perf: arm_pmuv3: Add support for Armv9.4 PMU instruction counter

Armv9.4/8.9 PMU adds optional support for a fixed instruction counter
similar to the fixed cycle counter. Support for the feature is indicated
in the ID_AA64DFR1_EL1 register PMICNTR field. The counter is not
accessible in AArch32.

Existing userspace using direct counter access won't know how to handle
the fixed instruction counter, so we have to avoid using the counter
when user access is requested.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Tested-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-7-280a8d7ff465@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
This commit is contained in:
Rob Herring (Arm) 2024-07-31 10:51:24 -06:00 committed by Will Deacon
parent 2f62701fa5
commit d8226d8cfb
7 changed files with 114 additions and 6 deletions

View File

@ -127,6 +127,12 @@ static inline u32 read_pmuver(void)
return (dfr0 >> 24) & 0xf;
}
static inline bool pmuv3_has_icntr(void)
{
/* FEAT_PMUv3_ICNTR not accessible for 32-bit */
return false;
}
static inline void write_pmcr(u32 val)
{
write_sysreg(val, PMCR);
@ -152,6 +158,13 @@ static inline u64 read_pmccntr(void)
return read_sysreg(PMCCNTR);
}
static inline void write_pmicntr(u64 val) {}
static inline u64 read_pmicntr(void)
{
return 0;
}
static inline void write_pmcntenset(u32 val)
{
write_sysreg(val, PMCNTENSET);
@ -177,6 +190,13 @@ static inline void write_pmccfiltr(u32 val)
write_sysreg(val, PMCCFILTR);
}
static inline void write_pmicfiltr(u64 val) {}
static inline u64 read_pmicfiltr(void)
{
return 0;
}
static inline void write_pmovsclr(u32 val)
{
write_sysreg(val, PMOVSR);

View File

@ -54,6 +54,14 @@ static inline u32 read_pmuver(void)
ID_AA64DFR0_EL1_PMUVer_SHIFT);
}
static inline bool pmuv3_has_icntr(void)
{
u64 dfr1 = read_sysreg(id_aa64dfr1_el1);
return !!cpuid_feature_extract_unsigned_field(dfr1,
ID_AA64DFR1_EL1_PMICNTR_SHIFT);
}
static inline void write_pmcr(u64 val)
{
write_sysreg(val, pmcr_el0);
@ -79,6 +87,16 @@ static inline u64 read_pmccntr(void)
return read_sysreg(pmccntr_el0);
}
static inline void write_pmicntr(u64 val)
{
write_sysreg_s(val, SYS_PMICNTR_EL0);
}
static inline u64 read_pmicntr(void)
{
return read_sysreg_s(SYS_PMICNTR_EL0);
}
static inline void write_pmcntenset(u64 val)
{
write_sysreg(val, pmcntenset_el0);
@ -109,6 +127,16 @@ static inline u64 read_pmccfiltr(void)
return read_sysreg(pmccfiltr_el0);
}
static inline void write_pmicfiltr(u64 val)
{
write_sysreg_s(val, SYS_PMICFILTR_EL0);
}
static inline u64 read_pmicfiltr(void)
{
return read_sysreg_s(SYS_PMICFILTR_EL0);
}
static inline void write_pmovsclr(u64 val)
{
write_sysreg(val, pmovsclr_el0);

View File

@ -66,24 +66,28 @@ void kvm_clr_pmu_events(u64 clr)
/*
* Read a value direct from PMEVTYPER<idx> where idx is 0-30
* or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31).
* or PMxCFILTR_EL0 where idx is 31-32.
*/
static u64 kvm_vcpu_pmu_read_evtype_direct(int idx)
{
if (idx == ARMV8_PMU_CYCLE_IDX)
return read_pmccfiltr();
else if (idx == ARMV8_PMU_INSTR_IDX)
return read_pmicfiltr();
return read_pmevtypern(idx);
}
/*
* Write a value direct to PMEVTYPER<idx> where idx is 0-30
* or PMCCFILTR_EL0 where idx is ARMV8_PMU_CYCLE_IDX (31).
* or PMxCFILTR_EL0 where idx is 31-32.
*/
static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val)
{
if (idx == ARMV8_PMU_CYCLE_IDX)
write_pmccfiltr(val);
else if (idx == ARMV8_PMU_INSTR_IDX)
write_pmicfiltr(val);
else
write_pmevtypern(idx, val);
}

View File

@ -2029,6 +2029,31 @@ Sysreg FAR_EL1 3 0 6 0 0
Field 63:0 ADDR
EndSysreg
Sysreg PMICNTR_EL0 3 3 9 4 0
Field 63:0 ICNT
EndSysreg
Sysreg PMICFILTR_EL0 3 3 9 6 0
Res0 63:59
Field 58 SYNC
Field 57:56 VS
Res0 55:32
Field 31 P
Field 30 U
Field 29 NSK
Field 28 NSU
Field 27 NSH
Field 26 M
Res0 25
Field 24 SH
Field 23 T
Field 22 RLK
Field 21 RLU
Field 20 RLH
Res0 19:16
Field 15:0 evtCount
EndSysreg
Sysreg PMSCR_EL1 3 0 9 9 0
Res0 63:8
Field 7:6 PCT

View File

@ -571,6 +571,8 @@ static u64 armv8pmu_read_counter(struct perf_event *event)
if (idx == ARMV8_PMU_CYCLE_IDX)
value = read_pmccntr();
else if (idx == ARMV8_PMU_INSTR_IDX)
value = read_pmicntr();
else
value = armv8pmu_read_hw_counter(event);
@ -604,6 +606,8 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
if (idx == ARMV8_PMU_CYCLE_IDX)
write_pmccntr(value);
else if (idx == ARMV8_PMU_INSTR_IDX)
write_pmicntr(value);
else
armv8pmu_write_hw_counter(event, value);
}
@ -641,6 +645,8 @@ static void armv8pmu_write_event_type(struct perf_event *event)
} else {
if (idx == ARMV8_PMU_CYCLE_IDX)
write_pmccfiltr(hwc->config_base);
else if (idx == ARMV8_PMU_INSTR_IDX)
write_pmicfiltr(hwc->config_base);
else
armv8pmu_write_evtype(idx, hwc->config_base);
}
@ -769,6 +775,8 @@ static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu)
ARMPMU_MAX_HWEVENTS) {
if (i == ARMV8_PMU_CYCLE_IDX)
write_pmccntr(0);
else if (i == ARMV8_PMU_INSTR_IDX)
write_pmicntr(0);
else
armv8pmu_write_evcntr(i, 0);
}
@ -936,6 +944,19 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
return -EAGAIN;
}
/*
* Always prefer to place a instruction counter into the instruction counter,
* but don't expose the instruction counter to userspace access as userspace
* may not know how to handle it.
*/
if ((evtype == ARMV8_PMUV3_PERFCTR_INST_RETIRED) &&
!armv8pmu_event_get_threshold(&event->attr) &&
test_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask) &&
!armv8pmu_event_want_user_access(event)) {
if (!test_and_set_bit(ARMV8_PMU_INSTR_IDX, cpuc->used_mask))
return ARMV8_PMU_INSTR_IDX;
}
/*
* Otherwise use events counters
*/
@ -1193,6 +1214,10 @@ static void __armv8pmu_probe_pmu(void *info)
/* Add the CPU cycles counter */
set_bit(ARMV8_PMU_CYCLE_IDX, cpu_pmu->cntr_mask);
/* Add the CPU instructions counter */
if (pmuv3_has_icntr())
set_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask);
pmceid[0] = pmceid_raw[0] = read_pmceid0();
pmceid[1] = pmceid_raw[1] = read_pmceid1();

View File

@ -17,10 +17,14 @@
#ifdef CONFIG_ARM_PMU
/*
* The ARMv7 CPU PMU supports up to 32 event counters.
* The Armv7 and Armv8.8 or less CPU PMU supports up to 32 event counters.
* The Armv8.9/9.4 CPU PMU supports up to 33 event counters.
*/
#ifdef CONFIG_ARM
#define ARMPMU_MAX_HWEVENTS 32
#else
#define ARMPMU_MAX_HWEVENTS 33
#endif
/*
* ARM PMU hw_event flags
*/

View File

@ -8,7 +8,7 @@
#define ARMV8_PMU_MAX_GENERAL_COUNTERS 31
#define ARMV8_PMU_CYCLE_IDX 31
#define ARMV8_PMU_INSTR_IDX 32 /* Not accessible from AArch32 */
/*
* Common architectural and microarchitectural event numbers.
@ -228,8 +228,10 @@
*/
#define ARMV8_PMU_OVSR_P GENMASK(30, 0)
#define ARMV8_PMU_OVSR_C BIT(31)
#define ARMV8_PMU_OVSR_F BIT_ULL(32) /* arm64 only */
/* Mask for writable bits is both P and C fields */
#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
#define ARMV8_PMU_OVERFLOWED_MASK (ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C | \
ARMV8_PMU_OVSR_F)
/*
* PMXEVTYPER: Event selection reg