[PATCH 1/5] perf, x86: Remove incorrect model number from Haswell perf

[PATCH 1/5] perf, x86: Remove incorrect model number from Haswell perf

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

71 is a Broadwell, not a Haswell. The model number was added
by mistake earlier.

Remove it for now, until it can be re-added later with
real Broadwell support.

In practice it does not cause a lot of issues because the Broadwell
PMU is very similar to Haswell, but some details were wrong,
and it's better to handle it correctly.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 89bc750..f962e26 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2544,7 +2544,6 @@ __init int intel_pmu_init(void)
 	case 63:
 	case 69:
 	case 70:
-	case 71:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-- 
1.9.3

[PATCH 2/5] perf, x86: Document all Haswell models

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add names for each Haswell model as requested by Peter.

v2: Remove Crystall Well name.
v3: Change names
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f962e26..7c9f78e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2540,10 +2540,10 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case 60: /* 22nm Haswell */
-	case 63:
-	case 69:
-	case 70:
+	case 60: /* 22nm Haswell Core */
+	case 63: /* 22nm Haswell Server */
+	case 69: /* 22nm Haswell ULT */
+	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-- 
1.9.3

[PATCH 3/5] perf, x86: Add Broadwell core support

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add Broadwell support for Broadwell Client to perf.
This is very similar to Haswell.  It uses a new cache event table,
because there were various changes there.

The constraint list has one new event that needs to be handled over Haswell.

The PEBS event list is the same, so we reuse Haswell's.

v2: Remove unnamed model numbers.
v3: Rename cache event list to hsw_*. Change names.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 150 +++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7c9f78e..61b5404 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+static __initconst const u64 hsw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x1b7,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 hsw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x2d5,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc0202d5,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc020122,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2565,6 +2694,27 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* 14nm Broadwell Core-M */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
-- 
1.9.3

[PATCH 4/5] perf, x86: Add INST_RETIRED.ALL workarounds

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

On Broadwell INST_RETIRED.ALL cannot be used with any period
that doesn't have the lowest 6 bits cleared. And the period
should not be smaller than 128.

Add a new callback to enforce this, and set it for Broadwell.

This is erratum BDM57 and BDM11.

How does this handle the case when an app requests a specific
period with some of the bottom bits set

The apps thinks it is sampling at X occurences per sample, when it is
in fact at X - 63 (worst case).

Short answer:

Any useful instruction sampling period needs to be 4-6 orders
of magnitude larger than 128, as an PMI every 128 instructions
would instantly overwhelm the system and be throttled.
So the +-64 error from this is really small compared to the
period, much smaller than normal system jitter.

Long answer:

<write up by Peter:>

IFF we guarantee perf_event_attr::sample_period >= 128.

Suppose we start out with sample_period=192; then we'll set period_left
to 192, we'll end up with left = 128 (we truncate the lower bits). We
get an interrupt, find that period_left = 64 (>0 so we return 0 and
don't get an overflow handler), up that to 128. Then we trigger again,
at n=256. Then we find period_left = -64 (<=0 so we return 1 and do get
an overflow). We increment with sample_period so we get left = 128. We
fire again, at n=384, period_left = 0 (<=0 so we return 1 and get an
overflow). And on and on.

So while the individual interrupts are 'wrong' we get then with
interval=256,128 in exactly the right ratio to average out at 192. And
this works for everything >=128.

So the num_samples*fixed_period thing is still entirely correct +- 127,
which is good enough I'd say, as you already have that error anyhow.

So no need to 'fix' the tools, al we need to do is refuse to create
INST_RETIRED:ALL events with sample_period < 128.

v2: Use correct event name in description. Use EVENT() macro.
v3: Use INTEL_ARCH_EVENT_MASK. Error out for events with too small period.
v4: Expand description.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.c       |  9 +++++++++
 arch/x86/kernel/cpu/perf_event.h       |  1 +
 arch/x86/kernel/cpu/perf_event_intel.c | 19 +++++++++++++++++++
 3 files changed, 29 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 0adc5e3..a6e4724 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -443,6 +443,12 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
+	if (event->attr.sample_period && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, event->attr.sample_period) >
+				event->attr.sample_period)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
@@ -980,6 +986,9 @@ int x86_perf_event_set_period(struct perf_event *event)
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
+	if (x86_pmu.limit_period)
+		left = x86_pmu.limit_period(event, left);
+
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index de81627..a46e391 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -456,6 +456,7 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 	bool		late_ack;
+	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
 
 	/*
 	 * sysfs attrs
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61b5404..6733a7f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2034,6 +2034,24 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	return c;
 }
 
+/*
+ * Broadwell:
+ * The INST_RETIRED.ALL period always needs to have lowest
+ * 6bits cleared (BDM57). It shall not use a period smaller
+ * than 100 (BDM11). We combine the two to enforce
+ * a min-period of 128.
+ */
+static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
+{
+	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
+			X86_CONFIG(.event=0xc0, .umask=0x01)) {
+		if (left < 128)
+			left = 128;
+		left &= ~0x3fu;
+	}
+	return left;
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -2712,6 +2730,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
 		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.limit_period = bdw_limit_period;
 		pr_cont("Broadwell events, ");
 		break;
 
-- 
1.9.3

[PATCH 5/5] perf, x86: Use Broadwell cache event list for Haswell

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Use the newly added Broadwell cache event list for Haswell too.
All Haswell and Broadwell events and offcore masks used in these lists
are identical.

However Haswell is very different from the Sandy Bridge
list that was used previously. That fixes a wide range of mis-counting
cache events.

The node events are now only for retired memory events, so prefetching
and speculative memory accesses are not included. They are PEBS
capable now, which makes it much easier to sample for them, plus it's
possible to create address maps with -d.

The prefetch events are gone now. They way the hardware counts
them is very misleading (some prefetches included, others not), so
it seemed best to leave them out.

v2: Change name of variable.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6733a7f..ecea3e5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2692,8 +2692,8 @@ __init int intel_pmu_init(void)
 	case 69: /* 22nm Haswell ULT */
 	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 
-- 
1.9.3

Re: [PATCH 1/5] perf, x86: Remove incorrect model number from Haswell perf

[Peter Zijlstra]

Thanks Andi

[tip:perf/core] perf/x86/intel: Remove incorrect model number from Haswell perf

[tip-bot for Andi Kleen]

Commit-ID:  b76146851eeba6ad9fef982e8cf7cd8ebd4d30e1
Gitweb:     http://git.kernel.org/tip/b76146851eeba6ad9fef982e8cf7cd8ebd4d30e1
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Sep 2014 11:44:11 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 24 Sep 2014 14:48:15 +0200

perf/x86/intel: Remove incorrect model number from Haswell perf

71 is a Broadwell, not a Haswell. The model number was added
by mistake earlier.

Remove it for now, until it can be re-added later with
real Broadwell support.

In practice it does not cause a lot of issues because the Broadwell
PMU is very similar to Haswell, but some details were wrong,
and it's better to handle it correctly.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: eranian@google.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Link: http://lkml.kernel.org/r/1409683455-29168-1-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 89bc750..f962e26 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2544,7 +2544,6 @@ __init int intel_pmu_init(void)
 	case 63:
 	case 69:
 	case 70:
-	case 71:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));

[tip:perf/core] perf/x86/intel: Document all Haswell models

[tip-bot for Andi Kleen]

Commit-ID:  d86c8eaf95700d932bdfa8a4f7b4e6d28949fd84
Gitweb:     http://git.kernel.org/tip/d86c8eaf95700d932bdfa8a4f7b4e6d28949fd84
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Sep 2014 11:44:12 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 24 Sep 2014 14:48:16 +0200

perf/x86/intel: Document all Haswell models

Add names for each Haswell model as requested by Peter.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1409683455-29168-2-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f962e26..7c9f78e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2540,10 +2540,10 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case 60: /* 22nm Haswell */
-	case 63:
-	case 69:
-	case 70:
+	case 60: /* 22nm Haswell Core */
+	case 63: /* 22nm Haswell Server */
+	case 69: /* 22nm Haswell ULT */
+	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));

[tip:perf/core] perf/x86/intel: Add Broadwell core support

[tip-bot for Andi Kleen]

Commit-ID:  86a349a28b249bf4c3b396af3cc550760dedb456
Gitweb:     http://git.kernel.org/tip/86a349a28b249bf4c3b396af3cc550760dedb456
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Sep 2014 11:44:13 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 24 Sep 2014 14:48:18 +0200

perf/x86/intel: Add Broadwell core support

Add Broadwell support for Broadwell Client to perf.  This is very
similar to Haswell.  It uses a new cache event table, because there
were various changes there.

The constraint list has one new event that needs to be handled over
Haswell.

The PEBS event list is the same, so we reuse Haswell's.

[fengguang.wu: make intel_bdw_event_constraints[] static]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1409683455-29168-3-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 150 +++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7c9f78e..5671566 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+static __initconst const u64 hsw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x1b7,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 hsw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x2d5,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc0202d5ull,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc020122ull,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2565,6 +2694,27 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* 14nm Broadwell Core-M */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:

[tip:perf/core] perf/x86: Add INST_RETIRED.ALL workarounds

[tip-bot for Andi Kleen]

Commit-ID:  c46e665f037743bbce7887e7c55750713eb7fb09
Gitweb:     http://git.kernel.org/tip/c46e665f037743bbce7887e7c55750713eb7fb09
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Sep 2014 11:44:14 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 24 Sep 2014 14:48:19 +0200

perf/x86: Add INST_RETIRED.ALL workarounds

On Broadwell INST_RETIRED.ALL cannot be used with any period
that doesn't have the lowest 6 bits cleared. And the period
should not be smaller than 128.

Add a new callback to enforce this, and set it for Broadwell.

This is erratum BDM57 and BDM11.

How does this handle the case when an app requests a specific
period with some of the bottom bits set

The apps thinks it is sampling at X occurences per sample, when it is
in fact at X - 63 (worst case).

Short answer:

Any useful instruction sampling period needs to be 4-6 orders
of magnitude larger than 128, as an PMI every 128 instructions
would instantly overwhelm the system and be throttled.
So the +-64 error from this is really small compared to the
period, much smaller than normal system jitter.

Long answer:

<write up by Peter:>

IFF we guarantee perf_event_attr::sample_period >= 128.

Suppose we start out with sample_period=192; then we'll set period_left
to 192, we'll end up with left = 128 (we truncate the lower bits). We
get an interrupt, find that period_left = 64 (>0 so we return 0 and
don't get an overflow handler), up that to 128. Then we trigger again,
at n=256. Then we find period_left = -64 (<=0 so we return 1 and do get
an overflow). We increment with sample_period so we get left = 128. We
fire again, at n=384, period_left = 0 (<=0 so we return 1 and get an
overflow). And on and on.

So while the individual interrupts are 'wrong' we get then with
interval=256,128 in exactly the right ratio to average out at 192. And
this works for everything >=128.

So the num_samples*fixed_period thing is still entirely correct +- 127,
which is good enough I'd say, as you already have that error anyhow.

So no need to 'fix' the tools, al we need to do is refuse to create
INST_RETIRED:ALL events with sample_period < 128.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Cc: Mark Davies <junk@eslaf.co.uk>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1409683455-29168-4-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event.c       |  9 +++++++++
 arch/x86/kernel/cpu/perf_event.h       |  1 +
 arch/x86/kernel/cpu/perf_event_intel.c | 19 +++++++++++++++++++
 3 files changed, 29 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 0646d3b..918d75f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -443,6 +443,12 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
+	if (event->attr.sample_period && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, event->attr.sample_period) >
+				event->attr.sample_period)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
@@ -980,6 +986,9 @@ int x86_perf_event_set_period(struct perf_event *event)
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
+	if (x86_pmu.limit_period)
+		left = x86_pmu.limit_period(event, left);
+
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fc5eb39..d98a34d 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -445,6 +445,7 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 	bool		late_ack;
+	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
 
 	/*
 	 * sysfs attrs
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 5671566..bbcd0d2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2034,6 +2034,24 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	return c;
 }
 
+/*
+ * Broadwell:
+ * The INST_RETIRED.ALL period always needs to have lowest
+ * 6bits cleared (BDM57). It shall not use a period smaller
+ * than 100 (BDM11). We combine the two to enforce
+ * a min-period of 128.
+ */
+static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
+{
+	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
+			X86_CONFIG(.event=0xc0, .umask=0x01)) {
+		if (left < 128)
+			left = 128;
+		left &= ~0x3fu;
+	}
+	return left;
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -2712,6 +2730,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
 		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.limit_period = bdw_limit_period;
 		pr_cont("Broadwell events, ");
 		break;
 

[tip:perf/core] perf/x86/intel: Use Broadwell cache event list for Haswell

[tip-bot for Andi Kleen]

Commit-ID:  fdda3c4aacec30bdf3c10904d0c32409145dc1b6
Gitweb:     http://git.kernel.org/tip/fdda3c4aacec30bdf3c10904d0c32409145dc1b6
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Tue, 2 Sep 2014 11:44:15 -0700
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 24 Sep 2014 14:48:20 +0200

perf/x86/intel: Use Broadwell cache event list for Haswell

Use the newly added Broadwell cache event list for Haswell too.
All Haswell and Broadwell events and offcore masks used in these lists
are identical.

However Haswell is very different from the Sandy Bridge
list that was used previously. That fixes a wide range of mis-counting
cache events.

The node events are now only for retired memory events, so prefetching
and speculative memory accesses are not included. They are PEBS
capable now, which makes it much easier to sample for them, plus it's
possible to create address maps with -d.

The prefetch events are gone now. They way the hardware counts
them is very misleading (some prefetches included, others not), so
it seemed best to leave them out.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1409683455-29168-5-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index bbcd0d2..3851def 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2692,8 +2692,8 @@ __init int intel_pmu_init(void)
 	case 69: /* 22nm Haswell ULT */
 	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 

[tip:perf/urgent] perf/x86/intel: Revert incomplete and undocumented Broadwell client support

[tip-bot for Ingo Molnar]

Commit-ID:  1776b10627e486dd431fe72d8d47e5a865cf65d1
Gitweb:     http://git.kernel.org/tip/1776b10627e486dd431fe72d8d47e5a865cf65d1
Author:     Ingo Molnar <mingo@kernel.org>
AuthorDate: Wed, 29 Oct 2014 10:18:17 +0100
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Wed, 29 Oct 2014 11:07:58 +0100

perf/x86/intel: Revert incomplete and undocumented Broadwell client support

These patches:

  86a349a28b24 ("perf/x86/intel: Add Broadwell core support")
  c46e665f0377 ("perf/x86: Add INST_RETIRED.ALL workarounds")
  fdda3c4aacec ("perf/x86/intel: Use Broadwell cache event list for Haswell")

introduced magic constants and unexplained changes:

  https://lkml.org/lkml/2014/10/28/1128
  https://lkml.org/lkml/2014/10/27/325
  https://lkml.org/lkml/2014/8/27/546
  https://lkml.org/lkml/2014/10/28/546

Peter Zijlstra has attempted to help out, to clean up the mess:

  https://lkml.org/lkml/2014/10/28/543

But has not received helpful and constructive replies which makes
me doubt wether it can all be finished in time until v3.18 is
released.

Despite various review feedback the author (Andi Kleen) has answered
only few of the review questions and has generally been uncooperative,
only giving replies when prompted repeatedly, and only giving minimal
answers instead of constructively explaining and helping along the effort.

That kind of behavior is not acceptable.

There's also a boot crash on Intel E5-1630 v3 CPUs reported for another
commit from Andi Kleen:

  e735b9db12d7 ("perf/x86/intel/uncore: Add Haswell-EP uncore support")

  https://lkml.org/lkml/2014/10/22/730

Which is not yet resolved. The uncore driver is independent in theory,
but the crash makes me worry about how well all these patches were
tested and makes me uneasy about the level of interminging that the
Broadwell and Haswell code has received by the commits above.

As a first step to resolve the mess revert the Broadwell client commits
back to the v3.17 version, before we run out of time and problematic
code hits a stable upstream kernel.

( If the Haswell-EP crash is not resolved via a simple fix then we'll have
  to revert the Haswell-EP uncore driver as well. )

The Broadwell client series has to be submitted in a clean fashion, with
single, well documented changes per patch. If they are submitted in time
and are accepted during review then they can possibly go into v3.19 but
will need additional scrutiny due to the rocky history of this patch set.

Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: eranian@google.com
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1409683455-29168-3-git-send-email-andi@firstfloor.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/perf_event.c       |   9 --
 arch/x86/kernel/cpu/perf_event.h       |   1 -
 arch/x86/kernel/cpu/perf_event_intel.c | 173 +--------------------------------
 3 files changed, 2 insertions(+), 181 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 66451a6..143e5f5 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -445,12 +445,6 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == PERF_TYPE_RAW)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
-		if (x86_pmu.limit_period(event, event->attr.sample_period) >
-				event->attr.sample_period)
-			return -EINVAL;
-	}
-
 	return x86_setup_perfctr(event);
 }
 
@@ -988,9 +982,6 @@ int x86_perf_event_set_period(struct perf_event *event)
 	if (left > x86_pmu.max_period)
 		left = x86_pmu.max_period;
 
-	if (x86_pmu.limit_period)
-		left = x86_pmu.limit_period(event, left);
-
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
 	/*
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d98a34d..fc5eb39 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -445,7 +445,6 @@ struct x86_pmu {
 	struct x86_pmu_quirk *quirks;
 	int		perfctr_second_write;
 	bool		late_ack;
-	unsigned	(*limit_period)(struct perf_event *event, unsigned l);
 
 	/*
 	 * sysfs attrs
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a73947c..944bf01 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,15 +220,6 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-static struct event_constraint intel_bdw_event_constraints[] = {
-	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
-	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
-	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
-	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
-	EVENT_CONSTRAINT_END
-};
-
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -424,126 +415,6 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
-static __initconst const u64 hsw_hw_cache_event_ids
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(L1D ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
-		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(L1I ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
-		[ C(RESULT_ACCESS) ] = 0x1b7,
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
-                   L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x1b7,
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
-		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x1b7,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(DTLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
-		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
-		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
- [ C(ITLB) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
-		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
- [ C(BPU ) ] = {
-	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
-		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
-	},
- },
-};
-
-static __initconst const u64 hsw_hw_cache_extra_regs
-				[PERF_COUNT_HW_CACHE_MAX]
-				[PERF_COUNT_HW_CACHE_OP_MAX]
-				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
-{
- [ C(LL  ) ] = {
-	[ C(OP_READ) ] = {
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
-		[ C(RESULT_ACCESS) ] = 0x2d5,
-		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
-                   L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x3fbc0202d5ull,
-	},
-	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
-		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
-		[ C(RESULT_MISS)   ] = 0x3fbc020122ull,
-	},
-	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0,
-		[ C(RESULT_MISS)   ] = 0x0,
-	},
- },
-};
-
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2034,24 +1905,6 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	return c;
 }
 
-/*
- * Broadwell:
- * The INST_RETIRED.ALL period always needs to have lowest
- * 6bits cleared (BDM57). It shall not use a period smaller
- * than 100 (BDM11). We combine the two to enforce
- * a min-period of 128.
- */
-static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
-{
-	if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
-			X86_CONFIG(.event=0xc0, .umask=0x01)) {
-		if (left < 128)
-			left = 128;
-		left &= ~0x3fu;
-	}
-	return left;
-}
-
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -2692,8 +2545,8 @@ __init int intel_pmu_init(void)
 	case 69: /* 22nm Haswell ULT */
 	case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
 		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 
@@ -2712,28 +2565,6 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
-	case 61: /* 14nm Broadwell Core-M */
-		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-
-		intel_pmu_lbr_init_snb();
-
-		x86_pmu.event_constraints = intel_bdw_event_constraints;
-		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
-		x86_pmu.extra_regs = intel_snbep_extra_regs;
-		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		/* all extra regs are per-cpu when HT is on */
-		x86_pmu.er_flags |= ERF_HAS_RSP_1;
-		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
-
-		x86_pmu.hw_config = hsw_hw_config;
-		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
-		x86_pmu.limit_period = bdw_limit_period;
-		pr_cont("Broadwell events, ");
-		break;
-
 	default:
 		switch (x86_pmu.version) {
 		case 1:

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Peter Zijlstra]

On Tue, Nov 04, 2014 at 02:14:59PM +0100, Stephane Eranian wrote:
> What's happening with Broadwell support?
> I don't see any support in 3.18-rc2. We need
> this ASAP now.

lkml.kernel.org/r/tip-1776b10627e486dd431fe72d8d47e5a865cf65d1@git.kernel.org

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Stephane Eranian]

Hi,

What's happening with Broadwell support?
I don't see any support in 3.18-rc2. We need
this ASAP now.


On Mon, Sep 1, 2014 at 3:51 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> On Mon, Aug 25, 2014 at 03:43:29PM -0700, Andi Kleen wrote:
>
>> +     case 61: /* Broadwell Client */
>
> Again, no other description has "Client" in.

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Peter Zijlstra]

On Mon, Aug 25, 2014 at 03:43:29PM -0700, Andi Kleen wrote:

> +	case 61: /* Broadwell Client */

Again, no other description has "Client" in.

[PATCH 3/5] perf, x86: Add Broadwell core support

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add Broadwell support for Broadwell Client to perf.
This is very similar to Haswell.  It uses a new cache event table,
because there were various changes there.

The constraint list has one new event that needs to be handled over Haswell.

The PEBS event list is the same, so we reuse Haswell's.

v2: Remove unnamed model numbers.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 150 +++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 71caf22..7930b56 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+static __initconst const u64 bdw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x1b7,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 bdw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x2d5,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc0202d5,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc020122,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2565,6 +2694,27 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* Broadwell Client */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, bdw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, bdw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
-- 
1.9.3

[PATCH 3/5] perf, x86: Add Broadwell core support

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add Broadwell support for Broadwell Client to perf.
This is very similar to Haswell.  It uses a new cache event table,
because there were various changes there.

The constraint list has one new event that needs to be handled over Haswell.

The PEBS event list is the same, so we reuse Haswell's.

v2: Remove unnamed model numbers.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 150 +++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0e9c272..1cca4ae 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+static __initconst const u64 bdw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x1b7,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 bdw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x2d5,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc0202d5,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc020122,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2565,6 +2694,27 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* Broadwell Client */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, bdw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, bdw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
-- 
1.9.3

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Peter Zijlstra]

[-- Attachment #1: Type: text/plain, Size: 373 bytes --]

On Thu, Aug 14, 2014 at 07:58:54AM -0700, Andi Kleen wrote:

> Really, Peter, it's futile to try to reproduce http://ark.intel.com
> in perf comments. If you need information on specific Intel
> products please look it up there.

ark.intel.com is useless, I never can find anything there.
The best I can find is wikipedia and they stopped listing model numbers
long ago :/

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Andi Kleen]

On Thu, Aug 14, 2014 at 09:32:10AM +0200, Peter Zijlstra wrote:
> On Thu, Aug 14, 2014 at 09:07:22AM +0200, Peter Zijlstra wrote:
> > On Wed, Aug 13, 2014 at 06:17:47PM -0700, Andi Kleen wrote:
> > 
> > > v2: Remove unnamed model numbers.
> > 
> > > +	case 61: /* Broadwell Client */
> > 
> > Seriously? So 71 and 79 are fine as a number but you cannot name them?
> 
> would something like:
> 
> 	case 71: /* 14nm Broadwell TBA */
> 
> work? Where you then will update the description at the appropriate
> time?

There won't be a single description, it will turn into all kinds 
of products. The names I used are the ones we use.

Really, Peter, it's futile to try to reproduce http://ark.intel.com
in perf comments. If you need information on specific Intel
products please look it up there.
 
-Andi

-- 
ak@linux.intel.com -- Speaking for myself only

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Peter Zijlstra]

[-- Attachment #1: Type: text/plain, Size: 433 bytes --]

On Thu, Aug 14, 2014 at 09:07:22AM +0200, Peter Zijlstra wrote:
> On Wed, Aug 13, 2014 at 06:17:47PM -0700, Andi Kleen wrote:
> 
> > v2: Remove unnamed model numbers.
> 
> > +	case 61: /* Broadwell Client */
> 
> Seriously? So 71 and 79 are fine as a number but you cannot name them?

would something like:

	case 71: /* 14nm Broadwell TBA */

work? Where you then will update the description at the appropriate
time?

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]

Re: [PATCH 3/5] perf, x86: Add Broadwell core support

[Peter Zijlstra]

[-- Attachment #1: Type: text/plain, Size: 206 bytes --]

On Wed, Aug 13, 2014 at 06:17:47PM -0700, Andi Kleen wrote:

> v2: Remove unnamed model numbers.

> +	case 61: /* Broadwell Client */

Seriously? So 71 and 79 are fine as a number but you cannot name them?

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]

[PATCH 3/5] perf, x86: Add Broadwell core support

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add Broadwell support for Broadwell Client to perf.
This is very similar to Haswell.  It uses a new cache event table,
because there were various changes there.

The constraint list has one new event that needs to be handled over Haswell.

The PEBS event list is the same, so we reuse Haswell's.

v2: Remove unnamed model numbers.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 150 +++++++++++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 03befdd..4bfb0ec 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids
 
 };
 
+static __initconst const u64 bdw_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x151, 	/* L1D.REPLACEMENT */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x280, 	/* ICACHE.MISSES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x1b7,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x1b7, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x1b7,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0, 	/* MEM_UOPS_RETIRED.ALL_LOADS */
+		[ C(RESULT_MISS)   ] = 0x108, 	/* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0, 	/* MEM_UOPS_RETIRED.ALL_STORES */
+		[ C(RESULT_MISS)   ] = 0x149, 	/* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x6085, 	/* ITLB_MISSES.STLB_HIT */
+		[ C(RESULT_MISS)   ] = 0x185, 	/* ITLB_MISSES.MISS_CAUSES_A_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0xc4, 	/* BR_INST_RETIRED.ALL_BRANCHES */
+		[ C(RESULT_MISS)   ] = 0xc5, 	/* BR_MISP_RETIRED.ALL_BRANCHES */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 bdw_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */
+		[ C(RESULT_ACCESS) ] = 0x2d5,
+		/* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE|
+                   L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc0202d5,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x122, 	/* OFFCORE_RESPONSE:ALL_RFO */
+		/* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */
+		[ C(RESULT_MISS)   ] = 0x3fbc020122,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+};
+
 static __initconst const u64 westmere_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2564,6 +2693,27 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* Broadwell Client */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, bdw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, bdw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
-- 
1.9.3