From: kan.liang@linux.intel.com
To: peterz@infradead.org, mingo@redhat.com, linux-kernel@vger.kernel.org
Cc: acme@kernel.org, namhyung@kernel.org, irogers@google.com,
eranian@google.com, ak@linux.intel.com,
Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH 1/2] perf/x86/intel/ds: Clarify adaptive PEBS processing
Date: Wed, 13 Nov 2024 07:14:26 -0800 [thread overview]
Message-ID: <20241113151427.677169-1-kan.liang@linux.intel.com> (raw)
From: Kan Liang <kan.liang@linux.intel.com>
Modify the pebs_basic and pebs_meminfo structs to make the bitfields
more explicit to ease readability of the code.
Co-developed-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
arch/x86/events/intel/ds.c | 43 ++++++++++++++-----------------
arch/x86/include/asm/perf_event.h | 16 ++++++++++--
2 files changed, 34 insertions(+), 25 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8afc4ad3cd16..4d0f7c49295a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1917,8 +1917,6 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
}
#define PEBS_LATENCY_MASK 0xffff
-#define PEBS_CACHE_LATENCY_OFFSET 32
-#define PEBS_RETIRE_LATENCY_OFFSET 32
/*
* With adaptive PEBS the layout depends on what fields are configured.
@@ -1932,8 +1930,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_basic *basic = __pebs;
void *next_record = basic + 1;
- u64 sample_type;
- u64 format_size;
+ u64 sample_type, format_group;
struct pebs_meminfo *meminfo = NULL;
struct pebs_gprs *gprs = NULL;
struct x86_perf_regs *perf_regs;
@@ -1945,7 +1942,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
perf_regs->xmm_regs = NULL;
sample_type = event->attr.sample_type;
- format_size = basic->format_size;
+ format_group = basic->format_group;
perf_sample_data_init(data, 0, event->hw.last_period);
data->period = event->hw.last_period;
@@ -1967,7 +1964,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
- data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+ data->weight.var3_w = basic->retire_latency;
else
data->weight.var3_w = 0;
}
@@ -1977,12 +1974,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
* But PERF_SAMPLE_TRANSACTION needs gprs->ax.
* Save the pointer here but process later.
*/
- if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (format_group & PEBS_DATACFG_MEMINFO) {
meminfo = next_record;
next_record = meminfo + 1;
}
- if (format_size & PEBS_DATACFG_GP) {
+ if (format_group & PEBS_DATACFG_GP) {
gprs = next_record;
next_record = gprs + 1;
@@ -1995,14 +1992,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
adaptive_pebs_save_regs(regs, gprs);
}
- if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (format_group & PEBS_DATACFG_MEMINFO) {
if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
- u64 weight = meminfo->latency;
+ u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
+ meminfo->cache_latency : meminfo->mem_latency;
- if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) {
- data->weight.var2_w = weight & PEBS_LATENCY_MASK;
- weight >>= PEBS_CACHE_LATENCY_OFFSET;
- }
+ if (x86_pmu.flags & PMU_FL_INSTR_LATENCY)
+ data->weight.var2_w = meminfo->instr_latency;
/*
* Although meminfo::latency is defined as a u64,
@@ -2010,12 +2006,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
* in practice on Ice Lake and earlier platforms.
*/
if (sample_type & PERF_SAMPLE_WEIGHT) {
- data->weight.full = weight ?:
+ data->weight.full = latency ?:
intel_get_tsx_weight(meminfo->tsx_tuning);
} else {
- data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
+ data->weight.var1_dw = (u32)latency ?:
intel_get_tsx_weight(meminfo->tsx_tuning);
}
+
data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
}
@@ -2036,16 +2033,16 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
}
}
- if (format_size & PEBS_DATACFG_XMMS) {
+ if (format_group & PEBS_DATACFG_XMMS) {
struct pebs_xmm *xmm = next_record;
next_record = xmm + 1;
perf_regs->xmm_regs = xmm->xmm;
}
- if (format_size & PEBS_DATACFG_LBRS) {
+ if (format_group & PEBS_DATACFG_LBRS) {
struct lbr_entry *lbr = next_record;
- int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT)
& 0xff) + 1;
next_record = next_record + num_lbr * sizeof(struct lbr_entry);
@@ -2055,11 +2052,11 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
}
}
- WARN_ONCE(next_record != __pebs + (format_size >> 48),
- "PEBS record size %llu, expected %llu, config %llx\n",
- format_size >> 48,
+ WARN_ONCE(next_record != __pebs + basic->format_size,
+ "PEBS record size %u, expected %llu, config %llx\n",
+ basic->format_size,
(u64)(next_record - __pebs),
- basic->format_size);
+ format_group);
}
static inline void *
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 91b73571412f..cd8023d5ea46 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -422,7 +422,9 @@ static inline bool is_topdown_idx(int idx)
*/
struct pebs_basic {
- u64 format_size;
+ u64 format_group:32,
+ retire_latency:16,
+ format_size:16;
u64 ip;
u64 applicable_counters;
u64 tsc;
@@ -431,7 +433,17 @@ struct pebs_basic {
struct pebs_meminfo {
u64 address;
u64 aux;
- u64 latency;
+ union {
+ /* pre Alder Lake */
+ u64 mem_latency;
+ /* Alder Lake and later */
+ struct {
+ u64 instr_latency:16;
+ u64 pad2:16;
+ u64 cache_latency:16;
+ u64 pad3:16;
+ };
+ };
u64 tsx_tuning;
};
--
2.38.1
next reply other threads:[~2024-11-13 15:13 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-13 15:14 kan.liang [this message]
2024-11-13 15:14 ` [PATCH 2/2] perf/x86/intel/ds: Simplify the PEBS records processing for adaptive PEBS kan.liang
2024-11-14 14:19 ` Peter Zijlstra
2024-11-14 15:51 ` Liang, Kan
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=20241113151427.677169-1-kan.liang@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=eranian@google.com \
--cc=irogers@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/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
Powered by JetHome