Merge tag 'perf-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 perf event updates from Ingo Molnar:

 - Fix address filtering for Intel/PT,ARM/CoreSight

 - Enable Intel/PEBS format 5

 - Allow more fixed-function counters for x86

 - Intel/PT: Enable not recording Taken-Not-Taken packets

 - Add a few branch-types

* tag 'perf-core-2022-03-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/uncore: Fix the build on !CONFIG_PHYS_ADDR_T_64BIT
  perf: Add irq and exception return branch types
  perf/x86/intel/uncore: Make uncore_discovery clean for 64 bit addresses
  perf/x86/intel/pt: Add a capability and config bit for disabling TNTs
  perf/x86/intel/pt: Add a capability and config bit for event tracing
  perf/x86/intel: Increase max number of the fixed counters
  KVM: x86: use the KVM side max supported fixed counter
  perf/x86/intel: Enable PEBS format 5
  perf/core: Allow kernel address filter when not filtering the kernel
  perf/x86/intel/pt: Fix address filter config for 32-bit kernel
  perf/core: Fix address filter parser for multiple filters
  x86: Share definition of __is_canonical_address()
  perf/x86/intel/pt: Relax address filter validation

23 files changed, 161 insertions, 54 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a3c7ca876aeb..e88791b420ee 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -181,6 +181,27 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_v5_gen_event_constraints[] __read_mostly =
+{
+	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 */
+	FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
+	FIXED_EVENT_CONSTRAINT(0x0500, 4),
+	FIXED_EVENT_CONSTRAINT(0x0600, 5),
+	FIXED_EVENT_CONSTRAINT(0x0700, 6),
+	FIXED_EVENT_CONSTRAINT(0x0800, 7),
+	FIXED_EVENT_CONSTRAINT(0x0900, 8),
+	FIXED_EVENT_CONSTRAINT(0x0a00, 9),
+	FIXED_EVENT_CONSTRAINT(0x0b00, 10),
+	FIXED_EVENT_CONSTRAINT(0x0c00, 11),
+	FIXED_EVENT_CONSTRAINT(0x0d00, 12),
+	FIXED_EVENT_CONSTRAINT(0x0e00, 13),
+	FIXED_EVENT_CONSTRAINT(0x0f00, 14),
+	FIXED_EVENT_CONSTRAINT(0x1000, 15),
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
@@ -6308,7 +6329,9 @@ __init int intel_pmu_init(void)
 			pr_cont("generic architected perfmon v1, ");
 			name = "generic_arch_v1";
 			break;
-		default:
+		case 2:
+		case 3:
+		case 4:
 			/*
 			 * default constraints for v2 and up
 			 */
@@ -6316,6 +6339,21 @@ __init int intel_pmu_init(void)
 			pr_cont("generic architected perfmon, ");
 			name = "generic_arch_v2+";
 			break;
+		default:
+			/*
+			 * The default constraints for v5 and up can support up to
+			 * 16 fixed counters. For the fixed counters 4 and later,
+			 * the pseudo-encoding is applied.
+			 * The constraints may be cut according to the CPUID enumeration
+			 * by inserting the EVENT_CONSTRAINT_END.
+			 */
+			if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED)
+				x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
+			intel_v5_gen_event_constraints[x86_pmu.num_counters_fixed].weight = -1;
+			x86_pmu.event_constraints = intel_v5_gen_event_constraints;
+			pr_cont("generic architected perfmon, ");
+			name = "generic_arch_v5+";
+			break;
 		}
 	}
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2e215369df4a..376cc3d66094 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1203,7 +1203,10 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 	if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
 		base = MSR_RELOAD_FIXED_CTR0;
 		idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-		value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
+		if (x86_pmu.intel_cap.pebs_format < 5)
+			value = ds->pebs_event_reset[MAX_PEBS_EVENTS_FMT4 + idx];
+		else
+			value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
 	}
 	wrmsrl(base + idx, value);
 }
@@ -1232,8 +1235,12 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 		}
 	}
 
-	if (idx >= INTEL_PMC_IDX_FIXED)
-		idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+	if (idx >= INTEL_PMC_IDX_FIXED) {
+		if (x86_pmu.intel_cap.pebs_format < 5)
+			idx = MAX_PEBS_EVENTS_FMT4 + (idx - INTEL_PMC_IDX_FIXED);
+		else
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+	}
 
 	/*
 	 * Use auto-reload if possible to save a MSR write in the PMI.
@@ -2204,6 +2211,7 @@ void __init intel_ds_init(void)
 			break;
 
 		case 4:
+		case 5:
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
 			x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
 			if (x86_pmu.intel_cap.pebs_baseline) {
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 669c2be14784..fe1742c4ca49 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1329,10 +1329,10 @@ static int branch_map[X86_BR_TYPE_MAP_MAX] = {
 	PERF_BR_SYSCALL,	/* X86_BR_SYSCALL */
 	PERF_BR_SYSRET,		/* X86_BR_SYSRET */
 	PERF_BR_UNKNOWN,	/* X86_BR_INT */
-	PERF_BR_UNKNOWN,	/* X86_BR_IRET */
+	PERF_BR_ERET,		/* X86_BR_IRET */
 	PERF_BR_COND,		/* X86_BR_JCC */
 	PERF_BR_UNCOND,		/* X86_BR_JMP */
-	PERF_BR_UNKNOWN,	/* X86_BR_IRQ */
+	PERF_BR_IRQ,		/* X86_BR_IRQ */
 	PERF_BR_IND_CALL,	/* X86_BR_IND_CALL */
 	PERF_BR_UNKNOWN,	/* X86_BR_ABORT */
 	PERF_BR_UNKNOWN,	/* X86_BR_IN_TX */
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 2d33bba9a144..82ef87e9a897 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -13,6 +13,8 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/types.h>
+#include <linux/bits.h>
+#include <linux/limits.h>
 #include <linux/slab.h>
 #include <linux/device.h>
 
@@ -57,6 +59,8 @@ static struct pt_cap_desc {
 	PT_CAP(mtc,			0, CPUID_EBX, BIT(3)),
 	PT_CAP(ptwrite,			0, CPUID_EBX, BIT(4)),
 	PT_CAP(power_event_trace,	0, CPUID_EBX, BIT(5)),
+	PT_CAP(event_trace,		0, CPUID_EBX, BIT(7)),
+	PT_CAP(tnt_disable,		0, CPUID_EBX, BIT(8)),
 	PT_CAP(topa_output,		0, CPUID_ECX, BIT(0)),
 	PT_CAP(topa_multiple_entries,	0, CPUID_ECX, BIT(1)),
 	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
@@ -108,6 +112,8 @@ PMU_FORMAT_ATTR(tsc,		"config:10"	);
 PMU_FORMAT_ATTR(noretcomp,	"config:11"	);
 PMU_FORMAT_ATTR(ptw,		"config:12"	);
 PMU_FORMAT_ATTR(branch,		"config:13"	);
+PMU_FORMAT_ATTR(event,		"config:31"	);
+PMU_FORMAT_ATTR(notnt,		"config:55"	);
 PMU_FORMAT_ATTR(mtc_period,	"config:14-17"	);
 PMU_FORMAT_ATTR(cyc_thresh,	"config:19-22"	);
 PMU_FORMAT_ATTR(psb_period,	"config:24-27"	);
@@ -116,6 +122,8 @@ static struct attribute *pt_formats_attr[] = {
 	&format_attr_pt.attr,
 	&format_attr_cyc.attr,
 	&format_attr_pwr_evt.attr,
+	&format_attr_event.attr,
+	&format_attr_notnt.attr,
 	&format_attr_fup_on_ptw.attr,
 	&format_attr_mtc.attr,
 	&format_attr_tsc.attr,
@@ -296,6 +304,8 @@ fail:
 			RTIT_CTL_CYC_PSB	| \
 			RTIT_CTL_MTC		| \
 			RTIT_CTL_PWR_EVT_EN	| \
+			RTIT_CTL_EVENT_EN	| \
+			RTIT_CTL_NOTNT		| \
 			RTIT_CTL_FUP_ON_PTW	| \
 			RTIT_CTL_PTW_EN)
 
@@ -350,6 +360,14 @@ static bool pt_event_valid(struct perf_event *event)
 	    !intel_pt_validate_hw_cap(PT_CAP_power_event_trace))
 		return false;
 
+	if (config & RTIT_CTL_EVENT_EN &&
+	    !intel_pt_validate_hw_cap(PT_CAP_event_trace))
+		return false;
+
+	if (config & RTIT_CTL_NOTNT &&
+	    !intel_pt_validate_hw_cap(PT_CAP_tnt_disable))
+		return false;
+
 	if (config & RTIT_CTL_PTW) {
 		if (!intel_pt_validate_hw_cap(PT_CAP_ptwrite))
 			return false;
@@ -472,7 +490,7 @@ static u64 pt_config_filters(struct perf_event *event)
 			pt->filters.filter[range].msr_b = filter->msr_b;
 		}
 
-		rtit_ctl |= filter->config << pt_address_ranges[range].reg_off;
+		rtit_ctl |= (u64)filter->config << pt_address_ranges[range].reg_off;
 	}
 
 	return rtit_ctl;
@@ -1348,10 +1366,26 @@ static void pt_addr_filters_fini(struct perf_event *event)
 	event->hw.addr_filters = NULL;
 }
 
-static inline bool valid_kernel_ip(unsigned long ip)
+#ifdef CONFIG_X86_64
+/* Clamp to a canonical address greater-than-or-equal-to the address given */
+static u64 clamp_to_ge_canonical_addr(u64 vaddr, u8 vaddr_bits)
+{
+	return __is_canonical_address(vaddr, vaddr_bits) ?
+	       vaddr :
+	       -BIT_ULL(vaddr_bits - 1);
+}
+
+/* Clamp to a canonical address less-than-or-equal-to the address given */
+static u64 clamp_to_le_canonical_addr(u64 vaddr, u8 vaddr_bits)
 {
-	return virt_addr_valid(ip) && kernel_ip(ip);
+	return __is_canonical_address(vaddr, vaddr_bits) ?
+	       vaddr :
+	       BIT_ULL(vaddr_bits - 1) - 1;
 }
+#else
+#define clamp_to_ge_canonical_addr(x, y) (x)
+#define clamp_to_le_canonical_addr(x, y) (x)
+#endif
 
 static int pt_event_addr_filters_validate(struct list_head *filters)
 {
@@ -1367,14 +1401,6 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 		    filter->action == PERF_ADDR_FILTER_ACTION_START)
 			return -EOPNOTSUPP;
 
-		if (!filter->path.dentry) {
-			if (!valid_kernel_ip(filter->offset))
-				return -EINVAL;
-
-			if (!valid_kernel_ip(filter->offset + filter->size))
-				return -EINVAL;
-		}
-
 		if (++range > intel_pt_validate_hw_cap(PT_CAP_num_address_ranges))
 			return -EOPNOTSUPP;
 	}
@@ -1398,9 +1424,26 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		if (filter->path.dentry && !fr[range].start) {
 			msr_a = msr_b = 0;
 		} else {
-			/* apply the offset */
-			msr_a = fr[range].start;
-			msr_b = msr_a + fr[range].size - 1;
+			unsigned long n = fr[range].size - 1;
+			unsigned long a = fr[range].start;
+			unsigned long b;
+
+			if (a > ULONG_MAX - n)
+				b = ULONG_MAX;
+			else
+				b = a + n;
+			/*
+			 * Apply the offset. 64-bit addresses written to the
+			 * MSRs must be canonical, but the range can encompass
+			 * non-canonical addresses. Since software cannot
+			 * execute at non-canonical addresses, adjusting to
+			 * canonical addresses does not affect the result of the
+			 * address filter.
+			 */
+			msr_a = clamp_to_ge_canonical_addr(a, boot_cpu_data.x86_virt_bits);
+			msr_b = clamp_to_le_canonical_addr(b, boot_cpu_data.x86_virt_bits);
+			if (msr_b < msr_a)
+				msr_a = msr_b = 0;
 		}
 
 		filters->filter[range].msr_a  = msr_a;
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 6ddadb482f68..5fd72d4b8bbb 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -215,10 +215,18 @@ static int parse_discovery_table(struct pci_dev *dev, int die,
 
 	pci_read_config_dword(dev, bar_offset, &val);
 
-	if (val & UNCORE_DISCOVERY_MASK)
+	if (val & ~PCI_BASE_ADDRESS_MEM_MASK & ~PCI_BASE_ADDRESS_MEM_TYPE_64)
 		return -EINVAL;
 
-	addr = (resource_size_t)(val & ~UNCORE_DISCOVERY_MASK);
+	addr = (resource_size_t)(val & PCI_BASE_ADDRESS_MEM_MASK);
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	if ((val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) == PCI_BASE_ADDRESS_MEM_TYPE_64) {
+		u32 val2;
+
+		pci_read_config_dword(dev, bar_offset + 4, &val2);
+		addr |= ((resource_size_t)val2) << 32;
+	}
+#endif
 	size = UNCORE_DISCOVERY_GLOBAL_MAP_SIZE;
 	io_addr = ioremap(addr, size);
 	if (!io_addr)
@@ -444,7 +452,7 @@ static struct intel_uncore_ops generic_uncore_pci_ops = {
 
 #define UNCORE_GENERIC_MMIO_SIZE		0x4000
 
-static unsigned int generic_uncore_mmio_box_ctl(struct intel_uncore_box *box)
+static u64 generic_uncore_mmio_box_ctl(struct intel_uncore_box *box)
 {
 	struct intel_uncore_type *type = box->pmu->type;
 
@@ -456,7 +464,7 @@ static unsigned int generic_uncore_mmio_box_ctl(struct intel_uncore_box *box)
 
 void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
 {
-	unsigned int box_ctl = generic_uncore_mmio_box_ctl(box);
+	u64 box_ctl = generic_uncore_mmio_box_ctl(box);
 	struct intel_uncore_type *type = box->pmu->type;
 	resource_size_t addr;
 
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index cfaf558bdb6b..f4439357779a 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -18,8 +18,6 @@
 #define UNCORE_DISCOVERY_BIR_BASE		0x10
 /* Discovery table BAR step */
 #define UNCORE_DISCOVERY_BIR_STEP		0x4
-/* Mask of the discovery table offset */
-#define UNCORE_DISCOVERY_MASK			0xf
 /* Global discovery table size */
 #define UNCORE_DISCOVERY_GLOBAL_MAP_SIZE	0x20
 
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 8380c3ddd4b2..2f9eeb5c3069 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -7,8 +7,9 @@
 #define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 
 /* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS		8
-#define MAX_FIXED_PEBS_EVENTS	4
+#define MAX_PEBS_EVENTS_FMT4	8
+#define MAX_PEBS_EVENTS		32
+#define MAX_FIXED_PEBS_EVENTS	16
 
 /*
  * A debug store configuration.
diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
index ebe8d2ea44fe..c796e9bc98b6 100644
--- a/arch/x86/include/asm/intel_pt.h
+++ b/arch/x86/include/asm/intel_pt.h
@@ -13,6 +13,8 @@ enum pt_capabilities {
 	PT_CAP_mtc,
 	PT_CAP_ptwrite,
 	PT_CAP_power_event_trace,
+	PT_CAP_event_trace,
+	PT_CAP_tnt_disable,
 	PT_CAP_topa_output,
 	PT_CAP_topa_multiple_entries,
 	PT_CAP_single_range_output,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ec9830d2aabf..b61e46743184 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -498,6 +498,7 @@ struct kvm_pmc {
 	bool intr;
 };
 
+#define KVM_PMC_MAX_FIXED	3
 struct kvm_pmu {
 	unsigned nr_arch_gp_counters;
 	unsigned nr_arch_fixed_counters;
@@ -511,7 +512,7 @@ struct kvm_pmu {
 	u64 reserved_bits;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
-	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
+	struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
 	struct irq_work irq_work;
 	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
 	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 0e7f303542bf..9f1741ac4769 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -205,6 +205,8 @@
 #define RTIT_CTL_DISRETC		BIT(11)
 #define RTIT_CTL_PTW_EN			BIT(12)
 #define RTIT_CTL_BRANCH_EN		BIT(13)
+#define RTIT_CTL_EVENT_EN		BIT(31)
+#define RTIT_CTL_NOTNT			BIT_ULL(55)
 #define RTIT_CTL_MTC_RANGE_OFFSET	14
 #define RTIT_CTL_MTC_RANGE		(0x0full << RTIT_CTL_MTC_RANGE_OFFSET)
 #define RTIT_CTL_CYC_THRESH_OFFSET	19
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 4d5810c8fab7..9cc82f305f4b 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -71,6 +71,16 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
 extern bool __virt_addr_valid(unsigned long kaddr);
 #define virt_addr_valid(kaddr)	__virt_addr_valid((unsigned long) (kaddr))
 
+static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits)
+{
+	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
+}
+
+static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits)
+{
+	return __canonical_address(vaddr, vaddr_bits) == vaddr;
+}
+
 #endif	/* __ASSEMBLY__ */
 
 #include <asm-generic/memory_model.h>
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8fc1b5003713..58d9e4b1fa0a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
  */
 
 #define INTEL_PMC_MAX_GENERIC				       32
-#define INTEL_PMC_MAX_FIXED					4
+#define INTEL_PMC_MAX_FIXED				       16
 #define INTEL_PMC_IDX_FIXED				       32
 
 #define X86_PMC_IDX_MAX					       64
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b8f8d268d058..8bf541b24b4b 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -879,7 +879,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		eax.split.bit_width = cap.bit_width_gp;
 		eax.split.mask_length = cap.events_mask_len;
 
-		edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
+		edx.split.num_counters_fixed =
+			min(cap.num_counters_fixed, KVM_PMC_MAX_FIXED);
 		edx.split.bit_width_fixed = cap.bit_width_fixed;
 		if (cap.version)
 			edx.split.anythread_deprecated = 1;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d8c087f1b831..50ca1db7247c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -680,7 +680,7 @@ static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt)
 static inline bool emul_is_noncanonical_address(u64 la,
 						struct x86_emulate_ctxt *ctxt)
 {
-	return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la;
+	return !__is_canonical_address(la, ctxt_virt_addr_bits(ctxt));
 }
 
 /*
@@ -730,7 +730,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
 	case X86EMUL_MODE_PROT64:
 		*linear = la;
 		va_bits = ctxt_virt_addr_bits(ctxt);
-		if (get_canonical(la, va_bits) != la)
+		if (!__is_canonical_address(la, va_bits))
 			goto bad;
 
 		*max_size = min_t(u64, ~0u, (1ull << va_bits) - la);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7a7b8d5b775e..9e66fba1d6a3 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -15,8 +15,6 @@
 #define VMWARE_BACKDOOR_PMC_REAL_TIME		0x10001
 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME	0x10002
 
-#define MAX_FIXED_COUNTERS	3
-
 struct kvm_event_hw_type_mapping {
 	u8 eventsel;
 	u8 unit_mask;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 466d18fc0c5d..9b26596099a1 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -565,7 +565,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->gp_counters[i].current_config = 0;
 	}
 
-	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
+	for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
 		pmu->fixed_counters[i].type = KVM_PMC_FIXED;
 		pmu->fixed_counters[i].vcpu = vcpu;
 		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
@@ -591,7 +591,7 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 		pmc->counter = pmc->eventsel = 0;
 	}
 
-	for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) {
+	for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
 		pmc = &pmu->fixed_counters[i];
 
 		pmc_stop_counter(pmc);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eb4029660bd9..eb8269a4c83c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1749,7 +1749,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 		 * value, and that something deterministic happens if the guest
 		 * invokes 64-bit SYSENTER.
 		 */
-		data = get_canonical(data, vcpu_virt_addr_bits(vcpu));
+		data = __canonical_address(data, vcpu_virt_addr_bits(vcpu));
 		break;
 	case MSR_TSC_AUX:
 		if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
@@ -6529,7 +6529,7 @@ static void kvm_init_msr_list(void)
 	u32 dummy[2];
 	unsigned i;
 
-	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
+	BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3,
 			 "Please update the fixed PMCs in msrs_to_saved_all[]");
 
 	perf_get_x86_pmu_capability(&x86_pmu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 767ec7f99516..f11d945ac41f 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -166,14 +166,9 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
 	return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48;
 }
 
-static inline u64 get_canonical(u64 la, u8 vaddr_bits)
-{
-	return ((int64_t)la << (64 - vaddr_bits)) >> (64 - vaddr_bits);
-}
-
 static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
 {
-	return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la;
+	return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu));
 }
 
 static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 92ec176a7293..5a53c2cc169c 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -4,11 +4,6 @@
 #include <linux/kernel.h>
 
 #ifdef CONFIG_X86_64
-static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits)
-{
-	return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
-}
-
 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 {
 	unsigned long vaddr = (unsigned long)unsafe_src;
@@ -19,7 +14,7 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
 	 * we also need to include the userspace guard page.
 	 */
 	return vaddr >= TASK_SIZE_MAX + PAGE_SIZE &&
-	       canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr;
+	       __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
 }
 #else
 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 82858b697c05..d37629dbad72 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -251,6 +251,8 @@ enum {
 	PERF_BR_SYSRET		= 8,	/* syscall return */
 	PERF_BR_COND_CALL	= 9,	/* conditional function call */
 	PERF_BR_COND_RET	= 10,	/* conditional function return */
+	PERF_BR_ERET		= 11,	/* exception return */
+	PERF_BR_IRQ		= 12,	/* irq */
 	PERF_BR_MAX,
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6859229497b1..e1461f99881f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10531,8 +10531,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 		 */
 		if (state == IF_STATE_END) {
 			ret = -EINVAL;
-			if (kernel && event->attr.exclude_kernel)
-				goto fail;
 
 			/*
 			 * ACTION "filter" must have a non-zero length region
@@ -10574,8 +10572,11 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 			}
 
 			/* ready to consume more filters */
+			kfree(filename);
+			filename = NULL;
 			state = IF_STATE_ACTION;
 			filter = NULL;
+			kernel = 0;
 		}
 	}
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 82858b697c05..d37629dbad72 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -251,6 +251,8 @@ enum {
 	PERF_BR_SYSRET		= 8,	/* syscall return */
 	PERF_BR_COND_CALL	= 9,	/* conditional function call */
 	PERF_BR_COND_RET	= 10,	/* conditional function return */
+	PERF_BR_ERET		= 11,	/* exception return */
+	PERF_BR_IRQ		= 12,	/* irq */
 	PERF_BR_MAX,
 };
 
diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c
index 2285b1eb3128..a9a909db8cc7 100644
--- a/tools/perf/util/branch.c
+++ b/tools/perf/util/branch.c
@@ -49,7 +49,9 @@ const char *branch_type_name(int type)
 		"SYSCALL",
 		"SYSRET",
 		"COND_CALL",
-		"COND_RET"
+		"COND_RET",
+		"ERET",
+		"IRQ"
 	};
 
 	if (type >= 0 && type < PERF_BR_MAX)