[ Upstream commit b5fcf7871a ]
Commit 180dccb0db ("blk-mq: fix tag_get wait task can't be awakened")
mentioned that in case of shared tags, there could be just one real
active hctx(queue) because of lazy detection of tag idle. Then driver tag
allocation may wait forever on this real active hctx(queue) if wake_batch
is > hctx_max_depth where hctx_max_depth is available tags depth for the
actve hctx(queue). However, the condition wake_batch > hctx_max_depth is
not strong enough to avoid IO hung as the sbitmap_queue_wake_up will only
wake up one wait queue for each wake_batch even though there is only one
waiter in the woken wait queue. After this, there is only one tag to free
and wake_batch may not be reached anymore. Commit 180dccb0db ("blk-mq:
fix tag_get wait task can't be awakened") methioned that driver tag
allocation may wait forever. Actually, the inactive hctx(queue) will be
truely idle after at most 30 seconds and will call blk_mq_tag_wakeup_all
to wake one waiter per wait queue to break the hung. But IO hung for 30
seconds is also not acceptable. Set batch size to small enough that depth
of the shared hctx(queue) is enough to wake up all of the queues like
sbq_calc_wake_batch do to fix this potential IO hung.
Although hctx_max_depth will be clamped to at least 4 while wake_batch
recalculation does not do the clamp, the wake_batch will be always
recalculated to 1 when hctx_max_depth <= 4.
Fixes: 180dccb0db ("blk-mq: fix tag_get wait task can't be awakened")
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Link: https://lore.kernel.org/r/20230116205059.3821738-6-shikemeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 4f8126bb23 ]
sbitmap suffers from code complexity, as demonstrated by recent fixes,
and eventual lost wake ups on nested I/O completion. The later happens,
from what I understand, due to the non-atomic nature of the updates to
wait_cnt, which needs to be subtracted and eventually reset when equal
to zero. This two step process can eventually miss an update when a
nested completion happens to interrupt the CPU in between the wait_cnt
updates. This is very hard to fix, as shown by the recent changes to
this code.
The code complexity arises mostly from the corner cases to avoid missed
wakes in this scenario. In addition, the handling of wake_batch
recalculation plus the synchronization with sbq_queue_wake_up is
non-trivial.
This patchset implements the idea originally proposed by Jan [1], which
removes the need for the two-step updates of wait_cnt. This is done by
tracking the number of completions and wakeups in always increasing,
per-bitmap counters. Instead of having to reset the wait_cnt when it
reaches zero, we simply keep counting, and attempt to wake up N threads
in a single wait queue whenever there is enough space for a batch.
Waking up less than batch_wake shouldn't be a problem, because we
haven't changed the conditions for wake up, and the existing batch
calculation guarantees at least enough remaining completions to wake up
a batch for each queue at any time.
Performance-wise, one should expect very similar performance to the
original algorithm for the case where there is no queueing. In both the
old algorithm and this implementation, the first thing is to check
ws_active, which bails out if there is no queueing to be managed. In the
new code, we took care to avoid accounting completions and wakeups when
there is no queueing, to not pay the cost of atomic operations
unnecessarily, since it doesn't skew the numbers.
For more interesting cases, where there is queueing, we need to take
into account the cross-communication of the atomic operations. I've
been benchmarking by running parallel fio jobs against a single hctx
nullb in different hardware queue depth scenarios, and verifying both
IOPS and queueing.
Each experiment was repeated 5 times on a 20-CPU box, with 20 parallel
jobs. fio was issuing fixed-size randwrites with qd=64 against nullb,
varying only the hardware queue length per test.
queue size 2 4 8 16 32 64
6.1-rc2 1681.1K (1.6K) 2633.0K (12.7K) 6940.8K (16.3K) 8172.3K (617.5K) 8391.7K (367.1K) 8606.1K (351.2K)
patched 1721.8K (15.1K) 3016.7K (3.8K) 7543.0K (89.4K) 8132.5K (303.4K) 8324.2K (230.6K) 8401.8K (284.7K)
The following is a similar experiment, ran against a nullb with a single
bitmap shared by 20 hctx spread across 2 NUMA nodes. This has 40
parallel fio jobs operating on the same device
queue size 2 4 8 16 32 64
6.1-rc2 1081.0K (2.3K) 957.2K (1.5K) 1699.1K (5.7K) 6178.2K (124.6K) 12227.9K (37.7K) 13286.6K (92.9K)
patched 1081.8K (2.8K) 1316.5K (5.4K) 2364.4K (1.8K) 6151.4K (20.0K) 11893.6K (17.5K) 12385.6K (18.4K)
It has also survived blktests and a 12h-stress run against nullb. I also
ran the code against nvme and a scsi SSD, and I didn't observe
performance regression in those. If there are other tests you think I
should run, please let me know and I will follow up with results.
[1] https://lore.kernel.org/all/aef9de29-e9f5-259a-f8be-12d1b734e72@google.com/
Cc: Hugh Dickins <hughd@google.com>
Cc: Keith Busch <kbusch@kernel.org>
Cc: Liu Song <liusong@linux.alibaba.com>
Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Link: https://lore.kernel.org/r/20221105231055.25953-1-krisman@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Stable-dep-of: b5fcf7871a ("sbitmap: correct wake_batch recalculation to avoid potential IO hung")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 903e86f3a6 ]
Commit fbb564a557 ("lib/sbitmap: Fix invalid loop in
__sbitmap_queue_get_batch()") mentioned that "Checking free bits when
setting the target bits. Otherwise, it may reuse the busying bits."
This commit add check to make sure all masked bits in word before
cmpxchg is zero. Then the existing check after cmpxchg to check any
zero bit is existing in masked bits in word is redundant.
Actually, old value of word before cmpxchg is stored in val and we
will filter out busy bits in val by "(get_mask & ~val)" after cmpxchg.
So we will not reuse busy bits methioned in commit fbb564a557
("lib/sbitmap: Fix invalid loop in __sbitmap_queue_get_batch()"). Revert
new-added check to remove redundant check.
Fixes: fbb564a557 ("lib/sbitmap: Fix invalid loop in __sbitmap_queue_get_batch()")
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Link: https://lore.kernel.org/r/20230116205059.3821738-3-shikemeng@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 856968e066 ]
For proper warm (re)boot from SD card the BPI-M5 board requires TFLASH_VDD_EN
and VDDIO_C pins to be switched to high impedance mode. This can be achieved
using OPEN_DRAIN instead of ACTIVE_HIGH to leave the GPIO pins in input mode
and retain high state (pin has the pull-up).
This change is inspired by meson-sm1-odroid.dtsi where OPEN_DRAIN has been
used to resolve similar problems with the Odroid C4 board (TF_IO in the C4
dts is the equivalent regulator).
Fixes: 976e920183 ("arm64: dts: meson-sm1: add Banana PI BPI-M5 board dts")
Suggested-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Christian Hewitt <christianshewitt@gmail.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20230127142221.3718184-2-christianshewitt@gmail.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit d7f9492dfc ]
The board used to originally introduce the Beacon Embedded RZ/G2[M/N/H]
boards had a GPIO expander with address 20, but this was changed when
the final board went to production.
The production boards changed both the part itself and the address.
With the incorrect address, the LCD cannot come up. If the LCD fails,
the rcar-du driver fails to come up, and that also breaks HDMI.
Pre-release board were not shipped to the general public, so it should
be safe to push this as a fix. Anyone with a production board would
have video fail due to this GPIO expander change.
Fixes: a1d8a344f1 ("arm64: dts: renesas: Introduce r8a774a1-beacon-rzg2m-kit")
Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20230114225647.227972-1-aford173@gmail.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3f5245538a ]
Commit:
91d2a812df ("locking/rwsem: Make handoff writer optimistically spin on owner")
... assumes that when the owner field is changed to NULL, the lock will
become free soon. But commit:
48dfb5d256 ("locking/rwsem: Disable preemption while trying for rwsem lock")
... disabled preemption when acquiring rwsem for write.
However, preemption has not yet been disabled when acquiring a read lock
on a rwsem. So a reader can add a RWSEM_READER_BIAS to count without
setting owner to signal a reader, got preempted out by a RT task which
then spins in the writer slowpath as owner remains NULL leading to live lock.
One easy way to fix this problem is to disable preemption at all the
down_read*() and up_read() code paths as implemented in this patch.
Fixes: 91d2a812df ("locking/rwsem: Make handoff writer optimistically spin on owner")
Reported-by: Mukesh Ojha <quic_mojha@quicinc.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230126003628.365092-3-longman@redhat.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit ebeb49f43c ]
The function call ida_simple_get maybe fail,we should deal with it.
And if ida_simple_get success ,it need to call ida_simple_remove also.
BTW,devm_kasprintf can handle id is zero for consistency.
Fixes: e76bdfd740 ("ARM: imx: Added perf functionality to mmdc driver")
Signed-off-by: Angus Chen <angus.chen@jaguarmicro.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5bf52f5e4d ]
The prototype does not match the definition, as gcc-13 points
out:
arch/arm/mach-s3c/s3c64xx.c:169:13: error: conflicting types for 's3c64xx_set_timer_source' due to enum/integer mismatch; have 'void(unsigned int, unsigned int)' [-Werror=enum-int-mismatch]
169 | void __init s3c64xx_set_timer_source(unsigned int event, unsigned int source)
| ^~~~~~~~~~~~~~~~~~~~~~~~
In file included from arch/arm/mach-s3c/s3c64xx.c:50:
arch/arm/mach-s3c/s3c64xx.h:62:20: note: previous declaration of 's3c64xx_set_timer_source' with type 'void(enum s3c64xx_timer_mode, enum s3c64xx_timer_mode)'
62 | extern void __init s3c64xx_set_timer_source(enum s3c64xx_timer_mode event,
| ^~~~~~~~~~~~~~~~~~~~~~~~
Fixes: 4280506ac9 ("ARM: SAMSUNG: Move all platforms to new clocksource driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20230118090224.2162863-1-arnd@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3cbd431c2b ]
Amlogic G12A devices experience CPU stalls and random board wedges when
the system idles and CPU cores clock down to lower opp points. Recent
vendor kernels include a change to remove 100-250MHz and other distro
sources also remove the 500/667MHz points. Unless all 100-667Mhz opps
are removed or the CPU governor forced to performance stalls are still
observed, so let's remove them to improve stability and uptime.
Fixes: b190056fa9 ("arm64: dts: meson-g12a: add cpus OPP table")
Signed-off-by: Christian Hewitt <christianshewitt@gmail.com>
Link: https://lore.kernel.org/r/20230119053031.21400-1-christianshewitt@gmail.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 0e8b90c025 ]
Current PCIe QMP PHY output name were changed in ("arm64: dts: qcom: Fix
IPQ8074 PCIe PHY nodes") however it did not account for the fact that GCC
driver is relying on the old names to match them as they are being used as
the parent for the gcc_pcie0_pipe_clk and gcc_pcie1_pipe_clk.
This broke parenting as GCC could not find the parent clock, so fix it by
changing to the names that driver is expecting.
Fixes: 942bcd33ed ("arm64: dts: qcom: Fix IPQ8074 PCIe PHY nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-9-robimarko@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3e83a9c41a ]
IPQ8074 comes in 2 silicon versions:
* v1 with 2x Gen2 PCIe ports and QMP PHY-s
* v2 with 1x Gen3 and 1x Gen2 PCIe ports and QMP PHY-s
v2 is the final and production version that is actually supported by the
kernel, however it looks like PCIe related nodes were added for the v1 SoC.
Finish the PCIe fixup by using the correct compatible, adding missing ATU
register space, declaring max-link-speed, use correct ranges, add missing
clocks and resets.
Fixes: 33057e1672 ("ARM: dts: ipq8074: Add pcie nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-8-robimarko@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 7ba33591b4 ]
IPQ8074 comes in 2 silicon versions:
* v1 with 2x Gen2 PCIe ports and QMP PHY-s
* v2 with 1x Gen3 and 1x Gen2 PCIe ports and QMP PHY-s
v2 is the final and production version that is actually supported by the
kernel, however it looks like PCIe related nodes were added for the v1 SoC.
Now that we have Gen3 QMP PHY support, we can start fixing the PCIe support
by fixing the Gen3 QMP PHY node first.
Change the compatible to the Gen3 QMP PHY, correct the register space start
and size, add the missing misc PCS register space.
Fixes: 33057e1672 ("ARM: dts: ipq8074: Add pcie nodes")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230113164449.906002-2-robimarko@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 877cff3568 ]
It seems that clock-output-names for the USB3 QMP PHY-s where set without
actually checking what is the GCC clock driver expecting, so clock core
could never actually find the parents for usb0_pipe_clk_src and
usb1_pipe_clk_src clocks in the GCC driver.
So, correct the names to be what the driver expects so that parenting
works.
Before:
gcc_usb0_pipe_clk_src 0 0 0 125000000 0 0 50000 Y
gcc_usb1_pipe_clk_src 0 0 0 125000000 0 0 50000 Y
After:
usb3phy_0_cc_pipe_clk 1 1 0 125000000 0 0 50000 Y
usb0_pipe_clk_src 1 1 0 125000000 0 0 50000 Y
gcc_usb0_pipe_clk 1 1 0 125000000 0 0 50000 Y
usb3phy_1_cc_pipe_clk 1 1 0 125000000 0 0 50000 Y
usb1_pipe_clk_src 1 1 0 125000000 0 0 50000 Y
gcc_usb1_pipe_clk 1 1 0 125000000 0 0 50000 Y
Fixes: 5e09bc51d0 ("arm64: dts: ipq8074: enable USB support")
Signed-off-by: Robert Marko <robimarko@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20230108130440.670181-2-robimarko@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 29bcc1eaca ]
When the top-level regulators were renamed, the 1.2V camera regulator
accidentally ended up with the same DT node name as the 1.8V camera
regulator.
Fixes: 097e01c610 ("arm64: tegra: Rename top-level regulators")
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 361e8b7144 ]
SPI nodes defined in the top-level AM62x SoC dtsi files are incomplete
and will not be functional unless they are extended with pinmux
information.
As the pinmux is only known at the board integration level, these
nodes should only be enabled when provided with this information.
Disable the SPI nodes in the dtsi files and only enable the ones that
are actually pinned out on a given board.
Signed-off-by: Andrew Davis <afd@ti.com>
Signed-off-by: Nishanth Menon <nm@ti.com>
Reviewed-by: Bryan Brattlof <bb@ti.com>
Link: https://lore.kernel.org/r/20221018211533.21335-4-afd@ti.com
Stable-dep-of: 6be5d8e5d1 ("arm64: dts: ti: k3-am62-main: Fix clocks for McSPI")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6d9c7f51b1 ]
So objtool found this bug:
vmlinux.o: warning: objtool: intel_idle_irq+0x10c: call to trace_hardirqs_off() leaves .noinstr.text section
As per commit 32d4fd5751 ("cpuidle,intel_idle: Fix CPUIDLE_FLAG_IRQ_ENABLE"):
"must not have tracing in idle functions"
Clearly people can't read and tinker along until splat dissapears.
This straight up reverts commit d295ad34f2 ("intel_idle: Fix false
positive RCU splats due to incorrect hardirqs state").
It doesn't re-introduce the problem because preceding patches fixed it
properly.
Fixes: d295ad34f2 ("intel_idle: Fix false positive RCU splats due to incorrect hardirqs state")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20230112195540.434302128@infradead.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
