perf, x86: Updated Broadwell patchkit

perf, x86: Updated Broadwell patchkit

[Andi Kleen]

Only minor changes to the last version. The Broadwell model number
patch now has a more expansive change log and does not 
reorder case statements anymore.

Some minor updates to commit logs.

[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.
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..71caf22 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 Client */
+	case 63: /* 22nm Haswell Server */
+	case 69: /* 22nm Haswell ULT */
+	case 70: /* 22nm Haswell Client */
 		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.
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 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.

v2: Use correct event name in description. Use EVENT() macro.
v3: Use INTEL_ARCH_EVENT_MASK. Error out for events with too small period.
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 7930b56..077205f 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.

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 077205f..55975ff 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 Client */
 		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, 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();
 
-- 
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

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

[Peter Zijlstra]

On Mon, Aug 25, 2014 at 03:43:30PM -0700, Andi Kleen wrote:
> 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.

This changelog could do with more words on the solution, esp. such that
you answer Stephanes question.

[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.

v2: Use correct event name in description. Use EVENT() macro.
v3: Use INTEL_ARCH_EVENT_MASK. Error out for events with too small period.
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 1cca4ae..53bd98d 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

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

[Andi Kleen]

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

Like this?

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a0adf58..c592d4d 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);
 }

-Andi

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

[Peter Zijlstra]

[-- Attachment #1: Type: text/plain, Size: 1861 bytes --]

On Thu, Aug 14, 2014 at 07:47:56PM +0200, Stephane Eranian wrote:
> [+perf tool maintainers]
> 
> On Thu, Aug 14, 2014 at 4:30 PM, Andi Kleen <ak@linux.intel.com> wrote:
> >
> > I understand all your points, but there's no alternative.
> > The only other way would be to disable INST_RETIRED.ALL.
> >
> You cannot do that either. INST_RETIRED:ALL is important.  I assume
> the bug applies whether or not the event is used with a filter.
> 
> I think we need to ensure that by looking at the perf.data file, one
> can reconstruct the total number of inst_Retired:all occurrences for
> the run. With a fixed period, one would do num_samples * fixed_period.
> I know the Gooda tool does that. It is used to estimate the number of
> events captured vs. the number of events occurring.

OK, I think we can make that work; 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.

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

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

[Andi Kleen]

On Thu, Aug 14, 2014 at 07:47:56PM +0200, Stephane Eranian wrote:
> [+perf tool maintainers]
> 
> On Thu, Aug 14, 2014 at 4:30 PM, Andi Kleen <ak@linux.intel.com> wrote:
> >
> > I understand all your points, but there's no alternative.
> > The only other way would be to disable INST_RETIRED.ALL.
> >
> You cannot do that either. INST_RETIRED:ALL is important.
> I assume the bug applies whether or not the event is used
> with a filter.

> 
> I think we need to ensure that by looking at the perf.data file,
> one can reconstruct the total number of inst_Retired:all
> occurrences for the run. With a fixed period, one would do
> num_samples * fixed_period. I know the Gooda tool does
> that. It is used to estimate the number of events captured
> vs. the number of events occurring.

Is that really a problem?

Normally periods are not that small, especially not for 
instruction retired. I don't think you can run such
a small period on instruction retired for
any significant time without throttling.

With sensible periods, let's say >10k, the error from
losing a few bits is very small. It would surprise
me if you can actually measure it.

There will be always much more jitter just from standard
system noise.

-Andi

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

[Stephane Eranian]

[+perf tool maintainers]

On Thu, Aug 14, 2014 at 4:30 PM, Andi Kleen <ak@linux.intel.com> wrote:
>
> I understand all your points, but there's no alternative.
> The only other way would be to disable INST_RETIRED.ALL.
>
You cannot do that either. INST_RETIRED:ALL is important.
I assume the bug applies whether or not the event is used
with a filter.

I think we need to ensure that by looking at the perf.data file,
one can reconstruct the total number of inst_Retired:all
occurrences for the run. With a fixed period, one would do
num_samples * fixed_period. I know the Gooda tool does
that. It is used to estimate the number of events captured
vs. the number of events occurring.

So what I am saying is that on BDW, we need to have
perf force PERF_SAMPLE_PERIOD even with a fixed
period is passed. The kernel cannot simply add
PERF_SAMPLE_PERIOD to the event sample_format
because the tool would get confused by the sample
record size otherwise.

I understand this is not pretty. We'd need to have
a on the evsel just before making the syscall. That
callback would be for x86 and it would check the
CPUID to force PERF_SAMPLE_PERIOD. That's
my thinking but there may be a better way of doing
this.

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

[Andi Kleen]

I understand all your points, but there's no alternative.
The only other way would be to disable INST_RETIRED.ALL.

-Andi

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

[Peter Zijlstra]

[-- Attachment #1: Type: text/plain, Size: 524 bytes --]

On Wed, Aug 13, 2014 at 06:17:48PM -0700, Andi Kleen wrote:
> v2: Use correct event name in description. Use EVENT() macro.

> +static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
> +{
> +	if ((event->hw.config & 0xffff) ==

I was thinking you should use INTEL_ARCH_EVENT_MASK or something instead
of the raw 0xFFFF there, but that X86_CONFIG() usage is nice too :-)

> +			X86_CONFIG(.event=0xc0, .umask=0x01)) {
> +		if (left < 128)
> +			left = 128;
> +		left &= ~0x3fu;
> +	}
> +	return left;
> +}

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

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

[Stephane Eranian]

On Thu, Aug 14, 2014 at 3:17 AM, Andi Kleen <andi@firstfloor.org> wrote:
> 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.
>
If you have frequency mode enabled, then I suspect this works okay.
It may be that the kernel will keep trying to set a period lower than 128
but you will correct it.

I am more worried about the case where the user sets a fixed period
with some of the bottom 6 bits set.  The apps thinks it is sampling at
X occurences per sample, when it is in fact at X - 63 (worst case).
I think this would be okay, if there was a trace of this in the sampling
buffer, i.e., PERF_SAMPLE_PERIOD. But I recall that perf record
does not request this flag when using a fixed period. So no way
of knowing what the actual period was, at least when using the
perf tool. I understand also that for this event, 64 occurrences
may not matter as much, maybe except if you use some filters
such as cmask.


> Add a new callback to enforce this, and set it for Broadwell.
>
> This is erratum BDM57 and BDM11.
>
> v2: Use correct event name in description. Use EVENT() macro.
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  arch/x86/kernel/cpu/perf_event.c       |  3 +++
>  arch/x86/kernel/cpu/perf_event.h       |  1 +
>  arch/x86/kernel/cpu/perf_event_intel.c | 19 +++++++++++++++++++
>  3 files changed, 23 insertions(+)
>
> diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
> index 0adc5e3..a0adf58 100644
> --- a/arch/x86/kernel/cpu/perf_event.c
> +++ b/arch/x86/kernel/cpu/perf_event.c
> @@ -980,6 +980,9 @@ 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 4bfb0ec..66260e1 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 & 0xffff) ==
> +                       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"     );
> @@ -2711,6 +2729,7 @@ __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 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.

v2: Use correct event name in description. Use EVENT() macro.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.c       |  3 +++
 arch/x86/kernel/cpu/perf_event.h       |  1 +
 arch/x86/kernel/cpu/perf_event_intel.c | 19 +++++++++++++++++++
 3 files changed, 23 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 0adc5e3..a0adf58 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -980,6 +980,9 @@ 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 4bfb0ec..66260e1 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 & 0xffff) ==
+			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"	);
@@ -2711,6 +2729,7 @@ __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