summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/perf
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/perf')
-rw-r--r--arch/powerpc/perf/8xx-pmu.c16
-rw-r--r--arch/powerpc/perf/callchain.h2
-rw-r--r--arch/powerpc/perf/callchain_32.c8
-rw-r--r--arch/powerpc/perf/callchain_64.c7
-rw-r--r--arch/powerpc/perf/core-book3s.c65
-rw-r--r--arch/powerpc/perf/isa207-common.c38
-rw-r--r--arch/powerpc/perf/isa207-common.h20
-rw-r--r--arch/powerpc/perf/power10-events-list.h9
-rw-r--r--arch/powerpc/perf/power10-pmu.c184
9 files changed, 309 insertions, 40 deletions
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index e53c3c161257..f970d1510d3d 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -153,6 +153,8 @@ static void mpc8xx_pmu_read(struct perf_event *event)
static void mpc8xx_pmu_del(struct perf_event *event, int flags)
{
+ struct ppc_inst insn = ppc_inst(PPC_RAW_MFSPR(10, SPRN_SPRG_SCRATCH2));
+
mpc8xx_pmu_read(event);
/* If it was the last user, stop counting to avoid useles overhead */
@@ -164,22 +166,12 @@ static void mpc8xx_pmu_del(struct perf_event *event, int flags)
mtspr(SPRN_ICTRL, 7);
break;
case PERF_8xx_ID_ITLB_LOAD_MISS:
- if (atomic_dec_return(&itlb_miss_ref) == 0) {
- /* mfspr r10, SPRN_SPRG_SCRATCH0 */
- struct ppc_inst insn = ppc_inst(PPC_INST_MFSPR | __PPC_RS(R10) |
- __PPC_SPR(SPRN_SPRG_SCRATCH0));
-
+ if (atomic_dec_return(&itlb_miss_ref) == 0)
patch_instruction_site(&patch__itlbmiss_exit_1, insn);
- }
break;
case PERF_8xx_ID_DTLB_LOAD_MISS:
- if (atomic_dec_return(&dtlb_miss_ref) == 0) {
- /* mfspr r10, SPRN_DAR */
- struct ppc_inst insn = ppc_inst(PPC_INST_MFSPR | __PPC_RS(R10) |
- __PPC_SPR(SPRN_DAR));
-
+ if (atomic_dec_return(&dtlb_miss_ref) == 0)
patch_instruction_site(&patch__dtlbmiss_exit_1, insn);
- }
break;
}
}
diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
index ae24d4a00da6..d6fa6e25234f 100644
--- a/arch/powerpc/perf/callchain.h
+++ b/arch/powerpc/perf/callchain.h
@@ -33,7 +33,7 @@ static inline int __read_user_stack(const void __user *ptr, void *ret,
rc = copy_from_user_nofault(ret, ptr, size);
- if (IS_ENABLED(CONFIG_PPC64) && rc)
+ if (IS_ENABLED(CONFIG_PPC64) && !radix_enabled() && rc)
return read_user_stack_slow(ptr, ret, size);
return rc;
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index 64e4013d8060..b83c47b7947f 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -59,8 +59,8 @@ static int is_sigreturn_32_address(unsigned int nip, unsigned int fp)
{
if (nip == fp + offsetof(struct signal_frame_32, mctx.mc_pad))
return 1;
- if (vdso32_sigtramp && current->mm->context.vdso_base &&
- nip == current->mm->context.vdso_base + vdso32_sigtramp)
+ if (current->mm->context.vdso &&
+ nip == VDSO32_SYMBOL(current->mm->context.vdso, sigtramp32))
return 1;
return 0;
}
@@ -70,8 +70,8 @@ static int is_rt_sigreturn_32_address(unsigned int nip, unsigned int fp)
if (nip == fp + offsetof(struct rt_signal_frame_32,
uc.uc_mcontext.mc_pad))
return 1;
- if (vdso32_rt_sigtramp && current->mm->context.vdso_base &&
- nip == current->mm->context.vdso_base + vdso32_rt_sigtramp)
+ if (current->mm->context.vdso &&
+ nip == VDSO32_SYMBOL(current->mm->context.vdso, sigtramp_rt32))
return 1;
return 0;
}
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index fed90e827f3a..8d0df4226328 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -21,7 +21,8 @@
/*
* On 64-bit we don't want to invoke hash_page on user addresses from
* interrupt context, so if the access faults, we read the page tables
- * to find which page (if any) is mapped and access it directly.
+ * to find which page (if any) is mapped and access it directly. Radix
+ * has no need for this so it doesn't use read_user_stack_slow.
*/
int read_user_stack_slow(const void __user *ptr, void *buf, int nb)
{
@@ -67,8 +68,8 @@ static int is_sigreturn_64_address(unsigned long nip, unsigned long fp)
{
if (nip == fp + offsetof(struct signal_frame_64, tramp))
return 1;
- if (vdso64_rt_sigtramp && current->mm->context.vdso_base &&
- nip == current->mm->context.vdso_base + vdso64_rt_sigtramp)
+ if (current->mm->context.vdso &&
+ nip == VDSO64_SYMBOL(current->mm->context.vdso, sigtramp_rt64))
return 1;
return 0;
}
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 6586f7e71cfb..28206b1fe172 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -95,6 +95,7 @@ static unsigned int freeze_events_kernel = MMCR0_FCS;
#define SPRN_SIER3 0
#define MMCRA_SAMPLE_ENABLE 0
#define MMCRA_BHRB_DISABLE 0
+#define MMCR0_PMCCEXT 0
static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
{
@@ -137,6 +138,9 @@ static void pmao_restore_workaround(bool ebb) { }
bool is_sier_available(void)
{
+ if (!ppmu)
+ return false;
+
if (ppmu->flags & PPMU_HAS_SIER)
return true;
@@ -250,11 +254,32 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
static inline u32 perf_get_misc_flags(struct pt_regs *regs)
{
bool use_siar = regs_use_siar(regs);
+ unsigned long mmcra = regs->dsisr;
+ int marked = mmcra & MMCRA_SAMPLE_ENABLE;
if (!use_siar)
return perf_flags_from_msr(regs);
/*
+ * Check the address in SIAR to identify the
+ * privilege levels since the SIER[MSR_HV, MSR_PR]
+ * bits are not set for marked events in power10
+ * DD1.
+ */
+ if (marked && (ppmu->flags & PPMU_P10_DD1)) {
+ unsigned long siar = mfspr(SPRN_SIAR);
+ if (siar) {
+ if (is_kernel_addr(siar))
+ return PERF_RECORD_MISC_KERNEL;
+ return PERF_RECORD_MISC_USER;
+ } else {
+ if (is_kernel_addr(regs->nip))
+ return PERF_RECORD_MISC_KERNEL;
+ return PERF_RECORD_MISC_USER;
+ }
+ }
+
+ /*
* If we don't have flags in MMCRA, rather than using
* the MSR, we intuit the flags from the address in
* SIAR which should give slightly more reliable
@@ -350,7 +375,14 @@ static inline int siar_valid(struct pt_regs *regs)
int marked = mmcra & MMCRA_SAMPLE_ENABLE;
if (marked) {
- if (ppmu->flags & PPMU_HAS_SIER)
+ /*
+ * SIER[SIAR_VALID] is not set for some
+ * marked events on power10 DD1, so drop
+ * the check for SIER[SIAR_VALID] and return true.
+ */
+ if (ppmu->flags & PPMU_P10_DD1)
+ return 0x1;
+ else if (ppmu->flags & PPMU_HAS_SIER)
return regs->dar & SIER_SIAR_VALID;
if (ppmu->flags & PPMU_SIAR_VALID)
@@ -1242,6 +1274,9 @@ static void power_pmu_disable(struct pmu *pmu)
val |= MMCR0_FC;
val &= ~(MMCR0_EBE | MMCR0_BHRBA | MMCR0_PMCC | MMCR0_PMAO |
MMCR0_FC56);
+ /* Set mmcr0 PMCCEXT for p10 */
+ if (ppmu->flags & PPMU_ARCH_31)
+ val |= MMCR0_PMCCEXT;
/*
* The barrier is to make sure the mtspr has been
@@ -1881,7 +1916,7 @@ static bool is_event_blacklisted(u64 ev)
static int power_pmu_event_init(struct perf_event *event)
{
u64 ev;
- unsigned long flags;
+ unsigned long flags, irq_flags;
struct perf_event *ctrs[MAX_HWEVENTS];
u64 events[MAX_HWEVENTS];
unsigned int cflags[MAX_HWEVENTS];
@@ -1989,7 +2024,9 @@ static int power_pmu_event_init(struct perf_event *event)
if (check_excludes(ctrs, cflags, n, 1))
return -EINVAL;
- cpuhw = &get_cpu_var(cpu_hw_events);
+ local_irq_save(irq_flags);
+ cpuhw = this_cpu_ptr(&cpu_hw_events);
+
err = power_check_constraints(cpuhw, events, cflags, n + 1);
if (has_branch_stack(event)) {
@@ -2000,13 +2037,13 @@ static int power_pmu_event_init(struct perf_event *event)
event->attr.branch_sample_type);
if (bhrb_filter == -1) {
- put_cpu_var(cpu_hw_events);
+ local_irq_restore(irq_flags);
return -EOPNOTSUPP;
}
cpuhw->bhrb_filter = bhrb_filter;
}
- put_cpu_var(cpu_hw_events);
+ local_irq_restore(irq_flags);
if (err)
return -EINVAL;
@@ -2125,6 +2162,16 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
perf_event_update_userpage(event);
/*
+ * Due to hardware limitation, sometimes SIAR could sample a kernel
+ * address even when freeze on supervisor state (kernel) is set in
+ * MMCR2. Check attr.exclude_kernel and address to drop the sample in
+ * these cases.
+ */
+ if (event->attr.exclude_kernel && record)
+ if (is_kernel_addr(mfspr(SPRN_SIAR)))
+ record = 0;
+
+ /*
* Finally record data if requested.
*/
if (record) {
@@ -2180,8 +2227,14 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
bool use_siar = regs_use_siar(regs);
+ unsigned long siar = mfspr(SPRN_SIAR);
- if (use_siar && siar_valid(regs))
+ if (ppmu->flags & PPMU_P10_DD1) {
+ if (siar)
+ return siar;
+ else
+ return regs->nip;
+ } else if (use_siar && siar_valid(regs))
return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
else if (use_siar)
return 0; // no valid instruction pointer
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 2848904df638..6ab5b272090a 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -247,6 +247,9 @@ void isa207_get_mem_weight(u64 *weight)
u64 sier = mfspr(SPRN_SIER);
u64 val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT;
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mantissa = P10_MMCRA_THR_CTR_MANT(mmcra);
+
if (val == 0 || val == 7)
*weight = 0;
else
@@ -311,9 +314,11 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
}
if (unit >= 6 && unit <= 9) {
- if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) {
- mask |= CNST_L2L3_GROUP_MASK;
- value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT);
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (unit == 6) {
+ mask |= CNST_L2L3_GROUP_MASK;
+ value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT);
+ }
} else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
mask |= CNST_CACHE_GROUP_MASK;
value |= CNST_CACHE_GROUP_VAL(event & 0xff);
@@ -339,12 +344,22 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp)
value |= CNST_L1_QUAL_VAL(cache);
}
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ mask |= CNST_RADIX_SCOPE_GROUP_MASK;
+ value |= CNST_RADIX_SCOPE_GROUP_VAL(event >> p10_EVENT_RADIX_SCOPE_QUAL_SHIFT);
+ }
+
if (is_event_marked(event)) {
mask |= CNST_SAMPLE_MASK;
value |= CNST_SAMPLE_VAL(event >> EVENT_SAMPLE_SHIFT);
}
- if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ if (event_is_threshold(event)) {
+ mask |= CNST_THRESH_CTL_SEL_MASK;
+ value |= CNST_THRESH_CTL_SEL_VAL(event >> EVENT_THRESH_SHIFT);
+ }
+ } else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
if (event_is_threshold(event) && is_thresh_cmp_valid(event)) {
mask |= CNST_THRESH_MASK;
value |= CNST_THRESH_VAL(event >> EVENT_THRESH_SHIFT);
@@ -456,6 +471,13 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
}
}
+ /* Set RADIX_SCOPE_QUAL bit */
+ if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+ val = (event[i] >> p10_EVENT_RADIX_SCOPE_QUAL_SHIFT) &
+ p10_EVENT_RADIX_SCOPE_QUAL_MASK;
+ mmcr1 |= val << p10_MMCR1_RADIX_SCOPE_QUAL_SHIFT;
+ }
+
if (is_event_marked(event[i])) {
mmcra |= MMCRA_SAMPLE_ENABLE;
@@ -539,6 +561,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev,
if (!(pmc_inuse & 0x60))
mmcr->mmcr0 |= MMCR0_FC56;
+ /*
+ * Set mmcr0 (PMCCEXT) for p10 which
+ * will restrict access to group B registers
+ * when MMCR0 PMCC=0b00.
+ */
+ if (cpu_has_feature(CPU_FTR_ARCH_31))
+ mmcr->mmcr0 |= MMCR0_PMCCEXT;
+
mmcr->mmcr1 = mmcr1;
mmcr->mmcra = mmcra;
mmcr->mmcr2 = mmcr2;
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 7025de5e60e7..454b32c31440 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -101,6 +101,9 @@
#define p10_EVENT_CACHE_SEL_MASK 0x3ull
#define p10_EVENT_MMCR3_MASK 0x7fffull
#define p10_EVENT_MMCR3_SHIFT 45
+#define p10_EVENT_RADIX_SCOPE_QUAL_SHIFT 9
+#define p10_EVENT_RADIX_SCOPE_QUAL_MASK 0x1
+#define p10_MMCR1_RADIX_SCOPE_QUAL_SHIFT 45
#define p10_EVENT_VALID_MASK \
((p10_SDAR_MODE_MASK << p10_SDAR_MODE_SHIFT | \
@@ -112,6 +115,7 @@
(p9_EVENT_COMBINE_MASK << p9_EVENT_COMBINE_SHIFT) | \
(p10_EVENT_MMCR3_MASK << p10_EVENT_MMCR3_SHIFT) | \
(EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
+ (p10_EVENT_RADIX_SCOPE_QUAL_MASK << p10_EVENT_RADIX_SCOPE_QUAL_SHIFT) | \
EVENT_LINUX_MASK | \
EVENT_PSEL_MASK))
/*
@@ -125,9 +129,9 @@
*
* 28 24 20 16 12 8 4 0
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- * [ ] | [ ] [ sample ] [ ] [6] [5] [4] [3] [2] [1]
- * | | | |
- * BHRB IFM -* | | | Count of events for each PMC.
+ * [ ] | [ ] | [ sample ] [ ] [6] [5] [4] [3] [2] [1]
+ * | | | | |
+ * BHRB IFM -* | | |*radix_scope | Count of events for each PMC.
* EBB -* | | p1, p2, p3, p4, p5, p6.
* L1 I/D qualifier -* |
* nc - number of counters -*
@@ -145,6 +149,9 @@
#define CNST_THRESH_VAL(v) (((v) & EVENT_THRESH_MASK) << 32)
#define CNST_THRESH_MASK CNST_THRESH_VAL(EVENT_THRESH_MASK)
+#define CNST_THRESH_CTL_SEL_VAL(v) (((v) & 0x7ffull) << 32)
+#define CNST_THRESH_CTL_SEL_MASK CNST_THRESH_CTL_SEL_VAL(0x7ff)
+
#define CNST_EBB_VAL(v) (((v) & EVENT_EBB_MASK) << 24)
#define CNST_EBB_MASK CNST_EBB_VAL(EVENT_EBB_MASK)
@@ -165,6 +172,9 @@
#define CNST_L2L3_GROUP_VAL(v) (((v) & 0x1full) << 55)
#define CNST_L2L3_GROUP_MASK CNST_L2L3_GROUP_VAL(0x1f)
+#define CNST_RADIX_SCOPE_GROUP_VAL(v) (((v) & 0x1ull) << 21)
+#define CNST_RADIX_SCOPE_GROUP_MASK CNST_RADIX_SCOPE_GROUP_VAL(1)
+
/*
* For NC we are counting up to 4 events. This requires three bits, and we need
* the fifth event to overflow and set the 4th bit. To achieve that we bias the
@@ -221,6 +231,10 @@
#define MMCRA_THR_CTR_EXP(v) (((v) >> MMCRA_THR_CTR_EXP_SHIFT) &\
MMCRA_THR_CTR_EXP_MASK)
+#define P10_MMCRA_THR_CTR_MANT_MASK 0xFFul
+#define P10_MMCRA_THR_CTR_MANT(v) (((v) >> MMCRA_THR_CTR_MANT_SHIFT) &\
+ P10_MMCRA_THR_CTR_MANT_MASK)
+
/* MMCRA Threshold Compare bit constant for power9 */
#define p9_MMCRA_THR_CMP_SHIFT 45
diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h
index 60c1b8111082..e45dafe818ed 100644
--- a/arch/powerpc/perf/power10-events-list.h
+++ b/arch/powerpc/perf/power10-events-list.h
@@ -15,6 +15,9 @@ EVENT(PM_EXEC_STALL, 0x30008);
EVENT(PM_RUN_INST_CMPL, 0x500fa);
EVENT(PM_BR_CMPL, 0x4d05e);
EVENT(PM_BR_MPRED_CMPL, 0x400f6);
+EVENT(PM_BR_FIN, 0x2f04a);
+EVENT(PM_MPRED_BR_FIN, 0x3e098);
+EVENT(PM_LD_DEMAND_MISS_L1_FIN, 0x400f0);
/* All L1 D cache load references counted at finish, gated by reject */
EVENT(PM_LD_REF_L1, 0x100fc);
@@ -36,6 +39,12 @@ EVENT(PM_IC_PREF_REQ, 0x040a0);
EVENT(PM_DATA_FROM_L3, 0x01340000001c040);
/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */
EVENT(PM_DATA_FROM_L3MISS, 0x300fe);
+/* All successful D-side store dispatches for this thread */
+EVENT(PM_L2_ST, 0x010000046080);
+/* All successful D-side store dispatches for this thread that were L2 Miss */
+EVENT(PM_L2_ST_MISS, 0x26880);
+/* Total HW L3 prefetches(Load+store) */
+EVENT(PM_L3_PF_MISS_L3, 0x100000016080);
/* Data PTEG reload */
EVENT(PM_DTLB_MISS, 0x300fc);
/* ITLB Reloaded */
diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c
index 9dbe8f9b89b4..79e0206ca454 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -23,10 +23,10 @@
*
* 28 24 20 16 12 8 4 0
* | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
- * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] m [ pmcxsel ]
- * | | | | | |
- * | | | | | *- mark
- * | | | *- L1/L2/L3 cache_sel |
+ * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] | m [ pmcxsel ]
+ * | | | | | | |
+ * | | | | | | *- mark
+ * | | | *- L1/L2/L3 cache_sel | |*-radix_scope_qual
* | | sdar_mode |
* | *- sampling mode for marked events *- combine
* |
@@ -59,6 +59,7 @@
*
* MMCR1[16] = cache_sel[0]
* MMCR1[17] = cache_sel[1]
+ * MMCR1[18] = radix_scope_qual
*
* if mark:
* MMCRA[63] = 1 (SAMPLE_ENABLE)
@@ -113,6 +114,9 @@ GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1);
GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1);
GENERIC_EVENT_ATTR(mem-loads, MEM_LOADS);
GENERIC_EVENT_ATTR(mem-stores, MEM_STORES);
+GENERIC_EVENT_ATTR(branch-instructions, PM_BR_FIN);
+GENERIC_EVENT_ATTR(branch-misses, PM_MPRED_BR_FIN);
+GENERIC_EVENT_ATTR(cache-misses, PM_LD_DEMAND_MISS_L1_FIN);
CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1);
CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1);
@@ -123,12 +127,15 @@ CACHE_EVENT_ATTR(L1-icache-loads, PM_INST_FROM_L1);
CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_REQ);
CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS);
CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3);
+CACHE_EVENT_ATTR(LLC-prefetches, PM_L3_PF_MISS_L3);
+CACHE_EVENT_ATTR(LLC-store-misses, PM_L2_ST_MISS);
+CACHE_EVENT_ATTR(LLC-stores, PM_L2_ST);
CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL);
CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL);
CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS);
CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS);
-static struct attribute *power10_events_attr[] = {
+static struct attribute *power10_events_attr_dd1[] = {
GENERIC_EVENT_PTR(PM_RUN_CYC),
GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
GENERIC_EVENT_PTR(PM_BR_CMPL),
@@ -153,6 +160,39 @@ static struct attribute *power10_events_attr[] = {
NULL
};
+static struct attribute *power10_events_attr[] = {
+ GENERIC_EVENT_PTR(PM_RUN_CYC),
+ GENERIC_EVENT_PTR(PM_RUN_INST_CMPL),
+ GENERIC_EVENT_PTR(PM_BR_FIN),
+ GENERIC_EVENT_PTR(PM_MPRED_BR_FIN),
+ GENERIC_EVENT_PTR(PM_LD_REF_L1),
+ GENERIC_EVENT_PTR(PM_LD_DEMAND_MISS_L1_FIN),
+ GENERIC_EVENT_PTR(MEM_LOADS),
+ GENERIC_EVENT_PTR(MEM_STORES),
+ CACHE_EVENT_PTR(PM_LD_MISS_L1),
+ CACHE_EVENT_PTR(PM_LD_REF_L1),
+ CACHE_EVENT_PTR(PM_LD_PREFETCH_CACHE_LINE_MISS),
+ CACHE_EVENT_PTR(PM_ST_MISS_L1),
+ CACHE_EVENT_PTR(PM_L1_ICACHE_MISS),
+ CACHE_EVENT_PTR(PM_INST_FROM_L1),
+ CACHE_EVENT_PTR(PM_IC_PREF_REQ),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS),
+ CACHE_EVENT_PTR(PM_DATA_FROM_L3),
+ CACHE_EVENT_PTR(PM_L3_PF_MISS_L3),
+ CACHE_EVENT_PTR(PM_L2_ST_MISS),
+ CACHE_EVENT_PTR(PM_L2_ST),
+ CACHE_EVENT_PTR(PM_BR_MPRED_CMPL),
+ CACHE_EVENT_PTR(PM_BR_CMPL),
+ CACHE_EVENT_PTR(PM_DTLB_MISS),
+ CACHE_EVENT_PTR(PM_ITLB_MISS),
+ NULL
+};
+
+static struct attribute_group power10_pmu_events_group_dd1 = {
+ .name = "events",
+ .attrs = power10_events_attr_dd1,
+};
+
static struct attribute_group power10_pmu_events_group = {
.name = "events",
.attrs = power10_events_attr,
@@ -175,6 +215,7 @@ PMU_FORMAT_ATTR(src_sel, "config:45-46");
PMU_FORMAT_ATTR(invert_bit, "config:47");
PMU_FORMAT_ATTR(src_mask, "config:48-53");
PMU_FORMAT_ATTR(src_match, "config:54-59");
+PMU_FORMAT_ATTR(radix_scope, "config:9");
static struct attribute *power10_pmu_format_attr[] = {
&format_attr_event.attr,
@@ -194,6 +235,7 @@ static struct attribute *power10_pmu_format_attr[] = {
&format_attr_invert_bit.attr,
&format_attr_src_mask.attr,
&format_attr_src_match.attr,
+ &format_attr_radix_scope.attr,
NULL,
};
@@ -202,13 +244,19 @@ static struct attribute_group power10_pmu_format_group = {
.attrs = power10_pmu_format_attr,
};
+static const struct attribute_group *power10_pmu_attr_groups_dd1[] = {
+ &power10_pmu_format_group,
+ &power10_pmu_events_group_dd1,
+ NULL,
+};
+
static const struct attribute_group *power10_pmu_attr_groups[] = {
&power10_pmu_format_group,
&power10_pmu_events_group,
NULL,
};
-static int power10_generic_events[] = {
+static int power10_generic_events_dd1[] = {
[PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
[PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL,
@@ -217,6 +265,15 @@ static int power10_generic_events[] = {
[PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1,
};
+static int power10_generic_events[] = {
+ [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC,
+ [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL,
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_FIN,
+ [PERF_COUNT_HW_BRANCH_MISSES] = PM_MPRED_BR_FIN,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1,
+ [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_DEMAND_MISS_L1_FIN,
+};
+
static u64 power10_bhrb_filter_map(u64 branch_sample_type)
{
u64 pmu_bhrb_filter = 0;
@@ -273,7 +330,7 @@ static void power10_config_bhrb(u64 pmu_bhrb_filter)
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
-static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+static u64 power10_cache_events_dd1[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(L1D)] = {
[C(OP_READ)] = {
[C(RESULT_ACCESS)] = PM_LD_REF_L1,
@@ -374,6 +431,107 @@ static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
},
};
+static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+ [C(L1D)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_LD_REF_L1,
+ [C(RESULT_MISS)] = PM_LD_MISS_L1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ST_MISS_L1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_LD_PREFETCH_CACHE_LINE_MISS,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(L1I)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1,
+ [C(RESULT_MISS)] = PM_L1_ICACHE_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = PM_INST_FROM_L1MISS,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_IC_PREF_REQ,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(LL)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_DATA_FROM_L3,
+ [C(RESULT_MISS)] = PM_DATA_FROM_L3MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = PM_L2_ST,
+ [C(RESULT_MISS)] = PM_L2_ST_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = PM_L3_PF_MISS_L3,
+ [C(RESULT_MISS)] = 0,
+ },
+ },
+ [C(DTLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_DTLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(ITLB)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = 0,
+ [C(RESULT_MISS)] = PM_ITLB_MISS,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(BPU)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = PM_BR_CMPL,
+ [C(RESULT_MISS)] = PM_BR_MPRED_CMPL,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = -1,
+ [C(RESULT_MISS)] = -1,
+ },
+ },
+};
+
#undef C
static struct power_pmu power10_pmu = {
@@ -403,6 +561,7 @@ static struct power_pmu power10_pmu = {
int init_power10_pmu(void)
{
+ unsigned int pvr;
int rc;
/* Comes from cpu_specs[] */
@@ -410,9 +569,20 @@ int init_power10_pmu(void)
strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10"))
return -ENODEV;
+ pvr = mfspr(SPRN_PVR);
+ /* Add the ppmu flag for power10 DD1 */
+ if ((PVR_CFG(pvr) == 1))
+ power10_pmu.flags |= PPMU_P10_DD1;
+
/* Set the PERF_REG_EXTENDED_MASK here */
PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+ if ((PVR_CFG(pvr) == 1)) {
+ power10_pmu.generic_events = power10_generic_events_dd1;
+ power10_pmu.attr_groups = power10_pmu_attr_groups_dd1;
+ power10_pmu.cache_events = &power10_cache_events_dd1;
+ }
+
rc = register_power_pmu(&power10_pmu);
if (rc)
return rc;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-17 01:06:33 +0100