diff options
Diffstat (limited to 'drivers/perf/riscv_pmu.c')
| -rw-r--r-- | drivers/perf/riscv_pmu.c | 139 |
1 files changed, 123 insertions, 16 deletions
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index 56897d4d4fd3..7644147d50b4 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -14,9 +14,80 @@ #include <linux/perf/riscv_pmu.h> #include <linux/printk.h> #include <linux/smp.h> +#include <linux/sched_clock.h> #include <asm/sbi.h> +static bool riscv_perf_user_access(struct perf_event *event) +{ + return ((event->attr.type == PERF_TYPE_HARDWARE) || + (event->attr.type == PERF_TYPE_HW_CACHE) || + (event->attr.type == PERF_TYPE_RAW)) && + !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) && + (event->hw.idx != -1); +} + +void arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, u64 now) +{ + struct clock_read_data *rd; + unsigned int seq; + u64 ns; + + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_time_short = 0; + userpg->cap_user_rdpmc = riscv_perf_user_access(event); + + /* + * The counters are 64-bit but the priv spec doesn't mandate all the + * bits to be implemented: that's why, counter width can vary based on + * the cpu vendor. + */ + if (userpg->cap_user_rdpmc) + userpg->pmc_width = to_riscv_pmu(event->pmu)->ctr_get_width(event->hw.idx) + 1; + + do { + rd = sched_clock_read_begin(&seq); + + userpg->time_mult = rd->mult; + userpg->time_shift = rd->shift; + userpg->time_zero = rd->epoch_ns; + userpg->time_cycles = rd->epoch_cyc; + userpg->time_mask = rd->sched_clock_mask; + + /* + * Subtract the cycle base, such that software that + * doesn't know about cap_user_time_short still 'works' + * assuming no wraps. + */ + ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift); + userpg->time_zero -= ns; + + } while (sched_clock_read_retry(seq)); + + userpg->time_offset = userpg->time_zero - now; + + /* + * time_shift is not expected to be greater than 31 due to + * the original published conversion algorithm shifting a + * 32-bit value (now specifies a 64-bit value) - refer + * perf_event_mmap_page documentation in perf_event.h. + */ + if (userpg->time_shift == 32) { + userpg->time_shift = 31; + userpg->time_mult >>= 1; + } + + /* + * Internal timekeeping for enabled/running/stopped times + * is always computed with the sched_clock. + */ + userpg->cap_user_time = 1; + userpg->cap_user_time_zero = 1; + userpg->cap_user_time_short = 1; +} + static unsigned long csr_read_num(int csr_num) { #define switchcase_csr_read(__csr_num, __val) {\ @@ -77,19 +148,11 @@ u64 riscv_pmu_ctr_get_width_mask(struct perf_event *event) struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - if (!rvpmu->ctr_get_width) - /** - * If the pmu driver doesn't support counter width, set it to default - * maximum allowed by the specification. - */ - cwidth = 63; - else { - if (hwc->idx == -1) - /* Handle init case where idx is not initialized yet */ - cwidth = rvpmu->ctr_get_width(0); - else - cwidth = rvpmu->ctr_get_width(hwc->idx); - } + if (hwc->idx == -1) + /* Handle init case where idx is not initialized yet */ + cwidth = rvpmu->ctr_get_width(0); + else + cwidth = rvpmu->ctr_get_width(hwc->idx); return GENMASK_ULL(cwidth, 0); } @@ -102,7 +165,7 @@ u64 riscv_pmu_event_update(struct perf_event *event) unsigned long cmask; u64 oldval, delta; - if (!rvpmu->ctr_read) + if (!rvpmu->ctr_read || (hwc->state & PERF_HES_UPTODATE)) return 0; cmask = riscv_pmu_ctr_get_width_mask(event); @@ -126,8 +189,6 @@ void riscv_pmu_stop(struct perf_event *event, int flags) struct hw_perf_event *hwc = &event->hw; struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); - WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); - if (!(hwc->state & PERF_HES_STOPPED)) { if (rvpmu->ctr_stop) { rvpmu->ctr_stop(event, 0); @@ -171,6 +232,8 @@ int riscv_pmu_event_set_period(struct perf_event *event) local64_set(&hwc->prev_count, (u64)-left); + perf_event_update_userpage(event); + return overflow; } @@ -246,6 +309,10 @@ static int riscv_pmu_event_init(struct perf_event *event) u64 event_config = 0; uint64_t cmask; + /* driver does not support branch stack sampling */ + if (has_branch_stack(event)) + return -EOPNOTSUPP; + hwc->flags = 0; mapped_event = rvpmu->event_map(event, &event_config); if (mapped_event < 0) { @@ -264,6 +331,9 @@ static int riscv_pmu_event_init(struct perf_event *event) hwc->idx = -1; hwc->event_base = mapped_event; + if (rvpmu->event_init) + rvpmu->event_init(event); + if (!is_sampling_event(event)) { /* * For non-sampling runs, limit the sample_period to half @@ -280,6 +350,39 @@ static int riscv_pmu_event_init(struct perf_event *event) return 0; } +static int riscv_pmu_event_idx(struct perf_event *event) +{ + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); + + if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) + return 0; + + if (rvpmu->csr_index) + return rvpmu->csr_index(event) + 1; + + return 0; +} + +static void riscv_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) +{ + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); + + if (rvpmu->event_mapped) { + rvpmu->event_mapped(event, mm); + perf_event_update_userpage(event); + } +} + +static void riscv_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) +{ + struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); + + if (rvpmu->event_unmapped) { + rvpmu->event_unmapped(event, mm); + perf_event_update_userpage(event); + } +} + struct riscv_pmu *riscv_pmu_alloc(void) { struct riscv_pmu *pmu; @@ -301,9 +404,13 @@ struct riscv_pmu *riscv_pmu_alloc(void) cpuc->n_events = 0; for (i = 0; i < RISCV_MAX_COUNTERS; i++) cpuc->events[i] = NULL; + cpuc->snapshot_addr = NULL; } pmu->pmu = (struct pmu) { .event_init = riscv_pmu_event_init, + .event_mapped = riscv_pmu_event_mapped, + .event_unmapped = riscv_pmu_event_unmapped, + .event_idx = riscv_pmu_event_idx, .add = riscv_pmu_add, .del = riscv_pmu_del, .start = riscv_pmu_start, |