1
0
Fork 0

ARCv2: perf: optimize given that num counters <= 32

use ffz primitive which maps to ARCv2 instruction, vs. non atomic
__test_and_set_bit

It is unlikely if we will even have more than 32 counters, but still add
a BUILD_BUG to catch that

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
hifive-unleashed-5.1
Vineet Gupta 2015-10-08 22:17:48 +05:30
parent 4d43129040
commit 5b9027d6d0
1 changed files with 6 additions and 8 deletions

View File

@ -336,15 +336,12 @@ static int arc_pmu_add(struct perf_event *event, int flags)
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
if (__test_and_set_bit(idx, pmu_cpu->used_mask)) {
idx = find_first_zero_bit(pmu_cpu->used_mask,
arc_pmu->n_counters);
if (idx == arc_pmu->n_counters)
return -EAGAIN;
idx = ffz(pmu_cpu->used_mask[0]);
if (idx == arc_pmu->n_counters)
return -EAGAIN;
__set_bit(idx, pmu_cpu->used_mask);
hwc->idx = idx;
}
__set_bit(idx, pmu_cpu->used_mask);
hwc->idx = idx;
write_aux_reg(ARC_REG_PCT_INDEX, idx);
@ -465,6 +462,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
pr_err("This core does not have performance counters!\n");
return -ENODEV;
}
BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);
READ_BCR(ARC_REG_CC_BUILD, cc_bcr);