6 files changed, 46 insertions, 5 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 3ea8056148d8..c3555e5237cf 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -969,7 +969,7 @@ static int __init amd_core_pmu_init(void)
 		 * numbered counter following it.
 		 */
 		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
-			even_ctr_mask |= 1 << i;
+			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index b7baaa973317..2e930d8c04d9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -312,6 +312,16 @@ static int perf_ibs_init(struct perf_event *event)
 	hwc->config_base = perf_ibs->msr;
 	hwc->config = config;
 
+	/*
+	 * rip recorded by IbsOpRip will not be consistent with rsp and rbp
+	 * recorded as part of interrupt regs. Thus we need to use rip from
+	 * interrupt regs while unwinding call stack. Setting _EARLY flag
+	 * makes sure we unwind call-stack before perf sample rip is set to
+	 * IbsOpRip.
+	 */
+	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+		event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
+
 	return 0;
 }
 
@@ -683,6 +693,14 @@ fail:
 		data.raw = &raw;
 	}
 
+	/*
+	 * rip recorded by IbsOpRip will not be consistent with rsp and rbp
+	 * recorded as part of interrupt regs. Thus we need to use rip from
+	 * interrupt regs while unwinding call stack.
+	 */
+	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+		data.callchain = perf_callchain(event, iregs);
+
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
 	if (throttle) {
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index b33540e1efa8..8ae7b8b4d460 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -250,7 +250,7 @@ static struct event_constraint intel_icl_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
 	INTEL_EVENT_CONSTRAINT(0x32, 0xf),	/* SW_PREFETCH_ACCESS.* */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x56, 0xf),
 	INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff),  /* CYCLE_ACTIVITY.STALLS_TOTAL */
 	INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff),  /* CYCLE_ACTIVITY.CYCLES_MEM_ANY */
@@ -4009,6 +4009,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = {
 	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 5, 0x00000000),
 	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 6, 0x00000000),
 	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 7, 0x00000000),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		11, 0x00000000),
 	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L,		 3, 0x0000007c),
 	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE,		 3, 0x0000007c),
 	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE,		 9, 0x0000004e),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 5965d341350c..6da90c6f3390 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -852,8 +852,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),	/* SLOTS */
 
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xff),			/* MEM_TRANS_RETIRED.LOAD_LATENCY */
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),	/* MEM_INST_RETIRED.LOAD */
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),	/* MEM_INST_RETIRED.STORE */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf),	/* MEM_INST_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf),	/* MEM_INST_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf),	/* MEM_INST_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf),	/* MEM_INST_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf),	/* MEM_INST_RETIRED.ALL_STORES */
 
 	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
 
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index aec6e63c6a04..0258e0065771 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -575,6 +575,22 @@ int snb_pci2phy_map_init(int devid)
 	return 0;
 }
 
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * SNB IMC counters are 32-bit and are laid out back to back
+	 * in MMIO space. Therefore we must use a 32-bit accessor function
+	 * using readq() from uncore_mmio_read_counter() causes problems
+	 * because it is reading 64-bit at a time. This is okay for the
+	 * uncore_perf_event_update() function because it drops the upper
+	 * 32-bits but not okay for plain uncore_read_counter() as invoked
+	 * in uncore_pmu_event_start().
+	 */
+	return (u64)readl(box->io_addr + hwc->event_base);
+}
+
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
@@ -594,7 +610,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = {
 	.disable_event	= snb_uncore_imc_disable_event,
 	.enable_event	= snb_uncore_imc_enable_event,
 	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= uncore_mmio_read_counter,
+	.read_counter	= snb_uncore_imc_read_counter,
 };
 
 static struct intel_uncore_type snb_uncore_imc = {
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 0f61f46e6086..fe2edc760e60 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2762,6 +2762,7 @@ static bool hswep_has_limit_sbox(unsigned int device)
 		return false;
 
 	pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4);
+	pci_dev_put(dev);
 	if (!hswep_get_chop(capid4))
 		return true;