| Message ID | 20201203141609.14148-1-liwei391@huawei.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [v4] drivers/perf: Add support for ARMv8.3-SPE | expand |
Ping... On 2020/12/3 22:16, Wei Li wrote: > Armv8.3 extends the SPE by adding: > - Alignment field in the Events packet, and filtering on this event > using PMSEVFR_EL1. > - Support for the Scalable Vector Extension (SVE). > > The main additions for SVE are: > - Recording the vector length for SVE operations in the Operation Type > packet. It is not possible to filter on vector length. > - Incomplete predicate and empty predicate fields in the Events packet, > and filtering on these events using PMSEVFR_EL1. > > Update the check of pmsevfr for empty/partial predicated SVE and > alignment event in SPE driver. > > Signed-off-by: Wei Li <liwei391@huawei.com> > --- > v3 -> v4: > - Return the highest supported version in default in arm_spe_pmsevfr_res0(). > - Drop the exposing of 'pmsver'. > (Suggested by Will.) > --- > v2 -> v3: > - Make the definition of 'pmsevfr_res0' progressive and easy to check. > (Suggested by Will.) > --- > v1 -> v2: > - Rename 'pmuver' to 'pmsver', change it's type to 'u16' from 'int'. > (Suggested by Will and Leo.) > - Expose 'pmsver' as cap attribute through sysfs, instead of printing. > (Suggested by Will.) > --- > arch/arm64/include/asm/sysreg.h | 9 ++++++++- > drivers/perf/arm_spe_pmu.c | 17 +++++++++++++++-- > 2 files changed, 23 insertions(+), 3 deletions(-) > > diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h > index d52c1b3ce589..57e5aee6f7e6 100644 > --- a/arch/arm64/include/asm/sysreg.h > +++ b/arch/arm64/include/asm/sysreg.h > @@ -287,7 +287,11 @@ > #define SYS_PMSFCR_EL1_ST_SHIFT 18 > > #define SYS_PMSEVFR_EL1 sys_reg(3, 0, 9, 9, 5) > -#define SYS_PMSEVFR_EL1_RES0 0x0000ffff00ff0f55UL > +#define SYS_PMSEVFR_EL1_RES0_8_2 \ > + (GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\ > + BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0)) > +#define SYS_PMSEVFR_EL1_RES0_8_3 \ > + (SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11))) > > #define SYS_PMSLATFR_EL1 sys_reg(3, 0, 9, 9, 6) > #define SYS_PMSLATFR_EL1_MINLAT_SHIFT 0 > @@ -829,6 +833,9 @@ > #define ID_AA64DFR0_PMUVER_8_5 0x6 > #define ID_AA64DFR0_PMUVER_IMP_DEF 0xf > > +#define ID_AA64DFR0_PMSVER_8_2 0x1 > +#define ID_AA64DFR0_PMSVER_8_3 0x2 > + > #define ID_DFR0_PERFMON_SHIFT 24 > > #define ID_DFR0_PERFMON_8_1 0x4 > diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c > index cc00915ad6d1..bce9aff9f546 100644 > --- a/drivers/perf/arm_spe_pmu.c > +++ b/drivers/perf/arm_spe_pmu.c > @@ -54,7 +54,7 @@ struct arm_spe_pmu { > struct hlist_node hotplug_node; > > int irq; /* PPI */ > - > + u16 pmsver; > u16 min_period; > u16 counter_sz; > > @@ -655,6 +655,18 @@ static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev) > return IRQ_HANDLED; > } > > +static u64 arm_spe_pmsevfr_res0(u16 pmsver) > +{ > + switch (pmsver) { > + case ID_AA64DFR0_PMSVER_8_2: > + return SYS_PMSEVFR_EL1_RES0_8_2; > + case ID_AA64DFR0_PMSVER_8_3: > + /* Return the highest version we support in default */ > + default: > + return SYS_PMSEVFR_EL1_RES0_8_3; > + } > +} > + > /* Perf callbacks */ > static int arm_spe_pmu_event_init(struct perf_event *event) > { > @@ -670,7 +682,7 @@ static int arm_spe_pmu_event_init(struct perf_event *event) > !cpumask_test_cpu(event->cpu, &spe_pmu->supported_cpus)) > return -ENOENT; > > - if (arm_spe_event_to_pmsevfr(event) & SYS_PMSEVFR_EL1_RES0) > + if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver)) > return -EOPNOTSUPP; > > if (attr->exclude_idle) > @@ -937,6 +949,7 @@ static void __arm_spe_pmu_dev_probe(void *info) > fld, smp_processor_id()); > return; > } > + spe_pmu->pmsver = (u16)fld; > > /* Read PMBIDR first to determine whether or not we have access */ > reg = read_sysreg_s(SYS_PMBIDR_EL1); >
On Thu, 3 Dec 2020 22:16:09 +0800, Wei Li wrote: > Armv8.3 extends the SPE by adding: > - Alignment field in the Events packet, and filtering on this event > using PMSEVFR_EL1. > - Support for the Scalable Vector Extension (SVE). > > The main additions for SVE are: > - Recording the vector length for SVE operations in the Operation Type > packet. It is not possible to filter on vector length. > - Incomplete predicate and empty predicate fields in the Events packet, > and filtering on these events using PMSEVFR_EL1. > > [...] Applied to will (for-next/perf), thanks! [1/1] drivers/perf: Add support for ARMv8.3-SPE https://git.kernel.org/will/c/4a669e2432fc Cheers,
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index d52c1b3ce589..57e5aee6f7e6 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -287,7 +287,11 @@ #define SYS_PMSFCR_EL1_ST_SHIFT 18 #define SYS_PMSEVFR_EL1 sys_reg(3, 0, 9, 9, 5) -#define SYS_PMSEVFR_EL1_RES0 0x0000ffff00ff0f55UL +#define SYS_PMSEVFR_EL1_RES0_8_2 \ + (GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\ + BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0)) +#define SYS_PMSEVFR_EL1_RES0_8_3 \ + (SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11))) #define SYS_PMSLATFR_EL1 sys_reg(3, 0, 9, 9, 6) #define SYS_PMSLATFR_EL1_MINLAT_SHIFT 0 @@ -829,6 +833,9 @@ #define ID_AA64DFR0_PMUVER_8_5 0x6 #define ID_AA64DFR0_PMUVER_IMP_DEF 0xf +#define ID_AA64DFR0_PMSVER_8_2 0x1 +#define ID_AA64DFR0_PMSVER_8_3 0x2 + #define ID_DFR0_PERFMON_SHIFT 24 #define ID_DFR0_PERFMON_8_1 0x4 diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index cc00915ad6d1..bce9aff9f546 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -54,7 +54,7 @@ struct arm_spe_pmu { struct hlist_node hotplug_node; int irq; /* PPI */ - + u16 pmsver; u16 min_period; u16 counter_sz; @@ -655,6 +655,18 @@ static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev) return IRQ_HANDLED; } +static u64 arm_spe_pmsevfr_res0(u16 pmsver) +{ + switch (pmsver) { + case ID_AA64DFR0_PMSVER_8_2: + return SYS_PMSEVFR_EL1_RES0_8_2; + case ID_AA64DFR0_PMSVER_8_3: + /* Return the highest version we support in default */ + default: + return SYS_PMSEVFR_EL1_RES0_8_3; + } +} + /* Perf callbacks */ static int arm_spe_pmu_event_init(struct perf_event *event) { @@ -670,7 +682,7 @@ static int arm_spe_pmu_event_init(struct perf_event *event) !cpumask_test_cpu(event->cpu, &spe_pmu->supported_cpus)) return -ENOENT; - if (arm_spe_event_to_pmsevfr(event) & SYS_PMSEVFR_EL1_RES0) + if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver)) return -EOPNOTSUPP; if (attr->exclude_idle) @@ -937,6 +949,7 @@ static void __arm_spe_pmu_dev_probe(void *info) fld, smp_processor_id()); return; } + spe_pmu->pmsver = (u16)fld; /* Read PMBIDR first to determine whether or not we have access */ reg = read_sysreg_s(SYS_PMBIDR_EL1);
Armv8.3 extends the SPE by adding: - Alignment field in the Events packet, and filtering on this event using PMSEVFR_EL1. - Support for the Scalable Vector Extension (SVE). The main additions for SVE are: - Recording the vector length for SVE operations in the Operation Type packet. It is not possible to filter on vector length. - Incomplete predicate and empty predicate fields in the Events packet, and filtering on these events using PMSEVFR_EL1. Update the check of pmsevfr for empty/partial predicated SVE and alignment event in SPE driver. Signed-off-by: Wei Li <liwei391@huawei.com> --- v3 -> v4: - Return the highest supported version in default in arm_spe_pmsevfr_res0(). - Drop the exposing of 'pmsver'. (Suggested by Will.) --- v2 -> v3: - Make the definition of 'pmsevfr_res0' progressive and easy to check. (Suggested by Will.) --- v1 -> v2: - Rename 'pmuver' to 'pmsver', change it's type to 'u16' from 'int'. (Suggested by Will and Leo.) - Expose 'pmsver' as cap attribute through sysfs, instead of printing. (Suggested by Will.) --- arch/arm64/include/asm/sysreg.h | 9 ++++++++- drivers/perf/arm_spe_pmu.c | 17 +++++++++++++++-- 2 files changed, 23 insertions(+), 3 deletions(-)