summaryrefslogtreecommitdiff
path: root/arch/powerpc/perf
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/perf')
-rw-r--r--arch/powerpc/perf/core-book3s.c4
-rw-r--r--arch/powerpc/perf/isa207-common.c91
-rw-r--r--arch/powerpc/perf/isa207-common.h30
-rw-r--r--arch/powerpc/perf/power8-pmu.c39
-rw-r--r--arch/powerpc/perf/power9-events-list.h2
-rw-r--r--arch/powerpc/perf/power9-pmu.c114
6 files changed, 231 insertions, 49 deletions
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 72c27b8d2cf3..270eb9b74e2e 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -295,6 +295,8 @@ static inline void perf_read_regs(struct pt_regs *regs)
*/
if (TRAP(regs) != 0xf00)
use_siar = 0;
+ else if ((ppmu->flags & PPMU_NO_SIAR))
+ use_siar = 0;
else if (marked)
use_siar = 1;
else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
@@ -2189,7 +2191,7 @@ int register_power_pmu(struct power_pmu *pmu)
#endif /* CONFIG_PPC64 */
perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
- cpuhp_setup_state(CPUHP_PERF_POWER, "PERF_POWER",
+ cpuhp_setup_state(CPUHP_PERF_POWER, "perf/powerpc:prepare",
power_pmu_prepare_cpu, NULL);
return 0;
}
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 6143c99f3ec5..50e598cf644b 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -12,6 +12,40 @@
*/
#include "isa207-common.h"
+PMU_FORMAT_ATTR(event, "config:0-49");
+PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
+PMU_FORMAT_ATTR(mark, "config:8");
+PMU_FORMAT_ATTR(combine, "config:11");
+PMU_FORMAT_ATTR(unit, "config:12-15");
+PMU_FORMAT_ATTR(pmc, "config:16-19");
+PMU_FORMAT_ATTR(cache_sel, "config:20-23");
+PMU_FORMAT_ATTR(sample_mode, "config:24-28");
+PMU_FORMAT_ATTR(thresh_sel, "config:29-31");
+PMU_FORMAT_ATTR(thresh_stop, "config:32-35");
+PMU_FORMAT_ATTR(thresh_start, "config:36-39");
+PMU_FORMAT_ATTR(thresh_cmp, "config:40-49");
+
+struct attribute *isa207_pmu_format_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_pmcxsel.attr,
+ &format_attr_mark.attr,
+ &format_attr_combine.attr,
+ &format_attr_unit.attr,
+ &format_attr_pmc.attr,
+ &format_attr_cache_sel.attr,
+ &format_attr_sample_mode.attr,
+ &format_attr_thresh_sel.attr,
+ &format_attr_thresh_stop.attr,
+ &format_attr_thresh_start.attr,
+ &format_attr_thresh_cmp.attr,
+ NULL,
+};
+
+struct attribute_group isa207_pmu_format_group = {
+ .name = "format",
+ .attrs = isa207_pmu_format_attr,
+};
+
static inline bool event_is_fab_match(u64 event)
{
/* Only check pmc, unit and pmcxsel, ignore the edge bit (0) */
@@ -21,6 +55,48 @@ static inline bool event_is_fab_match(u64 event)
return (event == 0x30056 || event == 0x4f052);
}
+static bool is_event_valid(u64 event)
+{
+ u64 valid_mask = EVENT_VALID_MASK;
+
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+ valid_mask = p9_EVENT_VALID_MASK;
+
+ return !(event & ~valid_mask);
+}
+
+static u64 mmcra_sdar_mode(u64 event)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+ return p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
+
+ return MMCRA_SDAR_MODE_TLB;
+}
+
+static u64 thresh_cmp_val(u64 value)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+ return value << p9_MMCRA_THR_CMP_SHIFT;
+
+ return value << MMCRA_THR_CMP_SHIFT;
+}
+
+static unsigned long combine_from_event(u64 event)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+ return p9_EVENT_COMBINE(event);
+
+ return EVENT_COMBINE(event);
+}
+
+static unsigned long combine_shift(unsigned long pmc)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+ return p9_MMCR1_COMBINE_SHIFT(pmc);
+
+ return MMCR1_COMBINE_SHIFT(pmc);
+}
+
int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
{
unsigned int unit, pmc, cache, ebb;
@@ -28,7 +104,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
mask = value = 0;
- if (event & ~EVENT_VALID_MASK)
+ if (!is_event_valid(event))
return -1;
pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
@@ -155,15 +231,13 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
pmc_inuse |= 1 << pmc;
}
- /* In continuous sampling mode, update SDAR on TLB miss */
- mmcra = MMCRA_SDAR_MODE_TLB;
- mmcr1 = mmcr2 = 0;
+ mmcra = mmcr1 = mmcr2 = 0;
/* Second pass: assign PMCs, set all MMCR1 fields */
for (i = 0; i < n_ev; ++i) {
pmc = (event[i] >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
unit = (event[i] >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
- combine = (event[i] >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK;
+ combine = combine_from_event(event[i]);
psel = event[i] & EVENT_PSEL_MASK;
if (!pmc) {
@@ -177,10 +251,13 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
if (pmc <= 4) {
mmcr1 |= unit << MMCR1_UNIT_SHIFT(pmc);
- mmcr1 |= combine << MMCR1_COMBINE_SHIFT(pmc);
+ mmcr1 |= combine << combine_shift(pmc);
mmcr1 |= psel << MMCR1_PMCSEL_SHIFT(pmc);
}
+ /* In continuous sampling mode, update SDAR on TLB miss */
+ mmcra |= mmcra_sdar_mode(event[i]);
+
if (event[i] & EVENT_IS_L1) {
cache = event[i] >> EVENT_CACHE_SEL_SHIFT;
mmcr1 |= (cache & 1) << MMCR1_IC_QUAL_SHIFT;
@@ -211,7 +288,7 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK;
mmcra |= val << MMCRA_THR_SEL_SHIFT;
val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK;
- mmcra |= val << MMCRA_THR_CMP_SHIFT;
+ mmcra |= thresh_cmp_val(val);
}
if (event[i] & EVENT_WANTS_BHRB) {
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 4d0a4e5017c2..90495f1580c7 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -107,6 +107,7 @@
#define EVENT_UNIT_MASK 0xf
#define EVENT_COMBINE_SHIFT 11 /* Combine bit */
#define EVENT_COMBINE_MASK 0x1
+#define EVENT_COMBINE(v) (((v) >> EVENT_COMBINE_SHIFT) & EVENT_COMBINE_MASK)
#define EVENT_MARKED_SHIFT 8 /* Marked bit */
#define EVENT_MARKED_MASK 0x1
#define EVENT_IS_MARKED (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
@@ -134,6 +135,26 @@
PERF_SAMPLE_BRANCH_KERNEL |\
PERF_SAMPLE_BRANCH_HV)
+/* Contants to support power9 raw encoding format */
+#define p9_EVENT_COMBINE_SHIFT 10 /* Combine bit */
+#define p9_EVENT_COMBINE_MASK 0x3ull
+#define p9_EVENT_COMBINE(v) (((v) >> p9_EVENT_COMBINE_SHIFT) & p9_EVENT_COMBINE_MASK)
+#define p9_SDAR_MODE_SHIFT 50
+#define p9_SDAR_MODE_MASK 0x3ull
+#define p9_SDAR_MODE(v) (((v) >> p9_SDAR_MODE_SHIFT) & p9_SDAR_MODE_MASK)
+
+#define p9_EVENT_VALID_MASK \
+ ((p9_SDAR_MODE_MASK << p9_SDAR_MODE_SHIFT | \
+ (EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \
+ (EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \
+ (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT) | \
+ (EVENT_PMC_MASK << EVENT_PMC_SHIFT) | \
+ (EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \
+ (p9_EVENT_COMBINE_MASK << p9_EVENT_COMBINE_SHIFT) | \
+ (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
+ EVENT_LINUX_MASK | \
+ EVENT_PSEL_MASK))
+
/*
* Layout of constraint bits:
*
@@ -210,15 +231,22 @@
#define MMCR1_DC_QUAL_SHIFT 47
#define MMCR1_IC_QUAL_SHIFT 46
+/* MMCR1 Combine bits macro for power9 */
+#define p9_MMCR1_COMBINE_SHIFT(pmc) (38 - ((pmc - 1) * 2))
+
/* Bits in MMCRA for PowerISA v2.07 */
#define MMCRA_SAMP_MODE_SHIFT 1
#define MMCRA_SAMP_ELIG_SHIFT 4
#define MMCRA_THR_CTL_SHIFT 8
#define MMCRA_THR_SEL_SHIFT 16
#define MMCRA_THR_CMP_SHIFT 32
-#define MMCRA_SDAR_MODE_TLB (1ull << 42)
+#define MMCRA_SDAR_MODE_SHIFT 42
+#define MMCRA_SDAR_MODE_TLB (1ull << MMCRA_SDAR_MODE_SHIFT)
#define MMCRA_IFM_SHIFT 30
+/* MMCR1 Threshold Compare bit constant for power9 */
+#define p9_MMCRA_THR_CMP_SHIFT 45
+
/* Bits in MMCR2 for PowerISA v2.07 */
#define MMCR2_FCS(pmc) (1ull << (63 - (((pmc) - 1) * 9)))
#define MMCR2_FCP(pmc) (1ull << (62 - (((pmc) - 1) * 9)))
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index ab830d106ec5..d07186382f3a 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -30,6 +30,9 @@ enum {
#define POWER8_MMCRA_IFM2 0x0000000080000000UL
#define POWER8_MMCRA_IFM3 0x00000000C0000000UL
+/* PowerISA v2.07 format attribute structure*/
+extern struct attribute_group isa207_pmu_format_group;
+
/* Table of alternatives, sorted by column 0 */
static const unsigned int event_alternatives[][MAX_ALT] = {
{ PM_MRK_ST_CMPL, PM_MRK_ST_CMPL_ALT },
@@ -175,42 +178,8 @@ static struct attribute_group power8_pmu_events_group = {
.attrs = power8_events_attr,
};
-PMU_FORMAT_ATTR(event, "config:0-49");
-PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
-PMU_FORMAT_ATTR(mark, "config:8");
-PMU_FORMAT_ATTR(combine, "config:11");
-PMU_FORMAT_ATTR(unit, "config:12-15");
-PMU_FORMAT_ATTR(pmc, "config:16-19");
-PMU_FORMAT_ATTR(cache_sel, "config:20-23");
-PMU_FORMAT_ATTR(sample_mode, "config:24-28");
-PMU_FORMAT_ATTR(thresh_sel, "config:29-31");
-PMU_FORMAT_ATTR(thresh_stop, "config:32-35");
-PMU_FORMAT_ATTR(thresh_start, "config:36-39");
-PMU_FORMAT_ATTR(thresh_cmp, "config:40-49");
-
-static struct attribute *power8_pmu_format_attr[] = {
- &format_attr_event.attr,
- &format_attr_pmcxsel.attr,
- &format_attr_mark.attr,
- &format_attr_combine.attr,
- &format_attr_unit.attr,
- &format_attr_pmc.attr,
- &format_attr_cache_sel.attr,
- &format_attr_sample_mode.attr,
- &format_attr_thresh_sel.attr,
- &format_attr_thresh_stop.attr,
- &format_attr_thresh_start.attr,
- &format_attr_thresh_cmp.attr,
- NULL,
-};
-
-static struct attribute_group power8_pmu_format_group = {
- .name = "format",
- .attrs = power8_pmu_format_attr,
-};
-
static const struct attribute_group *power8_pmu_attr_groups[] = {
- &power8_pmu_format_group,
+ &isa207_pmu_format_group,
&power8_pmu_events_group,
NULL,
};
diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h
index 6447dc1c3d89..929b56d47ad9 100644
--- a/arch/powerpc/perf/power9-events-list.h
+++ b/arch/powerpc/perf/power9-events-list.h
@@ -16,7 +16,7 @@ EVENT(PM_CYC, 0x0001e)
EVENT(PM_ICT_NOSLOT_CYC, 0x100f8)
EVENT(PM_CMPLU_STALL, 0x1e054)
EVENT(PM_INST_CMPL, 0x00002)
-EVENT(PM_BRU_CMPL, 0x40060)
+EVENT(PM_BRU_CMPL, 0x10012)
EVENT(PM_BR_MPRED_CMPL, 0x400f6)
/* All L1 D cache load references counted at finish, gated by reject */
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 8e9a81967ff8..7332634e18c9 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -16,6 +16,78 @@
#include "isa207-common.h"
/*
+ * Raw event encoding for Power9:
+ *
+ * 60 56 52 48 44 40 36 32
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ * | | [ ] [ ] [ thresh_cmp ] [ thresh_ctl ]
+ * | | | | |
+ * | | *- IFM (Linux) | thresh start/stop OR FAB match -*
+ * | *- BHRB (Linux) *sm
+ * *- EBB (Linux)
+ *
+ * 28 24 20 16 12 8 4 0
+ * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
+ * [ ] [ sample ] [cache] [ pmc ] [unit ] [] m [ pmcxsel ]
+ * | | | | |
+ * | | | | *- mark
+ * | | *- L1/L2/L3 cache_sel |
+ * | | |
+ * | *- sampling mode for marked events *- combine
+ * |
+ * *- thresh_sel
+ *
+ * Below uses IBM bit numbering.
+ *
+ * MMCR1[x:y] = unit (PMCxUNIT)
+ * MMCR1[24] = pmc1combine[0]
+ * MMCR1[25] = pmc1combine[1]
+ * MMCR1[26] = pmc2combine[0]
+ * MMCR1[27] = pmc2combine[1]
+ * MMCR1[28] = pmc3combine[0]
+ * MMCR1[29] = pmc3combine[1]
+ * MMCR1[30] = pmc4combine[0]
+ * MMCR1[31] = pmc4combine[1]
+ *
+ * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011
+ * # PM_MRK_FAB_RSP_MATCH
+ * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
+ * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001
+ * # PM_MRK_FAB_RSP_MATCH_CYC
+ * MMCR1[20:27] = thresh_ctl (FAB_CRESP_MATCH / FAB_TYPE_MATCH)
+ * else
+ * MMCRA[48:55] = thresh_ctl (THRESH START/END)
+ *
+ * if thresh_sel:
+ * MMCRA[45:47] = thresh_sel
+ *
+ * if thresh_cmp:
+ * MMCRA[9:11] = thresh_cmp[0:2]
+ * MMCRA[12:18] = thresh_cmp[3:9]
+ *
+ * if unit == 6 or unit == 7
+ * MMCRC[53:55] = cache_sel[1:3] (L2EVENT_SEL)
+ * else if unit == 8 or unit == 9:
+ * if cache_sel[0] == 0: # L3 bank
+ * MMCRC[47:49] = cache_sel[1:3] (L3EVENT_SEL0)
+ * else if cache_sel[0] == 1:
+ * MMCRC[50:51] = cache_sel[2:3] (L3EVENT_SEL1)
+ * else if cache_sel[1]: # L1 event
+ * MMCR1[16] = cache_sel[2]
+ * MMCR1[17] = cache_sel[3]
+ *
+ * if mark:
+ * MMCRA[63] = 1 (SAMPLE_ENABLE)
+ * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG)
+ * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE)
+ *
+ * if EBB and BHRB:
+ * MMCRA[32:33] = IFM
+ *
+ * MMCRA[SDAR_MODE] = sm
+ */
+
+/*
* Some power9 event codes.
*/
#define EVENT(_name, _code) _name = _code,
@@ -31,6 +103,9 @@ enum {
#define POWER9_MMCRA_IFM2 0x0000000080000000UL
#define POWER9_MMCRA_IFM3 0x00000000C0000000UL
+/* PowerISA v2.07 format attribute structure*/
+extern struct attribute_group isa207_pmu_format_group;
+
GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC);
GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_ICT_NOSLOT_CYC);
GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL);
@@ -90,10 +165,16 @@ static struct attribute_group power9_pmu_events_group = {
.attrs = power9_events_attr,
};
-PMU_FORMAT_ATTR(event, "config:0-49");
+static const struct attribute_group *power9_isa207_pmu_attr_groups[] = {
+ &isa207_pmu_format_group,
+ &power9_pmu_events_group,
+ NULL,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-51");
PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
PMU_FORMAT_ATTR(mark, "config:8");
-PMU_FORMAT_ATTR(combine, "config:11");
+PMU_FORMAT_ATTR(combine, "config:10-11");
PMU_FORMAT_ATTR(unit, "config:12-15");
PMU_FORMAT_ATTR(pmc, "config:16-19");
PMU_FORMAT_ATTR(cache_sel, "config:20-23");
@@ -102,6 +183,7 @@ PMU_FORMAT_ATTR(thresh_sel, "config:29-31");
PMU_FORMAT_ATTR(thresh_stop, "config:32-35");
PMU_FORMAT_ATTR(thresh_start, "config:36-39");
PMU_FORMAT_ATTR(thresh_cmp, "config:40-49");
+PMU_FORMAT_ATTR(sdar_mode, "config:50-51");
static struct attribute *power9_pmu_format_attr[] = {
&format_attr_event.attr,
@@ -116,6 +198,7 @@ static struct attribute *power9_pmu_format_attr[] = {
&format_attr_thresh_stop.attr,
&format_attr_thresh_start.attr,
&format_attr_thresh_cmp.attr,
+ &format_attr_sdar_mode.attr,
NULL,
};
@@ -291,6 +374,24 @@ static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
#undef C
+static struct power_pmu power9_isa207_pmu = {
+ .name = "POWER9",
+ .n_counter = MAX_PMU_COUNTERS,
+ .add_fields = ISA207_ADD_FIELDS,
+ .test_adder = ISA207_TEST_ADDER,
+ .compute_mmcr = isa207_compute_mmcr,
+ .config_bhrb = power9_config_bhrb,
+ .bhrb_filter_map = power9_bhrb_filter_map,
+ .get_constraint = isa207_get_constraint,
+ .disable_pmc = isa207_disable_pmc,
+ .flags = PPMU_NO_SIAR | PPMU_ARCH_207S,
+ .n_generic = ARRAY_SIZE(power9_generic_events),
+ .generic_events = power9_generic_events,
+ .cache_events = &power9_cache_events,
+ .attr_groups = power9_isa207_pmu_attr_groups,
+ .bhrb_nr = 32,
+};
+
static struct power_pmu power9_pmu = {
.name = "POWER9",
.n_counter = MAX_PMU_COUNTERS,
@@ -311,14 +412,19 @@ static struct power_pmu power9_pmu = {
static int __init init_power9_pmu(void)
{
- int rc;
+ int rc = 0;
/* Comes from cpu_specs[] */
if (!cur_cpu_spec->oprofile_cpu_type ||
strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power9"))
return -ENODEV;
- rc = register_power_pmu(&power9_pmu);
+ if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
+ rc = register_power_pmu(&power9_isa207_pmu);
+ } else {
+ rc = register_power_pmu(&power9_pmu);
+ }
+
if (rc)
return rc;
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-28 08:09:41 +0000