* [PATCH V5 01/12] perf/x86: Fix wrong PEBS_REGS
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
@ 2019-04-02 19:44 ` kan.liang
2019-04-16 11:32 ` [tip:perf/core] perf/x86: Fix incorrect PEBS_REGS tip-bot for Kan Liang
2019-04-02 19:44 ` [PATCH V5 02/12] perf/x86: Support outputting XMM registers kan.liang
` (11 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:44 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
PEBS_REGS used as mask for the supported registers for large PEBS.
However, the mask cannot filter the sample_regs_user/sample_regs_intr
correctly.
(1ULL << PERF_REG_X86_*) should be used to replace PERF_REG_X86_*, which
is only the index.
Rename PEBS_REGS to PEBS_GPRS_REGS. Because the mask is only for general
purpose registers.
Fixes: 2fe1bc1f501d ("perf/x86: Enable free running PEBS for REGS_USER/INTR")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
New patch for V5
arch/x86/events/intel/core.c | 2 +-
arch/x86/events/perf_event.h | 38 ++++++++++++++++++------------------
2 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8baa441d8000..a9721457f187 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
flags &= ~PERF_SAMPLE_TIME;
if (!event->attr.exclude_kernel)
flags &= ~PERF_SAMPLE_REGS_USER;
- if (event->attr.sample_regs_user & ~PEBS_REGS)
+ if (event->attr.sample_regs_user & ~PEBS_GPRS_REGS)
flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
return flags;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..00f700dd3c2d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -96,25 +96,25 @@ struct amd_nb {
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
-#define PEBS_REGS \
- (PERF_REG_X86_AX | \
- PERF_REG_X86_BX | \
- PERF_REG_X86_CX | \
- PERF_REG_X86_DX | \
- PERF_REG_X86_DI | \
- PERF_REG_X86_SI | \
- PERF_REG_X86_SP | \
- PERF_REG_X86_BP | \
- PERF_REG_X86_IP | \
- PERF_REG_X86_FLAGS | \
- PERF_REG_X86_R8 | \
- PERF_REG_X86_R9 | \
- PERF_REG_X86_R10 | \
- PERF_REG_X86_R11 | \
- PERF_REG_X86_R12 | \
- PERF_REG_X86_R13 | \
- PERF_REG_X86_R14 | \
- PERF_REG_X86_R15)
+#define PEBS_GPRS_REGS \
+ ((1ULL << PERF_REG_X86_AX) | \
+ (1ULL << PERF_REG_X86_BX) | \
+ (1ULL << PERF_REG_X86_CX) | \
+ (1ULL << PERF_REG_X86_DX) | \
+ (1ULL << PERF_REG_X86_DI) | \
+ (1ULL << PERF_REG_X86_SI) | \
+ (1ULL << PERF_REG_X86_SP) | \
+ (1ULL << PERF_REG_X86_BP) | \
+ (1ULL << PERF_REG_X86_IP) | \
+ (1ULL << PERF_REG_X86_FLAGS) | \
+ (1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
/*
* Per register state.
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86: Fix incorrect PEBS_REGS
2019-04-02 19:44 ` [PATCH V5 01/12] perf/x86: Fix wrong PEBS_REGS kan.liang
@ 2019-04-16 11:32 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:32 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, alexander.shishkin, linux-kernel, tglx, torvalds, hpa,
acme, peterz, stable, jolsa, kan.liang, vincent.weaver, mingo
Commit-ID: 9d5dcc93a6ddfc78124f006ccd3637ce070ef2fc
Gitweb: https://git.kernel.org/tip/9d5dcc93a6ddfc78124f006ccd3637ce070ef2fc
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:44:58 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:13:58 +0200
perf/x86: Fix incorrect PEBS_REGS
PEBS_REGS used as mask for the supported registers for large PEBS.
However, the mask cannot filter the sample_regs_user/sample_regs_intr
correctly.
(1ULL << PERF_REG_X86_*) should be used to replace PERF_REG_X86_*, which
is only the index.
Rename PEBS_REGS to PEBS_GP_REGS, because the mask is only for general
purpose registers.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Fixes: 2fe1bc1f501d ("perf/x86: Enable free running PEBS for REGS_USER/INTR")
Link: https://lkml.kernel.org/r/20190402194509.2832-2-kan.liang@linux.intel.com
[ Renamed it to PEBS_GP_REGS - as 'GPRS' is used elsewhere ;-) ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/core.c | 2 +-
arch/x86/events/perf_event.h | 38 +++++++++++++++++++-------------------
2 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index f61dcbef20ff..f9451566cd9b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
flags &= ~PERF_SAMPLE_TIME;
if (!event->attr.exclude_kernel)
flags &= ~PERF_SAMPLE_REGS_USER;
- if (event->attr.sample_regs_user & ~PEBS_REGS)
+ if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
return flags;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..1e98a42b560a 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -96,25 +96,25 @@ struct amd_nb {
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
PERF_SAMPLE_PERIOD)
-#define PEBS_REGS \
- (PERF_REG_X86_AX | \
- PERF_REG_X86_BX | \
- PERF_REG_X86_CX | \
- PERF_REG_X86_DX | \
- PERF_REG_X86_DI | \
- PERF_REG_X86_SI | \
- PERF_REG_X86_SP | \
- PERF_REG_X86_BP | \
- PERF_REG_X86_IP | \
- PERF_REG_X86_FLAGS | \
- PERF_REG_X86_R8 | \
- PERF_REG_X86_R9 | \
- PERF_REG_X86_R10 | \
- PERF_REG_X86_R11 | \
- PERF_REG_X86_R12 | \
- PERF_REG_X86_R13 | \
- PERF_REG_X86_R14 | \
- PERF_REG_X86_R15)
+#define PEBS_GP_REGS \
+ ((1ULL << PERF_REG_X86_AX) | \
+ (1ULL << PERF_REG_X86_BX) | \
+ (1ULL << PERF_REG_X86_CX) | \
+ (1ULL << PERF_REG_X86_DX) | \
+ (1ULL << PERF_REG_X86_DI) | \
+ (1ULL << PERF_REG_X86_SI) | \
+ (1ULL << PERF_REG_X86_SP) | \
+ (1ULL << PERF_REG_X86_BP) | \
+ (1ULL << PERF_REG_X86_IP) | \
+ (1ULL << PERF_REG_X86_FLAGS) | \
+ (1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
/*
* Per register state.
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 02/12] perf/x86: Support outputting XMM registers
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
2019-04-02 19:44 ` [PATCH V5 01/12] perf/x86: Fix wrong PEBS_REGS kan.liang
@ 2019-04-02 19:44 ` kan.liang
2019-04-16 11:34 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 03/12] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
` (10 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:44 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Starting from Icelake, XMM registers can be collected in PEBS record.
But current code only output the pt_regs.
Add a new struct x86_perf_regs for both pt_regs and xmm_regs. The
xmm_regs will be used later to keep a pointer to PEBS record which has
XMM information.
XMM registers are 128 bit. To simplify the code, they are handled like
two different registers, which means setting two bits in the register
bitmap. This also allows only sampling the lower 64bit bits in XMM.
The index of XMM registers starts from 32. There are 16 XMM registers.
So all reserved space for regs are used. Remove REG_RESERVED.
Add PERF_REG_X86_XMM_MAX, which stands for the max number of all x86
regs including both GPRs and XMM.
Add REG_NOSUPPORT for 32bit to exclude unsupported registers.
Previous platforms can not collect XMM information in PEBS record.
Adding pebs_no_xmm_regs to indicate the unsupported platforms.
The common code still validate the supported registers. However, it
cannot check model specific registers, e.g. XMM. Add extra check in
x86_pmu_hw_config() to reject invalid config of regs_user and regs_intr.
The regs_user never supports XMM collection.
The regs_intr only supports XMM collection when sampling PEBS event on
icelake and later platforms.
Originally-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
Changes since V4:
- Rename has_xmm_regs to pebs_no_xmm_regs
- Rename PEBS_REGS to PEBS_GPRS_REGS
Add PEBS_XMM_REGS for XMM registers
Refine the extra check in x86_pmu_hw_config()
arch/x86/events/core.c | 15 +++++++++++++++
arch/x86/events/intel/ds.c | 4 +++-
arch/x86/events/perf_event.h | 21 ++++++++++++++++++++-
arch/x86/include/asm/perf_event.h | 5 +++++
arch/x86/include/uapi/asm/perf_regs.h | 23 ++++++++++++++++++++++-
arch/x86/kernel/perf_regs.c | 27 ++++++++++++++++++++-------
6 files changed, 85 insertions(+), 10 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..e93c43e54c75 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event)
return -EINVAL;
}
+ /* sample_regs_user never support XMM registers */
+ if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+ return -EINVAL;
+ /*
+ * Besides the general purpose registers, XMM registers may
+ * be collected in PEBS on some platforms, e.g. Icelake
+ */
+ if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
+ if (!is_sampling_event(event) ||
+ !event->attr.precise_ip ||
+ x86_pmu.pebs_no_xmm_regs)
+ return -EINVAL;
+
+ }
+
return x86_setup_perfctr(event);
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 10c99ce1fead..f57e6cb7fd99 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1628,8 +1628,10 @@ void __init intel_ds_init(void)
x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
- if (x86_pmu.version <= 4)
+ if (x86_pmu.version <= 4) {
x86_pmu.pebs_no_isolation = 1;
+ x86_pmu.pebs_no_xmm_regs = 1;
+ }
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
int format = x86_pmu.intel_cap.pebs_format;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 00f700dd3c2d..cee4ad018a0e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -116,6 +116,24 @@ struct amd_nb {
(1ULL << PERF_REG_X86_R14) | \
(1ULL << PERF_REG_X86_R15))
+#define PEBS_XMM_REGS \
+ ((1ULL << PERF_REG_X86_XMM0) | \
+ (1ULL << PERF_REG_X86_XMM1) | \
+ (1ULL << PERF_REG_X86_XMM2) | \
+ (1ULL << PERF_REG_X86_XMM3) | \
+ (1ULL << PERF_REG_X86_XMM4) | \
+ (1ULL << PERF_REG_X86_XMM5) | \
+ (1ULL << PERF_REG_X86_XMM6) | \
+ (1ULL << PERF_REG_X86_XMM7) | \
+ (1ULL << PERF_REG_X86_XMM8) | \
+ (1ULL << PERF_REG_X86_XMM9) | \
+ (1ULL << PERF_REG_X86_XMM10) | \
+ (1ULL << PERF_REG_X86_XMM11) | \
+ (1ULL << PERF_REG_X86_XMM12) | \
+ (1ULL << PERF_REG_X86_XMM13) | \
+ (1ULL << PERF_REG_X86_XMM14) | \
+ (1ULL << PERF_REG_X86_XMM15))
+
/*
* Per register state.
*/
@@ -613,7 +631,8 @@ struct x86_pmu {
pebs_broken :1,
pebs_prec_dist :1,
pebs_no_tlb :1,
- pebs_no_isolation :1;
+ pebs_no_isolation :1,
+ pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
void (*drain_pebs)(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8bdf74902293..d9f5bbe44b3c 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -248,6 +248,11 @@ extern void perf_events_lapic_init(void);
#define PERF_EFLAGS_VM (1UL << 5)
struct pt_regs;
+struct x86_perf_regs {
+ struct pt_regs regs;
+ u64 *xmm_regs;
+};
+
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,8 +27,29 @@ enum perf_event_x86_regs {
PERF_REG_X86_R13,
PERF_REG_X86_R14,
PERF_REG_X86_R15,
-
+ /* These are the limits for the GPRs. */
PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+ /* These all need two bits set because they are 128bit */
+ PERF_REG_X86_XMM0 = 32,
+ PERF_REG_X86_XMM1 = 34,
+ PERF_REG_X86_XMM2 = 36,
+ PERF_REG_X86_XMM3 = 38,
+ PERF_REG_X86_XMM4 = 40,
+ PERF_REG_X86_XMM5 = 42,
+ PERF_REG_X86_XMM6 = 44,
+ PERF_REG_X86_XMM7 = 46,
+ PERF_REG_X86_XMM8 = 48,
+ PERF_REG_X86_XMM9 = 50,
+ PERF_REG_X86_XMM10 = 52,
+ PERF_REG_X86_XMM11 = 54,
+ PERF_REG_X86_XMM12 = 56,
+ PERF_REG_X86_XMM13 = 58,
+ PERF_REG_X86_XMM14 = 60,
+ PERF_REG_X86_XMM15 = 62,
+
+ /* These include both GPRs and XMMX registers */
+ PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
};
#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index c06c4c16c6b6..07c30ee17425 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
u64 perf_reg_value(struct pt_regs *regs, int idx)
{
+ struct x86_perf_regs *perf_regs;
+
+ if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ if (!perf_regs->xmm_regs)
+ return 0;
+ return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+ }
+
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
return 0;
return regs_get_register(regs, pt_regs_offset[idx]);
}
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
-
#ifdef CONFIG_X86_32
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
+
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
@@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
- return -EINVAL;
-
- if (mask & REG_NOSUPPORT)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86: Support outputting XMM registers
2019-04-02 19:44 ` [PATCH V5 02/12] perf/x86: Support outputting XMM registers kan.liang
@ 2019-04-16 11:34 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:34 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, jolsa, tglx, hpa, peterz, ak, alexander.shishkin,
kan.liang, vincent.weaver, mingo, torvalds, acme, linux-kernel
Commit-ID: 878068ea270ea82767ff1d26c91583263c81fba0
Gitweb: https://git.kernel.org/tip/878068ea270ea82767ff1d26c91583263c81fba0
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:44:59 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:19:36 +0200
perf/x86: Support outputting XMM registers
Starting from Icelake, XMM registers can be collected in PEBS record.
But current code only output the pt_regs.
Add a new struct x86_perf_regs for both pt_regs and xmm_regs. The
xmm_regs will be used later to keep a pointer to PEBS record which has
XMM information.
XMM registers are 128 bit. To simplify the code, they are handled like
two different registers, which means setting two bits in the register
bitmap. This also allows only sampling the lower 64bit bits in XMM.
The index of XMM registers starts from 32. There are 16 XMM registers.
So all reserved space for regs are used. Remove REG_RESERVED.
Add PERF_REG_X86_XMM_MAX, which stands for the max number of all x86
regs including both GPRs and XMM.
Add REG_NOSUPPORT for 32bit to exclude unsupported registers.
Previous platforms can not collect XMM information in PEBS record.
Adding pebs_no_xmm_regs to indicate the unsupported platforms.
The common code still validates the supported registers. However, it
cannot check model specific registers, e.g. XMM. Add extra check in
x86_pmu_hw_config() to reject invalid config of regs_user and regs_intr.
The regs_user never supports XMM collection.
The regs_intr only supports XMM collection when sampling PEBS event on
icelake and later platforms.
Originally-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-3-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/core.c | 15 +++++++++++++++
arch/x86/events/intel/ds.c | 4 +++-
arch/x86/events/perf_event.h | 21 ++++++++++++++++++++-
arch/x86/include/asm/perf_event.h | 5 +++++
arch/x86/include/uapi/asm/perf_regs.h | 23 ++++++++++++++++++++++-
arch/x86/kernel/perf_regs.c | 27 ++++++++++++++++++++-------
6 files changed, 85 insertions(+), 10 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index fdd106267fd2..de1a924a4914 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event)
return -EINVAL;
}
+ /* sample_regs_user never support XMM registers */
+ if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+ return -EINVAL;
+ /*
+ * Besides the general purpose registers, XMM registers may
+ * be collected in PEBS on some platforms, e.g. Icelake
+ */
+ if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
+ if (x86_pmu.pebs_no_xmm_regs)
+ return -EINVAL;
+
+ if (!event->attr.precise_ip)
+ return -EINVAL;
+ }
+
return x86_setup_perfctr(event);
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 10c99ce1fead..f57e6cb7fd99 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1628,8 +1628,10 @@ void __init intel_ds_init(void)
x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
- if (x86_pmu.version <= 4)
+ if (x86_pmu.version <= 4) {
x86_pmu.pebs_no_isolation = 1;
+ x86_pmu.pebs_no_xmm_regs = 1;
+ }
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
int format = x86_pmu.intel_cap.pebs_format;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9e474a5f3b86..7abfadb4f202 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -115,6 +115,24 @@ struct amd_nb {
(1ULL << PERF_REG_X86_R14) | \
(1ULL << PERF_REG_X86_R15))
+#define PEBS_XMM_REGS \
+ ((1ULL << PERF_REG_X86_XMM0) | \
+ (1ULL << PERF_REG_X86_XMM1) | \
+ (1ULL << PERF_REG_X86_XMM2) | \
+ (1ULL << PERF_REG_X86_XMM3) | \
+ (1ULL << PERF_REG_X86_XMM4) | \
+ (1ULL << PERF_REG_X86_XMM5) | \
+ (1ULL << PERF_REG_X86_XMM6) | \
+ (1ULL << PERF_REG_X86_XMM7) | \
+ (1ULL << PERF_REG_X86_XMM8) | \
+ (1ULL << PERF_REG_X86_XMM9) | \
+ (1ULL << PERF_REG_X86_XMM10) | \
+ (1ULL << PERF_REG_X86_XMM11) | \
+ (1ULL << PERF_REG_X86_XMM12) | \
+ (1ULL << PERF_REG_X86_XMM13) | \
+ (1ULL << PERF_REG_X86_XMM14) | \
+ (1ULL << PERF_REG_X86_XMM15))
+
/*
* Per register state.
*/
@@ -612,7 +630,8 @@ struct x86_pmu {
pebs_broken :1,
pebs_prec_dist :1,
pebs_no_tlb :1,
- pebs_no_isolation :1;
+ pebs_no_isolation :1,
+ pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
void (*drain_pebs)(struct pt_regs *regs);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8bdf74902293..d9f5bbe44b3c 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -248,6 +248,11 @@ extern void perf_events_lapic_init(void);
#define PERF_EFLAGS_VM (1UL << 5)
struct pt_regs;
+struct x86_perf_regs {
+ struct pt_regs regs;
+ u64 *xmm_regs;
+};
+
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
extern unsigned long perf_misc_flags(struct pt_regs *regs);
#define perf_misc_flags(regs) perf_misc_flags(regs)
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,8 +27,29 @@ enum perf_event_x86_regs {
PERF_REG_X86_R13,
PERF_REG_X86_R14,
PERF_REG_X86_R15,
-
+ /* These are the limits for the GPRs. */
PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+ /* These all need two bits set because they are 128bit */
+ PERF_REG_X86_XMM0 = 32,
+ PERF_REG_X86_XMM1 = 34,
+ PERF_REG_X86_XMM2 = 36,
+ PERF_REG_X86_XMM3 = 38,
+ PERF_REG_X86_XMM4 = 40,
+ PERF_REG_X86_XMM5 = 42,
+ PERF_REG_X86_XMM6 = 44,
+ PERF_REG_X86_XMM7 = 46,
+ PERF_REG_X86_XMM8 = 48,
+ PERF_REG_X86_XMM9 = 50,
+ PERF_REG_X86_XMM10 = 52,
+ PERF_REG_X86_XMM11 = 54,
+ PERF_REG_X86_XMM12 = 56,
+ PERF_REG_X86_XMM13 = 58,
+ PERF_REG_X86_XMM14 = 60,
+ PERF_REG_X86_XMM15 = 62,
+
+ /* These include both GPRs and XMMX registers */
+ PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
};
#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index c06c4c16c6b6..07c30ee17425 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
u64 perf_reg_value(struct pt_regs *regs, int idx)
{
+ struct x86_perf_regs *perf_regs;
+
+ if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ if (!perf_regs->xmm_regs)
+ return 0;
+ return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+ }
+
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
return 0;
return regs_get_register(regs, pt_regs_offset[idx]);
}
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
-
#ifdef CONFIG_X86_32
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
+ (1ULL << PERF_REG_X86_R9) | \
+ (1ULL << PERF_REG_X86_R10) | \
+ (1ULL << PERF_REG_X86_R11) | \
+ (1ULL << PERF_REG_X86_R12) | \
+ (1ULL << PERF_REG_X86_R13) | \
+ (1ULL << PERF_REG_X86_R14) | \
+ (1ULL << PERF_REG_X86_R15))
+
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
@@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
int perf_reg_validate(u64 mask)
{
- if (!mask || mask & REG_RESERVED)
- return -EINVAL;
-
- if (mask & REG_NOSUPPORT)
+ if (!mask || (mask & REG_NOSUPPORT))
return -EINVAL;
return 0;
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 03/12] perf/x86/intel: Extract memory code PEBS parser for reuse
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
2019-04-02 19:44 ` [PATCH V5 01/12] perf/x86: Fix wrong PEBS_REGS kan.liang
2019-04-02 19:44 ` [PATCH V5 02/12] perf/x86: Support outputting XMM registers kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:35 ` [tip:perf/core] " tip-bot for Andi Kleen
2019-04-02 19:45 ` [PATCH V5 04/12] perf/x86/intel/ds: Extract code of event update in short period kan.liang
` (9 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Andi Kleen <ak@linux.intel.com>
Extract some code related to memory profiling from the PEBS record
parser into separate functions. It can be reused by the upcoming
adaptive PEBS parser. No functional changes.
Rename intel_hsw_weight to intel_get_tsx_weight, and
intel_hsw_transaction to intel_get_tsx_transaction. Because the input is
not the hsw pebs format anymore.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/ds.c | 63 ++++++++++++++++++++------------------
1 file changed, 34 insertions(+), 29 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f57e6cb7fd99..2f80b7e282ff 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1125,34 +1125,50 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
- if (pebs->tsx_tuning) {
- union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ if (tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = tsx_tuning };
return tsx.cycles_last_block;
}
return 0;
}
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
- u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+ u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
/* For RTM XABORTs also log the abort code from AX */
- if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
- txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
return txn;
}
+#define PERF_X86_EVENT_PEBS_HSW_PREC \
+ (PERF_X86_EVENT_PEBS_ST_HSW | \
+ PERF_X86_EVENT_PEBS_LD_HSW | \
+ PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+ u64 val = PERF_MEM_NA;
+ int fl = event->hw.flags;
+ bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+ if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+ val = load_latency_data(aux);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, aux);
+ else if (fst)
+ val = precise_store_data(aux);
+ return val;
+}
+
static void setup_pebs_sample_data(struct perf_event *event,
struct pt_regs *iregs, void *__pebs,
struct perf_sample_data *data,
struct pt_regs *regs)
{
-#define PERF_X86_EVENT_PEBS_HSW_PREC \
- (PERF_X86_EVENT_PEBS_ST_HSW | \
- PERF_X86_EVENT_PEBS_LD_HSW | \
- PERF_X86_EVENT_PEBS_NA_HSW)
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
@@ -1160,17 +1176,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
- int fll, fst, dsrc;
- int fl = event->hw.flags;
+ int fll;
if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
- dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
- fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
- fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
perf_sample_data_init(data, 0, event->hw.last_period);
@@ -1185,16 +1197,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
/*
* data.data_src encodes the data source
*/
- if (dsrc) {
- u64 val = PERF_MEM_NA;
- if (fll)
- val = load_latency_data(pebs->dse);
- else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
- val = precise_datala_hsw(event, pebs->dse);
- else if (fst)
- val = precise_store_data(pebs->dse);
- data->data_src.val = val;
- }
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, pebs->dse);
/*
* We must however always use iregs for the unwinder to stay sane; the
@@ -1281,10 +1285,11 @@ static void setup_pebs_sample_data(struct perf_event *event,
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data->weight = intel_hsw_weight(pebs);
+ data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data->txn = intel_hsw_transaction(pebs);
+ data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+ pebs->ax);
}
/*
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel: Extract memory code PEBS parser for reuse
2019-04-02 19:45 ` [PATCH V5 03/12] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
@ 2019-04-16 11:35 ` tip-bot for Andi Kleen
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Andi Kleen @ 2019-04-16 11:35 UTC (permalink / raw)
To: linux-tip-commits
Cc: peterz, acme, tglx, alexander.shishkin, torvalds, linux-kernel,
mingo, hpa, jolsa, vincent.weaver, ak, kan.liang, eranian
Commit-ID: 48f38aa4cc5a48bc0fe85c5c4b1ab171fbb539b6
Gitweb: https://git.kernel.org/tip/48f38aa4cc5a48bc0fe85c5c4b1ab171fbb539b6
Author: Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:00 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:19:39 +0200
perf/x86/intel: Extract memory code PEBS parser for reuse
Extract some code related to memory profiling from the PEBS record
parser into separate functions. It can be reused by the upcoming
adaptive PEBS parser. No functional changes.
Rename intel_hsw_weight to intel_get_tsx_weight, and
intel_hsw_transaction to intel_get_tsx_transaction. Because the input is
not the hsw pebs format anymore.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-4-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/ds.c | 63 +++++++++++++++++++++++++---------------------
1 file changed, 34 insertions(+), 29 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f57e6cb7fd99..2f80b7e282ff 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1125,34 +1125,50 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
{
- if (pebs->tsx_tuning) {
- union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ if (tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = tsx_tuning };
return tsx.cycles_last_block;
}
return 0;
}
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
{
- u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+ u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
/* For RTM XABORTs also log the abort code from AX */
- if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
- txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+ txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
return txn;
}
+#define PERF_X86_EVENT_PEBS_HSW_PREC \
+ (PERF_X86_EVENT_PEBS_ST_HSW | \
+ PERF_X86_EVENT_PEBS_LD_HSW | \
+ PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+ u64 val = PERF_MEM_NA;
+ int fl = event->hw.flags;
+ bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+ if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+ val = load_latency_data(aux);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, aux);
+ else if (fst)
+ val = precise_store_data(aux);
+ return val;
+}
+
static void setup_pebs_sample_data(struct perf_event *event,
struct pt_regs *iregs, void *__pebs,
struct perf_sample_data *data,
struct pt_regs *regs)
{
-#define PERF_X86_EVENT_PEBS_HSW_PREC \
- (PERF_X86_EVENT_PEBS_ST_HSW | \
- PERF_X86_EVENT_PEBS_LD_HSW | \
- PERF_X86_EVENT_PEBS_NA_HSW)
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
@@ -1160,17 +1176,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_skl *pebs = __pebs;
u64 sample_type;
- int fll, fst, dsrc;
- int fl = event->hw.flags;
+ int fll;
if (pebs == NULL)
return;
sample_type = event->attr.sample_type;
- dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
- fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
- fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+ fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
perf_sample_data_init(data, 0, event->hw.last_period);
@@ -1185,16 +1197,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
/*
* data.data_src encodes the data source
*/
- if (dsrc) {
- u64 val = PERF_MEM_NA;
- if (fll)
- val = load_latency_data(pebs->dse);
- else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
- val = precise_datala_hsw(event, pebs->dse);
- else if (fst)
- val = precise_store_data(pebs->dse);
- data->data_src.val = val;
- }
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, pebs->dse);
/*
* We must however always use iregs for the unwinder to stay sane; the
@@ -1281,10 +1285,11 @@ static void setup_pebs_sample_data(struct perf_event *event,
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
- data->weight = intel_hsw_weight(pebs);
+ data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
if (sample_type & PERF_SAMPLE_TRANSACTION)
- data->txn = intel_hsw_transaction(pebs);
+ data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+ pebs->ax);
}
/*
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 04/12] perf/x86/intel/ds: Extract code of event update in short period
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (2 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 03/12] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:35 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 05/12] perf/x86/intel: Support adaptive PEBSv4 kan.liang
` (8 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
The drain_pebs() could be called twice in a short period for auto-reload
event in pmu::read(). The intel_pmu_save_and_restart_reload() should be
called to update the event->count.
This case should also be handled on Icelake. Extract the codes for reuse
later.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/ds.c | 34 +++++++++++++++++++++-------------
1 file changed, 21 insertions(+), 13 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2f80b7e282ff..d8881bb67d4e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1491,6 +1491,26 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
}
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc,
+ int size)
+{
+ struct perf_event *event;
+ int bit;
+
+ /*
+ * The drain_pebs() could be called twice in a short period
+ * for auto-reload event in pmu::read(). There are no
+ * overflows have happened in between.
+ * It needs to call intel_pmu_save_and_restart_reload() to
+ * update the event->count for this case.
+ */
+ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+ event = cpuc->events[bit];
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
+ }
+}
+
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1518,19 +1538,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
}
if (unlikely(base >= top)) {
- /*
- * The drain_pebs() could be called twice in a short period
- * for auto-reload event in pmu::read(). There are no
- * overflows have happened in between.
- * It needs to call intel_pmu_save_and_restart_reload() to
- * update the event->count for this case.
- */
- for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- size) {
- event = cpuc->events[bit];
- if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
- intel_pmu_save_and_restart_reload(event, 0);
- }
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
return;
}
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel/ds: Extract code of event update in short period
2019-04-02 19:45 ` [PATCH V5 04/12] perf/x86/intel/ds: Extract code of event update in short period kan.liang
@ 2019-04-16 11:35 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:35 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, tglx, mingo, kan.liang, jolsa, torvalds, peterz,
linux-kernel, hpa, vincent.weaver, alexander.shishkin, acme
Commit-ID: 477f00f9617009a9a3a9271885231573b728ca4f
Gitweb: https://git.kernel.org/tip/477f00f9617009a9a3a9271885231573b728ca4f
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:01 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:19:39 +0200
perf/x86/intel/ds: Extract code of event update in short period
The drain_pebs() could be called twice in a short period for auto-reload
event in pmu::read(). The intel_pmu_save_and_restart_reload() should be
called to update the event->count.
This case should also be handled on Icelake. Extract the code for
later reuse.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-5-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/ds.c | 33 ++++++++++++++++++++-------------
1 file changed, 20 insertions(+), 13 deletions(-)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2f80b7e282ff..9ac73860645d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1491,6 +1491,25 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
}
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+{
+ struct perf_event *event;
+ int bit;
+
+ /*
+ * The drain_pebs() could be called twice in a short period
+ * for auto-reload event in pmu::read(). There are no
+ * overflows have happened in between.
+ * It needs to call intel_pmu_save_and_restart_reload() to
+ * update the event->count for this case.
+ */
+ for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+ event = cpuc->events[bit];
+ if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+ intel_pmu_save_and_restart_reload(event, 0);
+ }
+}
+
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1518,19 +1537,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
}
if (unlikely(base >= top)) {
- /*
- * The drain_pebs() could be called twice in a short period
- * for auto-reload event in pmu::read(). There are no
- * overflows have happened in between.
- * It needs to call intel_pmu_save_and_restart_reload() to
- * update the event->count for this case.
- */
- for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
- size) {
- event = cpuc->events[bit];
- if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
- intel_pmu_save_and_restart_reload(event, 0);
- }
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
return;
}
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 05/12] perf/x86/intel: Support adaptive PEBSv4
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (3 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 04/12] perf/x86/intel/ds: Extract code of event update in short period kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-08 14:55 ` Peter Zijlstra
2019-04-16 11:36 ` [tip:perf/core] perf/x86/intel: Support adaptive PEBS v4 tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 06/12] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
` (7 subsequent siblings)
12 siblings, 2 replies; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Adaptive PEBS is a new way to report PEBS sampling information. Instead
of a fixed size record for all PEBS events it allows to configure the
PEBS record to only include the information needed. Events can then opt
in to use such an extended record, or stay with a basic record which
only contains the IP.
The major new feature is to support LBRs in PEBS record.
Besides normal LBR, this allows (much faster) large PEBS, while still
supporting callstacks through callstack LBR. So essentially a lot of
profiling can now be done without frequent interrupts, dropping the
overhead significantly.
The main requirement still is to use a period, and not use frequency
mode, because frequency mode requires reevaluating the frequency on each
overflow.
The floating point state (XMM) is also supported, which allows efficient
profiling of FP function arguments.
Introduce specific drain function to handle variable length records.
Use a new callback to parse the new record format, and also handle the
STATUS field now being at a different offset.
Add code to set up the configuration register. Since there is only a
single register, all events either get the full super set of all events,
or only the basic record.
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
Changes since V4:
- set pebs_no_xmm_regs to true if only basic record supported
arch/x86/events/intel/core.c | 2 +
arch/x86/events/intel/ds.c | 374 ++++++++++++++++++++++++++++--
arch/x86/events/intel/lbr.c | 22 ++
arch/x86/events/perf_event.h | 9 +
arch/x86/include/asm/msr-index.h | 1 +
arch/x86/include/asm/perf_event.h | 42 ++++
6 files changed, 430 insertions(+), 20 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a9721457f187..ad03cc78a229 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3507,6 +3507,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
+ cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index d8881bb67d4e..5ca681cacc4f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -906,17 +906,85 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- reserved * x86_pmu.pebs_record_size;
+ reserved * cpuc->pebs_record_size;
} else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
}
ds->pebs_interrupt_threshold = threshold;
}
+static void adaptive_pebs_record_size_update(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+ int sz = sizeof(struct pebs_basic);
+
+ if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+ sz += sizeof(struct pebs_meminfo);
+ if (pebs_data_cfg & PEBS_DATACFG_GPRS)
+ sz += sizeof(struct pebs_gprs);
+ if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+ sz += sizeof(struct pebs_xmm);
+ if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+ sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+ cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \
+ PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+ PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ u64 sample_type = attr->sample_type;
+ u64 pebs_data_cfg = 0;
+ bool gprs, tsx_weight;
+
+ if ((sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) ||
+ attr->precise_ip < 2) {
+
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+ /*
+ * Cases we need the registers:
+ * + user requested registers
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs too for the abort
+ * code. But we don't want to force GPRs for all other
+ * weights. So add it only collectfor the RTM abort event.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & 0xffffffff);
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & 0xffff) == x86_pmu.force_gpr_event);
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GPRS;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr >> 32))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ /*
+ * For now always log all LBRs. Could configure this
+ * later.
+ */
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+ }
+ }
+ return pebs_data_cfg;
+}
+
static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+ struct perf_event *event, bool add)
{
+ struct pmu *pmu = event->ctx->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
@@ -933,6 +1001,34 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
update = true;
}
+ /*
+ * The PEBS record doesn't shrink on the del. Because to get
+ * an accurate config needs to go through all the existing pebs events.
+ * It's not necessary.
+ * There is no harmful for a bigger PEBS record, except little
+ * performance impacts.
+ * Also, for most cases, the same pebs config is applied for all
+ * pebs events.
+ */
+ if (x86_pmu.intel_cap.pebs_baseline && add) {
+ u64 pebs_data_cfg;
+
+ /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+ if (cpuc->n_pebs == 1) {
+ cpuc->pebs_data_cfg = 0;
+ cpuc->pebs_record_size = sizeof(struct pebs_basic);
+ }
+
+ pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+ /* Update pebs_record_size if new event requires more data. */
+ if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+ cpuc->pebs_data_cfg |= pebs_data_cfg;
+ adaptive_pebs_record_size_update();
+ update = true;
+ }
+ }
+
if (update)
pebs_update_threshold(cpuc);
}
@@ -947,7 +1043,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, true);
}
void intel_pmu_pebs_enable(struct perf_event *event)
@@ -965,6 +1061,14 @@ void intel_pmu_pebs_enable(struct perf_event *event)
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+ if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+ wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+ cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+ }
+ }
+
/*
* Use auto-reload if possible to save a MSR write in the PMI.
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -991,7 +1095,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, false);
}
void intel_pmu_pebs_disable(struct perf_event *event)
@@ -1144,6 +1248,13 @@ static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
return txn;
}
+static inline u64 get_pebs_status(void *n)
+{
+ if (x86_pmu.intel_cap.pebs_format < 4)
+ return ((struct pebs_record_nhm *)n)->status;
+ return ((struct pebs_basic *)n)->applicable_counters;
+}
+
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
PERF_X86_EVENT_PEBS_LD_HSW | \
@@ -1164,7 +1275,7 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
return val;
}
-static void setup_pebs_sample_data(struct perf_event *event,
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
struct pt_regs *iregs, void *__pebs,
struct perf_sample_data *data,
struct pt_regs *regs)
@@ -1306,6 +1417,140 @@ static void setup_pebs_sample_data(struct perf_event *event,
data->br_stack = &cpuc->lbr_stack;
}
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+ struct pebs_gprs *gprs)
+{
+ regs->ax = gprs->ax;
+ regs->bx = gprs->bx;
+ regs->cx = gprs->cx;
+ regs->dx = gprs->dx;
+ regs->si = gprs->si;
+ regs->di = gprs->di;
+ regs->bp = gprs->bp;
+ regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+ regs->r8 = gprs->r8;
+ regs->r9 = gprs->r9;
+ regs->r10 = gprs->r10;
+ regs->r11 = gprs->r11;
+ regs->r12 = gprs->r12;
+ regs->r13 = gprs->r13;
+ regs->r14 = gprs->r14;
+ regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ 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;
+ struct pebs_meminfo *meminfo = NULL;
+ struct pebs_gprs *gprs = NULL;
+ struct x86_perf_regs *perf_regs;
+
+ if (basic == NULL)
+ return;
+
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ perf_regs->xmm_regs = NULL;
+
+ sample_type = event->attr.sample_type;
+ format_size = basic->format_size;
+ perf_sample_data_init(data, 0, event->hw.last_period);
+ data->period = event->hw.last_period;
+
+ if (event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(basic->tsc);
+
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happened between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ *regs = *iregs;
+ /* The ip in basic is EventingIP */
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+ /*
+ * The record for MEMINFO is in front of GPRS
+ * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+ * Save the pointer here but process later.
+ */
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ meminfo = next_record;
+ next_record = meminfo + 1;
+ }
+
+ if (format_size & PEBS_DATACFG_GPRS) {
+ gprs = next_record;
+ next_record = gprs + 1;
+
+ if (event->attr.precise_ip < 2) {
+ set_linear_ip(regs, gprs->ip);
+ regs->flags &= ~PERF_EFLAGS_EXACT;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR)
+ adaptive_pebs_save_regs(regs, gprs);
+ }
+
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ data->weight = meminfo->latency ?:
+ intel_get_tsx_weight(meminfo->tsx_tuning);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, meminfo->aux);
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+ data->addr = meminfo->address;
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+ gprs ? gprs->ax : 0);
+ }
+
+ if (format_size & 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) {
+ struct pebs_lbr *lbr = next_record;
+ int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ & 0xff) + 1;
+ next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+ if (has_branch_stack(event)) {
+ intel_pmu_store_pebs_lbrs(lbr);
+ data->br_stack = &cpuc->lbr_stack;
+ }
+ }
+
+ WARN_ONCE(next_record != __pebs + (format_size >> 48),
+ "PEBS record size %llu, expected %llu, config %llx\n",
+ format_size >> 48,
+ (u64)(next_record - __pebs),
+ basic->format_size);
+}
+
static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
@@ -1323,19 +1568,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
if (base == NULL)
return NULL;
- for (at = base; at < top; at += x86_pmu.pebs_record_size) {
- struct pebs_record_nhm *p = at;
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ unsigned long status = get_pebs_status(at);
- if (test_bit(bit, (unsigned long *)&p->status)) {
+ if (test_bit(bit, (unsigned long *)&status)) {
/* PEBS v3 has accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3)
return at;
- if (p->status == (1 << bit))
+ if (status == (1 << bit))
return at;
/* clear non-PEBS bit and re-check */
- pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status = status & cpuc->pebs_enabled;
pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
@@ -1415,11 +1660,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
- int bit, int count)
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
- struct pt_regs regs;
+ struct x86_perf_regs perf_regs;
+ struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1434,20 +1686,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
return;
while (count > 1) {
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
- perf_event_output(event, &data, ®s);
- at += x86_pmu.pebs_record_size;
+ setup_sample(event, iregs, at, &data, regs);
+ perf_event_output(event, &data, regs);
+ at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
+ setup_sample(event, iregs, at, &data, regs);
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, ®s)) {
+ if (perf_event_overflow(event, &data, regs)) {
x86_pmu_stop(event, 0);
return;
}
@@ -1488,7 +1740,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ setup_pebs_fixed_sample_data);
}
static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc,
@@ -1621,11 +1874,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
- top, bit, counts[bit]);
+ top, bit, counts[bit],
+ setup_pebs_fixed_sample_data);
}
}
}
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+ int bit, size;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+ return;
+
+ base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+ (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+ if (unlikely(base >= top)) {
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ return;
+ }
+
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ u64 pebs_status;
+
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ counts[bit]++;
+ }
+
+ for (bit = 0; bit < size; bit++) {
+ if (counts[bit] == 0)
+ continue;
+
+ event = cpuc->events[bit];
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
+
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit],
+ setup_pebs_adaptive_sample_data);
+ }
+}
+
/*
* BTS, PEBS probe and setup
*/
@@ -1647,6 +1955,7 @@ void __init intel_ds_init(void)
}
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
switch (format) {
@@ -1684,10 +1993,35 @@ void __init intel_ds_init(void)
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 4:
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+ x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ x86_pmu.large_pebs_flags |=
+ PERF_SAMPLE_BRANCH_STACK |
+ PERF_SAMPLE_TIME;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ pebs_qual = "-baseline";
+ } else {
+ /* Only basic record supported */
+ x86_pmu.pebs_no_xmm_regs = 1;
+ x86_pmu.large_pebs_flags &=
+ ~(PERF_SAMPLE_ADDR |
+ PERF_SAMPLE_TIME |
+ PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_TRANSACTION |
+ PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_REGS_INTR);
+ }
+ pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+ break;
+
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
}
+ if (format != 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
}
}
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 580c1b91c454..07b7175fc378 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1080,6 +1080,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
}
}
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int i;
+
+ cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ u64 info = lbr->lbr[i].info;
+ struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+ e->from = lbr->lbr[i].from;
+ e->to = lbr->lbr[i].to;
+ e->mispred = !!(info & LBR_INFO_MISPRED);
+ e->predicted = !(info & LBR_INFO_MISPRED);
+ e->in_tx = !!(info & LBR_INFO_IN_TX);
+ e->abort = !!(info & LBR_INFO_ABORT);
+ e->cycles = info & LBR_INFO_CYCLES;
+ e->reserved = 0;
+ }
+ intel_pmu_lbr_filter(cpuc);
+}
+
/*
* Map interface branch filters onto LBR filters
*/
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index cee4ad018a0e..d95014f88ef7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -225,6 +225,11 @@ struct cpu_hw_events {
int n_pebs;
int n_large_pebs;
+ /* Current super set of events hardware configuration */
+ u64 pebs_data_cfg;
+ u64 active_pebs_data_cfg;
+ int pebs_record_size;
+
/*
* Intel LBR bits
*/
@@ -491,6 +496,7 @@ union perf_capabilities {
* values > 32bit.
*/
u64 full_width_write:1;
+ u64 pebs_baseline:1;
};
u64 capabilities;
};
@@ -640,6 +646,7 @@ struct x86_pmu {
void (*pebs_aliases)(struct perf_event *event);
int max_pebs_events;
unsigned long large_pebs_flags;
+ u64 force_gpr_event;
/*
* Intel LBR
@@ -978,6 +985,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ca5bc0eacb95..1378518cf63f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -116,6 +116,7 @@
#define LBR_INFO_CYCLES 0xffff
#define MSR_IA32_PEBS_ENABLE 0x000003f1
+#define MSR_PEBS_DATA_CFG 0x000003f2
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index d9f5bbe44b3c..fd0ec2699213 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -32,6 +32,7 @@
#define HSW_IN_TX (1ULL << 32)
#define HSW_IN_TX_CHECKPOINTED (1ULL << 33)
+#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34)
#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40)
@@ -87,6 +88,12 @@
#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
#define ARCH_PERFMON_EVENTS_COUNT 7
+#define PEBS_DATACFG_MEMINFO BIT_ULL(0)
+#define PEBS_DATACFG_GPRS BIT_ULL(1)
+#define PEBS_DATACFG_XMMS BIT_ULL(2)
+#define PEBS_DATACFG_LBRS BIT_ULL(3)
+#define PEBS_DATACFG_LBR_SHIFT 24
+
/*
* Intel "Architectural Performance Monitoring" CPUID
* detection/enumeration details:
@@ -176,6 +183,41 @@ struct x86_pmu_capability {
#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58)
#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
+/*
+ * Adaptive PEBS v4
+ */
+
+struct pebs_basic {
+ u64 format_size;
+ u64 ip;
+ u64 applicable_counters;
+ u64 tsc;
+};
+
+struct pebs_meminfo {
+ u64 address;
+ u64 aux;
+ u64 latency;
+ u64 tsx_tuning;
+};
+
+struct pebs_gprs {
+ u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+ u64 r8, r9, r10, r11, r12, r13, r14, r15;
+};
+
+struct pebs_xmm {
+ u64 xmm[16*2]; /* two entries for each register */
+};
+
+struct pebs_lbr_entry {
+ u64 from, to, info;
+};
+
+struct pebs_lbr {
+ struct pebs_lbr_entry lbr[0]; /* Variable length */
+};
+
/*
* IBS cpuid feature detection
*/
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* Re: [PATCH V5 05/12] perf/x86/intel: Support adaptive PEBSv4
2019-04-02 19:45 ` [PATCH V5 05/12] perf/x86/intel: Support adaptive PEBSv4 kan.liang
@ 2019-04-08 14:55 ` Peter Zijlstra
2019-04-16 11:36 ` [tip:perf/core] perf/x86/intel: Support adaptive PEBS v4 tip-bot for Kan Liang
1 sibling, 0 replies; 37+ messages in thread
From: Peter Zijlstra @ 2019-04-08 14:55 UTC (permalink / raw)
To: kan.liang
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On Tue, Apr 02, 2019 at 12:45:02PM -0700, kan.liang@linux.intel.com wrote:
> +static u64 pebs_update_adaptive_cfg(struct perf_event *event)
> +{
> + struct perf_event_attr *attr = &event->attr;
> + u64 sample_type = attr->sample_type;
> + u64 pebs_data_cfg = 0;
> + bool gprs, tsx_weight;
> +
> + if ((sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) ||
> + attr->precise_ip < 2) {
> +
> + if (sample_type & PERF_PEBS_MEMINFO_TYPE)
> + pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
> +
> + /*
> + * Cases we need the registers:
> + * + user requested registers
> + * + precise_ip < 2 for the non event IP
> + * + For RTM TSX weight we need GPRs too for the abort
> + * code. But we don't want to force GPRs for all other
> + * weights. So add it only collectfor the RTM abort event.
> + */
> + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
> + (attr->sample_regs_intr & 0xffffffff);
did that want to be:
(attr->sample_regs_intr & PEBS_GPRS_REGS);
?
> + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
> + ((attr->config & 0xffff) == x86_pmu.force_gpr_event);
Why does that force_gpr_event exist? and why isn't it called
rtm_abort_event?
Also did that want to be:
(attr->config & INTEL_ARCH_EVENT_MASK)
?
> + if (gprs || (attr->precise_ip < 2) || tsx_weight)
> + pebs_data_cfg |= PEBS_DATACFG_GPRS;
> +
> + if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
> + (attr->sample_regs_intr >> 32))
Surely, you meant:
(attr->sample_regs_intr & PEBS_XMM_REGS)
?
> + pebs_data_cfg |= PEBS_DATACFG_XMMS;
> +
> + if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
> + /*
> + * For now always log all LBRs. Could configure this
> + * later.
> + */
> + pebs_data_cfg |= PEBS_DATACFG_LBRS |
> + ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
> + }
> + }
> + return pebs_data_cfg;
> +}
^ permalink raw reply [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel: Support adaptive PEBS v4
2019-04-02 19:45 ` [PATCH V5 05/12] perf/x86/intel: Support adaptive PEBSv4 kan.liang
2019-04-08 14:55 ` Peter Zijlstra
@ 2019-04-16 11:36 ` tip-bot for Kan Liang
1 sibling, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:36 UTC (permalink / raw)
To: linux-tip-commits
Cc: mingo, alexander.shishkin, jolsa, peterz, kan.liang, hpa,
vincent.weaver, linux-kernel, ak, tglx, torvalds, eranian, acme
Commit-ID: c22497f5838c237e3094a4dfb99d1c5de6353239
Gitweb: https://git.kernel.org/tip/c22497f5838c237e3094a4dfb99d1c5de6353239
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:02 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:25:47 +0200
perf/x86/intel: Support adaptive PEBS v4
Adaptive PEBS is a new way to report PEBS sampling information. Instead
of a fixed size record for all PEBS events it allows to configure the
PEBS record to only include the information needed. Events can then opt
in to use such an extended record, or stay with a basic record which
only contains the IP.
The major new feature is to support LBRs in PEBS record.
Besides normal LBR, this allows (much faster) large PEBS, while still
supporting callstacks through callstack LBR. So essentially a lot of
profiling can now be done without frequent interrupts, dropping the
overhead significantly.
The main requirement still is to use a period, and not use frequency
mode, because frequency mode requires reevaluating the frequency on each
overflow.
The floating point state (XMM) is also supported, which allows efficient
profiling of FP function arguments.
Introduce specific drain function to handle variable length records.
Use a new callback to parse the new record format, and also handle the
STATUS field now being at a different offset.
Add code to set up the configuration register. Since there is only a
single register, all events either get the full super set of all events,
or only the basic record.
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-6-kan.liang@linux.intel.com
[ Renamed GPRS => GP. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/core.c | 7 +
arch/x86/events/intel/ds.c | 380 +++++++++++++++++++++++++++++++++++---
arch/x86/events/intel/lbr.c | 22 +++
arch/x86/events/perf_event.h | 11 +-
arch/x86/include/asm/msr-index.h | 1 +
arch/x86/include/asm/perf_event.h | 43 +++++
6 files changed, 438 insertions(+), 26 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8265b5026a19..bdc366d709aa 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2145,6 +2145,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+ bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+ }
+
rdmsrl(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
@@ -3510,6 +3515,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
{
+ cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
cpuc->shared_regs = allocate_shared_regs(cpu);
if (!cpuc->shared_regs)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 9ac73860645d..6436452d6342 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -906,17 +906,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
if (cpuc->n_pebs == cpuc->n_large_pebs) {
threshold = ds->pebs_absolute_maximum -
- reserved * x86_pmu.pebs_record_size;
+ reserved * cpuc->pebs_record_size;
} else {
- threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+ threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
}
ds->pebs_interrupt_threshold = threshold;
}
+static void adaptive_pebs_record_size_update(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+ int sz = sizeof(struct pebs_basic);
+
+ if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+ sz += sizeof(struct pebs_meminfo);
+ if (pebs_data_cfg & PEBS_DATACFG_GP)
+ sz += sizeof(struct pebs_gprs);
+ if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+ sz += sizeof(struct pebs_xmm);
+ if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+ sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+ cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \
+ PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+ PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+ struct perf_event_attr *attr = &event->attr;
+ u64 sample_type = attr->sample_type;
+ u64 pebs_data_cfg = 0;
+ bool gprs, tsx_weight;
+
+ if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+ attr->precise_ip > 1)
+ return pebs_data_cfg;
+
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+ /*
+ * We need GPRs when:
+ * + user requested them
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs for the abort code.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GP_REGS);
+
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+ x86_pmu.rtm_abort_event);
+
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GP;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_XMM_REGS))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ /*
+ * For now always log all LBRs. Could configure this
+ * later.
+ */
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+ }
+
+ return pebs_data_cfg;
+}
+
static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+ struct perf_event *event, bool add)
{
+ struct pmu *pmu = event->ctx->pmu;
/*
* Make sure we get updated with the first PEBS
* event. It will trigger also during removal, but
@@ -933,6 +1003,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
update = true;
}
+ /*
+ * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+ * iterating all remaining PEBS events to reconstruct the config.
+ */
+ if (x86_pmu.intel_cap.pebs_baseline && add) {
+ u64 pebs_data_cfg;
+
+ /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+ if (cpuc->n_pebs == 1) {
+ cpuc->pebs_data_cfg = 0;
+ cpuc->pebs_record_size = sizeof(struct pebs_basic);
+ }
+
+ pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+ /* Update pebs_record_size if new event requires more data. */
+ if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+ cpuc->pebs_data_cfg |= pebs_data_cfg;
+ adaptive_pebs_record_size_update();
+ update = true;
+ }
+ }
+
if (update)
pebs_update_threshold(cpuc);
}
@@ -947,7 +1040,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs++;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, true);
}
void intel_pmu_pebs_enable(struct perf_event *event)
@@ -965,6 +1058,14 @@ void intel_pmu_pebs_enable(struct perf_event *event)
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+ if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+ wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+ cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+ }
+ }
+
/*
* Use auto-reload if possible to save a MSR write in the PMI.
* This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -991,7 +1092,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
cpuc->n_large_pebs--;
- pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+ pebs_update_state(needed_cb, cpuc, event, false);
}
void intel_pmu_pebs_disable(struct perf_event *event)
@@ -1144,6 +1245,13 @@ static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
return txn;
}
+static inline u64 get_pebs_status(void *n)
+{
+ if (x86_pmu.intel_cap.pebs_format < 4)
+ return ((struct pebs_record_nhm *)n)->status;
+ return ((struct pebs_basic *)n)->applicable_counters;
+}
+
#define PERF_X86_EVENT_PEBS_HSW_PREC \
(PERF_X86_EVENT_PEBS_ST_HSW | \
PERF_X86_EVENT_PEBS_LD_HSW | \
@@ -1164,7 +1272,7 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
return val;
}
-static void setup_pebs_sample_data(struct perf_event *event,
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
struct pt_regs *iregs, void *__pebs,
struct perf_sample_data *data,
struct pt_regs *regs)
@@ -1306,6 +1414,140 @@ static void setup_pebs_sample_data(struct perf_event *event,
data->br_stack = &cpuc->lbr_stack;
}
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+ struct pebs_gprs *gprs)
+{
+ regs->ax = gprs->ax;
+ regs->bx = gprs->bx;
+ regs->cx = gprs->cx;
+ regs->dx = gprs->dx;
+ regs->si = gprs->si;
+ regs->di = gprs->di;
+ regs->bp = gprs->bp;
+ regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+ regs->r8 = gprs->r8;
+ regs->r9 = gprs->r9;
+ regs->r10 = gprs->r10;
+ regs->r11 = gprs->r11;
+ regs->r12 = gprs->r12;
+ regs->r13 = gprs->r13;
+ regs->r14 = gprs->r14;
+ regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ struct pt_regs *iregs, void *__pebs,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ 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;
+ struct pebs_meminfo *meminfo = NULL;
+ struct pebs_gprs *gprs = NULL;
+ struct x86_perf_regs *perf_regs;
+
+ if (basic == NULL)
+ return;
+
+ perf_regs = container_of(regs, struct x86_perf_regs, regs);
+ perf_regs->xmm_regs = NULL;
+
+ sample_type = event->attr.sample_type;
+ format_size = basic->format_size;
+ perf_sample_data_init(data, 0, event->hw.last_period);
+ data->period = event->hw.last_period;
+
+ if (event->attr.use_clockid == 0)
+ data->time = native_sched_clock_from_tsc(basic->tsc);
+
+ /*
+ * We must however always use iregs for the unwinder to stay sane; the
+ * record BP,SP,IP can point into thin air when the record is from a
+ * previous PMI context or an (I)RET happened between the record and
+ * PMI.
+ */
+ if (sample_type & PERF_SAMPLE_CALLCHAIN)
+ data->callchain = perf_callchain(event, iregs);
+
+ *regs = *iregs;
+ /* The ip in basic is EventingIP */
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+ /*
+ * The record for MEMINFO is in front of GP
+ * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+ * Save the pointer here but process later.
+ */
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ meminfo = next_record;
+ next_record = meminfo + 1;
+ }
+
+ if (format_size & PEBS_DATACFG_GP) {
+ gprs = next_record;
+ next_record = gprs + 1;
+
+ if (event->attr.precise_ip < 2) {
+ set_linear_ip(regs, gprs->ip);
+ regs->flags &= ~PERF_EFLAGS_EXACT;
+ }
+
+ if (sample_type & PERF_SAMPLE_REGS_INTR)
+ adaptive_pebs_save_regs(regs, gprs);
+ }
+
+ if (format_size & PEBS_DATACFG_MEMINFO) {
+ if (sample_type & PERF_SAMPLE_WEIGHT)
+ data->weight = meminfo->latency ?:
+ intel_get_tsx_weight(meminfo->tsx_tuning);
+
+ if (sample_type & PERF_SAMPLE_DATA_SRC)
+ data->data_src.val = get_data_src(event, meminfo->aux);
+
+ if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+ data->addr = meminfo->address;
+
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
+ data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+ gprs ? gprs->ax : 0);
+ }
+
+ if (format_size & 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) {
+ struct pebs_lbr *lbr = next_record;
+ int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+ & 0xff) + 1;
+ next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+ if (has_branch_stack(event)) {
+ intel_pmu_store_pebs_lbrs(lbr);
+ data->br_stack = &cpuc->lbr_stack;
+ }
+ }
+
+ WARN_ONCE(next_record != __pebs + (format_size >> 48),
+ "PEBS record size %llu, expected %llu, config %llx\n",
+ format_size >> 48,
+ (u64)(next_record - __pebs),
+ basic->format_size);
+}
+
static inline void *
get_next_pebs_record_by_bit(void *base, void *top, int bit)
{
@@ -1323,19 +1565,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
if (base == NULL)
return NULL;
- for (at = base; at < top; at += x86_pmu.pebs_record_size) {
- struct pebs_record_nhm *p = at;
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ unsigned long status = get_pebs_status(at);
- if (test_bit(bit, (unsigned long *)&p->status)) {
+ if (test_bit(bit, (unsigned long *)&status)) {
/* PEBS v3 has accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3)
return at;
- if (p->status == (1 << bit))
+ if (status == (1 << bit))
return at;
/* clear non-PEBS bit and re-check */
- pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status = status & cpuc->pebs_enabled;
pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
@@ -1415,11 +1657,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs,
void *base, void *top,
- int bit, int count)
+ int bit, int count,
+ void (*setup_sample)(struct perf_event *,
+ struct pt_regs *,
+ void *,
+ struct perf_sample_data *,
+ struct pt_regs *))
{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
struct perf_sample_data data;
- struct pt_regs regs;
+ struct x86_perf_regs perf_regs;
+ struct pt_regs *regs = &perf_regs.regs;
void *at = get_next_pebs_record_by_bit(base, top, bit);
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1434,20 +1683,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
return;
while (count > 1) {
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
- perf_event_output(event, &data, ®s);
- at += x86_pmu.pebs_record_size;
+ setup_sample(event, iregs, at, &data, regs);
+ perf_event_output(event, &data, regs);
+ at += cpuc->pebs_record_size;
at = get_next_pebs_record_by_bit(at, top, bit);
count--;
}
- setup_pebs_sample_data(event, iregs, at, &data, ®s);
+ setup_sample(event, iregs, at, &data, regs);
/*
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, &data, ®s)) {
+ if (perf_event_overflow(event, &data, regs)) {
x86_pmu_stop(event, 0);
return;
}
@@ -1488,7 +1737,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
return;
}
- __intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+ __intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+ setup_pebs_fixed_sample_data);
}
static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
@@ -1550,8 +1800,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&pebs_status,
- size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
counts[bit]++;
continue;
@@ -1590,8 +1839,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* If collision happened, the record will be dropped.
*/
if (p->status != (1ULL << bit)) {
- for_each_set_bit(i, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
}
@@ -1599,7 +1847,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
@@ -1620,11 +1868,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
if (counts[bit]) {
__intel_pmu_pebs_event(event, iregs, base,
- top, bit, counts[bit]);
+ top, bit, counts[bit],
+ setup_pebs_fixed_sample_data);
}
}
}
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+ int bit, size;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+ return;
+
+ base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+ mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+ (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+ size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+ if (unlikely(base >= top)) {
+ intel_pmu_pebs_event_update_no_drain(cpuc, size);
+ return;
+ }
+
+ for (at = base; at < top; at += cpuc->pebs_record_size) {
+ u64 pebs_status;
+
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+ counts[bit]++;
+ }
+
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
+ if (counts[bit] == 0)
+ continue;
+
+ event = cpuc->events[bit];
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
+
+ __intel_pmu_pebs_event(event, iregs, base,
+ top, bit, counts[bit],
+ setup_pebs_adaptive_sample_data);
+ }
+}
+
/*
* BTS, PEBS probe and setup
*/
@@ -1646,8 +1949,12 @@ void __init intel_ds_init(void)
}
if (x86_pmu.pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
+ char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
+ if (format < 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -1683,6 +1990,29 @@ void __init intel_ds_init(void)
x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
break;
+ case 4:
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+ x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+ if (x86_pmu.intel_cap.pebs_baseline) {
+ x86_pmu.large_pebs_flags |=
+ PERF_SAMPLE_BRANCH_STACK |
+ PERF_SAMPLE_TIME;
+ x86_pmu.flags |= PMU_FL_PEBS_ALL;
+ pebs_qual = "-baseline";
+ } else {
+ /* Only basic record supported */
+ x86_pmu.pebs_no_xmm_regs = 1;
+ x86_pmu.large_pebs_flags &=
+ ~(PERF_SAMPLE_ADDR |
+ PERF_SAMPLE_TIME |
+ PERF_SAMPLE_DATA_SRC |
+ PERF_SAMPLE_TRANSACTION |
+ PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_REGS_INTR);
+ }
+ pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+ break;
+
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 580c1b91c454..07b7175fc378 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1080,6 +1080,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
}
}
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int i;
+
+ cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ u64 info = lbr->lbr[i].info;
+ struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+ e->from = lbr->lbr[i].from;
+ e->to = lbr->lbr[i].to;
+ e->mispred = !!(info & LBR_INFO_MISPRED);
+ e->predicted = !(info & LBR_INFO_MISPRED);
+ e->in_tx = !!(info & LBR_INFO_IN_TX);
+ e->abort = !!(info & LBR_INFO_ABORT);
+ e->cycles = info & LBR_INFO_CYCLES;
+ e->reserved = 0;
+ }
+ intel_pmu_lbr_filter(cpuc);
+}
+
/*
* Map interface branch filters onto LBR filters
*/
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 7abfadb4f202..2059c143946f 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -224,6 +224,11 @@ struct cpu_hw_events {
int n_pebs;
int n_large_pebs;
+ /* Current super set of events hardware configuration */
+ u64 pebs_data_cfg;
+ u64 active_pebs_data_cfg;
+ int pebs_record_size;
+
/*
* Intel LBR bits
*/
@@ -490,6 +495,7 @@ union perf_capabilities {
* values > 32bit.
*/
u64 full_width_write:1;
+ u64 pebs_baseline:1;
};
u64 capabilities;
};
@@ -634,11 +640,12 @@ struct x86_pmu {
pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
+ int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
- int max_pebs_events;
unsigned long large_pebs_flags;
+ u64 rtm_abort_event;
/*
* Intel LBR
@@ -978,6 +985,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
void intel_ds_init(void);
void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ca5bc0eacb95..1378518cf63f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -116,6 +116,7 @@
#define LBR_INFO_CYCLES 0xffff
#define MSR_IA32_PEBS_ENABLE 0x000003f1
+#define MSR_PEBS_DATA_CFG 0x000003f2
#define MSR_IA32_DS_AREA 0x00000600
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index d9f5bbe44b3c..997a6587d7cf 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -32,6 +32,8 @@
#define HSW_IN_TX (1ULL << 32)
#define HSW_IN_TX_CHECKPOINTED (1ULL << 33)
+#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34)
+#define ICL_FIXED_0_ADAPTIVE (1ULL << 32)
#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36)
#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40)
@@ -87,6 +89,12 @@
#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
#define ARCH_PERFMON_EVENTS_COUNT 7
+#define PEBS_DATACFG_MEMINFO BIT_ULL(0)
+#define PEBS_DATACFG_GP BIT_ULL(1)
+#define PEBS_DATACFG_XMMS BIT_ULL(2)
+#define PEBS_DATACFG_LBRS BIT_ULL(3)
+#define PEBS_DATACFG_LBR_SHIFT 24
+
/*
* Intel "Architectural Performance Monitoring" CPUID
* detection/enumeration details:
@@ -176,6 +184,41 @@ struct x86_pmu_capability {
#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58)
#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55)
+/*
+ * Adaptive PEBS v4
+ */
+
+struct pebs_basic {
+ u64 format_size;
+ u64 ip;
+ u64 applicable_counters;
+ u64 tsc;
+};
+
+struct pebs_meminfo {
+ u64 address;
+ u64 aux;
+ u64 latency;
+ u64 tsx_tuning;
+};
+
+struct pebs_gprs {
+ u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+ u64 r8, r9, r10, r11, r12, r13, r14, r15;
+};
+
+struct pebs_xmm {
+ u64 xmm[16*2]; /* two entries for each register */
+};
+
+struct pebs_lbr_entry {
+ u64 from, to, info;
+};
+
+struct pebs_lbr {
+ struct pebs_lbr_entry lbr[0]; /* Variable length */
+};
+
/*
* IBS cpuid feature detection
*/
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 06/12] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (4 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 05/12] perf/x86/intel: Support adaptive PEBSv4 kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:37 ` [tip:perf/core] " tip-bot for Andi Kleen
2019-04-02 19:45 ` [PATCH V5 07/12] perf/x86: Support constraint ranges kan.liang
` (6 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Andi Kleen <ak@linux.intel.com>
With adaptive PEBS the CPU can directly supply the LBR information,
so we don't need to read it again. But the LBRs still need to be
enabled. Add a special count to the cpuc that distinguishes these
two cases, and avoid reading the LBRs unnecessarily when PEBS is
active.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/lbr.c | 13 ++++++++++++-
arch/x86/events/perf_event.h | 1 +
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 07b7175fc378..6f814a27416b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
* be 'new'. Conversely, a new event can get installed through the
* context switch path for the first time.
*/
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users++;
perf_sched_cb_inc(event->ctx->pmu);
if (!cpuc->lbr_users++ && !event->total_time_running)
intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event)
task_ctx->lbr_callstack_users--;
}
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users--;
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
+ WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
}
@@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (!cpuc->lbr_users)
+ /*
+ * Don't read when all LBRs users are using adaptive PEBS.
+ *
+ * This could be smarter and actually check the event,
+ * but this simple approach seems to work for now.
+ */
+ if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index d95014f88ef7..089c38e3d2bf 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -234,6 +234,7 @@ struct cpu_hw_events {
* Intel LBR bits
*/
int lbr_users;
+ int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them
2019-04-02 19:45 ` [PATCH V5 06/12] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
@ 2019-04-16 11:37 ` tip-bot for Andi Kleen
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Andi Kleen @ 2019-04-16 11:37 UTC (permalink / raw)
To: linux-tip-commits
Cc: eranian, alexander.shishkin, linux-kernel, vincent.weaver, ak,
tglx, mingo, hpa, torvalds, acme, peterz, jolsa, kan.liang
Commit-ID: d3617b98b04583df222f34992e65712862a77bf1
Gitweb: https://git.kernel.org/tip/d3617b98b04583df222f34992e65712862a77bf1
Author: Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:03 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:17 +0200
perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them
With adaptive PEBS the CPU can directly supply the LBR information,
so we don't need to read it again. But the LBRs still need to be
enabled. Add a special count to the cpuc that distinguishes these
two cases, and avoid reading the LBRs unnecessarily when PEBS is
active.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-7-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/lbr.c | 13 ++++++++++++-
arch/x86/events/perf_event.h | 1 +
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 07b7175fc378..6f814a27416b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
* be 'new'. Conversely, a new event can get installed through the
* context switch path for the first time.
*/
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users++;
perf_sched_cb_inc(event->ctx->pmu);
if (!cpuc->lbr_users++ && !event->total_time_running)
intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event)
task_ctx->lbr_callstack_users--;
}
+ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+ cpuc->lbr_pebs_users--;
cpuc->lbr_users--;
WARN_ON_ONCE(cpuc->lbr_users < 0);
+ WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
perf_sched_cb_dec(event->ctx->pmu);
}
@@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- if (!cpuc->lbr_users)
+ /*
+ * Don't read when all LBRs users are using adaptive PEBS.
+ *
+ * This could be smarter and actually check the event,
+ * but this simple approach seems to work for now.
+ */
+ if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
return;
if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 2059c143946f..dced91582147 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -233,6 +233,7 @@ struct cpu_hw_events {
* Intel LBR bits
*/
int lbr_users;
+ int lbr_pebs_users;
struct perf_branch_stack lbr_stack;
struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
struct er_account *lbr_sel;
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 07/12] perf/x86: Support constraint ranges
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (5 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 06/12] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:37 ` [tip:perf/core] " tip-bot for Peter Zijlstra
2019-04-02 19:45 ` [PATCH V5 08/12] perf/x86/intel: Add Icelake support kan.liang
` (5 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Peter Zijlstra <peterz@infradead.org>
Icelake extended the general counters to 8, even when SMT is enabled.
However only a (large) subset of the events can be used on all 8
counters.
The events that can or cannot be used on all counters are organized
in ranges.
A lot of scheduler constraints are required to handle all this.
To avoid blowing up the tables add event code ranges to the constraint
tables, and a new inline function to match them.
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/core.c | 2 +-
arch/x86/events/intel/ds.c | 2 +-
arch/x86/events/perf_event.h | 42 ++++++++++++++++++++++++++++++------
3 files changed, 38 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ad03cc78a229..7828090dcd09 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2688,7 +2688,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 5ca681cacc4f..155fca3af062 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -858,7 +858,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 089c38e3d2bf..583d72884ddb 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,11 +49,12 @@ struct event_constraint {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
- u64 code;
- u64 cmask;
- int weight;
- int overlap;
- int flags;
+ u64 code;
+ u64 cmask;
+ int weight;
+ int overlap;
+ int flags;
+ unsigned int size;
};
/*
* struct hw_perf_event.flags flags
@@ -71,6 +72,10 @@ struct event_constraint {
#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */
#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+ return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
struct amd_nb {
int nb_id; /* NorthBridge id */
@@ -281,18 +286,29 @@ struct cpu_hw_events {
void *kfree_on_online[X86_PERF_KFREE_MAX];
};
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
+ .size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+ __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
+/*
+ * Only works for Intel events, which has 'small' event codes.
+ * Need to fix the rang compare for 'big' event codes, e.g AMD64_EVENTSEL_EVENT
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+ __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
@@ -327,6 +343,12 @@ struct cpu_hw_events {
#define INTEL_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
+/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
/*
* Constraint on the Event code + UMask + fixed-mask
*
@@ -374,6 +396,9 @@ struct cpu_hw_events {
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -390,6 +415,11 @@ struct cpu_hw_events {
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+ __EVENT_CONSTRAINT_RANGE(code, end, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86: Support constraint ranges
2019-04-02 19:45 ` [PATCH V5 07/12] perf/x86: Support constraint ranges kan.liang
@ 2019-04-16 11:37 ` tip-bot for Peter Zijlstra
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Peter Zijlstra @ 2019-04-16 11:37 UTC (permalink / raw)
To: linux-tip-commits
Cc: acme, peterz, eranian, hpa, mingo, jolsa, torvalds, linux-kernel,
kan.liang, alexander.shishkin, tglx, ak, vincent.weaver
Commit-ID: 63b79f6ebc464afb730bc45762c820795e276da1
Gitweb: https://git.kernel.org/tip/63b79f6ebc464afb730bc45762c820795e276da1
Author: Peter Zijlstra <peterz@infradead.org>
AuthorDate: Tue, 2 Apr 2019 12:45:04 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:17 +0200
perf/x86: Support constraint ranges
Icelake extended the general counters to 8, even when SMT is enabled.
However only a (large) subset of the events can be used on all 8
counters.
The events that can or cannot be used on all counters are organized
in ranges.
A lot of scheduler constraints are required to handle all this.
To avoid blowing up the tables add event code ranges to the constraint
tables, and a new inline function to match them.
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> # developer hat on
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> # maintainer hat on
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-8-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/core.c | 2 +-
arch/x86/events/intel/ds.c | 2 +-
arch/x86/events/perf_event.h | 43 +++++++++++++++++++++++++++++++++++++------
3 files changed, 39 insertions(+), 8 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bdc366d709aa..d4b52896f173 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2693,7 +2693,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (x86_pmu.event_constraints) {
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 6436452d6342..4429bfa92fbc 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -858,7 +858,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
if (x86_pmu.pebs_constraints) {
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
- if ((event->hw.config & c->cmask) == c->code) {
+ if (constraint_match(c, event->hw.config)) {
event->hw.flags |= c->flags;
return c;
}
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index dced91582147..0ff0c5ae8c29 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,13 +49,19 @@ struct event_constraint {
unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
u64 idxmsk64;
};
- u64 code;
- u64 cmask;
- int weight;
- int overlap;
- int flags;
+ u64 code;
+ u64 cmask;
+ int weight;
+ int overlap;
+ int flags;
+ unsigned int size;
};
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+ return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
+
/*
* struct hw_perf_event.flags flags
*/
@@ -280,18 +286,29 @@ struct cpu_hw_events {
void *kfree_on_online[X86_PERF_KFREE_MAX];
};
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \
{ .idxmsk64 = (n) }, \
.code = (c), \
+ .size = (e) - (c), \
.cmask = (m), \
.weight = (w), \
.overlap = (o), \
.flags = f, \
}
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+ __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
#define EVENT_CONSTRAINT(c, n, m) \
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
+/*
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+ __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
#define INTEL_EXCLEVT_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
0, PERF_X86_EVENT_EXCL)
@@ -326,6 +343,12 @@ struct cpu_hw_events {
#define INTEL_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
+/*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
/*
* Constraint on the Event code + UMask + fixed-mask
*
@@ -373,6 +396,9 @@ struct cpu_hw_events {
#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \
+ EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
/* Check only flags, but allow all event/umask */
#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -389,6 +415,11 @@ struct cpu_hw_events {
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+ __EVENT_CONSTRAINT_RANGE(code, end, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
__EVENT_CONSTRAINT(code, n, \
ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (6 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 07/12] perf/x86: Support constraint ranges kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-08 15:06 ` Peter Zijlstra
2019-04-16 11:38 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 09/12] perf/x86/intel/cstate: " kan.liang
` (4 subsequent siblings)
12 siblings, 2 replies; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Add Icelake core PMU perf code, including constraint tables and the main
enable code.
Icelake expanded the generic counters to always 8 even with HT on, but a
range of events cannot be scheduled on the extra 4 counters.
Add new constraint ranges to describe this to the scheduler.
The number of constraints that need to be checked is larger now than
with earlier CPUs.
At some point we may need a new data structure to look them up more
efficiently than with linear search. So far it still seems to be
acceptable however.
Icelake added a new fixed counter SLOTS. Full support for it is added
later in the patch series.
The cache events table is identical to Skylake.
Compare to PEBS instruction event on generic counter, fixed counter 0
has less skid. Force instruction:ppp always in fixed counter 0.
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
Changes since V4:
- remove has_xmm_regs
arch/x86/events/intel/core.c | 111 ++++++++++++++++++++++++++++++
arch/x86/events/intel/ds.c | 26 ++++++-
arch/x86/events/perf_event.h | 2 +
arch/x86/include/asm/intel_ds.h | 2 +-
arch/x86/include/asm/perf_event.h | 2 +-
5 files changed, 139 insertions(+), 4 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7828090dcd09..47984eb93f3b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+static struct event_constraint intel_icl_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+ INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
+ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+ INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+ EVENT_EXTRA_END
+};
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
@@ -3366,6 +3395,9 @@ static struct event_constraint counter0_constraint =
static struct event_constraint counter2_constraint =
EVENT_CONSTRAINT(0, 0x4, 0);
+static struct event_constraint fixed_counter0_constraint =
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
static struct event_constraint *
hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -3384,6 +3416,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
return c;
}
+static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ /*
+ * Fixed counter 0 has less skid.
+ * Force instruction:ppp in Fixed counter 0
+ */
+ if ((event->attr.precise_ip == 3) &&
+ ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
+ return &fixed_counter0_constraint;
+
+ return hsw_get_event_constraints(cpuc, idx, event);
+}
+
static struct event_constraint *
glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -4110,6 +4157,42 @@ static struct attribute *hsw_tsx_events_attrs[] = {
NULL
};
+EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_capacity_read),
+ EVENT_PTR(tx_capacity_write),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_capacity_read),
+ EVENT_PTR(el_capacity_write),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
+ NULL,
+};
+
+static __init struct attribute **get_icl_events_attrs(void)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ?
+ merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
+ icl_events_attrs;
+}
+
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@@ -4697,6 +4780,34 @@ __init int intel_pmu_init(void)
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_MOBILE:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_icl_event_constraints;
+ x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_icl_extra_regs;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = icl_get_event_constraints;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+ extra_attr = merge_attr(extra_attr, skl_format_attr);
+ x86_pmu.cpu_events = get_icl_events_attrs();
+ x86_pmu.force_gpr_event = 0x2ca;
+ x86_pmu.lbr_pt_coexist = true;
+ intel_pmu_pebs_data_source_skl(false);
+ pr_cont("Icelake events, ");
+ name = "icelake";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 155fca3af062..9c1ba58e166d 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
+
+ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
@@ -1056,7 +1076,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+ (x86_pmu.version < 5))
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
@@ -1108,7 +1129,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+ (x86_pmu.version < 5))
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 583d72884ddb..bf5d81a94901 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -998,6 +998,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[];
extern struct event_constraint intel_skl_pebs_event_constraints[];
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index ae26df1c2789..8380c3ddd4b2 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,7 +8,7 @@
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
-#define MAX_FIXED_PEBS_EVENTS 3
+#define MAX_FIXED_PEBS_EVENTS 4
/*
* A debug store configuration.
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index fd0ec2699213..dcb8bac6fddb 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
*/
#define INTEL_PMC_MAX_GENERIC 32
-#define INTEL_PMC_MAX_FIXED 3
+#define INTEL_PMC_MAX_FIXED 4
#define INTEL_PMC_IDX_FIXED 32
#define X86_PMC_IDX_MAX 64
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* Re: [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-02 19:45 ` [PATCH V5 08/12] perf/x86/intel: Add Icelake support kan.liang
@ 2019-04-08 15:06 ` Peter Zijlstra
2019-04-08 15:45 ` Liang, Kan
2019-04-16 11:38 ` [tip:perf/core] " tip-bot for Kan Liang
1 sibling, 1 reply; 37+ messages in thread
From: Peter Zijlstra @ 2019-04-08 15:06 UTC (permalink / raw)
To: kan.liang
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On Tue, Apr 02, 2019 at 12:45:05PM -0700, kan.liang@linux.intel.com wrote:
> +static struct event_constraint *
> +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
> + struct perf_event *event)
> +{
> + /*
> + * Fixed counter 0 has less skid.
> + * Force instruction:ppp in Fixed counter 0
> + */
> + if ((event->attr.precise_ip == 3) &&
> + ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
> + return &fixed_counter0_constraint;
Does that want to be:
event->hw.config == X86_CONFIG(.event=0xc0)
?
That is, are there really bits we want to mask in there?
> +
> + return hsw_get_event_constraints(cpuc, idx, event);
> +}
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-08 15:06 ` Peter Zijlstra
@ 2019-04-08 15:45 ` Liang, Kan
2019-04-10 18:22 ` Liang, Kan
0 siblings, 1 reply; 37+ messages in thread
From: Liang, Kan @ 2019-04-08 15:45 UTC (permalink / raw)
To: Peter Zijlstra
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On 4/8/2019 11:06 AM, Peter Zijlstra wrote:
> On Tue, Apr 02, 2019 at 12:45:05PM -0700, kan.liang@linux.intel.com wrote:
>> +static struct event_constraint *
>> +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
>> + struct perf_event *event)
>> +{
>> + /*
>> + * Fixed counter 0 has less skid.
>> + * Force instruction:ppp in Fixed counter 0
>> + */
>> + if ((event->attr.precise_ip == 3) &&
>> + ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
>> + return &fixed_counter0_constraint;
>
> Does that want to be:
>
> event->hw.config == X86_CONFIG(.event=0xc0)
>
> ?
>
> That is, are there really bits we want to mask in there?
For instruction event, right, we don't need mask it.
I will change it.
Thanks,
Kan
>
>> +
>> + return hsw_get_event_constraints(cpuc, idx, event);
>> +}
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-08 15:45 ` Liang, Kan
@ 2019-04-10 18:22 ` Liang, Kan
2019-04-10 19:47 ` Peter Zijlstra
0 siblings, 1 reply; 37+ messages in thread
From: Liang, Kan @ 2019-04-10 18:22 UTC (permalink / raw)
To: Peter Zijlstra
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On 4/8/2019 11:45 AM, Liang, Kan wrote:
>
>
> On 4/8/2019 11:06 AM, Peter Zijlstra wrote:
>> On Tue, Apr 02, 2019 at 12:45:05PM -0700, kan.liang@linux.intel.com
>> wrote:
>>> +static struct event_constraint *
>>> +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
>>> + struct perf_event *event)
>>> +{
>>> + /*
>>> + * Fixed counter 0 has less skid.
>>> + * Force instruction:ppp in Fixed counter 0
>>> + */
>>> + if ((event->attr.precise_ip == 3) &&
>>> + ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
>>> + return &fixed_counter0_constraint;
>>
>> Does that want to be:
>>
>> event->hw.config == X86_CONFIG(.event=0xc0)
>>
>> ?
>>
>> That is, are there really bits we want to mask in there?
>
> For instruction event, right, we don't need mask it.
> I will change it.
>
Actually, we have to mask some bits here, e.g.
ARCH_PERFMON_EVENTSEL_INT, ARCH_PERFMON_EVENTSEL_USR and
ARCH_PERFMON_EVENTSEL_OS. Those bits will be set in hw_config().
Also, other filds, e.g the INV, ANY, E, or CMASK fields are not allowed
for reduced Skid PEBS.
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index dae3d84..3fa36c9 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3463,6 +3463,9 @@ hsw_get_event_constraints(struct cpu_hw_events
*cpuc, int idx,
return c;
}
+#define EVENT_CONFIG(config) \
+ (config & (X86_ALL_EVENT_FLAGS | INTEL_ARCH_EVENT_MASK))
+
static struct event_constraint *
icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -3472,7 +3475,7 @@ icl_get_event_constraints(struct cpu_hw_events
*cpuc, int idx,
* Force instruction:ppp in Fixed counter 0
*/
if ((event->attr.precise_ip == 3) &&
- (event->hw.config == X86_CONFIG(.event=0xc0)))
+ (EVENT_CONFIG(event->hw.config) == X86_CONFIG(.event=0xc0)))
return &fixed_counter0_constraint;
return hsw_get_event_constraints(cpuc, idx, event);
Thanks,
Kan
^ permalink raw reply related [flat|nested] 37+ messages in thread
* Re: [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-10 18:22 ` Liang, Kan
@ 2019-04-10 19:47 ` Peter Zijlstra
2019-04-11 9:00 ` Peter Zijlstra
0 siblings, 1 reply; 37+ messages in thread
From: Peter Zijlstra @ 2019-04-10 19:47 UTC (permalink / raw)
To: Liang, Kan
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On Wed, Apr 10, 2019 at 02:22:21PM -0400, Liang, Kan wrote:
> > > That is, are there really bits we want to mask in there?
> >
> > For instruction event, right, we don't need mask it.
> > I will change it.
> >
>
> Actually, we have to mask some bits here, e.g. ARCH_PERFMON_EVENTSEL_INT,
> ARCH_PERFMON_EVENTSEL_USR and ARCH_PERFMON_EVENTSEL_OS. Those bits will be
> set in hw_config().
Ah, bah, You're right. I misread and though we were comparing against
the user provided raw config.
>
> Also, other filds, e.g the INV, ANY, E, or CMASK fields are not allowed for
> reduced Skid PEBS.
Sure, those are actually forced 0 with the existing thing.
I'll go fold smething like back in. Thanks!
>
> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
> index dae3d84..3fa36c9 100644
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -3463,6 +3463,9 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc,
> int idx,
> return c;
> }
>
> +#define EVENT_CONFIG(config) \
> + (config & (X86_ALL_EVENT_FLAGS | INTEL_ARCH_EVENT_MASK))
> +
> static struct event_constraint *
> icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
> struct perf_event *event)
> @@ -3472,7 +3475,7 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc,
> int idx,
> * Force instruction:ppp in Fixed counter 0
> */
> if ((event->attr.precise_ip == 3) &&
> - (event->hw.config == X86_CONFIG(.event=0xc0)))
> + (EVENT_CONFIG(event->hw.config) == X86_CONFIG(.event=0xc0)))
> return &fixed_counter0_constraint;
>
> return hsw_get_event_constraints(cpuc, idx, event);
>
> Thanks,
> Kan
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-10 19:47 ` Peter Zijlstra
@ 2019-04-11 9:00 ` Peter Zijlstra
2019-04-11 13:29 ` Liang, Kan
0 siblings, 1 reply; 37+ messages in thread
From: Peter Zijlstra @ 2019-04-11 9:00 UTC (permalink / raw)
To: Liang, Kan
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On Wed, Apr 10, 2019 at 09:47:20PM +0200, Peter Zijlstra wrote:
> Sure, those are actually forced 0 with the existing thing.
>
> I'll go fold smething like back in. Thanks!
> > @@ -3472,7 +3475,7 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc,
> > int idx,
> > * Force instruction:ppp in Fixed counter 0
> > */
> > if ((event->attr.precise_ip == 3) &&
> > - (event->hw.config == X86_CONFIG(.event=0xc0)))
> > + (EVENT_CONFIG(event->hw.config) == X86_CONFIG(.event=0xc0)))
> > return &fixed_counter0_constraint;
> >
> > return hsw_get_event_constraints(cpuc, idx, event);
Staring at that I came up with the below; how does that look?
Note: FIXED_EVENT_CONSTRAINT(0x00c0, 0) has FIXED_EVENT_FLAGS for
->cmask and includes the correct event code.
---
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3433,7 +3433,7 @@ icl_get_event_constraints(struct cpu_hw_
* Force instruction:ppp in Fixed counter 0
*/
if ((event->attr.precise_ip == 3) &&
- (event->hw.config == X86_CONFIG(.event=0xc0)))
+ constraint_match(&fixed_counter0_constraint, event->hw.config))
return &fixed_counter0_constraint;
return hsw_get_event_constraints(cpuc, idx, event);
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 08/12] perf/x86/intel: Add Icelake support
2019-04-11 9:00 ` Peter Zijlstra
@ 2019-04-11 13:29 ` Liang, Kan
0 siblings, 0 replies; 37+ messages in thread
From: Liang, Kan @ 2019-04-11 13:29 UTC (permalink / raw)
To: Peter Zijlstra
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On 4/11/2019 5:00 AM, Peter Zijlstra wrote:
> On Wed, Apr 10, 2019 at 09:47:20PM +0200, Peter Zijlstra wrote:
>> Sure, those are actually forced 0 with the existing thing.
>>
>> I'll go fold smething like back in. Thanks!
>
>>> @@ -3472,7 +3475,7 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc,
>>> int idx,
>>> * Force instruction:ppp in Fixed counter 0
>>> */
>>> if ((event->attr.precise_ip == 3) &&
>>> - (event->hw.config == X86_CONFIG(.event=0xc0)))
>>> + (EVENT_CONFIG(event->hw.config) == X86_CONFIG(.event=0xc0)))
>>> return &fixed_counter0_constraint;
>>>
>>> return hsw_get_event_constraints(cpuc, idx, event);
>
> Staring at that I came up with the below; how does that look?
>
Yes, it looks better.
Thanks,
Kan
> Note: FIXED_EVENT_CONSTRAINT(0x00c0, 0) has FIXED_EVENT_FLAGS for
> ->cmask and includes the correct event code.
>
> ---
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -3433,7 +3433,7 @@ icl_get_event_constraints(struct cpu_hw_
> * Force instruction:ppp in Fixed counter 0
> */
> if ((event->attr.precise_ip == 3) &&
> - (event->hw.config == X86_CONFIG(.event=0xc0)))
> + constraint_match(&fixed_counter0_constraint, event->hw.config))
> return &fixed_counter0_constraint;
>
> return hsw_get_event_constraints(cpuc, idx, event);
>
^ permalink raw reply [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel: Add Icelake support
2019-04-02 19:45 ` [PATCH V5 08/12] perf/x86/intel: Add Icelake support kan.liang
2019-04-08 15:06 ` Peter Zijlstra
@ 2019-04-16 11:38 ` tip-bot for Kan Liang
1 sibling, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:38 UTC (permalink / raw)
To: linux-tip-commits
Cc: ak, linux-kernel, torvalds, mingo, tglx, eranian, jolsa, peterz,
hpa, vincent.weaver, kan.liang, acme, alexander.shishkin
Commit-ID: 6017608936c1825ff5d7325270484042f597edff
Gitweb: https://git.kernel.org/tip/6017608936c1825ff5d7325270484042f597edff
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:05 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:18 +0200
perf/x86/intel: Add Icelake support
Add Icelake core PMU perf code, including constraint tables and the main
enable code.
Icelake expanded the generic counters to always 8 even with HT on, but a
range of events cannot be scheduled on the extra 4 counters.
Add new constraint ranges to describe this to the scheduler.
The number of constraints that need to be checked is larger now than
with earlier CPUs.
At some point we may need a new data structure to look them up more
efficiently than with linear search. So far it still seems to be
acceptable however.
Icelake added a new fixed counter SLOTS. Full support for it is added
later in the patch series.
The cache events table is identical to Skylake.
Compare to PEBS instruction event on generic counter, fixed counter 0
has less skid. Force instruction:ppp always in fixed counter 0.
Originally-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-9-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/core.c | 111 ++++++++++++++++++++++++++++++++++++++
arch/x86/events/intel/ds.c | 25 ++++++++-
arch/x86/events/perf_event.h | 2 +
arch/x86/include/asm/intel_ds.h | 2 +-
arch/x86/include/asm/perf_event.h | 2 +-
5 files changed, 138 insertions(+), 4 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d4b52896f173..156c6ae53d3c 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+static struct event_constraint intel_icl_event_constraints[] = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+ INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
+ INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+ INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */
+ INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+ INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+ INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+ INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+ EVENT_EXTRA_END
+};
+
EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
@@ -3374,6 +3403,9 @@ static struct event_constraint counter0_constraint =
static struct event_constraint counter2_constraint =
EVENT_CONSTRAINT(0, 0x4, 0);
+static struct event_constraint fixed0_constraint =
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
static struct event_constraint *
hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -3392,6 +3424,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
return c;
}
+static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+ struct perf_event *event)
+{
+ /*
+ * Fixed counter 0 has less skid.
+ * Force instruction:ppp in Fixed counter 0
+ */
+ if ((event->attr.precise_ip == 3) &&
+ constraint_match(&fixed0_constraint, event->hw.config))
+ return &fixed0_constraint;
+
+ return hsw_get_event_constraints(cpuc, idx, event);
+}
+
static struct event_constraint *
glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -4124,6 +4171,42 @@ static struct attribute *hsw_tsx_events_attrs[] = {
NULL
};
+EVENT_ATTR_STR(tx-capacity-read, tx_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read, el_capacity_read, "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+ EVENT_PTR(mem_ld_hsw),
+ EVENT_PTR(mem_st_hsw),
+ NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_capacity_read),
+ EVENT_PTR(tx_capacity_write),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_capacity_read),
+ EVENT_PTR(el_capacity_write),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
+ NULL,
+};
+
+static __init struct attribute **get_icl_events_attrs(void)
+{
+ return boot_cpu_has(X86_FEATURE_RTM) ?
+ merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
+ icl_events_attrs;
+}
+
static ssize_t freeze_on_smi_show(struct device *cdev,
struct device_attribute *attr,
char *buf)
@@ -4757,6 +4840,34 @@ __init int intel_pmu_init(void)
name = "skylake";
break;
+ case INTEL_FAM6_ICELAKE_MOBILE:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+ intel_pmu_lbr_init_skl();
+
+ x86_pmu.event_constraints = intel_icl_event_constraints;
+ x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_icl_extra_regs;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = icl_get_event_constraints;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+ extra_attr = merge_attr(extra_attr, skl_format_attr);
+ x86_pmu.cpu_events = get_icl_events_attrs();
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
+ x86_pmu.lbr_pt_coexist = true;
+ intel_pmu_pebs_data_source_skl(false);
+ pr_cont("Icelake events, ");
+ name = "icelake";
+ break;
+
default:
switch (x86_pmu.version) {
case 1:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 4429bfa92fbc..7a9f5dac5abe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
+
+ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
+
+ /*
+ * Everything else is handled by PMU_FL_PEBS_ALL, because we
+ * need the full constraints from the main table.
+ */
+
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
@@ -1053,7 +1073,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
@@ -1105,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
- if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+ (x86_pmu.version < 5))
cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled &= ~(1ULL << 63);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 0ff0c5ae8c29..07fc84bb85c1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -999,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[];
extern struct event_constraint intel_skl_pebs_event_constraints[];
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_add(struct perf_event *event);
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index ae26df1c2789..8380c3ddd4b2 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,7 +8,7 @@
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
-#define MAX_FIXED_PEBS_EVENTS 3
+#define MAX_FIXED_PEBS_EVENTS 4
/*
* A debug store configuration.
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 997a6587d7cf..04768a3a5454 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
*/
#define INTEL_PMC_MAX_GENERIC 32
-#define INTEL_PMC_MAX_FIXED 3
+#define INTEL_PMC_MAX_FIXED 4
#define INTEL_PMC_IDX_FIXED 32
#define X86_PMC_IDX_MAX 64
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 09/12] perf/x86/intel/cstate: Add Icelake support
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (7 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 08/12] perf/x86/intel: Add Icelake support kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:39 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 10/12] perf/x86/intel/rapl: " kan.liang
` (3 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Icelake uses the same C-state residency events as Sandy Bridge.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/cstate.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 94a4b7fc75d0..dd5658ec31d5 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel/cstate: Add Icelake support
2019-04-02 19:45 ` [PATCH V5 09/12] perf/x86/intel/cstate: " kan.liang
@ 2019-04-16 11:39 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:39 UTC (permalink / raw)
To: linux-tip-commits
Cc: torvalds, tglx, vincent.weaver, linux-kernel, hpa, mingo, acme,
kan.liang, jolsa, alexander.shishkin, peterz, eranian
Commit-ID: f08c47d1f86c6dc666c7e659d94bf6d4492aa9d7
Gitweb: https://git.kernel.org/tip/f08c47d1f86c6dc666c7e659d94bf6d4492aa9d7
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:06 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:18 +0200
perf/x86/intel/cstate: Add Icelake support
Icelake uses the same C-state residency events as Sandy Bridge.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-10-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/cstate.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 94a4b7fc75d0..dd5658ec31d5 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 10/12] perf/x86/intel/rapl: Add Icelake support
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (8 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 09/12] perf/x86/intel/cstate: " kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:39 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 11/12] perf/x86/msr: " kan.liang
` (2 subsequent siblings)
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Icelake support the same RAPL counters as Skylake.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/rapl.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 94dc564146ca..37ebf6fc5415 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
+
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
{},
};
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel/rapl: Add Icelake support
2019-04-02 19:45 ` [PATCH V5 10/12] perf/x86/intel/rapl: " kan.liang
@ 2019-04-16 11:39 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:39 UTC (permalink / raw)
To: linux-tip-commits
Cc: vincent.weaver, peterz, tglx, alexander.shishkin, hpa, torvalds,
jolsa, kan.liang, linux-kernel, mingo, eranian, acme
Commit-ID: b3377c3acb9e54cf86efcfe25f2e792bca599ed4
Gitweb: https://git.kernel.org/tip/b3377c3acb9e54cf86efcfe25f2e792bca599ed4
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:07 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:18 +0200
perf/x86/intel/rapl: Add Icelake support
Icelake support the same RAPL counters as Skylake.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-11-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/rapl.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 94dc564146ca..37ebf6fc5415 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
+
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, skl_rapl_init),
{},
};
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 11/12] perf/x86/msr: Add Icelake support
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (9 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 10/12] perf/x86/intel/rapl: " kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:40 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-02 19:45 ` [PATCH V5 12/12] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
2019-04-08 15:41 ` [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) Peter Zijlstra
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Icelake is the same as the existing Skylake parts.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/msr.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index a878e6286e4a..f3f4c2263501 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,6 +89,7 @@ static bool test_intel(int idx)
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_ICELAKE_MOBILE:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/msr: Add Icelake support
2019-04-02 19:45 ` [PATCH V5 11/12] perf/x86/msr: " kan.liang
@ 2019-04-16 11:40 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:40 UTC (permalink / raw)
To: linux-tip-commits
Cc: jolsa, peterz, mingo, alexander.shishkin, tglx, hpa, acme,
vincent.weaver, torvalds, eranian, kan.liang, linux-kernel
Commit-ID: cf50d79a8cfe5adae37fec026220b009559bbeed
Gitweb: https://git.kernel.org/tip/cf50d79a8cfe5adae37fec026220b009559bbeed
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:08 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:19 +0200
perf/x86/msr: Add Icelake support
Icelake is the same as the existing Skylake parts.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-12-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/msr.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index a878e6286e4a..f3f4c2263501 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,6 +89,7 @@ static bool test_intel(int idx)
case INTEL_FAM6_SKYLAKE_X:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_KABYLAKE_DESKTOP:
+ case INTEL_FAM6_ICELAKE_MOBILE:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [PATCH V5 12/12] perf/x86/intel/uncore: Add Intel Icelake uncore support
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (10 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 11/12] perf/x86/msr: " kan.liang
@ 2019-04-02 19:45 ` kan.liang
2019-04-16 11:40 ` [tip:perf/core] " tip-bot for Kan Liang
2019-04-08 15:41 ` [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) Peter Zijlstra
12 siblings, 1 reply; 37+ messages in thread
From: kan.liang @ 2019-04-02 19:45 UTC (permalink / raw)
To: peterz, acme, mingo, linux-kernel
Cc: tglx, jolsa, eranian, alexander.shishkin, ak, Kan Liang
From: Kan Liang <kan.liang@linux.intel.com>
Add Intel Icelake uncore support,
- The init code is based on Skylake
- Add new pci id for IMC
- New MSR address for CBOX
- Get CBOX# from CNL_UNC_CBO_CONFIG MSR directly
- Create a new PMU for fixed clocktick counter
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
No changes since V4.
arch/x86/events/intel/uncore.c | 6 ++
arch/x86/events/intel/uncore.h | 1 +
arch/x86/events/intel/uncore_snb.c | 91 ++++++++++++++++++++++++++++++
3 files changed, 98 insertions(+)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9fe64c01a2e5..fc40a1473058 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
.pci_init = skx_uncore_pci_init,
};
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .pci_init = skl_uncore_pci_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
{},
};
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 853a49a8ccf6..79eb2e21e4f0 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -512,6 +512,7 @@ int skl_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 13493f43b247..f8431819b3e1 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -34,6 +34,8 @@
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -93,6 +95,12 @@
#define SKL_UNC_PERF_GLOBAL_CTL 0xe01
#define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1)
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG 0x396
+#define ICL_UNC_NUM_CBO_MASK 0xf
+#define ICL_UNC_CBO_0_PER_CTR0 0x702
+#define ICL_UNC_CBO_MSR_OFFSET 0x8
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void)
snb_uncore_arb.ops = &skl_uncore_msr_ops;
}
+static struct intel_uncore_type icl_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .perf_ctr_bits = 44,
+ .perf_ctr = ICL_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = ICL_UNC_CBO_MSR_OFFSET,
+ .ops = &skl_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+ .name = "format",
+ .attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+ .name = "clock",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_CTL_EV_SEL_MASK,
+ .format_group = &icl_uncore_clock_format_group,
+ .ops = &skl_uncore_msr_ops,
+ .event_descs = icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+ &icl_uncore_cbox,
+ &snb_uncore_arb,
+ &icl_uncore_clockbox,
+ NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+ u64 num_boxes;
+
+ rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+ return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = icl_msr_uncores;
+ icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+ snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
enum {
SNB_PCI_UNCORE_IMC,
};
@@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
{ /* end: all zeroes */ },
};
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = {
.id_table = skl_uncore_pci_ids,
};
+static struct pci_driver icl_uncore_pci_driver = {
+ .name = "icl_uncore",
+ .id_table = icl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
+ IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
};
--
2.17.1
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [tip:perf/core] perf/x86/intel/uncore: Add Intel Icelake uncore support
2019-04-02 19:45 ` [PATCH V5 12/12] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
@ 2019-04-16 11:40 ` tip-bot for Kan Liang
0 siblings, 0 replies; 37+ messages in thread
From: tip-bot for Kan Liang @ 2019-04-16 11:40 UTC (permalink / raw)
To: linux-tip-commits
Cc: hpa, kan.liang, jolsa, torvalds, eranian, vincent.weaver, tglx,
peterz, mingo, acme, alexander.shishkin, linux-kernel
Commit-ID: 6e394376ee89233508fa21d006546357f8efee31
Gitweb: https://git.kernel.org/tip/6e394376ee89233508fa21d006546357f8efee31
Author: Kan Liang <kan.liang@linux.intel.com>
AuthorDate: Tue, 2 Apr 2019 12:45:09 -0700
Committer: Ingo Molnar <mingo@kernel.org>
CommitDate: Tue, 16 Apr 2019 12:26:19 +0200
perf/x86/intel/uncore: Add Intel Icelake uncore support
Add Intel Icelake uncore support:
- The init code is based on Skylake
- Add new PCI id for IMC
- New MSR address for CBOX
- Get CBOX# from CNL_UNC_CBO_CONFIG MSR directly
- Create a new PMU for fixed clocktick counter
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-13-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/events/intel/uncore.c | 6 +++
arch/x86/events/intel/uncore.h | 1 +
arch/x86/events/intel/uncore_snb.c | 91 ++++++++++++++++++++++++++++++++++++++
3 files changed, 98 insertions(+)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9fe64c01a2e5..fc40a1473058 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
.pci_init = skx_uncore_pci_init,
};
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+ .cpu_init = icl_uncore_cpu_init,
+ .pci_init = skl_uncore_pci_init,
+};
+
static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP, nhm_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM, nhm_uncore_init),
@@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X, skx_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+ X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
{},
};
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 853a49a8ccf6..79eb2e21e4f0 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -512,6 +512,7 @@ int skl_uncore_pci_init(void);
void snb_uncore_cpu_init(void);
void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 13493f43b247..f8431819b3e1 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -34,6 +34,8 @@
#define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC 0x3e33
#define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC 0x3eca
#define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC 0x3e32
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC 0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC 0x8a12
/* SNB event control */
#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
@@ -93,6 +95,12 @@
#define SKL_UNC_PERF_GLOBAL_CTL 0xe01
#define SKL_UNC_GLOBAL_CTL_CORE_ALL ((1 << 5) - 1)
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG 0x396
+#define ICL_UNC_NUM_CBO_MASK 0xf
+#define ICL_UNC_CBO_0_PER_CTR0 0x702
+#define ICL_UNC_CBO_MSR_OFFSET 0x8
+
DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void)
snb_uncore_arb.ops = &skl_uncore_msr_ops;
}
+static struct intel_uncore_type icl_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .perf_ctr_bits = 44,
+ .perf_ctr = ICL_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = ICL_UNC_CBO_MSR_OFFSET,
+ .ops = &skl_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+ .name = "format",
+ .attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+ .name = "clock",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_CTL_EV_SEL_MASK,
+ .format_group = &icl_uncore_clock_format_group,
+ .ops = &skl_uncore_msr_ops,
+ .event_descs = icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+ &icl_uncore_cbox,
+ &snb_uncore_arb,
+ &icl_uncore_clockbox,
+ NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+ u64 num_boxes;
+
+ rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+ return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = icl_msr_uncores;
+ icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+ snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
enum {
SNB_PCI_UNCORE_IMC,
};
@@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
{ /* end: all zeroes */ },
};
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
static struct pci_driver snb_uncore_pci_driver = {
.name = "snb_uncore",
.id_table = snb_uncore_pci_ids,
@@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = {
.id_table = skl_uncore_pci_ids,
};
+static struct pci_driver icl_uncore_pci_driver = {
+ .name = "icl_uncore",
+ .id_table = icl_uncore_pci_ids,
+};
+
struct imc_uncore_pci_dev {
__u32 pci_id;
struct pci_driver *driver;
@@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 4 Cores Server */
IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 6 Cores Server */
IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver), /* 8th Gen Core S 8 Cores Server */
+ IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
+ IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver), /* 10th Gen Core Mobile */
{ /* end marker */ }
};
^ permalink raw reply related [flat|nested] 37+ messages in thread
* Re: [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown)
2019-04-02 19:44 [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) kan.liang
` (11 preceding siblings ...)
2019-04-02 19:45 ` [PATCH V5 12/12] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
@ 2019-04-08 15:41 ` Peter Zijlstra
2019-04-08 16:06 ` Liang, Kan
12 siblings, 1 reply; 37+ messages in thread
From: Peter Zijlstra @ 2019-04-08 15:41 UTC (permalink / raw)
To: kan.liang
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
I currently have something like the below on top, is that correct?
If so, I'll fold it back in.
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -563,16 +563,17 @@ int x86_pmu_hw_config(struct perf_event
/* sample_regs_user never support XMM registers */
if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
return -EINVAL;
+
/*
* Besides the general purpose registers, XMM registers may
* be collected in PEBS on some platforms, e.g. Icelake
*/
if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
- if (!is_sampling_event(event) ||
- !event->attr.precise_ip ||
- x86_pmu.pebs_no_xmm_regs)
+ if (x86_pmu.pebs_no_xmm_regs)
return -EINVAL;
+ if (!event->attr.precise_ip)
+ return -EINVAL;
}
return x86_setup_perfctr(event);
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3428,7 +3428,7 @@ icl_get_event_constraints(struct cpu_hw_
* Force instruction:ppp in Fixed counter 0
*/
if ((event->attr.precise_ip == 3) &&
- ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
+ (event->hw.config == X86_CONFIG(.event=0xc0)))
return &fixed_counter0_constraint;
return hsw_get_event_constraints(cpuc, idx, event);
@@ -4810,7 +4810,7 @@ __init int intel_pmu_init(void)
hsw_format_attr : nhm_format_attr;
extra_attr = merge_attr(extra_attr, skl_format_attr);
x86_pmu.cpu_events = get_icl_events_attrs();
- x86_pmu.force_gpr_event = 0x2ca;
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
x86_pmu.lbr_pt_coexist = true;
intel_pmu_pebs_data_source_skl(false);
pr_cont("Icelake events, ");
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -853,13 +853,13 @@ struct event_constraint intel_icl_pebs_e
INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
- INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
- INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
/*
* Everything else is handled by PMU_FL_PEBS_ALL, because we
@@ -963,40 +963,42 @@ static u64 pebs_update_adaptive_cfg(stru
u64 pebs_data_cfg = 0;
bool gprs, tsx_weight;
- if ((sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) ||
- attr->precise_ip < 2) {
+ if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+ attr->precise_ip > 1)
+ return pebs_data_cfs;
- if (sample_type & PERF_PEBS_MEMINFO_TYPE)
- pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+ if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+ pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+ /*
+ * We need GPRs when:
+ * + user requested them
+ * + precise_ip < 2 for the non event IP
+ * + For RTM TSX weight we need GPRs for the abort code.
+ */
+ gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PEBS_GPRS_REGS);
+
+ tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+ ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+ x86_pmu.rtm_abort_event);
+
+ if (gprs || (attr->precise_ip < 2) || tsx_weight)
+ pebs_data_cfg |= PEBS_DATACFG_GPRS;
+
+ if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+ (attr->sample_regs_intr & PERF_XMM_REGS))
+ pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
/*
- * Cases we need the registers:
- * + user requested registers
- * + precise_ip < 2 for the non event IP
- * + For RTM TSX weight we need GPRs too for the abort
- * code. But we don't want to force GPRs for all other
- * weights. So add it only collectfor the RTM abort event.
+ * For now always log all LBRs. Could configure this
+ * later.
*/
- gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
- (attr->sample_regs_intr & 0xffffffff);
- tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
- ((attr->config & 0xffff) == x86_pmu.force_gpr_event);
- if (gprs || (attr->precise_ip < 2) || tsx_weight)
- pebs_data_cfg |= PEBS_DATACFG_GPRS;
-
- if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
- (attr->sample_regs_intr >> 32))
- pebs_data_cfg |= PEBS_DATACFG_XMMS;
-
- if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
- /*
- * For now always log all LBRs. Could configure this
- * later.
- */
- pebs_data_cfg |= PEBS_DATACFG_LBRS |
- ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
- }
+ pebs_data_cfg |= PEBS_DATACFG_LBRS |
+ ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
}
+
return pebs_data_cfg;
}
@@ -1022,13 +1024,8 @@ pebs_update_state(bool needed_cb, struct
}
/*
- * The PEBS record doesn't shrink on the del. Because to get
- * an accurate config needs to go through all the existing pebs events.
- * It's not necessary.
- * There is no harmful for a bigger PEBS record, except little
- * performance impacts.
- * Also, for most cases, the same pebs config is applied for all
- * pebs events.
+ * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+ * iterating all remaining PEBS events to reconstruct the config.
*/
if (x86_pmu.intel_cap.pebs_baseline && add) {
u64 pebs_data_cfg;
@@ -1076,8 +1073,7 @@ void intel_pmu_pebs_enable(struct perf_e
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
- (x86_pmu.version < 5))
+ if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
cpuc->pebs_enabled |= 1ULL << 63;
@@ -1766,8 +1762,7 @@ static void intel_pmu_drain_pebs_core(st
setup_pebs_fixed_sample_data);
}
-static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc,
- int size)
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
{
struct perf_event *event;
int bit;
@@ -1826,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(str
/* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&pebs_status,
- size)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
counts[bit]++;
continue;
@@ -1866,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(str
* If collision happened, the record will be dropped.
*/
if (p->status != (1ULL << bit)) {
- for_each_set_bit(i, (unsigned long *)&pebs_status,
- x86_pmu.max_pebs_events)
+ for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
}
@@ -1875,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(str
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)&mask, size) {
if ((counts[bit] == 0) && (error[bit] == 0))
continue;
@@ -1939,7 +1932,7 @@ static void intel_pmu_drain_pebs_icl(str
counts[bit]++;
}
- for (bit = 0; bit < size; bit++) {
+ for_each_set_bit(bit, (unsigned long *)mask, size) {
if (counts[bit] == 0)
continue;
@@ -1980,6 +1973,9 @@ void __init intel_ds_init(void)
char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
+ if (format < 4)
+ x86_pmu.intel_cap.pebs_baseline = 0;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -2042,8 +2038,6 @@ void __init intel_ds_init(void)
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
x86_pmu.pebs = 0;
}
- if (format != 4)
- x86_pmu.intel_cap.pebs_baseline = 0;
}
}
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -303,8 +303,8 @@ struct cpu_hw_events {
__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
/*
- * Only works for Intel events, which has 'small' event codes.
- * Need to fix the rang compare for 'big' event codes, e.g AMD64_EVENTSEL_EVENT
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
*/
#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
__EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
@@ -672,12 +672,12 @@ struct x86_pmu {
pebs_no_xmm_regs :1;
int pebs_record_size;
int pebs_buffer_size;
+ int max_pebs_events;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
void (*pebs_aliases)(struct perf_event *event);
- int max_pebs_events;
unsigned long large_pebs_flags;
- u64 force_gpr_event;
+ u64 rtm_abort_event;
/*
* Intel LBR
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown)
2019-04-08 15:41 ` [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown) Peter Zijlstra
@ 2019-04-08 16:06 ` Liang, Kan
2019-04-08 16:25 ` Liang, Kan
2019-04-08 22:49 ` Liang, Kan
0 siblings, 2 replies; 37+ messages in thread
From: Liang, Kan @ 2019-04-08 16:06 UTC (permalink / raw)
To: Peter Zijlstra
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On 4/8/2019 11:41 AM, Peter Zijlstra wrote:
>
> I currently have something like the below on top, is that correct?
Yes, it's correct.
>
> If so, I'll fold it back in.
Thanks. It's really appreciated.
Kan
>
>
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -563,16 +563,17 @@ int x86_pmu_hw_config(struct perf_event
> /* sample_regs_user never support XMM registers */
> if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
> return -EINVAL;
> +
> /*
> * Besides the general purpose registers, XMM registers may
> * be collected in PEBS on some platforms, e.g. Icelake
> */
> if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
> - if (!is_sampling_event(event) ||
> - !event->attr.precise_ip ||
> - x86_pmu.pebs_no_xmm_regs)
> + if (x86_pmu.pebs_no_xmm_regs)
> return -EINVAL;
>
> + if (!event->attr.precise_ip)
> + return -EINVAL;
> }
>
> return x86_setup_perfctr(event);
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -3428,7 +3428,7 @@ icl_get_event_constraints(struct cpu_hw_
> * Force instruction:ppp in Fixed counter 0
> */
> if ((event->attr.precise_ip == 3) &&
> - ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
> + (event->hw.config == X86_CONFIG(.event=0xc0)))
> return &fixed_counter0_constraint;
>
> return hsw_get_event_constraints(cpuc, idx, event);
> @@ -4810,7 +4810,7 @@ __init int intel_pmu_init(void)
> hsw_format_attr : nhm_format_attr;
> extra_attr = merge_attr(extra_attr, skl_format_attr);
> x86_pmu.cpu_events = get_icl_events_attrs();
> - x86_pmu.force_gpr_event = 0x2ca;
> + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
> x86_pmu.lbr_pt_coexist = true;
> intel_pmu_pebs_data_source_skl(false);
> pr_cont("Icelake events, ");
> --- a/arch/x86/events/intel/ds.c
> +++ b/arch/x86/events/intel/ds.c
> @@ -853,13 +853,13 @@ struct event_constraint intel_icl_pebs_e
> INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
> INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
>
> - INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
> - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
> - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
> + INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
> + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
> + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
>
> INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
>
> - INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
> + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */
>
> /*
> * Everything else is handled by PMU_FL_PEBS_ALL, because we
> @@ -963,40 +963,42 @@ static u64 pebs_update_adaptive_cfg(stru
> u64 pebs_data_cfg = 0;
> bool gprs, tsx_weight;
>
> - if ((sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) ||
> - attr->precise_ip < 2) {
> + if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
> + attr->precise_ip > 1)
> + return pebs_data_cfs;
>
> - if (sample_type & PERF_PEBS_MEMINFO_TYPE)
> - pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
> + if (sample_type & PERF_PEBS_MEMINFO_TYPE)
> + pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
>
> + /*
> + * We need GPRs when:
> + * + user requested them
> + * + precise_ip < 2 for the non event IP
> + * + For RTM TSX weight we need GPRs for the abort code.
> + */
> + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
> + (attr->sample_regs_intr & PEBS_GPRS_REGS);
> +
> + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
> + ((attr->config & INTEL_ARCH_EVENT_MASK) ==
> + x86_pmu.rtm_abort_event);
> +
> + if (gprs || (attr->precise_ip < 2) || tsx_weight)
> + pebs_data_cfg |= PEBS_DATACFG_GPRS;
> +
> + if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
> + (attr->sample_regs_intr & PERF_XMM_REGS))
> + pebs_data_cfg |= PEBS_DATACFG_XMMS;
> +
> + if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
> /*
> - * Cases we need the registers:
> - * + user requested registers
> - * + precise_ip < 2 for the non event IP
> - * + For RTM TSX weight we need GPRs too for the abort
> - * code. But we don't want to force GPRs for all other
> - * weights. So add it only collectfor the RTM abort event.
> + * For now always log all LBRs. Could configure this
> + * later.
> */
> - gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
> - (attr->sample_regs_intr & 0xffffffff);
> - tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
> - ((attr->config & 0xffff) == x86_pmu.force_gpr_event);
> - if (gprs || (attr->precise_ip < 2) || tsx_weight)
> - pebs_data_cfg |= PEBS_DATACFG_GPRS;
> -
> - if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
> - (attr->sample_regs_intr >> 32))
> - pebs_data_cfg |= PEBS_DATACFG_XMMS;
> -
> - if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
> - /*
> - * For now always log all LBRs. Could configure this
> - * later.
> - */
> - pebs_data_cfg |= PEBS_DATACFG_LBRS |
> - ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
> - }
> + pebs_data_cfg |= PEBS_DATACFG_LBRS |
> + ((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
> }
> +
> return pebs_data_cfg;
> }
>
> @@ -1022,13 +1024,8 @@ pebs_update_state(bool needed_cb, struct
> }
>
> /*
> - * The PEBS record doesn't shrink on the del. Because to get
> - * an accurate config needs to go through all the existing pebs events.
> - * It's not necessary.
> - * There is no harmful for a bigger PEBS record, except little
> - * performance impacts.
> - * Also, for most cases, the same pebs config is applied for all
> - * pebs events.
> + * The PEBS record doesn't shrink on pmu::del(). Doing so would require
> + * iterating all remaining PEBS events to reconstruct the config.
> */
> if (x86_pmu.intel_cap.pebs_baseline && add) {
> u64 pebs_data_cfg;
> @@ -1076,8 +1073,7 @@ void intel_pmu_pebs_enable(struct perf_e
>
> cpuc->pebs_enabled |= 1ULL << hwc->idx;
>
> - if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
> - (x86_pmu.version < 5))
> + if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
> cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
> else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
> cpuc->pebs_enabled |= 1ULL << 63;
> @@ -1766,8 +1762,7 @@ static void intel_pmu_drain_pebs_core(st
> setup_pebs_fixed_sample_data);
> }
>
> -static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc,
> - int size)
> +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
> {
> struct perf_event *event;
> int bit;
> @@ -1826,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(str
>
> /* PEBS v3 has more accurate status bits */
> if (x86_pmu.intel_cap.pebs_format >= 3) {
> - for_each_set_bit(bit, (unsigned long *)&pebs_status,
> - size)
> + for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
> counts[bit]++;
>
> continue;
> @@ -1866,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(str
> * If collision happened, the record will be dropped.
> */
> if (p->status != (1ULL << bit)) {
> - for_each_set_bit(i, (unsigned long *)&pebs_status,
> - x86_pmu.max_pebs_events)
> + for_each_set_bit(i, (unsigned long *)&pebs_status, size)
> error[i]++;
> continue;
> }
> @@ -1875,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(str
> counts[bit]++;
> }
>
> - for (bit = 0; bit < size; bit++) {
> + for_each_set_bit(bit, (unsigned long *)&mask, size) {
> if ((counts[bit] == 0) && (error[bit] == 0))
> continue;
>
> @@ -1939,7 +1932,7 @@ static void intel_pmu_drain_pebs_icl(str
> counts[bit]++;
> }
>
> - for (bit = 0; bit < size; bit++) {
> + for_each_set_bit(bit, (unsigned long *)mask, size) {
> if (counts[bit] == 0)
> continue;
>
> @@ -1980,6 +1973,9 @@ void __init intel_ds_init(void)
> char *pebs_qual = "";
> int format = x86_pmu.intel_cap.pebs_format;
>
> + if (format < 4)
> + x86_pmu.intel_cap.pebs_baseline = 0;
> +
> switch (format) {
> case 0:
> pr_cont("PEBS fmt0%c, ", pebs_type);
> @@ -2042,8 +2038,6 @@ void __init intel_ds_init(void)
> pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
> x86_pmu.pebs = 0;
> }
> - if (format != 4)
> - x86_pmu.intel_cap.pebs_baseline = 0;
> }
> }
>
> --- a/arch/x86/events/perf_event.h
> +++ b/arch/x86/events/perf_event.h
> @@ -303,8 +303,8 @@ struct cpu_hw_events {
> __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
>
> /*
> - * Only works for Intel events, which has 'small' event codes.
> - * Need to fix the rang compare for 'big' event codes, e.g AMD64_EVENTSEL_EVENT
> + * The constraint_match() function only works for 'simple' event codes
> + * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
> */
> #define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
> __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
> @@ -672,12 +672,12 @@ struct x86_pmu {
> pebs_no_xmm_regs :1;
> int pebs_record_size;
> int pebs_buffer_size;
> + int max_pebs_events;
> void (*drain_pebs)(struct pt_regs *regs);
> struct event_constraint *pebs_constraints;
> void (*pebs_aliases)(struct perf_event *event);
> - int max_pebs_events;
> unsigned long large_pebs_flags;
> - u64 force_gpr_event;
> + u64 rtm_abort_event;
>
> /*
> * Intel LBR
>
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown)
2019-04-08 16:06 ` Liang, Kan
@ 2019-04-08 16:25 ` Liang, Kan
2019-04-08 16:28 ` Peter Zijlstra
2019-04-08 22:49 ` Liang, Kan
1 sibling, 1 reply; 37+ messages in thread
From: Liang, Kan @ 2019-04-08 16:25 UTC (permalink / raw)
To: Peter Zijlstra
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
>> @@ -963,40 +963,42 @@ static u64 pebs_update_adaptive_cfg(stru
>> u64 pebs_data_cfg = 0;
>> bool gprs, tsx_weight;
>> - if ((sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) ||
>> - attr->precise_ip < 2) {
>> + if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
>> + attr->precise_ip > 1)
>> + return pebs_data_cfs;
Sorry, there are two typos. I didn't find in the previous email.
Should be pebs_data_cfg.
>> - if (sample_type & PERF_PEBS_MEMINFO_TYPE)
>> - pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
>> + if (sample_type & PERF_PEBS_MEMINFO_TYPE)
>> + pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
>> + /*
>> + * We need GPRs when:
>> + * + user requested them
>> + * + precise_ip < 2 for the non event IP
>> + * + For RTM TSX weight we need GPRs for the abort code.
>> + */
>> + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
>> + (attr->sample_regs_intr & PEBS_GPRS_REGS);
>> +
>> + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
>> + ((attr->config & INTEL_ARCH_EVENT_MASK) ==
>> + x86_pmu.rtm_abort_event);
>> +
>> + if (gprs || (attr->precise_ip < 2) || tsx_weight)
>> + pebs_data_cfg |= PEBS_DATACFG_GPRS;
>> +
>> + if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
>> + (attr->sample_regs_intr & PERF_XMM_REGS))
Should be PEBS_XMM_REGS.
Thanks,
Kan
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown)
2019-04-08 16:25 ` Liang, Kan
@ 2019-04-08 16:28 ` Peter Zijlstra
0 siblings, 0 replies; 37+ messages in thread
From: Peter Zijlstra @ 2019-04-08 16:28 UTC (permalink / raw)
To: Liang, Kan
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On Mon, Apr 08, 2019 at 12:25:17PM -0400, Liang, Kan wrote:
>
> > > @@ -963,40 +963,42 @@ static u64 pebs_update_adaptive_cfg(stru
> > > u64 pebs_data_cfg = 0;
> > > bool gprs, tsx_weight;
> > > - if ((sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) ||
> > > - attr->precise_ip < 2) {
> > > + if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
> > > + attr->precise_ip > 1)
> > > + return pebs_data_cfs;
>
> Sorry, there are two typos. I didn't find in the previous email.
> Should be pebs_data_cfg.
>
> > > - if (sample_type & PERF_PEBS_MEMINFO_TYPE)
> > > - pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
> > > + if (sample_type & PERF_PEBS_MEMINFO_TYPE)
> > > + pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
> > > + /*
> > > + * We need GPRs when:
> > > + * + user requested them
> > > + * + precise_ip < 2 for the non event IP
> > > + * + For RTM TSX weight we need GPRs for the abort code.
> > > + */
> > > + gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
> > > + (attr->sample_regs_intr & PEBS_GPRS_REGS);
> > > +
> > > + tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
> > > + ((attr->config & INTEL_ARCH_EVENT_MASK) ==
> > > + x86_pmu.rtm_abort_event);
> > > +
> > > + if (gprs || (attr->precise_ip < 2) || tsx_weight)
> > > + pebs_data_cfg |= PEBS_DATACFG_GPRS;
> > > +
> > > + if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
> > > + (attr->sample_regs_intr & PERF_XMM_REGS))
>
> Should be PEBS_XMM_REGS.
>
Ha!, clearly I compile-tested it... oh wait :-)
^ permalink raw reply [flat|nested] 37+ messages in thread
* Re: [PATCH V5 00/12] perf: Add Icelake support (kernel only, except Topdown)
2019-04-08 16:06 ` Liang, Kan
2019-04-08 16:25 ` Liang, Kan
@ 2019-04-08 22:49 ` Liang, Kan
1 sibling, 0 replies; 37+ messages in thread
From: Liang, Kan @ 2019-04-08 22:49 UTC (permalink / raw)
To: Peter Zijlstra
Cc: acme, mingo, linux-kernel, tglx, jolsa, eranian, alexander.shishkin, ak
On 4/8/2019 12:06 PM, Liang, Kan wrote:
> @@ -1875,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(str
> counts[bit]++;
> }
> - for (bit = 0; bit < size; bit++) {
> + for_each_set_bit(bit, (unsigned long *)&mask, size) {
> if ((counts[bit] == 0) && (error[bit] == 0))
> continue;
> @@ -1939,7 +1932,7 @@ static void intel_pmu_drain_pebs_icl(str
> counts[bit]++;
> }
> - for (bit = 0; bit < size; bit++) {
> + for_each_set_bit(bit, (unsigned long *)mask, size) {
> if (counts[bit] == 0)
> continue;
I have finished the tests for the changes. There is one more regression
found by another typo on ICL.
Should be "for_each_set_bit(bit, (unsigned long *)&mask, size) {"
Thanks,
Kan
^ permalink raw reply [flat|nested] 37+ messages in thread