diff options
| author |   Mark Rutland <mark.rutland@arm.com> | 2014-05-13 19:46:10 +0100 |
|---|---|---|
| committer |   Will Deacon <will.deacon@arm.com> | 2014-10-30 12:17:00 +0000 |
| commit | 5ebd92003494a19ac5246ae385c073be16de1144 (patch) | |
| tree | 8c9367b21854ea92a92a355978523a33abf48a3c /arch/arm/include/asm/pmu.h | |
| parent | arm: perf: kill get_hw_events() (diff) | |
| download | linux-dev-5ebd92003494a19ac5246ae385c073be16de1144.tar.xz linux-dev-5ebd92003494a19ac5246ae385c073be16de1144.zip | |
arm: perf: fold percpu_pmu into pmu_hw_events
Currently the percpu_pmu pointers used as percpu_irq dev_id values are
defined separately from the other per-cpu accounting data, which make
dynamically allocating the data (as will be required for systems with
heterogeneous CPUs) difficult.
This patch moves the percpu_pmu pointers into pmu_hw_events (which is
itself allocated per cpu), which will allow for easier dynamic
allocation. Both percpu and regular irqs are requested using percpu_pmu
pointers as tokens, freeing us from having to know whether an irq is
percpu within the handler, and thus avoiding a radix tree lookup on the
handler path.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Diffstat (limited to 'arch/arm/include/asm/pmu.h')
| -rw-r--r-- | arch/arm/include/asm/pmu.h | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h index f273dd2285a1..cc0149835507 100644 --- a/arch/arm/include/asm/pmu.h +++ b/arch/arm/include/asm/pmu.h @@ -81,6 +81,12 @@ struct pmu_hw_events { * read/modify/write sequences. */ raw_spinlock_t pmu_lock; + + /* + * When using percpu IRQs, we need a percpu dev_id. Place it here as we + * already have to allocate this struct per cpu. + */ + struct arm_pmu *percpu_pmu; }; struct arm_pmu { |