3 files changed, 24 insertions, 31 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cb8522290e6a..86138267b68a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2110,6 +2110,27 @@ again:
 		    GLOBAL_STATUS_LBRS_FROZEN);
 	if (!status)
 		goto done;
+	/*
+	 * In case multiple PEBS events are sampled at the same time,
+	 * it is possible to have GLOBAL_STATUS bit 62 set indicating
+	 * PEBS buffer overflow and also seeing at most 3 PEBS counters
+	 * having their bits set in the status register. This is a sign
+	 * that there was at least one PEBS record pending at the time
+	 * of the PMU interrupt. PEBS counters must only be processed
+	 * via the drain_pebs() calls and not via the regular sample
+	 * processing loop coming after that the function, otherwise
+	 * phony regular samples may be generated in the sampling buffer
+	 * not marked with the EXACT tag. Another possibility is to have
+	 * one PEBS event and at least one non-PEBS event whic hoverflows
+	 * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will
+	 * not be set, yet the overflow status bit for the PEBS counter will
+	 * be on Skylake.
+	 *
+	 * To avoid this problem, we systematically ignore the PEBS-enabled
+	 * counters from the GLOBAL_STATUS mask and we always process PEBS
+	 * events via drain_pebs().
+	 */
+	status &= ~cpuc->pebs_enabled;
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
@@ -2117,15 +2138,6 @@ again:
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
 		handled++;
 		x86_pmu.drain_pebs(regs);
-		/*
-		 * There are cases where, even though, the PEBS ovfl bit is set
-		 * in GLOBAL_OVF_STATUS, the PEBS events may also have their
-		 * overflow bits set for their counters. We must clear them
-		 * here because they have been processed as exact samples in
-		 * the drain_pebs() routine. They must not be processed again
-		 * in the for_each_bit_set() loop for regular samples below.
-		 */
-		status &= ~cpuc->pebs_enabled;
 		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 	}
 
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8f82b02934fa..0c45cc8e64ba 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -7,9 +7,9 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel_rdt_common.h>
 #include "../perf_event.h"
 
-#define MSR_IA32_PQR_ASSOC	0x0c8f
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
@@ -24,32 +24,13 @@ static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 static bool cqm_enabled, mbm_enabled;
 unsigned int mbm_socket_max;
 
-/**
- * struct intel_pqr_state - State cache for the PQR MSR
- * @rmid:		The cached Resource Monitoring ID
- * @closid:		The cached Class Of Service ID
- * @rmid_usecnt:	The usage counter for rmid
- *
- * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
- * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
- * contains both parts, so we need to cache them.
- *
- * The cache also helps to avoid pointless updates if the value does
- * not change.
- */
-struct intel_pqr_state {
-	u32			rmid;
-	u32			closid;
-	int			rmid_usecnt;
-};
-
 /*
  * The cached intel_pqr_state is strictly per CPU and can never be
  * updated from a remote CPU. Both functions which modify the state
  * (intel_cqm_event_start and intel_cqm_event_stop) are called with
  * interrupts disabled, which is sufficient for the protection.
  */
-static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 static struct hrtimer *mbm_timers;
 /**
  * struct sample - mbm event's (local or total) data
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 272427700d48..e6832be714bc 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -669,7 +669,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
-	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+	UNCORE_EVENT_CONSTRAINT(0x1f, 0xe),
 	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
 	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),