid after the gendisk is removed. Work around this
by caching the dev_t for the tracepoints. The real fix would be to
properly tear down the I/O schedulers with the gendisk, but that is
a much more invasive change.
block: keep q_usage_counter in atomic mode after del_gendisk
Don't switch back to percpu mode to avoid the double RCU grace period
when tearing down SCSI devices. After removing the disk only passthrough
commands can be send anyway.
Instead of delaying draining of file system I/O related items like the
blk-qos queues, the integrity read workqueue and timeouts only when the
request_queue is removed, do that when del_gendisk is called. This is
important for SCSI where the upper level drivers that control the gendisk
are separate entities, and the disk can be freed much earlier than the
request_queue, or can even be unbound without tearing down the queue.
To prepare for fixing a gendisk shutdown race, open code the
blk_queue_enter logic in bio_queue_enter. This also removes the
pointless flags translation.
Factor out the code to try to get q_usage_counter without blocking into
a separate helper. Both to improve code readability and to prepare for
splitting bio_queue_enter from blk_queue_enter.
block: call submit_bio_checks under q_usage_counter
Ensure all bios check the current values of the queue under freeze
protection, i.e. to make sure the zero capacity set by del_gendisk
is actually seen before dispatching to the driver.
Steven Rostedt [Thu, 14 Oct 2021 18:35:07 +0000 (14:35 -0400)]
nds32/ftrace: Fix Error: invalid operands (*UND* and *UND* sections) for `^'
I received a build failure for a new patch I'm working on the nds32
architecture, and when I went to test it, I couldn't get to my build error,
because it failed to build with a bunch of:
Error: invalid operands (*UND* and *UND* sections) for `^'
issues with various files. Those files were temporary asm files that looked
like: kernel/.tmp_mc_fork.s
I decided to look deeper, and found that the "mc" portion of that name
stood for "mcount", and was created by the recordmcount.pl script. One that
I wrote over a decade ago. Once I knew the source of the problem, I was
able to investigate it further.
The way the recordmcount.pl script works (BTW, there's a C version that
simply modifies the ELF object) is by doing an "objdump" on the object
file. Looks for all the calls to "mcount", and creates an offset of those
locations from some global variable it can use (usually a global function
name, found with <.*>:). Creates a asm file that is a table of references
to these locations, using the found variable/function. Compiles it and
links it back into the original object file. This asm file is called
".tmp_mc_<object_base_name>.s".
The problem here is that the objdump produced by the nds32 object file,
contains things that look like:
Building csky:allmodconfig results in the following build errors.
arch/csky/mm/tcm.c:9:2: error:
#error "You should define ITCM_RAM_BASE"
9 | #error "You should define ITCM_RAM_BASE"
| ^~~~~
arch/csky/mm/tcm.c:14:2: error:
#error "You should define DTCM_RAM_BASE"
14 | #error "You should define DTCM_RAM_BASE"
| ^~~~~
arch/csky/mm/tcm.c:18:2: error:
#error "You should define correct DTCM_RAM_BASE"
18 | #error "You should define correct DTCM_RAM_BASE"
This is seen with compile tests since those enable HAVE_TCM,
but do not provide useful default values for ITCM_RAM_BASE or
DTCM_RAM_BASE. Disable HAVE_TCM for commpile tests to avoid
the error.
Building csky:allmodconfig results in the following build error.
In file included from ./include/linux/bitops.h:33,
from ./include/linux/log2.h:12,
from kernel/bounds.c:13:
./arch/csky/include/asm/bitops.h:77: error: "__clear_bit" redefined
Since commit 9248e52fec95 ("locking/atomic: simplify non-atomic wrappers"),
__clear_bit is defined in include/asm-generic/bitops/non-atomic.h,
and the define in the csky include file is no longer necessary or useful.
Remove it.
gpr_get() return the entire pt_regs (include sr) to userspace, if we
don't restore the C bit in gpr_set, it may break the ALU result in
that context. So the C flag bit is part of gpr context, that's why
riscv totally remove the C bit in the ISA. That makes sr reg clear
from userspace to supervisor privilege.
Al Viro [Fri, 24 Sep 2021 00:35:42 +0000 (00:35 +0000)]
csky: don't let sigreturn play with priveleged bits of status register
csky restore_sigcontext() blindly overwrites regs->sr with the value
it finds in sigcontext. Attacker can store whatever they want in there,
which includes things like S-bit. Userland shouldn't be able to set
that, or anything other than C flag (bit 0).
Do the same thing other architectures with protected bits in flags
register do - preserve everything that shouldn't be settable in
user mode, picking the rest from the value saved is sigcontext.
Linus Torvalds [Fri, 15 Oct 2021 14:27:20 +0000 (10:27 -0400)]
Merge tag 'gpio-fixes-for-v5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux
Pull gpio fixes from Bartosz Golaszewski:
- fix module autoloading on gpio-74x164 after a revert of OF modaliases
- fix problems with the bias setting in gpio-pca953x
- fix a use-after-free bug in gpio-mockup by using software nodes
* tag 'gpio-fixes-for-v5.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux:
gpio: mockup: Convert to use software nodes
gpio: pca953x: Improve bias setting
gpio: 74x164: Add SPI device ID table
Linus Torvalds [Fri, 15 Oct 2021 14:21:46 +0000 (10:21 -0400)]
Merge tag 'spi-fix-v5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi
Pull spi fixes from Mark Brown:
"A few small fixes.
Mostly driver specific but there's one in the core which fixes a
deadlock when adding devices on spi-mux that's triggered because
spi-mux is a SPI device which is itself a SPI controller and so can
instantiate devices when registered.
We were using a global lock to protect against reusing chip selects
but they're a per controller thing so moving the lock per controller
resolves that"
* tag 'spi-fix-v5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi:
spi-mux: Fix false-positive lockdep splats
spi: Fix deadlock when adding SPI controllers on SPI buses
spi: bcm-qspi: clear MSPI spifie interrupt during probe
spi: spi-nxp-fspi: don't depend on a specific node name erratum workaround
spi: mediatek: skip delays if they are 0
spi: atmel: Fix PDC transfer setup bug
spi: spidev: Add SPI ID table
spi: Use 'flash' node name instead of 'spi-flash' in example
Linus Torvalds [Fri, 15 Oct 2021 14:20:18 +0000 (10:20 -0400)]
Merge tag 'regulator-fix-v5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator
Pull regulator fix from Mark Brown:
"Just a trivial fix to the MAINTAINERS file for an update missed during
conversion of the DT bindings to YAML format"
* tag 'regulator-fix-v5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator:
MAINTAINERS: rectify entry for SY8106A REGULATOR DRIVER
Linus Torvalds [Fri, 15 Oct 2021 14:09:09 +0000 (10:09 -0400)]
Merge tag 'drm-fixes-2021-10-15-1' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Dave Airlie:
"It has a few scattered msm and i915 fixes, a few core fixes and a
mediatek feature revert.
I've had to pick a bunch of patches into this, as the drm-misc-fixes
tree had a bunch of vc4 patches I wasn't comfortable with sending to
you at least as part of this, they were delayed due to your reverts.
If it's really useful as fixes I'll do a separate pull.
Summary:
Core:
- clamp fbdev size
- edid cap blocks read to avoid out of bounds
panel:
- fix missing crc32 dependency
msm:
- Fix a new crash on dev file close if the dev file was opened when
GPU is not loaded (such as missing fw in initrd)
- Switch to single drm_sched_entity per priority level per drm_file
to unbreak multi-context userspace
- Serialize GMU access to fix GMU OOB errors
- Various error path fixes
- A couple integer overflow fixes
- Fix mdp5 cursor plane WARNs
i915:
- Fix ACPI object leak
- Fix context leak in user proto-context creation
- Fix missing i915_sw_fence_fini call
hyperv:
- hide hw pointer
nouveau:
- fix engine selection bit
r128:
- fix UML build
rcar-du:
- unconncted LVDS regression fix
mediatek:
- revert CMDQ refinement patches"
* tag 'drm-fixes-2021-10-15-1' of git://anongit.freedesktop.org/drm/drm: (34 commits)
drm/panel: olimex-lcd-olinuxino: select CRC32
drm/r128: fix build for UML
drm/nouveau/fifo: Reinstate the correct engine bit programming
drm/hyperv: Fix double mouse pointers
drm/fbdev: Clamp fbdev surface size if too large
drm/edid: In connector_bad_edid() cap num_of_ext by num_blocks read
drm/i915: Free the returned object of acpi_evaluate_dsm()
drm/i915: Fix bug in user proto-context creation that leaked contexts
drm: rcar-du: Don't create encoder for unconnected LVDS outputs
drm/msm/dsi: fix off by one in dsi_bus_clk_enable error handling
drm/msm/dsi: Fix an error code in msm_dsi_modeset_init()
drm/msm/dsi: dsi_phy_14nm: Take ready-bit into account in poll_for_ready
drm/msm/dsi/phy: fix clock names in 28nm_8960 phy
drm/msm/dpu: Fix address of SM8150 PINGPONG5 IRQ register
drm/msm: Do not run snapshot on non-DPU devices
drm/msm/a3xx: fix error handling in a3xx_gpu_init()
drm/msm/a4xx: fix error handling in a4xx_gpu_init()
drm/msm: Fix null pointer dereference on pointer edp
drm/msm/mdp5: fix cursor-related warnings
drm/msm: Avoid potential overflow in timeout_to_jiffies()
...
- some typos, wrong returned error codes, dead code, etc"
* tag 'ntfs3_for_5.15' of git://github.com/Paragon-Software-Group/linux-ntfs3: (70 commits)
fs/ntfs3: Check for NULL pointers in ni_try_remove_attr_list
fs/ntfs3: Refactor ntfs_read_mft
fs/ntfs3: Refactor ni_parse_reparse
fs/ntfs3: Refactor ntfs_create_inode
fs/ntfs3: Refactor ntfs_readlink_hlp
fs/ntfs3: Rework ntfs_utf16_to_nls
fs/ntfs3: Fix memory leak if fill_super failed
fs/ntfs3: Keep prealloc for all types of files
fs/ntfs3: Remove unnecessary functions
fs/ntfs3: Forbid FALLOC_FL_PUNCH_HOLE for normal files
fs/ntfs3: Refactoring of ntfs_set_ea
fs/ntfs3: Remove locked argument in ntfs_set_ea
fs/ntfs3: Use available posix_acl_release instead of ntfs_posix_acl_release
fs/ntfs3: Check for NULL if ATTR_EA_INFO is incorrect
fs/ntfs3: Refactoring of ntfs_init_from_boot
fs/ntfs3: Reject mount if boot's cluster size < media sector size
fs/ntfs3: Refactoring lock in ntfs_init_acl
fs/ntfs3: Change posix_acl_equiv_mode to posix_acl_update_mode
fs/ntfs3: Pass flags to ntfs_set_ea in ntfs_set_acl_ex
fs/ntfs3: Refactor ntfs_get_acl_ex for better readability
...
Michael Ellerman [Fri, 15 Oct 2021 12:02:08 +0000 (23:02 +1100)]
KVM: PPC: Book3S HV: Make idle_kvm_start_guest() return 0 if it went to guest
We call idle_kvm_start_guest() from power7_offline() if the thread has
been requested to enter KVM. We pass it the SRR1 value that was returned
from power7_idle_insn() which tells us what sort of wakeup we're
processing.
Depending on the SRR1 value we pass in, the KVM code might enter the
guest, or it might return to us to do some host action if the wakeup
requires it.
If idle_kvm_start_guest() is able to handle the wakeup, and enter the
guest it is supposed to indicate that by returning a zero SRR1 value to
us.
That was the behaviour prior to commit 10d91611f426 ("powerpc/64s:
Reimplement book3s idle code in C"), however in that commit the
handling of SRR1 was reworked, and the zeroing behaviour was lost.
Returning from idle_kvm_start_guest() without zeroing the SRR1 value can
confuse the host offline code, causing the guest to crash and other
weirdness.
Michael Ellerman [Fri, 15 Oct 2021 12:01:48 +0000 (23:01 +1100)]
KVM: PPC: Book3S HV: Fix stack handling in idle_kvm_start_guest()
In commit 10d91611f426 ("powerpc/64s: Reimplement book3s idle code in
C") kvm_start_guest() became idle_kvm_start_guest(). The old code
allocated a stack frame on the emergency stack, but didn't use the
frame to store anything, and also didn't store anything in its caller's
frame.
idle_kvm_start_guest() on the other hand is written more like a normal C
function, it creates a frame on entry, and also stores CR/LR into its
callers frame (per the ABI). The problem is that there is no caller
frame on the emergency stack.
The emergency stack for a given CPU is allocated with:
So emergency_sp actually points to the first address above the emergency
stack allocation for a given CPU, we must not store above it without
first decrementing it to create a frame. This is different to the
regular kernel stack, paca->kstack, which is initialised to point at an
initial frame that is ready to use.
idle_kvm_start_guest() stores the backchain, CR and LR all of which
write outside the allocation for the emergency stack. It then creates a
stack frame and saves the non-volatile registers. Unfortunately the
frame it creates is not large enough to fit the non-volatiles, and so
the saving of the non-volatile registers also writes outside the
emergency stack allocation.
The end result is that we corrupt whatever is at 0-24 bytes, and 112-248
bytes above the emergency stack allocation.
In practice this has gone unnoticed because the memory immediately above
the emergency stack happens to be used for other stack allocations,
either another CPUs mc_emergency_sp or an IRQ stack. See the order of
calls to irqstack_early_init() and emergency_stack_init().
The low addresses of another stack are the top of that stack, and so are
only used if that stack is under extreme pressue, which essentially
never happens in practice - and if it did there's a high likelyhood we'd
crash due to that stack overflowing.
Still, we shouldn't be corrupting someone else's stack, and it is purely
luck that we aren't corrupting something else.
To fix it we save CR/LR into the caller's frame using the existing r1 on
entry, we then create a SWITCH_FRAME_SIZE frame (which has space for
pt_regs) on the emergency stack with the backchain pointing to the
existing stack, and then finally we switch to the new frame on the
emergency stack.