During write to some of debugfs in ath10k, few variables exposing stack
data when process user input. which leads to possible information leak.
This patch fix this issue by initializing buffer and checks
the return valure of 'simple_write_to_buffer'.
Signed-off-by: Venkateswara Naralasetty <vnaralas@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Our out-of-line atomics are built with a special calling convention,
preventing pointless stack spilling, and allowing us to patch call sites
with ARMv8.1 atomic instructions.
Instrumentation inserted by the compiler may result in calls to
functions not following this special calling convention, resulting in
registers being unexpectedly clobbered, and various problems resulting
from this.
For example, if a kernel is built with KCOV and ARM64_LSE_ATOMICS, the
compiler inserts calls to __sanitizer_cov_trace_pc in the prologues of
the atomic functions. This has been observed to result in spurious
cmpxchg failures, leading to a hang early on in the boot process.
This patch avoids such issues by preventing instrumentation of our
out-of-line atomics.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Replace the manual validity checks for the GPIO with the
gpio_is_valid().
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
preallocate pages should use platform device,
since we set dma mask for platform device.
Signed-off-by: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
preallocate pages should use platform device,
since we set dma mask for platform device.
Signed-off-by: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Commit e9f5f1e456 ("ARM: OMAP2+: Remove legacy mux code") removed
CONFIG_OMAP_MUX making impossible to build Nokia N810 audio support. Remove
this dependency so we can do at least build tests.
Fixes: e9f5f1e456 ("ARM: OMAP2+: Remove legacy mux code")
Signed-off-by: Jarkko Nikula <jarkko.nikula@bitmer.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The bias for the analog HS microphone is coming from Retu/Vilma chip and
we do not have control over it, yet.
For clarity, add a new DAPM_MIC widget for the HS mic and document the
current state.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The non DT boot is no longer supported and when booting with DT the device
names are different.
Fix them up for now, but the n810.c should be updated to support probing
via DT with proper bindings.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Acked-by: Jarkko Nikula <jarkko.nikula@bitmer.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Fix the capture DAPM route due to core changes regarding to mic bias.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Acked-by: Jarkko Nikula <jarkko.nikula@bitmer.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The native clear_pending() function is identical to the PV version, so the
latter can simply be removed.
This fixes the build for systems with >= 16K CPUs using the PV lock implementation.
Reported-by: Waiman Long <longman@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/20180427101619.GB21705@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
So by chance I looked into x86 assembly in arch/x86/net/bpf_jit_comp.c and
noticed the weird and inconsistent comment style it mistakenly learned from
the networking code:
/* Multi-line comment ...
* ... looks like this.
*/
Fix this to use the standard comment style specified in Documentation/CodingStyle
and used in arch/x86/ as well:
/*
* Multi-line comment ...
* ... looks like this.
*/
Also, to quote Linus's ... more explicit views about this:
http://article.gmane.org/gmane.linux.kernel.cryptoapi/21066
> But no, the networking code picked *none* of the above sane formats.
> Instead, it picked these two models that are just half-arsed
> shit-for-brains:
>
> (no)
> /* This is disgusting drug-induced
> * crap, and should die
> */
>
> (no-no-no)
> /* This is also very nasty
> * and visually unbalanced */
>
> Please. The networking code actually has the *worst* possible comment
> style. You can literally find that (no-no-no) style, which is just
> really horribly disgusting and worse than the otherwise fairly similar
> (d) in pretty much every way.
Also improve the comments and some other details while at it:
- Don't mix same-line and previous-line comment style on otherwise
identical code patterns within the same function,
- capitalize 'BPF' and x86 register names consistently,
- capitalize sentences consistently,
- instead of 'x64' use 'x86-64': x64 is a Microsoft specific term,
- use more consistent punctuation,
- use standard coding style in macros as well,
- fix typos and a few other minor details.
Consistent coding style is not optional, at least in arch/x86/.
No change in functionality.
( In case this commit causes conflicts with pending development code
I'll be glad to help resolve any conflicts! )
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch removes boilerplate of GPLv2, use only SPDX identifier as
same as other recently ASoC DAI drivers.
Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
When CONFIG_BPF_JIT_ALWAYS_ON is enabled, kernel has limitation for
bpf_jit_enable, so it has fixed value 1 and we cannot set it to 2
for JIT opcode dumping; this patch is to update the doc for it.
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Add reset lines for MPEG2 transport stream I/O and demux system (HSC)
on UniPhier LD11/LD20 SoCs.
Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Add reset lines for SATA controller on UniPhier SoCs.
This adds support for Pro4 and PXs3 in addition to PXs2.
And this changes the ID of the reset line for SATA-PHY on PXs2.
Since some SoCs have two controller instances with a common PHY, this moves
the ID of SATA-PHY for consistency.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Add reset lines for PCIe controller on UniPhier SoCs. This adds support for
Pro5, LD20 and PXs3.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
For LD20, the bit 5 of the offset 0x200c turned out to be a USB3
reset. The hardware document says it is the GIO reset despite LD20
has no GIO bus, confusingly.
Also, fix confusing comments for PXs3.
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Recently kernelCI reported the board mt7622-rfb1 has a fail test with
kernel: ERROR: did not start booting whose details could be seen at [1].
The cause is that UART0 can't output anything when it's missing a proper
pin setup with current DTS, so the essential driver is always getting
enabled to fix up the issue.
[1] https://kernelci.org/boot/id/5ad7d62759b51461bfb1f829/
Cc: Kevin Hilman <khilman@baylibre.com>
Cc: stable@vger.kernel.org
Fixes: ae457b7679 ("arm64: dts: mt7622: add SoC and peripheral related device nodes")
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Matthias Brugger <matthias.bgg@gmail.com>
Currently we are enabling handling of interrupts specific to Tegra124+
which happen to overlap with previous generations. Let's specify
interrupts mask per SoC generation for consistency and in a preparation
of squashing of Tegra20 driver into the common one that will enable
handling of GART faults which may be undesirable by newer generations.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
The ISR reads interrupts-enable mask, but doesn't utilize it. Apply the
mask to the interrupt status and don't handle interrupts that MC driver
haven't asked for. Kernel would disable spurious MC IRQ and report the
error. This would happen only in a case of a very severe bug.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Move the device tree bindings for the Tegra20 memory controller to the
same location as the Tegra30 (and later) memory controller bindings.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Memory Controller has a memory client "hot reset" functionality, which
resets the DMA interface of a memory client, so MC is a reset controller.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Memory Controller has a memory client "hot reset" functionality, which
resets the DMA interface of a memory client. So MC is a reset controller
in addition to IOMMU.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
There are two bindings for the same Memory Controller. One of the bindings
became obsolete long time ago and probably was left unnoticed, remove it
for consistency.
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
As the Geminilake firmware is now merged to linux-firmware.git
use MODUE_FIRMWARE to load the firmware.
This removes the error message in the dmesg log:
i915 0000:00:02.0: Direct firmware load for
i915/glk_dmc_ver1_04.bin failed with error -2
i915 0000:00:02.0: Failed to load DMC firmware
i915/glk_dmc_ver1_04.bin. Disabling runtime power management.
i915 0000:00:02.0: DMC firmware homepage:
https://01.org/linuxgraphics/downloads/firmware
and now shows that the firmware has correctly loaded:
[drm] Finished loading DMC firmware i915/glk_dmc_ver1_04.bin (v1.4)
Signed-off-by: Ian W MORRISON <ianwmorrison@gmail.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180411044213.383-1-ianwmorrison@gmail.com
Add mode_valid() function to filter modes according to available
pll clock values and "preferred" modes. It is particularly
useful for hdmi modes that require precise pixel clocks.
Note that "preferred" modes are always accepted:
- this is important for panels because panel clock tolerances are
bigger than hdmi ones and there is no reason to not accept them
(the fps may vary a little but it is not a problem).
- the hdmi preferred mode will be accepted too, but userland will
be able to use others hdmi "valid" modes if necessary.
Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Reviewed-by: Yannick Fertré <yannick.fertre@st.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180417114026.8709-1-philippe.cornu@st.com
When a driver related to one of the endpoints is deferred
due to probe dependencies (i2c, spi...) but the other one
is ready, ltdc probe continues and the deferred driver
will never be probed again.
The fix consists in waiting for all deferred endpoints before
continuing the ltdc probe.
Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Reviewed-by: Yannick Fertré <yannick.fertre@st.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180417113441.8214-1-philippe.cornu@st.com
for 4.17, please pull the following:
- Srinath fixes the register base address of all SATA controllers on
Stingray
-----BEGIN PGP SIGNATURE-----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=oT+3
-----END PGP SIGNATURE-----
Merge tag 'arm-soc/for-4.17/devicetree-arm64-fixes' of https://github.com/Broadcom/stblinux into fixes
Pull "Broadcom devicetree-arm64 fixes for 4.17" from Florian Fainelli:
This pull request contains Broadcom ARM64-based SoCs Device Tree fixes
for 4.17, please pull the following:
- Srinath fixes the register base address of all SATA controllers on
Stingray
* tag 'arm-soc/for-4.17/devicetree-arm64-fixes' of https://github.com/Broadcom/stblinux:
arm64: dts: correct SATA addresses for Stingray
I've been heavily involved with concurrency and memory ordering stuff
(see ATOMIC INFRASTRUCTURE and LINUX KERNEL MEMORY CONSISTENCY MODEL)
and with arm64 now using qrwlock with a view to using qspinlock in the
near future, I'm going to continue being involved with the core locking
primitives. Reflect this by adding myself as a co-maintainer alongside
Ingo and Peter.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-15-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, the qspinlock_stat code tracks only statistical counts in the
PV qspinlock code. However, it may also be useful to track the number
of locking operations done via the pending code vs. the MCS lock queue
slowpath for the non-PV case.
The qspinlock stat code is modified to do that. The stat counter
pv_lock_slowpath is renamed to lock_slowpath so that it can be used by
both the PV and non-PV cases.
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1524738868-31318-14-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When reaching the head of an uncontended queue on the qspinlock slow-path,
using a try_cmpxchg() instead of a cmpxchg() operation to transition the
lock work to _Q_LOCKED_VAL generates slightly better code for x86 and
pretty much identical code for arm64.
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-13-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The qspinlock slowpath must ensure that the MCS node is fully initialised
before it can be reached by another other CPU. This is currently enforced
by using a RELEASE operation when updating the tail and also when linking
the node into the waitqueue, since the control dependency off xchg_tail
is insufficient to enforce sufficient ordering, see:
95bcade33a ("locking/qspinlock: Ensure node is initialised before updating prev->next")
Back-to-back RELEASE operations may be expensive on some architectures,
particularly those that implement them using fences under the hood. We
can replace the two RELEASE operations with a single smp_wmb() fence and
use RELAXED operations for the subsequent publishing of the node.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-12-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
A qspinlock can be unlocked simply by writing zero to the locked byte.
This can be implemented in the generic code, so do that and remove the
arch-specific override for x86 in the !PV case.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-11-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a locker reaches the head of the queue and takes the lock, a
concurrent locker may enqueue and force the lock holder to spin
whilst its node->next field is initialised. Rather than open-code
a READ_ONCE/cpu_relax() loop, this can be implemented using
smp_cond_load_relaxed() instead.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-10-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For qspinlocks on ARM64, we would like to use WFE instead
of purely spinning. Qspinlocks internally have lock
contenders spin on an MCS lock.
Update arch_mcs_spin_lock_contended() such that it uses
the new smp_cond_load_acquire() so that ARM64 can also
override this spin loop with its own implementation using WFE.
On x86, this can also be cheaper than spinning on
smp_load_acquire().
Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-9-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Rather than dig into the counter field of the atomic_t inside the
qspinlock structure so that we can call smp_cond_load_acquire(), use
atomic_cond_read_acquire() instead, which operates on the atomic_t
directly.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-8-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a queued locker reaches the head of the queue, it claims the lock
by setting _Q_LOCKED_VAL in the lockword. If there isn't contention, it
must also clear the tail as part of this operation so that subsequent
lockers can avoid taking the slowpath altogether.
Currently this is expressed as a cmpxchg() loop that practically only
runs up to two iterations. This is confusing to the reader and unhelpful
to the compiler. Rewrite the cmpxchg() loop without the loop, so that a
failed cmpxchg() implies that there is contention and we just need to
write to _Q_LOCKED_VAL without considering the rest of the lockword.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-7-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The qspinlock locking slowpath utilises a "pending" bit as a simple form
of an embedded test-and-set lock that can avoid the overhead of explicit
queuing in cases where the lock is held but uncontended. This bit is
managed using a cmpxchg() loop which tries to transition the uncontended
lock word from (0,0,0) -> (0,0,1) or (0,0,1) -> (0,1,1).
Unfortunately, the cmpxchg() loop is unbounded and lockers can be starved
indefinitely if the lock word is seen to oscillate between unlocked
(0,0,0) and locked (0,0,1). This could happen if concurrent lockers are
able to take the lock in the cmpxchg() loop without queuing and pass it
around amongst themselves.
This patch fixes the problem by unconditionally setting _Q_PENDING_VAL
using atomic_fetch_or, and then inspecting the old value to see whether
we need to spin on the current lock owner, or whether we now effectively
hold the lock. The tricky scenario is when concurrent lockers end up
queuing on the lock and the lock becomes available, causing us to see
a lockword of (n,0,0). With pending now set, simply queuing could lead
to deadlock as the head of the queue may not have observed the pending
flag being cleared. Conversely, if the head of the queue did observe
pending being cleared, then it could transition the lock from (n,0,0) ->
(0,0,1) meaning that any attempt to "undo" our setting of the pending
bit could race with a concurrent locker trying to set it.
We handle this race by preserving the pending bit when taking the lock
after reaching the head of the queue and leaving the tail entry intact
if we saw pending set, because we know that the tail is going to be
updated shortly.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-6-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On x86, atomic_cond_read_relaxed will busy-wait with a cpu_relax() loop,
so it is desirable to increase the number of times we spin on the qspinlock
lockword when it is found to be transitioning from pending to locked.
According to Waiman Long:
| Ideally, the spinning times should be at least a few times the typical
| cacheline load time from memory which I think can be down to 100ns or
| so for each cacheline load with the newest systems or up to several
| hundreds ns for older systems.
which in his benchmarking corresponded to 512 iterations.
Suggested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-5-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If a locker taking the qspinlock slowpath reads a lock value indicating
that only the pending bit is set, then it will spin whilst the
concurrent pending->locked transition takes effect.
Unfortunately, there is no guarantee that such a transition will ever be
observed since concurrent lockers could continuously set pending and
hand over the lock amongst themselves, leading to starvation. Whilst
this would probably resolve in practice, it means that it is not
possible to prove liveness properties about the lock and means that lock
acquisition time is unbounded.
Rather than removing the pending->locked spinning from the slowpath
altogether (which has been shown to heavily penalise a 2-threaded
locking stress test on x86), this patch replaces the explicit spinning
with a call to atomic_cond_read_relaxed and allows the architecture to
provide a bound on the number of spins. For architectures that can
respond to changes in cacheline state in their smp_cond_load implementation,
it should be sufficient to use the default bound of 1.
Suggested-by: Waiman Long <longman@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-4-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
'struct __qspinlock' provides a handy union of fields so that
subcomponents of the lockword can be accessed by name, without having to
manage shifts and masks explicitly and take endianness into account.
This is useful in qspinlock.h and also potentially in arch headers, so
move the 'struct __qspinlock' into 'struct qspinlock' and kill the extra
definition.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Acked-by: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: paulmck@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1524738868-31318-3-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
