From 1537bf26e212ffcf007d0590958025f6bfdd4ac8 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Tue, 30 Aug 2022 18:53:05 +0300 Subject: perf: RISC-V: exclude invalid pmu counters from SBI calls SBI firmware may not provide information for some counters in response to SBI_EXT_PMU_COUNTER_GET_INFO call. Exclude such counters from the subsequent SBI requests. For this purpose use global mask to keep track of fully specified counters. Signed-off-by: Sergey Matyukevich Reviewed-by: Atish Patra Link: https://lore.kernel.org/r/20220830155306.301714-3-geomatsi@gmail.com Signed-off-by: Palmer Dabbelt --- drivers/perf/riscv_pmu_legacy.c | 4 ++-- drivers/perf/riscv_pmu_sbi.c | 27 ++++++++++++++++----------- 2 files changed, 18 insertions(+), 13 deletions(-) (limited to 'drivers/perf') diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 342778782359..7d7131c47bc0 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -14,7 +14,6 @@ #define RISCV_PMU_LEGACY_CYCLE 0 #define RISCV_PMU_LEGACY_INSTRET 1 -#define RISCV_PMU_LEGACY_NUM_CTR 2 static bool pmu_init_done; @@ -83,7 +82,8 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) { pr_info("Legacy PMU implementation is available\n"); - pmu->num_counters = RISCV_PMU_LEGACY_NUM_CTR; + pmu->cmask = BIT(RISCV_PMU_LEGACY_CYCLE) | + BIT(RISCV_PMU_LEGACY_INSTRET); pmu->ctr_start = pmu_legacy_ctr_start; pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 6f6681bbfd36..1d05aff88c58 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -271,7 +271,6 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) struct sbiret ret; int idx; uint64_t cbase = 0; - uint64_t cmask = GENMASK_ULL(rvpmu->num_counters - 1, 0); unsigned long cflags = 0; if (event->attr.exclude_kernel) @@ -281,11 +280,12 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) /* retrieve the available counter index */ #if defined(CONFIG_32BIT) - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, - cflags, hwc->event_base, hwc->config, hwc->config >> 32); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + rvpmu->cmask, cflags, hwc->event_base, hwc->config, + hwc->config >> 32); #else - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, - cflags, hwc->event_base, hwc->config, 0); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0); #endif if (ret.error) { pr_debug("Not able to find a counter for event %lx config %llx\n", @@ -294,7 +294,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } idx = ret.value; - if (idx >= rvpmu->num_counters || !pmu_ctr_list[idx].value) + if (!test_bit(idx, &rvpmu->cmask) || !pmu_ctr_list[idx].value) return -ENOENT; /* Additional sanity check for the counter id */ @@ -463,7 +463,7 @@ static int pmu_sbi_find_num_ctrs(void) return sbi_err_map_linux_errno(ret.error); } -static int pmu_sbi_get_ctrinfo(int nctr) +static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) { struct sbiret ret; int i, num_hw_ctr = 0, num_fw_ctr = 0; @@ -478,6 +478,9 @@ static int pmu_sbi_get_ctrinfo(int nctr) if (ret.error) /* The logical counter ids are not expected to be contiguous */ continue; + + *mask |= BIT(i); + cinfo.value = ret.value; if (cinfo.type == SBI_PMU_CTR_TYPE_FW) num_fw_ctr++; @@ -498,7 +501,7 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) * which may include counters that are not enabled yet. */ sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - 0, GENMASK_ULL(pmu->num_counters - 1, 0), 0, 0, 0, 0); + 0, pmu->cmask, 0, 0, 0, 0); } static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) @@ -788,8 +791,9 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu) static int pmu_sbi_device_probe(struct platform_device *pdev) { struct riscv_pmu *pmu = NULL; - int num_counters; + unsigned long cmask = 0; int ret = -ENODEV; + int num_counters; pr_info("SBI PMU extension is available\n"); pmu = riscv_pmu_alloc(); @@ -803,7 +807,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) } /* cache all the information about counters now */ - if (pmu_sbi_get_ctrinfo(num_counters)) + if (pmu_sbi_get_ctrinfo(num_counters, &cmask)) goto out_free; ret = pmu_sbi_setup_irqs(pmu, pdev); @@ -812,8 +816,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; } + pmu->pmu.attr_groups = riscv_pmu_attr_groups; - pmu->num_counters = num_counters; + pmu->cmask = cmask; pmu->ctr_start = pmu_sbi_ctr_start; pmu->ctr_stop = pmu_sbi_ctr_stop; pmu->event_map = pmu_sbi_event_map; -- cgit v1.2.3 From 096b52fd2bb4996fd68d22b3b7ad21a1296db9d3 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Tue, 30 Aug 2022 18:53:06 +0300 Subject: perf: RISC-V: throttle perf events Call perf_sample_event_took() to report time spent in overflow interrupts. Perf core uses these measurements to throttle perf events properly. Signed-off-by: Sergey Matyukevich Reviewed-by: Atish Patra Link: https://lore.kernel.org/r/20220830155306.301714-4-geomatsi@gmail.com Signed-off-by: Palmer Dabbelt --- drivers/perf/riscv_pmu_sbi.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/perf') diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 1d05aff88c58..3e8179359933 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -570,6 +571,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) unsigned long overflow; unsigned long overflowed_ctrs = 0; struct cpu_hw_events *cpu_hw_evt = dev; + u64 start_clock = sched_clock(); if (WARN_ON_ONCE(!cpu_hw_evt)) return IRQ_NONE; @@ -638,7 +640,9 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) perf_event_overflow(event, &data, regs); } } + pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs); + perf_sample_event_took(sched_clock() - start_clock); return IRQ_HANDLED; } -- cgit v1.2.3