Since the PMU register interface is banked per CPU, CPU PMU interrrupts
cannot be handled by a CPU other than the one with the PMU asserting the
interrupt. This means that migrating PMU SPIs, as we do during a CPU
hotplug operation doesn't make any sense and can lead to the IRQ being
disabled entirely if we route a spurious IRQ to the new affinity target.
This has been observed in practice on AMD Seattle, where CPUs on the
non-boot cluster appear to take a spurious PMU IRQ when coming online,
which is routed to CPU0 where it cannot be handled.
This patch passes IRQF_PERCPU for PMU SPIs and forcefully sets their
affinity prior to requesting them, ensuring that they cannot
be migrated during hotplug events. This interacts badly with the DB8500
erratum workaround that ping-pongs the interrupt affinity from the handler,
so we avoid passing IRQF_PERCPU in that case by allowing the IRQ flags
to be overridden in the platdata.
Fixes: 3cf7ee98b8 ("drivers/perf: arm_pmu: move irq request/free into probe")
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
This patch adds framework code to handle parsing PMU data out of the
MADT, sanity checking this, and managing the association of CPUs (and
their interrupts) with appropriate logical PMUs.
For the time being, we expect that only one PMU driver (PMUv3) will make
use of this, and we simply pass in a single probe function.
This is based on an earlier patch from Jeremy Linton.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Now that we've split the pdev and DT probing logic from the runtime
management, let's move the former into its own file. We gain a few lines
due to the copyright header and includes, but this should keep the logic
clearly separated, and paves the way for adding ACPI support in a
similar fashion.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
[will: rename nr_irqs to avoid conflict with global variable]
Signed-off-by: Will Deacon <will.deacon@arm.com>
We expect an ARM PMU's init function to have a particular prototype,
which we open-code in a few places. This is less than ideal, considering
that we cast a void value to this type in one location, and a mismatch
could easily be missed.
Add a typedef so that we can ensure this is consistent.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
For historical reasons, we lazily request and free interrupts in the
arm pmu driver. This requires us to refcount use of the pmu (by way of
counting the active events) in order to request/free interrupts at the
correct times, which complicates the driver somewhat.
The existing logic is flawed, as it only considers currently online CPUs
when requesting, freeing, or managing the affinity of interrupts.
Intervening hotplug events can result in erroneous IRQ affinity, online
CPUs for which interrupts have not been requested, or offline CPUs whose
interrupts are still requested.
To fix this, this patch splits the requesting of interrupts from any
per-cpu management (i.e. per-cpu enable/disable, and configuration of
cpu affinity). We now request all interrupts up-front at probe time (and
never free them, since we never unregister PMUs).
The management of affinity, and per-cpu enable/disable now happens in
our cpu hotplug callback, ensuring it occurs consistently. This means
that we must now invoke the CPU hotplug callback at boot time in order
to configure IRQs, and since the callback also resets the PMU hardware,
we can remove the duplicate reset in the probe path.
This rework renders our event refcounting unnecessary, so this is
removed.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
[will: make armpmu_get_cpu_irq static]
Signed-off-by: Will Deacon <will.deacon@arm.com>
When requesting or freeing interrupts, we use platform_get_irq() to find
relevant irqs, backing this up with additional information in an
optional irq_affinity table.
This means that our irq request and free paths are tied to a
platform_device, and our request path must jump through a number of
hoops in order to determine the required affinity of each interrupt.
Given that the affinity must be static, we can compute the affinity once
up-front at probe time, simplifying the irq request and free paths. By
recording interrupts in a per-cpu data structure, we simplify a few
paths, and permit a subsequent rework of the request and free paths.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
[will: rename local nr_irqs variable to avoid conflict with global]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Pull CPU hotplug updates from Thomas Gleixner:
"Yet another batch of cpu hotplug core updates and conversions:
- Provide core infrastructure for multi instance drivers so the
drivers do not have to keep custom lists.
- Convert custom lists to the new infrastructure. The block-mq custom
list conversion comes through the block tree and makes the diffstat
tip over to more lines removed than added.
- Handle unbalanced hotplug enable/disable calls more gracefully.
- Remove the obsolete CPU_STARTING/DYING notifier support.
- Convert another batch of notifier users.
The relayfs changes which conflicted with the conversion have been
shipped to me by Andrew.
The remaining lot is targeted for 4.10 so that we finally can remove
the rest of the notifiers"
* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
cpufreq: Fix up conversion to hotplug state machine
blk/mq: Reserve hotplug states for block multiqueue
x86/apic/uv: Convert to hotplug state machine
s390/mm/pfault: Convert to hotplug state machine
mips/loongson/smp: Convert to hotplug state machine
mips/octeon/smp: Convert to hotplug state machine
fault-injection/cpu: Convert to hotplug state machine
padata: Convert to hotplug state machine
cpufreq: Convert to hotplug state machine
ACPI/processor: Convert to hotplug state machine
virtio scsi: Convert to hotplug state machine
oprofile/timer: Convert to hotplug state machine
block/softirq: Convert to hotplug state machine
lib/irq_poll: Convert to hotplug state machine
x86/microcode: Convert to hotplug state machine
sh/SH-X3 SMP: Convert to hotplug state machine
ia64/mca: Convert to hotplug state machine
ARM/OMAP/wakeupgen: Convert to hotplug state machine
ARM/shmobile: Convert to hotplug state machine
arm64/FP/SIMD: Convert to hotplug state machine
...
Move the PMU name into a common header file so it may
be referenced by other users.
Signed-off-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
In systems with heterogeneous CPUs, there are multiple logical CPU PMUs,
each of which covers a subset of CPUs in the system. In some cases
userspace needs to know which CPUs a given logical PMU covers, so we'd
like to expose a cpumask under sysfs, similar to what is done for uncore
PMUs.
Unfortunately, prior to commit 00e727bb38 ("perf stat: Balance
opening and reading events"), perf stat only correctly handled a cpumask
holding a single CPU, and only when profiling in system-wide mode. In
other cases, the presence of a cpumask file could cause perf stat to
behave erratically.
Thus, exposing a cpumask file would break older perf binaries in cases
where they would otherwise work.
To avoid this issue while still providing userspace with the information
it needs, this patch exposes a differently-named file (cpus) under
sysfs. New tools can look for this and operate correctly, while older
tools will not be adversely affected by its presence.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
In preparation for adding common attribute groups, add an array of
attribute group pointers to arm_pmu, which will be used if the
backend hasn't already set pmu::attr_groups.
Subsequent patches will move backends over to using these, before adding
common fields.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Mark Rutland pointed out that this commit is incomplete:
7d88eb695a ("arm/perf: Convert to hotplug state machine")
The problem is that:
> We may have multiple PMUs (e.g. two in big.LITTLE systems), and
> __oprofile_cpu_pmu only contains one of these. So this conversion is not
> correct.
>
> We were relying on the notifier list implicitly containing a list of
> those PMUs. It seems like we need an explicit list here.
>
> We keep __oprofile_cpu_pmu around for legacy 32-bit users of OProfile
> (on non-hetereogeneous systems), and that's all that the variable should
> be used for.
Introduce arm_pmu_list to correctly handle multiple PMUs in the system.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Anna-Maria Gleixner <anna-maria@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-tip-commits@vger.kernel.org
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160719111733.GA22911@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The complete common architectural and micro-architectural
event number structure is filtered based on PMCEIDn_EL0 and
exposed to /sys using is_visibile function pointer in events
attribute_group.
To filter the events in is_visible function, pmceid based bitmap
is stored in arm_pmu structure and the id field from
perf_pmu_events_attr is used to check against the bitmap.
The function which derives event bitmap from PMCEIDn_EL0 is
executed in the cpus, which has the pmu being initialized,
for heterogeneous pmu support.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ashok Kumar <ashoks@broadcom.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
When a CPU is suspended (either through suspend-to-RAM or CPUidle),
its PMU registers content can be lost, which means that counters
registers values that were initialized on power down entry have to be
reprogrammed on power-up to make sure the counters set-up is preserved
(ie on power-up registers take the reset values on Cold or Warm reset,
which can be architecturally UNKNOWN).
To guarantee seamless profiling conditions across a core power down
this patch adds a CPU PM notifier to ARM pmus, that upon CPU PM
entry/exit from low-power states saves/restores the pmu registers
set-up (by using the ARM perf API), so that the power-down/up cycle does
not affect the perf behaviour (apart from a black-out period between
power-up/down CPU PM notifications that is unavoidable).
Cc: Will Deacon <will.deacon@arm.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Acked-by: Ashwin Chaugule <ashwin.chaugule@linaro.org>
Acked-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
ARMv7 counters other than the CPU cycle counter only work if the Secure
Debug Enable Register (SDER) SUNIDEN bit is set.
Since access to the SDER is only possible in secure state, it will
only be done if the device tree property "secure-reg-access" is set.
Without this:
Performance counter stats for 'sleep 1':
14606094 cycles # 0.000 GHz
0 instructions # 0.00 insns per cycle
After applying:
Performance counter stats for 'sleep 1':
5843809 cycles
2566484 instructions # 0.44 insns per cycle
1.020144000 seconds time elapsed
Some platforms (eg i.MX53) may also need additional platform specific
setup.
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Martin Fuzzey <mfuzzey@parkeon.com>
Signed-off-by: Pooya Keshavarzi <Pooya.Keshavarzi@de.bosch.com>
Signed-off-by: George G. Davis <george_davis@mentor.com>
[will: add warning if property is found on arm64]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Nothing outside of drivers/perf/arm_pmu.c should call armpmu_register
any more, so it no longer needs to be in include/linux/perf/arm_pmu.h.
Additionally, by folding it in to arm_pmu_device_probe we can allow
drivers to override struct pmu fields without getting blatted by the
armpmu code.
This patch folds armpmu_register into arm_pmu_device_probe. The logging
to the console is moved to after the PMU is successfully registered with
the core perf code.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Suggested-by: Will Deacon <will.deacon@arm.com>
Cc: Drew Richardson <drew.richardson@arm.com>
Cc: Pawel Moll <pawel.moll@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
To enable sharing of the arm_pmu code with arm64, this patch factors it
out to drivers/perf/. A new drivers/perf directory is added for
performance monitor drivers to live under.
MAINTAINERS is updated accordingly. Files added previously without a
corresponsing MAINTAINERS update (perf_regs.c, perf_callchain.c, and
perf_event.h) are also added.
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
[will: augmented Kconfig help slightly]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Will Deacon