Re: [PATCH 1/2] perf/x86: update Haswell PEBS event constraints

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Jun 19, 2014 at 11:00:28AM -0700, Andi Kleen wrote:
> However these days I'm actually thinking of just getting
> rid of the detailed table except for PREC_DIST. All the PEBS
> controls should be noops if the event does not support PEBS

I had something like the below stuck on the 'look more at later' list
and later never really ever happened.

---
 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 ++++++++++++++--
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 38 +++++++++++++++++--------------
 4 files changed, 42 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index ae407f7226c8..f42405c9868b 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1541,6 +1541,7 @@ static int __init init_hw_perf_events(void)
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
 	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+	x86_pmu.attr_strict_pebs = 1;
 
 	for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
 		quirk->func();
@@ -1855,9 +1856,11 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 }
 
 static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
+static DEVICE_BOOL_ATTR(strict_pebs, S_IRUSR | S_IWUSR, x86_pmu.attr_strict_pebs);
 
 static struct attribute *x86_pmu_attrs[] = {
 	&dev_attr_rdpmc.attr,
+	&dev_attr_strict_pebs.attr.attr,
 	NULL,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3b2f9bdd974b..a11eeab9b611 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -413,6 +413,7 @@ struct x86_pmu {
 	 */
 	int		attr_rdpmc_broken;
 	int		attr_rdpmc;
+	bool		attr_strict_pebs;
 	struct attribute **format_attrs;
 	struct attribute **event_attrs;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa333d966886..6e68f3dc9a30 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1729,6 +1729,12 @@ static void intel_pebs_aliases_snb(struct perf_event *event)
 	}
 }
 
+#define ARCH_PERFMON_STRICT_PEBS	\
+	(ARCH_PERFMON_EVENTSEL_ANY   |	\
+	 ARCH_PERFMON_EVENTSEL_CMASK |	\
+	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
+	 ARCH_PERFMON_EVENTSEL_INV)
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -1736,8 +1742,17 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
-		x86_pmu.pebs_aliases(event);
+	if (event->attr.precise_ip) {
+		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == 0x0000)
+			return -EINVAL;
+
+		if ((event->attr.config & ARCH_PERFMON_STRICT_PEBS) &&
+		    (x86_pmu.attr_strict_pebs || !capable(CAP_SYS_ADMIN)))
+			return -EINVAL;
+
+		if (x86_pmu.pebs_aliases)
+			x86_pmu.pebs_aliases(event);
+	}
 
 	if (intel_pmu_needs_lbr_smpl(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index ae96cfa5eddd..36b1f2afa61c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -540,6 +540,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
 	INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
 	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0x1), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -547,6 +548,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
 	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
 	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0x1), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -573,6 +575,7 @@ struct event_constraint intel_slm_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
 	INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
 	INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0x1), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -588,6 +591,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
 	INTEL_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0xf), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -603,6 +607,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
 	INTEL_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0xf), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -619,6 +624,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0xf), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -634,42 +640,36 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
         INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0xf), /* generic PEBS mask */
         EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-	INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf),/* UOPS_RETIRED.ALL */
 	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
 	INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
 	INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	/* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf),
-	/* MEM_UOPS_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
 	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
 	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
-	/* MEM_UOPS_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
 	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
-	INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
+	INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf),/* MEM_UOPS_RETIRED.ALL_STORES */
 	INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
 	INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
 	INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */
-	/* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
-	INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf),
-	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
-	INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf),
-	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf),
-	/* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
-	INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
+	INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
+	INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
+	INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
 	INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */
 	INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */
-
+	INTEL_UEVENT_CONSTRAINT(0x0000, 0xf), /* generic PEBS mask */
 	EVENT_CONSTRAINT_END
 };
 
@@ -686,6 +686,10 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 				event->hw.flags |= c->flags;
 				return c;
 			}
+			if (!x86_pmu.attr_strict_pebs &&
+			    capable(CAP_SYS_ADMIN) &&
+			    !c->code)
+				return c;
 		}
 	}