The NMI watchdog uses either the fixed cycles or a generic cycles
counter. This causes a lot of conflicts with users of the PMU who want
to run a full group including the cycles fixed counter, for example
the --topdown support recently added to perf stat. The code needs to
fall back to not use groups, which can cause measurement inaccuracy
due to multiplexing errors.
This patch switches the NMI watchdog to use reference cycles
on Intel systems. This is actually more accurate than cycles,
because cycles can tick faster than the measured CPU Frequency
due to Turbo mode.
The ref cycles always tick at their frequency, or slower when
the system is idling. That means the NMI watchdog can never
expire too early, unlike with cycles.
The reference cycles tick roughly at the frequency of the TSC,
so the same period computation can be used.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1465478079-19993-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch adds guest steal-time support to full dynticks CPU
time accounting. After the following commit:
ff9a9b4c43 ("sched, time: Switch VIRT_CPU_ACCOUNTING_GEN to jiffy granularity")
... time sampling became jiffy based, even if we do the sampling from the
context tracking code, so steal_account_process_tick() can be reused
to account how many 'ticks' are stolen-time, after the last accumulation.
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1465813966-3116-4-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit:
e9532e69b8 ("sched/cputime: Fix steal time accounting vs. CPU hotplug")
... set rq->prev_* to 0 after a CPU hotplug comes back, in order to
fix the case where (after CPU hotplug) steal time is smaller than
rq->prev_steal_time.
However, this should never happen. Steal time was only smaller because of the
KVM-specific bug fixed by the previous patch. Worse, the previous patch
triggers a bug on CPU hot-unplug/plug operation: because
rq->prev_steal_time is cleared, all of the CPU's past steal time will be
accounted again on hot-plug.
Since the root cause has been fixed, we can just revert commit e9532e69b8.
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 'commit e9532e69b8 ("sched/cputime: Fix steal time accounting vs. CPU hotplug")'
Link: http://lkml.kernel.org/r/1465813966-3116-3-git-send-email-wanpeng.li@hotmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Kasan causes the compiler to instrument C code and is used at runtime to
detect accesses to memory that has been freed, or not yet allocated.
The code in snapshot.c saves and restores memory when hibernating. This will
access whole pages in the slab cache that have both free and allocated
areas, resulting in a large number of false positives from Kasan.
Disable instrumentation of this file.
Signed-off-by: James Morse <james.morse@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
- Fix a few bugs in configuring the default trigger from the irqdomain layer
- Make the genirq layer PM aware
- Add PM capability to the ARM GIC driver
- Add support for 2-level translation tables to the GICv3 ITS driver
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=OnlS
-----END PGP SIGNATURE-----
Merge tag 'irqchip-for-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core
First drop of irqchip updates for 4.8 from Marc Zyngier:
- Fix a few bugs in configuring the default trigger from the irqdomain layer
- Make the genirq layer PM aware
- Add PM capability to the ARM GIC driver
- Add support for 2-level translation tables to the GICv3 ITS driver
Some IRQ chips may be located in a power domain outside of the CPU
subsystem and hence will require device specific runtime power
management. In order to support such IRQ chips, add a pointer for a
device structure to the irq_chip structure, and if this pointer is
populated by the IRQ chip driver and CONFIG_PM is selected in the kernel
configuration, then the pm_runtime_get/put APIs for this chip will be
called when an IRQ is requested/freed, respectively.
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Some IRQ chips, such as GPIO controllers or secondary level interrupt
controllers, may require require additional runtime power management
control to ensure they are accessible. For such IRQ chips, it makes sense
to enable the IRQ chip when interrupts are requested and disabled them
again once all interrupts have been freed.
When mapping an IRQ, the IRQ type settings are read and then programmed.
The mapping of the IRQ happens before the IRQ is requested and so the
programming of the type settings occurs before the IRQ is requested. This
is a problem for IRQ chips that require additional power management
control because they may not be accessible yet. Therefore, when mapping
the IRQ, don't program the type settings, just save them and then program
these saved settings when the IRQ is requested (so long as if they are not
overridden via the call to request the IRQ).
Add a stub function for irq_domain_free_irqs() to avoid any compilation
errors when CONFIG_IRQ_DOMAIN_HIERARCHY is not selected.
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
As we now do for non-percpu interrupt, perform a lookup of the
interrupt trigger if the user doesn't supply one. The difference
here is that we can only do it at enable time (trigger configuration
can be per-cpu as well).
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
For some devices the IRQ trigger type for a device is read from
firmware, such as device-tree. The IRQ trigger type is typically read
when the mapping for IRQ is created, which is before the IRQ is
requested. Hence, the IRQ trigger type is programmed when mapping the
IRQ and not when requesting the IRQ.
Although this works for most cases, in order to support IRQ chips which
require runtime power management, which may not be accessible prior
to requesting the IRQ, it is desirable to look-up the IRQ trigger type
when it is requested. Therefore, if the IRQ trigger type is not
specified when __setup_irq() is called, look-up the saved IRQ trigger
type. This will allow us to defer the programming of the trigger type
from when the IRQ is mapped to when it is actually requested.
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
When mapping an IRQ, it is possible that a mapping for the IRQ already
exists. If mapping does exist then there are the following issues with
regard to the handling of the IRQ type settings ...
1. If the domain is part of a hierarchy, then:
a. We do not check that the type settings for the existing mapping
match those of the new mapping.
b. We do not check to see if the type settings have been programmed
yet (and they might not have been) and so we may never set the
type.
2. If the domain is NOT part of a hierarchy, we will overwrite the
current type settings programmed if they are different from the
previous mapping. Please note that irq_create_mapping()
calls irq_find_mapping() to check if a mapping already exists.
Although, it may be unlikely that the type settings for a shared
interrupt would not match, nonetheless we should check for this.
Therefore, to fix this check if a mapping exists (regardless of whether
the domain is part of a hierarchy or not) and if it does then:
1. Return the IRQ number if the type settings match or are not
specified.
2. Program the type settings and return the IRQ number if the type
settings have not been programmed yet.
3. Otherwise if the type setting do not match, then print a warning
and don't return the IRQ number.
Furthermore, add a warning if the type return by irq_domain_translate()
has bits outside the sense mask set and then clear these bits. If these
bits are not cleared then this will cause the comparision of the type
settings for an existing mapping to fail with that of the new mapping
even if the sense bit themselves match. The reason being is that the
existing type settings are read by calling irq_get_trigger_type() which
will clear any bits outside the sense mask. This will allow us to detect
irqchips that are not correctly clearing these bits and fix them.
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Merge filesystem stacking fixes from Jann Horn.
* emailed patches from Jann Horn <jannh@google.com>:
sched: panic on corrupted stack end
ecryptfs: forbid opening files without mmap handler
proc: prevent stacking filesystems on top
Until now, hitting this BUG_ON caused a recursive oops (because oops
handling involves do_exit(), which calls into the scheduler, which in
turn raises an oops), which caused stuff below the stack to be
overwritten until a panic happened (e.g. via an oops in interrupt
context, caused by the overwritten CPU index in the thread_info).
Just panic directly.
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull perf fixes from Ingo Molnar:
"A handful of tooling fixes, two PMU driver fixes and a cleanup of
redundant code that addresses a security analyzer false positive"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/core: Remove a redundant check
perf/x86/intel/uncore: Remove SBOX support for Broadwell server
perf ctf: Convert invalid chars in a string before set value
perf record: Fix crash when kptr is restricted
perf symbols: Check kptr_restrict for root
perf/x86/intel/rapl: Fix pmus free during cleanup
Pull locking fixes from Ingo Molnar:
"Misc fixes:
- a file-based futex fix
- one more spin_unlock_wait() fix
- a ww-mutex deadlock detection improvement/fix
- and a raw_read_seqcount_latch() barrier fix"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
futex: Calculate the futex key based on a tail page for file-based futexes
locking/qspinlock: Fix spin_unlock_wait() some more
locking/ww_mutex: Report recursive ww_mutex locking early
locking/seqcount: Re-fix raw_read_seqcount_latch()
Pull networking fixes from David Miller:
1) nfnetlink timestamp taken from wrong skb, fix from Florian Westphal.
2) Revert some msleep conversions in rtlwifi as these spots are in
atomic context, from Larry Finger.
3) Validate that NFTA_SET_TABLE attribute is actually specified when we
call nf_tables_getset(). From Phil Turnbull.
4) Don't do mdio_reset in stmmac driver with spinlock held as that can
sleep, from Vincent Palatin.
5) sk_filter() does things other than run a BPF filter, so we should
not elide it's call just because sk->sk_filter is NULL. Fix from
Eric Dumazet.
6) Fix missing backlog updates in several packet schedulers, from Cong
Wang.
7) bnx2x driver should allow VLAN add/remove while the interface is
down, from Michal Schmidt.
8) Several RDS/TCP race fixes from Sowmini Varadhan.
9) fq_codel scheduler doesn't return correct queue length in dumps,
from Eric Dumazet.
10) Fix TCP stats for tail loss probe and early retransmit in ipv6, from
Yuchung Cheng.
11) Properly initialize udp_tunnel_socket_cfg in l2tp_tunnel_create(),
from Guillaume Nault.
12) qfq scheduler leaks SKBs if a kzalloc fails, fix from Florian
Westphal.
13) sock_fprog passed into PACKET_FANOUT_DATA needs compat handling,
from Willem de Bruijn.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (85 commits)
vmxnet3: segCnt can be 1 for LRO packets
packet: compat support for sock_fprog
stmmac: fix parameter to dwmac4_set_umac_addr()
net/mlx5e: Fix blue flame quota logic
net/mlx5e: Use ndo_stop explicitly at shutdown flow
net/mlx5: E-Switch, always set mc_promisc for allmulti vports
net/mlx5: E-Switch, Modify node guid on vf set MAC
net/mlx5: E-Switch, Fix vport enable flow
net/mlx5: E-Switch, Use the correct error check on returned pointers
net/mlx5: E-Switch, Use the correct free() function
net/mlx5: Fix E-Switch flow steering capabilities check
net/mlx5: Fix flow steering NIC capabilities check
net/mlx5: Fix root flow table update
net/mlx5: Fix MLX5_CMD_OP_MAX to be defined correctly
net/mlx5: Fix masking of reserved bits in XRCD number
net/mlx5: Fix the size of modify QP mailbox
mlxsw: spectrum: Don't sleep during ndo_get_phys_port_name()
mlxsw: spectrum: Make split flow match firmware requirements
wext: Fix 32 bit iwpriv compatibility issue with 64 bit Kernel
cfg80211: remove get/set antenna and tx power warnings
...
- Fix two intel_pstate initialization issues, one of which was
introduced during the 4.4 cycle (Srinivas Pandruvada).
- Fix kernel build with CONFIG_UBSAN set and CONFIG_CPU_IDLE
unset (Catalin Marinas).
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
iQIcBAABCAAGBQJXWgWVAAoJEILEb/54YlRxG5EP/itHzuh6Sq706zRRAL2zLAiW
9ZEgnH7Q0rbcaGTkRUe9BInJgS1lOxXlnzaQvx0nMN8omahYasl0FjX+5a+pwV6T
wE2tuw2wby0XI0gDwsEvTHpy6etCis46JfH8TJfPSkJOog83ZYoWeeolE9jwXPpP
Zgw8Eby/PvLr89tiDJr1/keChnQu0u2Ejz2hHEygc1Z5uxthVWfM8aEVaq8TnAPx
TBExCvjZ3+KuEjQTQdSy2Bw8h8z0AO086NARQJ7JwCtSqIyo6WEPvJ5q+Wcrt/Uq
P0C7Lpkcv6323sHm5hMCy+M3ES5Kws7cRFK3D2qjpTdtGr0/ibbHcrp2Vcw6b1Pr
8yRzN/ZJ4eLnLZLqggi42FByCygo1uy9zcqcbBCwDtmseM55+NgZGtmGgRBlRRw0
eOZwNmDHV++uUMF0EclBpIPG4mgUa7EdlJBFBgsRDeRMk+7VqKuw2Nl+F8d+gfvn
a0uUMHLUoSA7eI8/pKwGbdiaMVSKQahhPXhZcJOmBdV7eLFX5rCKiRujhNg2XNgU
GaVCRgwP7HRs5RmrQQByQS09BeCgK/sqCZcWZh1VrHQFfww/cxnFQTYJuapgnz2i
y0n6B2foMF2B3dxMDioqDkNWl7V/fgO0YuKCAea5eFrQA9GZf1zM8sbEtaq2khZw
xCa0iom5cIrBOCc3gvTv
=qmBM
-----END PGP SIGNATURE-----
Merge tag 'pm-4.7-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management fixes from Rafael Wysocki:
"Stable-candidate fixes for the intel_pstate driver and the cpuidle
core.
Specifics:
- Fix two intel_pstate initialization issues, one of which was
introduced during the 4.4 cycle (Srinivas Pandruvada)
- Fix kernel build with CONFIG_UBSAN set and CONFIG_CPU_IDLE unset
(Catalin Marinas)"
* tag 'pm-4.7-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
cpufreq: intel_pstate: Fix ->set_policy() interface for no_turbo
cpufreq: intel_pstate: Fix code ordering in intel_pstate_set_policy()
cpuidle: Do not access cpuidle_devices when !CONFIG_CPU_IDLE
sprintf() and snprintf() implementation of kernel guarantees that
its result is terminated with null byte if size is larger than 0. So we
don't need to call memset() at all.
Signed-off-by: Weongyo Jeong <weongyo.linux@gmail.com>
Link: http://lkml.kernel.org/r/1459451703-5744-1-git-send-email-weongyo.linux@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Only need CONFIG_NO_HZ_COMMON as this block is already in a
CONFIG_SMP block.
Signed-off-by: Pratyush Patel <pratyushpatel.1995@gmail.com>
Link: http://lkml.kernel.org/r/20160301172849.GA18152@cyborg
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Update the usleep_range() function comment to make it clear that it can
only be used in non-atomic context.
Previously we claimed usleep_range() was a drop-in replacement for udelay()
where wakeup is flexible. But that's only true in non-atomic contexts,
where it's possible to sleep instead of delay.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: John Stultz <john.stultz@linaro.org>
Link: http://lkml.kernel.org/r/20160531212302.28502.44995.stgit@bhelgaas-glaptop2.roam.corp.google.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* pm-cpufreq-fixes:
cpufreq: intel_pstate: Fix ->set_policy() interface for no_turbo
cpufreq: intel_pstate: Fix code ordering in intel_pstate_set_policy()
* pm-cpuidle:
cpuidle: Do not access cpuidle_devices when !CONFIG_CPU_IDLE
Instead of overloading the discard support with the REQ_SECURE flag.
Use the opportunity to rename the queue flag as well, and remove the
dead checks for this flag in the RAID 1 and RAID 10 drivers that don't
claim support for secure erase.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Mike Galbraith reported that the LTP test case futex_wake04 was broken
by commit 65d8fc777f ("futex: Remove requirement for lock_page()
in get_futex_key()").
This test case uses futexes backed by hugetlbfs pages and so there is an
associated inode with a futex stored on such pages. The problem is that
the key is being calculated based on the head page index of the hugetlbfs
page and not the tail page.
Prior to the optimisation, the page lock was used to stabilise mappings and
pin the inode is file-backed which is overkill. If the page was a compound
page, the head page was automatically looked up as part of the page lock
operation but the tail page index was used to calculate the futex key.
After the optimisation, the compound head is looked up early and the page
lock is only relied upon to identify truncated pages, special pages or a
shmem page moving to swapcache. The head page is looked up because without
the page lock, special care has to be taken to pin the inode correctly.
However, the tail page is still required to calculate the futex key so
this patch records the tail page.
On vanilla 4.6, the output of the test case is;
futex_wake04 0 TINFO : Hugepagesize 2097152
futex_wake04 1 TFAIL : futex_wake04.c:126: Bug: wait_thread2 did not wake after 30 secs.
With the patch applied
futex_wake04 0 TINFO : Hugepagesize 2097152
futex_wake04 1 TPASS : Hi hydra, thread2 awake!
Fixes: 65d8fc777f "futex: Remove requirement for lock_page() in get_futex_key()"
Reported-and-tested-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20160608132522.GM2469@suse.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
A while back Viro posted a number of 'interesting' mutex_is_locked()
users on IRC, one of those was RCU.
RCU seems to use mutex_is_locked() to avoid doing mutex_trylock(), the
regular load before modify pattern.
While the use isn't wrong per se, its curious in that its needed at all,
mutex_trylock() should be good enough on its own to avoid the pointless
cacheline bounces.
So fix those and remove the mutex_is_locked() (ab)use from RCU.
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paul McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hpe.com>
Link: http://lkml.kernel.org/r/20160601185815.GW3190@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch moves the owner loading and checking code entirely inside of
rwsem_spin_on_owner() to simplify the logic of rwsem_optimistic_spin()
loop.
Suggested-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1463534783-38814-6-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In __rwsem_do_wake(), the reader wakeup code will assume a writer
has stolen the lock if the active reader/writer count is not 0.
However, this is not as reliable an indicator as the original
"< RWSEM_WAITING_BIAS" check. If another reader is present, the code
will still break out and exit even if the writer is gone. This patch
changes it to check the same "< RWSEM_WAITING_BIAS" condition to
reduce the chance of false positive.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Peter Hurley <peter@hurleysoftware.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1463534783-38814-5-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Without using WRITE_ONCE(), the compiler can potentially break a
write into multiple smaller ones (store tearing). So a read from the
same data by another task concurrently may return a partial result.
This can result in a kernel crash if the data is a memory address
that is being dereferenced.
This patch changes all write to rwsem->owner to use WRITE_ONCE()
to make sure that store tearing will not happen. READ_ONCE() may
not be needed for rwsem->owner as long as the value is only used for
comparison and not dereferencing.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1463534783-38814-3-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, it is not possible to determine for sure if a reader
owns a rwsem by looking at the content of the rwsem data structure.
This patch adds a new state RWSEM_READER_OWNED to the owner field
to indicate that readers currently own the lock. This enables us to
address the following 2 issues in the rwsem optimistic spinning code:
1) rwsem_can_spin_on_owner() will disallow optimistic spinning if
the owner field is NULL which can mean either the readers own
the lock or the owning writer hasn't set the owner field yet.
In the latter case, we miss the chance to do optimistic spinning.
2) While a writer is waiting in the OSQ and a reader takes the lock,
the writer will continue to spin when out of the OSQ in the main
rwsem_optimistic_spin() loop as the owner field is NULL wasting
CPU cycles if some of readers are sleeping.
Adding the new state will allow optimistic spinning to go forward as
long as the owner field is not RWSEM_READER_OWNED and the owner is
running, if set, but stop immediately when that state has been reached.
On a 4-socket Haswell machine running on a 4.6-rc1 based kernel, the
fio test with multithreaded randrw and randwrite tests on the same
file on a XFS partition on top of a NVDIMM were run, the aggregated
bandwidths before and after the patch were as follows:
Test BW before patch BW after patch % change
---- --------------- -------------- --------
randrw 988 MB/s 1192 MB/s +21%
randwrite 1513 MB/s 1623 MB/s +7.3%
The perf profile of the rwsem_down_write_failed() function in randrw
before and after the patch were:
19.95% 5.88% fio [kernel.vmlinux] [k] rwsem_down_write_failed
14.20% 1.52% fio [kernel.vmlinux] [k] rwsem_down_write_failed
The actual CPU cycles spend in rwsem_down_write_failed() dropped from
5.88% to 1.52% after the patch.
The xfstests was also run and no regression was observed.
Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Jason Low <jason.low2@hp.com>
Acked-by: Davidlohr Bueso <dave@stgolabs.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1463534783-38814-2-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Convert the rwsem count variable to an atomic_long_t since we use it
as an atomic variable. This also allows us to remove the
rwsem_atomic_{add,update}() "abstraction" which would now be an unnecesary
level of indirection. In follow up patches, we also remove the
rwsem_atomic_{add,update}() definitions across the various architectures.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jason Low <jason.low2@hpe.com>
[ Build warning fixes on various architectures. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Terry Rudd <terry.rudd@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Waiman Long <Waiman.Long@hpe.com>
Link: http://lkml.kernel.org/r/1465017963-4839-2-git-send-email-jason.low2@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
I figured we need to document the spin_is_locked() and
spin_unlock_wait() constraints somwehere.
Ideally 'someone' would rewrite Documentation/atomic_ops.txt and we
could find a place in there. But currently that document is stale to
the point of hardly being useful.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <waiman.long@hpe.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While going over the code I noticed that xchg_tail() is a RELEASE but
had no obvious pairing commented.
It pairs with a somewhat unique address dependency through
decode_tail().
So the store-release of xchg_tail() is paired by the address
dependency of the load of xchg_tail followed by the dereference from
the pointer computed from that load.
The @old -> @prev transformation itself is pure, and therefore does
not depend on external state, so that is immaterial wrt. ordering.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <waiman.long@hpe.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The nr_migrations field is updated independently of CONFIG_SCHEDSTATS,
so it can be displayed regardless.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/5b1b04057ae2b14d73c2d03f56582c1d38cfe066.1464994423.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The 'schedstats=enable' option doesn't work, and also produces the
following warning during boot:
WARNING: CPU: 0 PID: 0 at /home/jpoimboe/git/linux/kernel/jump_label.c:61 static_key_slow_inc+0x8c/0xa0
static_key_slow_inc used before call to jump_label_init
Modules linked in:
CPU: 0 PID: 0 Comm: swapper Not tainted 4.7.0-rc1+ #25
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
0000000000000086 3ae3475a4bea95d4 ffffffff81e03da8 ffffffff8143fc83
ffffffff81e03df8 0000000000000000 ffffffff81e03de8 ffffffff810b1ffb
0000003d00000096 ffffffff823514d0 ffff88007ff197c8 0000000000000000
Call Trace:
[<ffffffff8143fc83>] dump_stack+0x85/0xc2
[<ffffffff810b1ffb>] __warn+0xcb/0xf0
[<ffffffff810b207f>] warn_slowpath_fmt+0x5f/0x80
[<ffffffff811e9c0c>] static_key_slow_inc+0x8c/0xa0
[<ffffffff810e07c6>] static_key_enable+0x16/0x40
[<ffffffff8216d633>] setup_schedstats+0x29/0x94
[<ffffffff82148a05>] unknown_bootoption+0x89/0x191
[<ffffffff810d8617>] parse_args+0x297/0x4b0
[<ffffffff82148d61>] start_kernel+0x1d8/0x4a9
[<ffffffff8214897c>] ? set_init_arg+0x55/0x55
[<ffffffff82148120>] ? early_idt_handler_array+0x120/0x120
[<ffffffff821482db>] x86_64_start_reservations+0x2f/0x31
[<ffffffff82148427>] x86_64_start_kernel+0x14a/0x16d
The problem is that it tries to update the 'sched_schedstats' static key
before jump labels have been initialized.
Changing jump_label_init() to be called earlier before
parse_early_param() wouldn't fix it: it would still fail trying to
poke_text() because mm isn't yet initialized.
Instead, just create a temporary '__sched_schedstats' variable which can
be copied to the static key later during sched_init() after jump labels
have been initialized.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: cb2517653f ("sched/debug: Make schedstats a runtime tunable that is disabled by default")
Link: http://lkml.kernel.org/r/453775fe3433bed65731a583e228ccea806d18cd.1465322027.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit:
cb2517653f ("sched/debug: Make schedstats a runtime tunable that is disabled by default")
... introduced a bug when CONFIG_SCHEDSTATS is enabled and the
runtime tunable is disabled (which is the default).
The wait-time, sum-exec, and sum-sleep fields are missing from the
/proc/sched_debug file in the runnable_tasks section.
Fix it with a new schedstat_val() macro which returns the field value
when schedstats is enabled and zero otherwise. The macro works with
both SCHEDSTATS and !SCHEDSTATS. I put the macro in stats.h since it
might end up being useful in other places.
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: cb2517653f ("sched/debug: Make schedstats a runtime tunable that is disabled by default")
Link: http://lkml.kernel.org/r/bcda7c2790cf2ccbe586a28c02dd7b6fe7749a2b.1464994423.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is no way to end up in _free_event() with event::pmu being NULL.
The latter is initialized in event allocation path and remains set
forever. In case of allocation failure, the error path doesn't use
_free_event().
Having the check, however, suggests that it is possible to have a
event::pmu==NULL situation in _free_event() and confuses the robots.
This patch gets rid of the check.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: eranian@google.com
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/1465303455-26032-1-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While this prior commit:
54cf809b95 ("locking,qspinlock: Fix spin_is_locked() and spin_unlock_wait()")
... fixes spin_is_locked() and spin_unlock_wait() for the usage
in ipc/sem and netfilter, it does not in fact work right for the
usage in task_work and futex.
So while the 2 locks crossed problem:
spin_lock(A) spin_lock(B)
if (!spin_is_locked(B)) spin_unlock_wait(A)
foo() foo();
... works with the smp_mb() injected by both spin_is_locked() and
spin_unlock_wait(), this is not sufficient for:
flag = 1;
smp_mb(); spin_lock()
spin_unlock_wait() if (!flag)
// add to lockless list
// iterate lockless list
... because in this scenario, the store from spin_lock() can be delayed
past the load of flag, uncrossing the variables and loosing the
guarantee.
This patch reworks spin_is_locked() and spin_unlock_wait() to work in
both cases by exploiting the observation that while the lock byte
store can be delayed, the contender must have registered itself
visibly in other state contained in the word.
It also allows for architectures to override both functions, as PPC
and ARM64 have an additional issue for which we currently have no
generic solution.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Giovanni Gherdovich <ggherdovich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <waiman.long@hpe.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: stable@vger.kernel.org # v4.2 and later
Fixes: 54cf809b95 ("locking,qspinlock: Fix spin_is_locked() and spin_unlock_wait()")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
One warning should be enough to get one motivated to fix this. It is
possible that this happens more than once and that starts flooding the
output. Later the prints will be suppressed so we only get half of it.
Depending on the console system used it might not be helpful.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1464356838-1755-1-git-send-email-bigeasy@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Use __jhash_mix() to mix the class_idx into the class_key. This
function provides better mixing than the previously used, home grown
mix function.
Leave hashing to the professionals :-)
Suggested-by: George Spelvin <linux@sciencehorizons.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
unaccount_pmu_sb_event() did not check for attributes in event->attr
before calling detach_sb_event(), while account_pmu_event() did.
This caused NULL pointer reference in cgroup events that did not
have any of the attributes checked by account_pmu_event().
To trigger the bug just wait for a cgroup event to terminate, e.g.:
$ mkdir /dev/cgroup/devices/test
$ perf stat -e cycles -a -G test sleep 0
... see crash ...
Signed-off-by: David Carrillo-Cisneros <davidcc@google.com>
Reviewed-by: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Zheng <zheng.z.yan@intel.com>
Link: http://lkml.kernel.org/r/1464809585-66072-1-git-send-email-davidcc@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In bpf_perf_event_read() and bpf_perf_event_output(), we must use
READ_ONCE() for fetching the struct file pointer, which could get
updated concurrently, so we must prevent the compiler from potential
refetching.
We already do this with tail calls for fetching the related bpf_prog,
but not so on stored perf events. Semantics for both are the same
with regards to updates.
Fixes: a43eec3042 ("bpf: introduce bpf_perf_event_output() helper")
Fixes: 35578d7984 ("bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
To avoid confusion between REQ_OP_FLUSH, which is handled by
request_fn drivers, and upper layers requesting the block layer
perform a flush sequence along with possibly a WRITE, this patch
renames REQ_FLUSH to REQ_PREFLUSH.
Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
