From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
To: mpe@ellerman.id.au
Cc: mikey@neuling.org, maddy@linux.ibm.com, linuxppc-dev@lists.ozlabs.org
Subject: [PATCH 3/4] powerpc/perf: Fix to update l2l3 events and generic event codes for power10
Date: Tue, 10 Nov 2020 23:33:08 -0500 [thread overview]
Message-ID: <1605069189-2740-4-git-send-email-atrajeev@linux.vnet.ibm.com> (raw)
In-Reply-To: <1605069189-2740-1-git-send-email-atrajeev@linux.vnet.ibm.com>
Fix the event code for events: branch-instructions (to PM_BR_FIN),
branch-misses (to PM_BR_MPRED_FIN) and cache-misses (to
PM_LD_DEMAND_MISS_L1_FIN) for power10 PMU. Update the
list of generic events with this modified event code.
Export l2l3 events (PM_L2_ST_MISS and PM_L2_ST) and LLC-prefetches
(PM_L3_PF_MISS_L3) via sysfs, and also add these to cache_events.
To maintain the current event code work with DD1, rename
existing array of generic_events, cache_events and pmu_attr_groups
with suffix _dd1. Update the power10 pmu init code to pick the
dd1 list while registering the power PMU, based on the pvr
(Processor Version Register) value.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
---
arch/powerpc/perf/power10-events-list.h | 9 ++
arch/powerpc/perf/power10-pmu.c | 166 +++++++++++++++++++++++++++++++-
2 files changed, 173 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h
index 60c1b81..9e0b3c9 100644
--- a/arch/powerpc/perf/power10-events-list.h
+++ b/arch/powerpc/perf/power10-events-list.h
@@ -15,6 +15,9 @@
EVENT(PM_RUN_INST_CMPL, 0x500fa);
EVENT(PM_BR_CMPL, 0x4d05e);
EVENT(PM_BR_MPRED_CMPL, 0x400f6);
+EVENT(PM_BR_FIN, 0x2f04a);
+EVENT(PM_BR_MPRED_FIN, 0x35884);
+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_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 cf44fb7..86665ad 100644
--- a/arch/powerpc/perf/power10-pmu.c
+++ b/arch/powerpc/perf/power10-pmu.c
@@ -114,6 +114,9 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
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_BR_MPRED_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);
@@ -124,12 +127,15 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
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),
@@ -154,11 +160,44 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
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_BR_MPRED_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 = {
.name = "events",
.attrs = power10_events_attr,
};
+static struct attribute_group power10_pmu_events_group_dd1 = {
+ .name = "events",
+ .attrs = power10_events_attr_dd1,
+};
+
PMU_FORMAT_ATTR(event, "config:0-59");
PMU_FORMAT_ATTR(pmcxsel, "config:0-7");
PMU_FORMAT_ATTR(mark, "config:8");
@@ -211,7 +250,13 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
NULL,
};
-static int power10_generic_events[] = {
+static const struct attribute_group *power10_pmu_attr_groups_dd1[] = {
+ &power10_pmu_format_group,
+ &power10_pmu_events_group_dd1,
+ NULL,
+};
+
+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,
@@ -220,6 +265,15 @@ static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[])
[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_BR_MPRED_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;
@@ -311,6 +365,107 @@ static void power10_config_bhrb(u64 pmu_bhrb_filter)
[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,
+ },
+ },
+};
+
+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,
+ [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)] = -1,
[C(RESULT_MISS)] = -1,
},
@@ -407,6 +562,7 @@ static void power10_config_bhrb(u64 pmu_bhrb_filter)
int init_power10_pmu(void)
{
int rc;
+ unsigned int pvr = mfspr(SPRN_PVR);
/* Comes from cpu_specs[] */
if (!cur_cpu_spec->oprofile_cpu_type ||
@@ -416,6 +572,12 @@ int init_power10_pmu(void)
/* Set the PERF_REG_EXTENDED_MASK here */
PERF_REG_EXTENDED_MASK = PERF_REG_PMU_MASK_31;
+ if ((PVR_MAJ(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;
--
1.8.3.1
next prev parent reply other threads:[~2020-11-11 5:02 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-11 4:33 [PATCH 0/4] powerpc/perf: Fixes for power10 PMU Athira Rajeev
2020-11-11 4:33 ` [PATCH 1/4] powerpc/perf: Fix to update radix_scope_qual in power10 Athira Rajeev
2020-11-11 4:33 ` [PATCH 2/4] powerpc/perf: Update the PMU group constraints for l2l3 and threshold events " Athira Rajeev
2020-11-18 4:32 ` Michael Ellerman
2020-11-18 5:21 ` Athira Rajeev
2020-11-11 4:33 ` Athira Rajeev [this message]
2020-11-18 4:36 ` [PATCH 3/4] powerpc/perf: Fix to update l2l3 events and generic event codes for power10 Michael Ellerman
2020-11-18 5:23 ` Athira Rajeev
2020-11-11 4:33 ` [PATCH 4/4] powerpc/perf: MMCR0 control for PMU registers under PMCC=00 Athira Rajeev
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1605069189-2740-4-git-send-email-atrajeev@linux.vnet.ibm.com \
--to=atrajeev@linux.vnet.ibm.com \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=maddy@linux.ibm.com \
--cc=mikey@neuling.org \
--cc=mpe@ellerman.id.au \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).