When a CPU is taken out of reset, either cold booted or hotplugged in,
some of its PMU registers can contain UNKNOWN values.

This patch adds a hotplug notifier to ARM core perf code so that upon
CPU restart the PMU unit is reset and becomes ready to use again.
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

On ARM, the PMU does not stop counting after an overflow and therefore
IRQ latency affects the new counter value read by the kernel. This is
significant for non-sampling runs where it is possible for the new value
to overtake the previous one, causing the delta to be out by up to
max_period events.

Commit a737823d ("ARM: 6835/1: perf: ensure overflows aren't missed due
to IRQ latency") attempted to fix this problem by allowing interrupt
handlers to pass an overflow flag to the event update function, causing
the overflow calculation to assume that the counter passed through zero
when going from prev to new. Unfortunately, this doesn't work when
overflow occurs on the perf_task_tick path because we have the flag
cleared and end up computing a large negative delta.

This patch removes the overflow flag from armpmu_event_update and
instead limits the sample_period to half of the max_period for
non-sampling profiling runs.

Cc: <stable@vger.kernel.org>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

In the unlikely case that a platform registers a PMU platform_device
when running on a CPU that is unsupported by perf, we will encounter a
NULL dereference when trying to assign the platform_device to the
cpu_pmu structure.

This patch checks that the CPU is supported by perf before assigning
the platform_device.
Reported-by: NPawel Moll <pawel.moll@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

This patch introduces .enable_irq and .disable_irq into
struct arm_pmu_platdata, so platform specific irq enablement
can be handled after request_irq, and platform specific irq
disablement can be handled before free_irq.

This patch is for support of  pmu irq routed from CTI on omap4.
Acked-by: NJean Pihet <j-pihet@ti.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

armpmu_get_max_events is only called from perf_num_counters, so we can
inline it there. It existed as a separate entity as a hangover from
the original perf-based oprofile implementation.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Attempting to use a hardware counter on a platform with a supported PMU
but where the platform_device (defining the interrupts) has not been
registered results in a NULL pointer dereference.

This patch fixes the problem by checking that we actually have a platform
device registered before attempting to grab the interrupts.
Reported-by: NPawel Moll <pawel.moll@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

When validating an event group, we call pmu->get_event_idx for each
group member in order to check that the group can be scheduled as a
unit on an empty PMU.

As a result of 3fc2c830 ("ARM: perf: remove event limit from
pmu_hw_events"), the used_mask member of struct cpu_hw_events must be
setup explicitly, something which we don't do for the fake cpu_hw_events
used for validation.

This patch sets up an empty used_mask for the fake validation
cpu_hw_events, preventing NULL deferences when trying to get the event
index.
Reported-by: NPawel Moll <pawel.moll@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

People (Linus) objected to using -ENOSPC to signal not having enough
resources on the PMU to satisfy the request. Use -EINVAL.
Requested-by: NLinus Torvalds <torvalds@linux-foundation.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-xv8geaz2zpbjhlx0svmpp28n@git.kernel.org
[ merged to newer kernel, fixed up MIPS impact ]
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Many of the core ARM kernel files are not modules, but just
including module.h for exporting symbols.  Now these files can
use the lighter footprint export.h for this role.

There are probably lots more, but ARM files of mach-* and plat-*
don't get coverage via a simple yesconfig build.  They will have
to be cleaned up and tested via using their respective configs.
Signed-off-by: NPaul Gortmaker <paul.gortmaker@windriver.com>

Currently, armpmu_enable iterates through the events for a given
counter set, calling armpmu->enable on each before calling
armpmu->start to start the PMU's counters.

As armpmu->enable is called when each event is added, each event is
already configured in hardware. Due to this, calling armpmu->enable
in armpmu_enable is unnecessary and confusing.

This patch removes the unnecessary calls to armpmu->enable.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, struct arm_pmu and related functions are only visible to
{,arch/arm/}/kernel/perf_event.c. This prevents new drivers from using
the framework.

This patch  moves declarations to asm/pmu.h, allowing new PMU drivers
to use the framework.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently struct cpu_hw_events stores data on events running on a
PMU associated with a CPU. As this data is general enough to be used
for system PMUs, this name is a misnomer, and may cause confusion when
it is used for system PMUs.

Additionally, 'armpmu' is commonly used as a parameter name for an
instance of struct arm_pmu. The name is also used for a global instance
which represents the CPU's PMU.

As cpu_hw_events is now not tied to CPU PMUs, it is renamed to
pmu_hw_events, with instances of it renamed similarly. As the global
'armpmu' is CPU-specfic, it is renamed to cpu_pmu. This should make it
clearer which code is generic, and which is coupled with the CPU.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently the event accounting data in pmu_hw_events is stored in
fixed-sized arrays within the structure.

This patch refactors the accounting data to allow any number of events
to be managed.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, a single static instance of struct pmu is used when
registering an ARM PMU with the main perf subsystem. This limits
the ARM perf code to supporting a single PMU.

This patch replaces the static struct pmu instance with a member
variable on struct arm_pmu. This provides bidirectional mapping
between the two structs, and therefore allows for support of multiple
PMUs. The function 'to_arm_pmu' is provided for convenience.

PMU-generic functions are also updated to use the new mapping, and
PMU-generic initialisation of the member variables is moved into a new
function: armpmu_init.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently mapping an event type to a hardware configuration value
depends on the data being pointed to from struct arm_pmu. These fields
(cache_map, event_map, raw_event_mask) are currently specific to CPU
PMUs, and do not serve the general case well.

This patch replaces the event map pointers on struct arm_pmu with a new
'map_event' function pointer. Small shim functions are used to reuse
the existing common code.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, the ARM perf code assumes all PMUs it will handle are
CPU PMUs, having ARM_PMU_DEVICE_CPU hardcoded when reserving or
releasing hardware. This means that currently, the ARM perf code can't
support system PMUs.

This patch adds a 'type' field to struct arm_pmu, which allows the code
to reserve & release the hardware regardless of the PMU type.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, a single lock serialises access to CPU PMU registers. This
global locking is unnecessary as PMU registers are local to the CPU
they monitor.

This patch replaces the global lock with a per-CPU lock. As the lock is
in struct cpu_hw_events, PMUs providing a single cpu_hw_events instance
can be locked globally.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

As armpmu_disable will call armpmu->stop when the last event has been
removed, this is pointless and simply adds to the noise when debugging.
Additionally, due to this call occurring in a preemptible context, this
is problematic for per-cpu locking of PMU registers (where we will
attempt to access per-cpu spinlock for use with raw_spin_lock_irqsave).

This patch removes the call to armpmu->stop.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, cpu_hw_events is a global per-CPU variable. To enable
support for multiple PMUs, there needs to be a mapping from an instance
of arm_pmu to its cpu_hw_events. Additionally, as system PMUs are not
CPU-affine, they should not have this stored per-CPU.

This patch moves access to the hardware events data behind an accessor
function (arm_pmu::get_hw_events). This allows each instance to have
its own hardware event data, which can be stored per-CPU or globally as
required.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently the ARM perf code supports having a single struct
platform_device to supply IRQ numbers, limiting it to supporting a
single PMU.

This patch makes a platform_device instance variable on struct arm_pmu.
This should allow for multiple PMUs to be supported in future.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch moves the active_events counter into struct arm_pmu, in
preparation for supporting multiple PMUs. This also moves
pmu_reserve_mutex, as it is used to guard accesses to active_events.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, pmu_hw_events::active_mask is used to keep track of which
events are active in hardware. As we can stop counters and their
interrupts, this is unnecessary.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, event group validation compares each event's 'pmu' pointer
against the static 'pmu' pointer. This limits the code to supporting
only 1 PMU.

This patch changes the behaviour to consider an event's group leader's
'pmu' pointer as canonical for validation. This should ease later
generalisation of the code to support multiple PMUs at once.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, an "empty" struct pmu is registered as the CPU PMU,
regardless of whether there is a physical PMU. This burdens the
accessor functions with checks to see whether a PMU is actually
present.

This patch changes initialisation to register a PMU only if there is a
supported PMU present, and removes the checks that this change makes
redundant.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Reviewed-by: NWill Deacon <will.deacon@arm.com>
Reviewed-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Modern PMUs allow for mode exclusion, so we no longer wish to return
-EPERM if it is requested.

This patch provides a hook in the armpmu structure for implementing
mode exclusion. The hw_perf_event initialisation is slightly delayed so
that the backend code can update the structure if required.
Acked-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NJean Pihet <j-pihet@ti.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

ARM PMU code used to use 1-based indices for PMU registers. This caused
several data structures (pmu_hw_events::{active_events, used_mask, events})
to have an unused element at index zero. ARMPMU_MAX_HWEVENTS still takes
this indexing into account, and currently equates to 33.

This patch updates the core ARM perf code to use the 0th index again.
Acked-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NJean Pihet <j-pihet@ti.com>
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Commit 5dfc54e0 ("ARM: GIC: avoid routing interrupts to offline CPUs")
prevents the GIC from setting the affinity of an IRQ to a CPU with
id >= nr_cpu_ids. This was previously abused by perf on some platforms
where more IRQs were registered than possible CPUs.

This patch fixes the problem by using a cpumask_t to keep track of the
active (requested) interrupts in perf. The same effect could be achieved
by limiting the number of IRQs to the number of CPUs, but using a mask
instead will be useful for adding extended CPU hotplug support in the
future.
Acked-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NJean Pihet <j-pihet@ti.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Once upon a time, OProfile and Perf fought hard over who could play with
the PMU. To stop all hell from breaking loose, pmu.c offered an internal
reserve/release API and took care of parsing PMU platform data passed in
from board support code.

Now that Perf has ingested OProfile, let's move the platform device
handling into the Perf driver and out of the PMU locking code.
Unfortunately, the lock has to remain to prevent Perf being bitten by
out-of-tree modules such as LTTng, which still claim a right to the PMU
when Perf isn't looking.
Acked-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NJean Pihet <j-pihet@ti.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch removes const qualifiers from instances of struct arm_pmu,
and functions initialising them, in preparation for generalising
arm_pmu usage to system (AKA uncore) PMUs.

This will allow for dynamically modifiable structures (locks,
struct pmu) to be added as members of struct arm_pmu.
Acked-by: NJamie Iles <jamie@jamieiles.com>
Reviewed-by: NJean Pihet <j-pihet@ti.com>
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch adds support for the Cortex-A15 PMU to the ARMv7
perf-event backend.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This patch adds support for the Cortex-A5 PMU to the ARMv7 perf-event
backend.
Signed-off-by: NWill Deacon <will.deacon@arm.com>

armpmu_enable can be called in situations where no events are present
(for example, from the event rotation tick after a profiled task has
exited). In this case, we currently start the PMU anyway which may
leave it active inevitably without any events being monitored.

This patch adds a simple check to the enabling code so that we avoid
starting the PMU when no events are present.

Cc: <stable@kernel.org>
Reported-by: NAshwin Chaugle <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Currently, PMU platform_device reservation relies on some minor abuse
of the platform_device::id field for determining the type of PMU. This
is problematic for device tree based probing, where the ID cannot be
controlled.

This patch removes reliance on the id field, and depends on each PMU's
platform driver to figure out which type it is. As all PMUs handled by
the current platform_driver name "arm-pmu" are CPU PMUs, this
convention is hardcoded. New PMU types can be supported through the use
of {of,platform}_device_id tables
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Acked-by: NJamie Iles <jamie@jamieiles.com>
Acked-by: NWill Deacon <will.deacon@arm.com>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

When initialising a PMU, there is a check to protect against races with
other CPUs filling all of the available event slots. Since armpmu_add
checks that an event can be scheduled, we do not need to do this at
initialisation time. Furthermore the current code is broken because it
assumes that atomic_inc_not_zero will unconditionally increment
active_counts and then tries to decrement it again on failure.

This patch removes the broken, redundant code.
Signed-off-by: NMark Rutland <mark.rutland@arm.com>
Acked-by: NWill Deacon <will.deacon@arm.com>
Cc: Jamie Iles <jamie@jamieiles.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

The ARM user backtrace code can get into an infinite loop if it
runs into an invalid stack frame which points back to itself.
This situation has been observed in practice.  Fix it by capping
the number of entries in the backtrace.  This is also what other
architectures do in their backtrace code.
Signed-off-by: NSonny Rao <sonnyrao@chromium.org>
Acked-by: NJamie Iles <jamie@jamieiles.com>
Acked-by: NOlof Johansson <olof@lixom.net>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Commit a737823d ("ARM: perf: ensure overflows aren't missed due to IRQ
latency") changed the way that event deltas are calculated on overflow
so that we don't miss events when the new count value overtakes the
previous one.

Unfortunately, we forget to count the event that passes through zero so
we end up being off by 1. This patch adds on the correction.
Reported-by: NChris Moore <moore@free.fr>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

If a counter overflows during a perf stat profiling run it may overtake
the last known value of the counter:

    0        prev     new                0xffffffff
    |----------|-------|----------------------|

In this case, the number of events that have occurred is
(0xffffffff - prev) + new. Unfortunately, the event update code will
not realise an overflow has occurred and will instead report the event
delta as (new - prev) which may be considerably smaller than the real
count.

This patch adds an extra argument to armpmu_event_update which indicates
whether or not an overflow has occurred. If an overflow has occurred
then we use the maximum period of the counter to calculate the elapsed
events.
Acked-by: NJamie Iles <jamie@jamieiles.com>
Reported-by: NAshwin Chaugule <ashwinc@codeaurora.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

ARMv7 dictates that the interrupt-enable and count-enable registers for
each PMU counter are UNKNOWN following core reset.

This patch adds a new (optional) function pointer to struct arm_pmu for
resetting the PMU state during init. The reset function is called on
each CPU via an arch_initcall in the generic ARM perf_event code and
allows the PMU backend to write sane values to any UNKNOWN registers.
Acked-by: NJean Pihet <j-pihet@ti.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Allow a platform-specific IRQ handler to be specified via platform data.
This will be used to implement the single-irq workaround for the DB8500.
Signed-off-by: NRabin Vincent <rabin.vincent@stericsson.com>
Acked-by: NLee Jones <lee.jones@linaro.org>
Acked-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NLinus Walleij <linus.walleij@linaro.org>

Since tail is the previous fp - 1, we need to compare the new fp with tail + 1
to ensure that we don't end up passing in the same tail again, in order to
avoid a potential infinite loop in the perf interrupt handler (which has been
observed to occur).  A similar fix seems to be needed in the OProfile code.
Acked-by: NWill Deacon <will.deacon@arm.com>
Signed-off-by: NRabin Vincent <rabin.vincent@stericsson.com>
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>