evie/android_kernel_oneplus_msm8998
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

perf/x86/intel/cqm: Remove pointless spinlock from state cache

Browse source 
'struct intel_cqm_state' is a strict per CPU cache of the rmid and the
usage counter. It can never be modified from a remote CPU.

The three functions which modify the content: intel_cqm_event[start|stop|del]
(del maps to stop) are called from the perf core with interrupts disabled
which is enough protection for the per CPU state values.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Matt Fleming <matt.fleming@intel.com>
Cc: Kanaka Juvva <kanaka.d.juvva@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vikas Shivappa <vikas.shivappa@linux.intel.com>
Cc: Will Auld <will.auld@intel.com>
Link: http://lkml.kernel.org/r/20150518235150.001006529@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Thomas Gleixner 2015-05-19 00:00:53 +00:00 • committed by Ingo Molnar
parent b3df4ec442
commit 9e7eaac95a
1 changed files with 6 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
arch/x86/kernel/cpu/perf_event_intel_cqm.c
View file

@ -17,11 +17,16 @@ static unsigned int cqm_max_rmid = -1;
static unsigned int cqm_l3_scale; /* supposedly cacheline size */ static unsigned int cqm_l3_scale; /* supposedly cacheline size */
struct intel_cqm_state { struct intel_cqm_state {
raw_spinlock_t lock;
u32 rmid; u32 rmid;
int cnt; int cnt;
}; };
/*
* The cached intel_cqm_state is strictly per CPU and can never be
* updated from a remote CPU. Both functions which modify the state
* (intel_cqm_event_start and intel_cqm_event_stop) are called with
* interrupts disabled, which is sufficient for the protection.
*/
static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
/* /*
@ -963,15 +968,12 @@ static void intel_cqm_event_start(struct perf_event *event, int mode)
{ {
struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
u32 rmid = event->hw.cqm_rmid; u32 rmid = event->hw.cqm_rmid;
unsigned long flags;
if (!(event->hw.cqm_state & PERF_HES_STOPPED)) if (!(event->hw.cqm_state & PERF_HES_STOPPED))
return; return;
event->hw.cqm_state &= ~PERF_HES_STOPPED; event->hw.cqm_state &= ~PERF_HES_STOPPED;
raw_spin_lock_irqsave(&state->lock, flags);
if (state->cnt++) if (state->cnt++)
WARN_ON_ONCE(state->rmid != rmid); WARN_ON_ONCE(state->rmid != rmid);
else else
@ -984,21 +986,17 @@ static void intel_cqm_event_start(struct perf_event *event, int mode)
* Technology component. * Technology component.
*/ */
wrmsr(MSR_IA32_PQR_ASSOC, rmid, 0); wrmsr(MSR_IA32_PQR_ASSOC, rmid, 0);
raw_spin_unlock_irqrestore(&state->lock, flags);
} }
static void intel_cqm_event_stop(struct perf_event *event, int mode) static void intel_cqm_event_stop(struct perf_event *event, int mode)
{ {
struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
unsigned long flags;
if (event->hw.cqm_state & PERF_HES_STOPPED) if (event->hw.cqm_state & PERF_HES_STOPPED)
return; return;
event->hw.cqm_state |= PERF_HES_STOPPED; event->hw.cqm_state |= PERF_HES_STOPPED;
raw_spin_lock_irqsave(&state->lock, flags);
intel_cqm_event_read(event); intel_cqm_event_read(event);
if (!--state->cnt) { if (!--state->cnt) {
@ -1013,8 +1011,6 @@ static void intel_cqm_event_stop(struct perf_event *event, int mode)
} else { } else {
WARN_ON_ONCE(!state->rmid); WARN_ON_ONCE(!state->rmid);
} }
raw_spin_unlock_irqrestore(&state->lock, flags);
} }
static int intel_cqm_event_add(struct perf_event *event, int mode) static int intel_cqm_event_add(struct perf_event *event, int mode)
@ -1257,7 +1253,6 @@ static void intel_cqm_cpu_prepare(unsigned int cpu)
struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *c = &cpu_data(cpu);
raw_spin_lock_init(&state->lock);
state->rmid = 0; state->rmid = 0;
state->cnt = 0; state->cnt = 0;