perf: RISC-V: misc fixes and improvements
Subsystems (3)
v4 cover perf: RISC-V: misc fixes and improvements
Hi all,
Another respin: updated commit message and more RB tags.
Regards,
Sergey
v3 -> v4:
- added Fixes info to the first patch
- updated commt message for the first patch
- added RB tags by Atish Patra to the remaining patches
v2 -> v3:
- rebased on top of for-next branch in riscv kernel tree
- added RB tag by Atish Patra to the first patch
- added perf throttle patch
v1 -> v2:
- drop changes for access to the highest available counter as they are now handled on the OpenSBI side
- drop switch to IDR: in fact there is no need to handle non-contiguous counter ranges
Sergey Matyukevich (3):
perf: RISC-V: fix access beyond allocated array
perf: RISC-V: exclude invalid pmu counters from SBI calls
perf: RISC-V: throttle perf events
drivers/perf/riscv_pmu_legacy.c | 4 ++-- drivers/perf/riscv_pmu_sbi.c | 33 +++++++++++++++++++++------------ include/linux/perf/riscv_pmu.h | 2 +- 3 files changed, 24 insertions(+), 15 deletions(-)
Signature · 7 lines
2.37.1 _______________________________________________ linux-riscv mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-riscv
PATCH v4 1/3 perf: RISC-V: fix access beyond allocated array
From: Sergey Matyukevich <[email protected]>
SBI firmware should report total number of firmware and hardware counters including unused ones or special ones. In this case the kernel doesn't need to make any assumptions about gaps in reported counters, e.g. excluded timer counter. That was fixed in OpenSBI v1.1 by commit 3f66465fb6bf ("lib: pmu:
allow to use the highest available counter"). This kernel patch has no effect if SBI firmware behaves correctly. However it eliminates access beyond the allocated pmu_ctr_list if the kernel is used with OpenSBI older than v1.1.
--- drivers/perf/riscv_pmu_sbi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/perf/riscv_pmu_sbi.c +1 -1
@@ -473,7 +473,7 @@ static int pmu_sbi_get_ctrinfo(int nctr)if (!pmu_ctr_list)return -ENOMEM ; -for (i =0 ; i <= nctr; i++) { +for (i =0 ; i < nctr; i++) { ret =sbi_ecall (SBI_EXT_PMU ,SBI_EXT_PMU_COUNTER_GET_INFO , i,0 ,0 ,0 ,0 ,0 );if (ret.error)/* The logical counter ids are not expected to be contiguous */
Signature · 7 lines
2.37.1 _______________________________________________ linux-riscv mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-riscv
PATCH v4 2/3 perf: RISC-V: exclude invalid pmu counters from SBI calls
In reply to Sergey MatyukevichFrom: Sergey Matyukevich <[email protected]>
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.
--- drivers/perf/riscv_pmu_legacy.c | 4 ++-- drivers/perf/riscv_pmu_sbi.c | 27 ++++++++++++++++----------- include/linux/perf/riscv_pmu.h | 2 +- 3 files changed, 19 insertions(+), 14 deletions(-)
drivers/perf/riscv_pmu_legacy.c +2 -2
@@ -14,7 +14,6 @@#define RISCV_PMU_LEGACY_CYCLE 0#define RISCV_PMU_LEGACY_INSTRET 1 -#define RISCV_PMU_LEGACY_NUM_CTR 2static 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;
drivers/perf/riscv_pmu_sbi.c +16 -11
@@ -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;
include/linux/perf/riscv_pmu.h +1 -1
@@ -45,7 +45,7 @@ struct riscv_pmu {irqreturn_t (*handle_irq)(int irq_num,void *dev); -int num_counters; +unsigned long cmask;u64 (*ctr_read)(struct perf_event *event);int (*ctr_get_idx)(struct perf_event *event);int (*ctr_get_width)(int idx);
Signature · 7 lines
2.37.1 _______________________________________________ linux-riscv mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-riscv
PATCH v4 3/3 perf: RISC-V: throttle perf events
In reply to Sergey MatyukevichFrom: Sergey Matyukevich <[email protected]>
Call perf_sample_event_took() to report time spent in overflow interrupts. Perf core uses these measurements to throttle perf events properly.
--- drivers/perf/riscv_pmu_sbi.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/perf/riscv_pmu_sbi.c +4 -0
@@ -18,6 +18,7 @@#include <linux/of_irq.h> #include <linux/of.h> #include <linux/cpu_pm.h> +#include <linux/sched/clock.h> #include <asm/sbi.h> #include <asm/hwcap.h>
@@ -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 ; }
Signature · 7 lines
2.37.1 _______________________________________________ linux-riscv mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-riscv
Palmer Dabbelt
maintainerQuoted 29 lines · On Tue, 30 Aug 2022 08:53:03 PDT (-0700), [email protected] wrote:
Hi all,
Another respin: updated commit message and more RB tags.
Regards,
Sergeyv3 -> v4:
- added Fixes info to the first patch
- updated commt message for the first patch
- added RB tags by Atish Patra to the remaining patchesv2 -> v3:
- rebased on top of for-next branch in riscv kernel tree
- added RB tag by Atish Patra to the first patch
- added perf throttle patchv1 -> v2:
- drop changes for access to the highest available counter as they are now handled on the OpenSBI side
- drop switch to IDR: in fact there is no need to handle non-contiguous counter rangesSergey Matyukevich (3):
perf: RISC-V: fix access beyond allocated array
perf: RISC-V: exclude invalid pmu counters from SBI calls
perf: RISC-V: throttle perf events
Quoted 4 lines
drivers/perf/riscv_pmu_legacy.c | 4 ++-- drivers/perf/riscv_pmu_sbi.c | 33 +++++++++++++++++++++------------ include/linux/perf/riscv_pmu.h | 2 +- 3 files changed, 24 insertions(+), 15 deletions(-)
I think only the first one here is a fix, the others are the improvements. So I split this up and put the first on fixes, the others on for-next.
Thanks!
_______________________________________________
linux-riscv mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-riscv