Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf tooling fixes from Ingo  Molnar:
 "These are all perf tooling changes: most of them are fixes.

  Note that the large CPU count related fixes go beyond regression
  fixes, but the IPI-flood symptoms are severe enough that I think
  justifies their inclusion"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
  perf vendor events s390: Remove name from L1D_RO_EXCL_WRITES description
  perf vendor events s390: Fix counter long description for DTLB1_GPAGE_WRITES
  libtraceevent: Allow custom libdir path
  perf header: Fix false warning when there are no duplicate cache entries
  perf metricgroup: Fix printing event names of metric group with multiple events
  perf/x86/pmu-events: Fix Kernel_Utilization metric
  perf top: Do not bail out when perf_env__read_cpuid() returns ENOSYS
  perf arch: Make the default get_cpuid() return compatible error
  tools headers kvm: Sync linux/kvm.h with the kernel sources
  tools headers UAPI: Update tools's copy of drm.h headers
  tools headers UAPI: Sync drm/i915_drm.h with the kernel sources
  perf inject: Fix processing of ID index for injected instruction tracing
  perf report: Bail out --mem-mode if mem info is not available
  perf report: Make -F more strict like -s
  perf report/top TUI: Replace pr_err() with ui__error()
  libtraceevent: Copy pkg-config file to output folder when using O=
  libtraceevent: Fix lib installation with O=
  perf kvm: Clarify the 'perf kvm' -i and -o command line options
  tools arch x86: Sync asm/cpufeatures.h with the kernel sources
  perf beauty: Add CLEAR_SIGHAND support for clone's flags arg
  ...

65 files changed, 976 insertions, 289 deletions

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 2769360f195c..03cd7c19a683 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -131,8 +131,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 67c21f9bdbad..820e5751ada7 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -164,8 +164,9 @@ struct kvm_vcpu_events {
 	struct {
 		__u8 serror_pending;
 		__u8 serror_has_esr;
+		__u8 ext_dabt_pending;
 		/* Align it to 8 bytes */
-		__u8 pad[6];
+		__u8 pad[5];
 		__u64 serror_esr;
 	} exception;
 	__u32 reserved[12];
@@ -323,6 +324,8 @@ struct kvm_vcpu_events {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define KVM_ARM_VCPU_PVTIME_CTRL	2
+#define   KVM_ARM_VCPU_PVTIME_IPA	0
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_VCPU2_SHIFT		28
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index b0f72dea8b11..264e266a85bf 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char {
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
+#define KVM_DEV_XICS_GRP_CTRL		2
+#define   KVM_DEV_XICS_NR_SERVERS	1
 
 /* Layout of 64-bit source attribute values */
 #define  KVM_XICS_DESTINATION_SHIFT	0
@@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_DEV_XIVE_GRP_CTRL		1
 #define   KVM_DEV_XIVE_RESET		1
 #define   KVM_DEV_XIVE_EQ_SYNC		2
+#define   KVM_DEV_XIVE_NR_SERVERS	3
 #define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 0652d3eed9bd..e9b62498fe75 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -292,6 +292,7 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_RDPRU		(13*32+ 4) /* Read processor register at user level */
 #define X86_FEATURE_WBNOINVD		(13*32+ 9) /* WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
@@ -399,5 +400,7 @@
 #define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
 #define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
 #define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
+#define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
+#define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 20ce682a2540..084e98da04a7 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -93,6 +93,18 @@
 						  * Microarchitectural Data
 						  * Sampling (MDS) vulnerabilities.
 						  */
+#define ARCH_CAP_PSCHANGE_MC_NO		BIT(6)	 /*
+						  * The processor is not susceptible to a
+						  * machine check error due to modifying the
+						  * code page size along with either the
+						  * physical address or cache type
+						  * without TLB invalidation.
+						  */
+#define ARCH_CAP_TSX_CTRL_MSR		BIT(7)	/* MSR for TSX control is available. */
+#define ARCH_CAP_TAA_NO			BIT(8)	/*
+						 * Not susceptible to
+						 * TSX Async Abort (TAA) vulnerabilities.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
@@ -103,6 +115,10 @@
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
+#define MSR_IA32_TSX_CTRL		0x00000122
+#define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
+#define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
+
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
 #define MSR_IA32_SYSENTER_EIP		0x00000176
@@ -393,6 +409,8 @@
 #define MSR_AMD_PSTATE_DEF_BASE		0xc0010064
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD_PPIN_CTL		0xc00102f0
+#define MSR_AMD_PPIN			0xc00102f1
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_BU_CFG2		0xc001102a
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 92748660ba51..df767afc690f 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -28,8 +28,8 @@
  * Output:
  * rax original destination
  */
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_LOCAL(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
@@ -41,8 +41,8 @@ ENTRY(memcpy)
 	movl %edx, %ecx
 	rep movsb
 	ret
-ENDPROC(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END(memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(memcpy)
 EXPORT_SYMBOL(__memcpy)
 
@@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy)
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
  * simpler than memcpy. Use memcpy_erms when possible.
  */
-ENTRY(memcpy_erms)
+SYM_FUNC_START(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
 	ret
-ENDPROC(memcpy_erms)
+SYM_FUNC_END(memcpy_erms)
 
-ENTRY(memcpy_orig)
+SYM_FUNC_START(memcpy_orig)
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx
@@ -182,7 +182,7 @@ ENTRY(memcpy_orig)
 
 .Lend:
 	retq
-ENDPROC(memcpy_orig)
+SYM_FUNC_END(memcpy_orig)
 
 #ifndef CONFIG_UML
 
@@ -193,7 +193,7 @@ MCSAFE_TEST_CTL
  * Note that we only catch machine checks when reading the source addresses.
  * Writes to target are posted and don't generate machine checks.
  */
-ENTRY(__memcpy_mcsafe)
+SYM_FUNC_START(__memcpy_mcsafe)
 	cmpl $8, %edx
 	/* Less than 8 bytes? Go to byte copy loop */
 	jb .L_no_whole_words
@@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe)
 	xorl %eax, %eax
 .L_done:
 	ret
-ENDPROC(__memcpy_mcsafe)
+SYM_FUNC_END(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 
 	.section .fixup, "ax"
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index f8f3dc0a6690..fd5d25a474b7 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -18,8 +18,8 @@
  *
  * rax   original destination
  */
-ENTRY(memset)
-ENTRY(__memset)
+SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
 	 * to use it when possible. If not available, use fast string instructions.
@@ -42,8 +42,8 @@ ENTRY(__memset)
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset)
-ENDPROC(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_END_ALIAS(memset)
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses
@@ -56,16 +56,16 @@ ENDPROC(__memset)
  *
  * rax   original destination
  */
-ENTRY(memset_erms)
+SYM_FUNC_START(memset_erms)
 	movq %rdi,%r9
 	movb %sil,%al
 	movq %rdx,%rcx
 	rep stosb
 	movq %r9,%rax
 	ret
-ENDPROC(memset_erms)
+SYM_FUNC_END(memset_erms)
 
-ENTRY(memset_orig)
+SYM_FUNC_START(memset_orig)
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -136,4 +136,4 @@ ENTRY(memset_orig)
 	subq %r8,%rdx
 	jmp .Lafter_bad_alignment
 .Lfinal:
-ENDPROC(memset_orig)
+SYM_FUNC_END(memset_orig)
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 8a5b2f8f8eb9..868bf7996c0f 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -778,11 +778,12 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */
 struct drm_syncobj_timeline_array {
 	__u64 handles;
 	__u64 points;
 	__u32 count_handles;
-	__u32 pad;
+	__u32 flags;
 };
 
 
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 469dc512cca3..5400d7e057f1 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -611,6 +611,13 @@ typedef struct drm_i915_irq_wait {
  * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
  */
 #define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
+
+/*
+ * Revision of the i915-perf uAPI. The value returned helps determine what
+ * i915-perf features are available. See drm_i915_perf_property_id.
+ */
+#define I915_PARAM_PERF_REVISION	54
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1565,6 +1572,21 @@ struct drm_i915_gem_context_param {
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
+
+/*
+ * I915_CONTEXT_PARAM_PERSISTENCE:
+ *
+ * Allow the context and active rendering to survive the process until
+ * completion. Persistence allows fire-and-forget clients to queue up a
+ * bunch of work, hand the output over to a display server and then quit.
+ * If the context is marked as not persistent, upon closing (either via
+ * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
+ * or process termination), the context and any outstanding requests will be
+ * cancelled (and exported fences for cancelled requests marked as -EIO).
+ *
+ * By default, new contexts allow persistence.
+ */
+#define I915_CONTEXT_PARAM_PERSISTENCE	0xb
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -1844,23 +1866,31 @@ enum drm_i915_perf_property_id {
 	 * Open the stream for a specific context handle (as used with
 	 * execbuffer2). A stream opened for a specific context this way
 	 * won't typically require root privileges.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
 
 	/**
 	 * A value of 1 requests the inclusion of raw OA unit reports as
 	 * part of stream samples.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_SAMPLE_OA,
 
 	/**
 	 * The value specifies which set of OA unit metrics should be
 	 * be configured, defining the contents of any OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_METRICS_SET,
 
 	/**
 	 * The value specifies the size and layout of OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_FORMAT,
 
@@ -1870,9 +1900,22 @@ enum drm_i915_perf_property_id {
 	 * from this exponent as follows:
 	 *
 	 *   80ns * 2^(period_exponent + 1)
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_EXPONENT,
 
+	/**
+	 * Specifying this property is only valid when specify a context to
+	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
+	 * will hold preemption of the particular context we want to gather
+	 * performance data about. The execbuf2 submissions must include a
+	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
+	 *
+	 * This property is available in perf revision 3.
+	 */
+	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
@@ -1901,6 +1944,8 @@ struct drm_i915_perf_open_param {
  * to close and re-open a stream with the same configuration.
  *
  * It's undefined whether any pending data for the stream will be lost.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
 
@@ -1908,10 +1953,25 @@ struct drm_i915_perf_open_param {
  * Disable data capture for a stream.
  *
  * It is an error to try and read a stream that is disabled.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
 /**
+ * Change metrics_set captured by a stream.
+ *
+ * If the stream is bound to a specific context, the configuration change
+ * will performed inline with that context such that it takes effect before
+ * the next execbuf submission.
+ *
+ * Returns the previously bound metrics set id, or a negative error code.
+ *
+ * This ioctl is available in perf revision 2.
+ */
+#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
+
+/**
  * Common to all i915 perf records
  */
 struct drm_i915_perf_record_header {
@@ -1984,6 +2044,7 @@ struct drm_i915_query_item {
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
 #define DRM_I915_QUERY_ENGINE_INFO	2
+#define DRM_I915_QUERY_PERF_CONFIG      3
 /* Must be kept compact -- no holes and well documented */
 
 	/*
@@ -1995,9 +2056,18 @@ struct drm_i915_query_item {
 	__s32 length;
 
 	/*
-	 * Unused for now. Must be cleared to zero.
+	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+	 *
+	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
+	 * following :
+	 *         - DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *         - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *         - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
 	 */
 	__u32 flags;
+#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
 
 	/*
 	 * Data will be written at the location pointed by data_ptr when the
@@ -2033,8 +2103,10 @@ struct drm_i915_query {
  *           (data[X / 8] >> (X % 8)) & 1
  *
  * - the subslice mask for each slice with one bit per subslice telling
- *   whether a subslice is available. The availability of subslice Y in slice
- *   X can be queried with the following formula :
+ *   whether a subslice is available. Gen12 has dual-subslices, which are
+ *   similar to two gen11 subslices. For gen12, this array represents dual-
+ *   subslices. The availability of subslice Y in slice X can be queried
+ *   with the following formula :
  *
  *           (data[subslice_offset +
  *                 X * subslice_stride +
@@ -2123,6 +2195,56 @@ struct drm_i915_query_engine_info {
 	struct drm_i915_engine_info engines[];
 };
 
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG.
+ */
+struct drm_i915_query_perf_config {
+	union {
+		/*
+		 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets
+		 * this fields to the number of configurations available.
+		 */
+		__u64 n_configs;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 */
+		__u64 config;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 *
+		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
+		 */
+		char uuid[36];
+	};
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will
+	 * write an array of __u64 of configuration identifiers.
+	 *
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will
+	 * write a struct drm_i915_perf_oa_config. If the following fields of
+	 * drm_i915_perf_oa_config are set not set to 0, i915 will write into
+	 * the associated pointers the values of submitted when the
+	 * configuration was created :
+	 *
+	 *         - n_mux_regs
+	 *         - n_boolean_regs
+	 *         - n_flex_regs
+	 */
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 39ccfe9311c3..1beb174ad950 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -17,7 +17,8 @@
 #define FSCRYPT_POLICY_FLAGS_PAD_32		0x03
 #define FSCRYPT_POLICY_FLAGS_PAD_MASK		0x03
 #define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
-#define FSCRYPT_POLICY_FLAGS_VALID		0x07
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64	0x08
+#define FSCRYPT_POLICY_FLAGS_VALID		0x0F
 
 /* Encryption algorithms */
 #define FSCRYPT_MODE_AES_256_XTS		1
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 52641d8ca9e8..f0a16b4adbbd 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -235,6 +235,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_S390_STSI        25
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
+#define KVM_EXIT_ARM_NISV         28
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -394,6 +395,11 @@ struct kvm_run {
 		} eoi;
 		/* KVM_EXIT_HYPERV */
 		struct kvm_hyperv_exit hyperv;
+		/* KVM_EXIT_ARM_NISV */
+		struct {
+			__u64 esr_iss;
+			__u64 fault_ipa;
+		} arm_nisv;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1000,6 +1006,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PMU_EVENT_FILTER 173
 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
 #define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
+#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
+#define KVM_CAP_ARM_NISV_TO_USER 177
+#define KVM_CAP_ARM_INJECT_EXT_DABT 178
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1227,6 +1236,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_ITS	KVM_DEV_TYPE_ARM_VGIC_ITS
 	KVM_DEV_TYPE_XIVE,
 #define KVM_DEV_TYPE_XIVE		KVM_DEV_TYPE_XIVE
+	KVM_DEV_TYPE_ARM_PV_TIME,
+#define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
 	KVM_DEV_TYPE_MAX,
 };
 
@@ -1337,6 +1348,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 /* Available with KVM_CAP_PMU_EVENT_FILTER */
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
+#define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 99335e1f4a27..4a0217832464 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -33,27 +33,48 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
+/* Flags for the clone3() syscall. */
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+
 #ifndef __ASSEMBLY__
 /**
  * struct clone_args - arguments for the clone3 syscall
- * @flags:       Flags for the new process as listed above.
- *               All flags are valid except for CSIGNAL and
- *               CLONE_DETACHED.
- * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
- *               returned in this argument.
- * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
- *               child process will be returned in the child's
- *               memory.
- * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
- *               the child process will be returned in the
- *               parent's memory.
- * @exit_signal: The exit_signal the parent process will be
- *               sent when the child exits.
- * @stack:       Specify the location of the stack for the
- *               child process.
- * @stack_size:  The size of the stack for the child process.
- * @tls:         If CLONE_SETTLS is set, the tls descriptor
- *               is set to tls.
+ * @flags:        Flags for the new process as listed above.
+ *                All flags are valid except for CSIGNAL and
+ *                CLONE_DETACHED.
+ * @pidfd:        If CLONE_PIDFD is set, a pidfd will be
+ *                returned in this argument.
+ * @child_tid:    If CLONE_CHILD_SETTID is set, the TID of the
+ *                child process will be returned in the child's
+ *                memory.
+ * @parent_tid:   If CLONE_PARENT_SETTID is set, the TID of
+ *                the child process will be returned in the
+ *                parent's memory.
+ * @exit_signal:  The exit_signal the parent process will be
+ *                sent when the child exits.
+ * @stack:        Specify the location of the stack for the
+ *                child process.
+ *                Note, @stack is expected to point to the
+ *                lowest address. The stack direction will be
+ *                determined by the kernel and set up
+ *                appropriately based on @stack_size.
+ * @stack_size:   The size of the stack for the child process.
+ * @tls:          If CLONE_SETTLS is set, the tls descriptor
+ *                is set to tls.
+ * @set_tid:      Pointer to an array of type *pid_t. The size
+ *                of the array is defined using @set_tid_size.
+ *                This array is used to select PIDs/TIDs for
+ *                newly created processes. The first element in
+ *                this defines the PID in the most nested PID
+ *                namespace. Each additional element in the array
+ *                defines the PID in the parent PID namespace of
+ *                the original PID namespace. If the array has
+ *                less entries than the number of currently
+ *                nested PID namespaces only the PIDs in the
+ *                corresponding namespaces are set.
+ * @set_tid_size: This defines the size of the array referenced
+ *                in @set_tid. This cannot be larger than the
+ *                kernel's limit of nested PID namespaces.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -68,10 +89,13 @@ struct clone_args {
 	__aligned_u64 stack;
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
+	__aligned_u64 set_tid;
+	__aligned_u64 set_tid_size;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
 
 /*
  * Scheduling policies
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 7b35e98d3c58..ad80a5c885d5 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -167,8 +167,8 @@ struct statx {
 #define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
 #define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
 #define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
-
 #define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 
 
 #endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index cbb429f55062..c874c017c636 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -39,11 +39,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
-  libdir_relative = lib64
+  libdir_relative_temp = lib64
 else
-  libdir_relative = lib
+  libdir_relative_temp = lib
 endif
 
+libdir_relative ?= $(libdir_relative_temp)
 prefix ?= /usr/local
 libdir = $(prefix)/$(libdir_relative)
 man_dir = $(prefix)/share/man
@@ -97,6 +98,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
 
 LIB_TARGET  = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION)
 LIB_INSTALL = libtraceevent.a libtraceevent.so*
+LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL))
 
 INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
 
@@ -207,10 +209,11 @@ define do_install
 	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
 endef
 
-PKG_CONFIG_FILE = libtraceevent.pc
+PKG_CONFIG_SOURCE_FILE = libtraceevent.pc
+PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE))
 define do_install_pkgconfig_file
 	if [ -n "${pkgconfig_dir}" ]; then 					\
-		cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; 		\
+		cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE};	\
 		sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; 		\
 		sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \
 		sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \
diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile
index f440989fa55e..349bb81482ab 100644
--- a/tools/lib/traceevent/plugins/Makefile
+++ b/tools/lib/traceevent/plugins/Makefile
@@ -32,11 +32,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
 ifeq ($(LP64), 1)
-  libdir_relative = lib64
+  libdir_relative_tmp = lib64
 else
-  libdir_relative = lib
+  libdir_relative_tmp = lib
 endif
 
+libdir_relative ?= $(libdir_relative_tmp)
 prefix ?= /usr/local
 libdir = $(prefix)/$(libdir_relative)
 
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6a5bb2b17039..cf95baef7b61 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -68,10 +68,11 @@ OPTIONS
 -------
 -i::
 --input=<path>::
-        Input file name.
+        Input file name, for the 'report', 'diff' and 'buildid-list' subcommands.
 -o::
 --output=<path>::
-        Output file name.
+        Output file name, for the 'record' subcommand. Doesn't work with 'report',
+        just redirect the output to a file when using 'report'.
 --host::
         Collect host side performance profile.
 --guest::
diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S
index 6e2495cc4517..4284307d7822 100644
--- a/tools/perf/arch/arm/tests/regs_load.S
+++ b/tools/perf/arch/arm/tests/regs_load.S
@@ -37,7 +37,7 @@
 
 .text
 .type perf_regs_load,%function
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	str r0, [r0, #R0]
 	str r1, [r0, #R1]
 	str r2, [r0, #R2]
@@ -56,4 +56,4 @@ ENTRY(perf_regs_load)
 	str lr, [r0, #PC]	// store pc as lr in order to skip the call
 	                        //  to this function
 	mov pc, lr
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
index 07042511dca9..d49de40b6818 100644
--- a/tools/perf/arch/arm64/tests/regs_load.S
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -7,7 +7,7 @@
 #define LDR_REG(r)	ldr x##r, [x0, 8 * r]
 #define SP	(8 * 31)
 #define PC	(8 * 32)
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	STR_REG(0)
 	STR_REG(1)
 	STR_REG(2)
@@ -44,4 +44,4 @@ ENTRY(perf_regs_load)
 	str x30, [x0, #PC]
 	LDR_REG(1)
 	ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
index bbe5a0d16e51..80f14f52e3f6 100644
--- a/tools/perf/arch/x86/tests/regs_load.S
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -28,7 +28,7 @@
 
 .text
 #ifdef HAVE_ARCH_X86_64_SUPPORT
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	movq %rax, AX(%rdi)
 	movq %rbx, BX(%rdi)
 	movq %rcx, CX(%rdi)
@@ -60,9 +60,9 @@ ENTRY(perf_regs_load)
 	movq %r14, R14(%rdi)
 	movq %r15, R15(%rdi)
 	ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
 #else
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
 	push %edi
 	movl 8(%esp), %edi
 	movl %eax, AX(%edi)
@@ -88,7 +88,7 @@ ENTRY(perf_regs_load)
 	movl $0, FS(%edi)
 	movl $0, GS(%edi)
 	ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
 #endif
 
 /*
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9664a72a089d..7e124a7b8bfd 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -403,17 +403,6 @@ static int perf_event__repipe_tracing_data(struct perf_session *session,
 	return err;
 }
 
-static int perf_event__repipe_id_index(struct perf_session *session,
-				       union perf_event *event)
-{
-	int err;
-
-	perf_event__repipe_synth(session->tool, event);
-	err = perf_event__process_id_index(session, event);
-
-	return err;
-}
-
 static int dso__read_build_id(struct dso *dso)
 {
 	if (dso->has_build_id)
@@ -651,7 +640,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.comm	    = perf_event__repipe_comm;
 		inject->tool.namespaces	    = perf_event__repipe_namespaces;
 		inject->tool.exit	    = perf_event__repipe_exit;
-		inject->tool.id_index	    = perf_event__repipe_id_index;
+		inject->tool.id_index	    = perf_event__process_id_index;
 		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;
 		inject->tool.auxtrace	    = perf_event__process_auxtrace;
 		inject->tool.aux	    = perf_event__drop_aux;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b5063d3b6fd0..fb19ef63cc35 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -832,7 +832,7 @@ try_again:
 			if ((errno == EINVAL || errno == EBADF) &&
 			    pos->leader != pos &&
 			    pos->weak_group) {
-			        pos = perf_evlist__reset_weak_group(evlist, pos);
+			        pos = perf_evlist__reset_weak_group(evlist, pos, true);
 				goto try_again;
 			}
 			rc = -errno;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 830d563de889..387311c67264 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -388,6 +388,14 @@ static int report__setup_sample_type(struct report *rep)
 		}
 	}
 
+	if (sort__mode == SORT_MODE__MEMORY) {
+		if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) {
+			ui__error("Selected --mem-mode but no mem data. "
+				  "Did you call perf record without -d?\n");
+			return -1;
+		}
+	}
+
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
 		    (sample_type & PERF_SAMPLE_STACK_USER)) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0a15253b438c..a098c2ebf4ea 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
 #include "util/target.h"
 #include "util/time-utils.h"
 #include "util/top.h"
+#include "util/affinity.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -265,15 +266,10 @@ static int read_single_counter(struct evsel *counter, int cpu,
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
  */
-static int read_counter(struct evsel *counter, struct timespec *rs)
+static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 {
 	int nthreads = perf_thread_map__nr(evsel_list->core.threads);
-	int ncpus, cpu, thread;
-
-	if (target__has_cpu(&target) && !target__has_per_thread(&target))
-		ncpus = perf_evsel__nr_cpus(counter);
-	else
-		ncpus = 1;
+	int thread;
 
 	if (!counter->supported)
 		return -ENOENT;
@@ -282,40 +278,38 @@ static int read_counter(struct evsel *counter, struct timespec *rs)
 		nthreads = 1;
 
 	for (thread = 0; thread < nthreads; thread++) {
-		for (cpu = 0; cpu < ncpus; cpu++) {
-			struct perf_counts_values *count;
-
-			count = perf_counts(counter->counts, cpu, thread);
-
-			/*
-			 * The leader's group read loads data into its group members
-			 * (via perf_evsel__read_counter) and sets threir count->loaded.
-			 */
-			if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
-			    read_single_counter(counter, cpu, thread, rs)) {
-				counter->counts->scaled = -1;
-				perf_counts(counter->counts, cpu, thread)->ena = 0;
-				perf_counts(counter->counts, cpu, thread)->run = 0;
-				return -1;
-			}
+		struct perf_counts_values *count;
 
-			perf_counts__set_loaded(counter->counts, cpu, thread, false);
+		count = perf_counts(counter->counts, cpu, thread);
 
-			if (STAT_RECORD) {
-				if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
-					pr_err("failed to write stat event\n");
-					return -1;
-				}
-			}
+		/*
+		 * The leader's group read loads data into its group members
+		 * (via perf_evsel__read_counter()) and sets their count->loaded.
+		 */
+		if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
+		    read_single_counter(counter, cpu, thread, rs)) {
+			counter->counts->scaled = -1;
+			perf_counts(counter->counts, cpu, thread)->ena = 0;
+			perf_counts(counter->counts, cpu, thread)->run = 0;
+			return -1;
+		}
+
+		perf_counts__set_loaded(counter->counts, cpu, thread, false);
 
-			if (verbose > 1) {
-				fprintf(stat_config.output,
-					"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
-						perf_evsel__name(counter),
-						cpu,
-						count->val, count->ena, count->run);
+		if (STAT_RECORD) {
+			if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+				pr_err("failed to write stat event\n");
+				return -1;
 			}
 		}
+
+		if (verbose > 1) {
+			fprintf(stat_config.output,
+				"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+					perf_evsel__name(counter),
+					cpu,
+					count->val, count->ena, count->run);
+		}
 	}
 
 	return 0;
@@ -324,15 +318,37 @@ static int read_counter(struct evsel *counter, struct timespec *rs)
 static void read_counters(struct timespec *rs)
 {
 	struct evsel *counter;
-	int ret;
+	struct affinity affinity;
+	int i, ncpus, cpu;
+
+	if (affinity__setup(&affinity) < 0)
+		return;
+
+	ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
+	if (!target__has_cpu(&target) || target__has_per_thread(&target))
+		ncpus = 1;
+	evlist__for_each_cpu(evsel_list, i, cpu) {
+		if (i >= ncpus)
+			break;
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evsel_list, counter) {
+			if (evsel__cpu_iter_skip(counter, cpu))
+				continue;
+			if (!counter->err) {
+				counter->err = read_counter_cpu(counter, rs,
+								counter->cpu_iter - 1);
+			}
+		}
+	}
+	affinity__cleanup(&affinity);
 
 	evlist__for_each_entry(evsel_list, counter) {
-		ret = read_counter(counter, rs);
-		if (ret)
+		if (counter->err)
 			pr_debug("failed to read counter %s\n", counter->name);
-
-		if (ret == 0 && perf_stat_process_counter(&stat_config, counter))
+		if (counter->err == 0 && perf_stat_process_counter(&stat_config, counter))
 			pr_warning("failed to process counter %s\n", counter->name);
+		counter->err = 0;
 	}
 }
 
@@ -420,6 +436,62 @@ static bool is_target_alive(struct target *_target,
 	return false;
 }
 
+enum counter_recovery {
+	COUNTER_SKIP,
+	COUNTER_RETRY,
+	COUNTER_FATAL,
+};
+
+static enum counter_recovery stat_handle_error(struct evsel *counter)
+{
+	char msg[BUFSIZ];
+	/*
+	 * PPC returns ENXIO for HW counters until 2.6.37
+	 * (behavior changed with commit b0a873e).
+	 */
+	if (errno == EINVAL || errno == ENOSYS ||
+	    errno == ENOENT || errno == EOPNOTSUPP ||
+	    errno == ENXIO) {
+		if (verbose > 0)
+			ui__warning("%s event is not supported by the kernel.\n",
+				    perf_evsel__name(counter));
+		counter->supported = false;
+		/*
+		 * errored is a sticky flag that means one of the counter's
+		 * cpu event had a problem and needs to be reexamined.
+		 */
+		counter->errored = true;
+
+		if ((counter->leader != counter) ||
+		    !(counter->leader->core.nr_members > 1))
+			return COUNTER_SKIP;
+	} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+		if (verbose > 0)
+			ui__warning("%s\n", msg);
+		return COUNTER_RETRY;
+	} else if (target__has_per_thread(&target) &&
+		   evsel_list->core.threads &&
+		   evsel_list->core.threads->err_thread != -1) {
+		/*
+		 * For global --per-thread case, skip current
+		 * error thread.
+		 */
+		if (!thread_map__remove(evsel_list->core.threads,
+					evsel_list->core.threads->err_thread)) {
+			evsel_list->core.threads->err_thread = -1;
+			return COUNTER_RETRY;
+		}
+	}
+
+	perf_evsel__open_strerror(counter, &target,
+				  errno, msg, sizeof(msg));
+	ui__error("%s\n", msg);
+
+	if (child_pid != -1)
+		kill(child_pid, SIGTERM);
+	return COUNTER_FATAL;
+}
+
 static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
@@ -433,6 +505,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	int status = 0;
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
+	struct affinity affinity;
+	int i, cpu;
+	bool second_pass = false;
 
 	if (interval) {
 		ts.tv_sec  = interval / USEC_PER_MSEC;
@@ -457,61 +532,104 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (group)
 		perf_evlist__set_leader(evsel_list);
 
-	evlist__for_each_entry(evsel_list, counter) {
+	if (affinity__setup(&affinity) < 0)
+		return -1;
+
+	evlist__for_each_cpu (evsel_list, i, cpu) {
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evsel_list, counter) {
+			if (evsel__cpu_iter_skip(counter, cpu))
+				continue;
+			if (counter->reset_group || counter->errored)
+				continue;
 try_again:
-		if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
-
-			/* Weak group failed. Reset the group. */
-			if ((errno == EINVAL || errno == EBADF) &&
-			    counter->leader != counter &&
-			    counter->weak_group) {
-				counter = perf_evlist__reset_weak_group(evsel_list, counter);
-				goto try_again;
-			}
+			if (create_perf_stat_counter(counter, &stat_config, &target,
+						     counter->cpu_iter - 1) < 0) {
 
-			/*
-			 * PPC returns ENXIO for HW counters until 2.6.37
-			 * (behavior changed with commit b0a873e).
-			 */
-			if (errno == EINVAL || errno == ENOSYS ||
-			    errno == ENOENT || errno == EOPNOTSUPP ||
-			    errno == ENXIO) {
-				if (verbose > 0)
-					ui__warning("%s event is not supported by the kernel.\n",
-						    perf_evsel__name(counter));
-				counter->supported = false;
-
-				if ((counter->leader != counter) ||
-				    !(counter->leader->core.nr_members > 1))
-					continue;
-			} else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
-                                if (verbose > 0)
-                                        ui__warning("%s\n", msg);
-                                goto try_again;
-			} else if (target__has_per_thread(&target) &&
-				   evsel_list->core.threads &&
-				   evsel_list->core.threads->err_thread != -1) {
 				/*
-				 * For global --per-thread case, skip current
-				 * error thread.
+				 * Weak group failed. We cannot just undo this here
+				 * because earlier CPUs might be in group mode, and the kernel
+				 * doesn't support mixing group and non group reads. Defer
+				 * it to later.
+				 * Don't close here because we're in the wrong affinity.
 				 */
-				if (!thread_map__remove(evsel_list->core.threads,
-							evsel_list->core.threads->err_thread)) {
-					evsel_list->core.threads->err_thread = -1;
+				if ((errno == EINVAL || errno == EBADF) &&
+				    counter->leader != counter &&
+				    counter->weak_group) {
+					perf_evlist__reset_weak_group(evsel_list, counter, false);
+					assert(counter->reset_group);
+					second_pass = true;
+					continue;
+				}
+
+				switch (stat_handle_error(counter)) {
+				case COUNTER_FATAL:
+					return -1;
+				case COUNTER_RETRY:
 					goto try_again;
+				case COUNTER_SKIP:
+					continue;
+				default:
+					break;
 				}
+
 			}
+			counter->supported = true;
+		}
+	}
 
-			perf_evsel__open_strerror(counter, &target,
-						  errno, msg, sizeof(msg));
-			ui__error("%s\n", msg);
+	if (second_pass) {
+		/*
+		 * Now redo all the weak group after closing them,
+		 * and also close errored counters.
+		 */
 
-			if (child_pid != -1)
-				kill(child_pid, SIGTERM);
+		evlist__for_each_cpu(evsel_list, i, cpu) {
+			affinity__set(&affinity, cpu);
+			/* First close errored or weak retry */
+			evlist__for_each_entry(evsel_list, counter) {
+				if (!counter->reset_group && !counter->errored)
+					continue;
+				if (evsel__cpu_iter_skip_no_inc(counter, cpu))
+					continue;
+				perf_evsel__close_cpu(&counter->core, counter->cpu_iter);
+			}
+			/* Now reopen weak */
+			evlist__for_each_entry(evsel_list, counter) {
+				if (!counter->reset_group && !counter->errored)
+					continue;
+				if (evsel__cpu_iter_skip(counter, cpu))
+					continue;
+				if (!counter->reset_group)
+					continue;
+try_again_reset:
+				pr_debug2("reopening weak %s\n", perf_evsel__name(counter));
+				if (create_perf_stat_counter(counter, &stat_config, &target,
+							     counter->cpu_iter - 1) < 0) {
+
+					switch (stat_handle_error(counter)) {
+					case COUNTER_FATAL:
+						return -1;
+					case COUNTER_RETRY:
+						goto try_again_reset;
+					case COUNTER_SKIP:
+						continue;
+					default:
+						break;
+					}
+				}
+				counter->supported = true;
+			}
+		}
+	}
+	affinity__cleanup(&affinity);
 
-			return -1;
+	evlist__for_each_entry(evsel_list, counter) {
+		if (!counter->supported) {
+			perf_evsel__free_fd(&counter->core);
+			continue;
 		}
-		counter->supported = true;
 
 		l = strlen(counter->unit);
 		if (l > stat_config.unit_width)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index dc80044bc46f..795e353de095 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1568,9 +1568,13 @@ int cmd_top(int argc, const char **argv)
 	 */
 	status = perf_env__read_cpuid(&perf_env);
 	if (status) {
-		pr_err("Couldn't read the cpuid for this machine: %s\n",
-		       str_error_r(errno, errbuf, sizeof(errbuf)));
-		goto out_delete_evlist;
+		/*
+		 * Some arches do not provide a get_cpuid(), so just use pr_debug, otherwise
+		 * warn the user explicitely.
+		 */
+		eprintf(status == ENOSYS ? 1 : 0, verbose,
+			"Couldn't read the cpuid for this machine: %s\n",
+			str_error_r(errno, errbuf, sizeof(errbuf)));
 	}
 	top.evlist->env = &perf_env;
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index a1dc16724352..68039a96c1dc 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -110,8 +110,8 @@ for i in $FILES; do
 done
 
 # diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"'
+check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/ctype.h	      '-I "isdigit("'
diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index 2ca1fafa620d..f93f4e703e4c 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -68,14 +68,28 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	return cpus;
 }
 
+static int cmp_int(const void *a, const void *b)
+{
+	return *(const int *)a - *(const int*)b;
+}
+
 static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
 {
 	size_t payload_size = nr_cpus * sizeof(int);
 	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+	int i, j;
 
 	if (cpus != NULL) {
-		cpus->nr = nr_cpus;
 		memcpy(cpus->map, tmp_cpus, payload_size);
+		qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+		/* Remove dups */
+		j = 0;
+		for (i = 0; i < nr_cpus; i++) {
+			if (i == 0 || cpus->map[i] != cpus->map[i - 1])
+				cpus->map[j++] = cpus->map[i];
+		}
+		cpus->nr = j;
+		assert(j <= nr_cpus);
 		refcount_set(&cpus->refcnt, 1);
 	}
 
@@ -272,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
 
 	return max;
 }
+
+/*
+ * Merge two cpumaps
+ *
+ * orig either gets freed and replaced with a new map, or reused
+ * with no reference count change (similar to "realloc")
+ * other has its reference count increased.
+ */
+
+struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+					 struct perf_cpu_map *other)
+{
+	int *tmp_cpus;
+	int tmp_len;
+	int i, j, k;
+	struct perf_cpu_map *merged;
+
+	if (!orig && !other)
+		return NULL;
+	if (!orig) {
+		perf_cpu_map__get(other);
+		return other;
+	}
+	if (!other)
+		return orig;
+	if (orig->nr == other->nr &&
+	    !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+		return orig;
+
+	tmp_len = orig->nr + other->nr;
+	tmp_cpus = malloc(tmp_len * sizeof(int));
+	if (!tmp_cpus)
+		return NULL;
+
+	/* Standard merge algorithm from wikipedia */
+	i = j = k = 0;
+	while (i < orig->nr && j < other->nr) {
+		if (orig->map[i] <= other->map[j]) {
+			if (orig->map[i] == other->map[j])
+				j++;
+			tmp_cpus[k++] = orig->map[i++];
+		} else
+			tmp_cpus[k++] = other->map[j++];
+	}
+
+	while (i < orig->nr)
+		tmp_cpus[k++] = orig->map[i++];
+
+	while (j < other->nr)
+		tmp_cpus[k++] = other->map[j++];
+	assert(k <= tmp_len);
+
+	merged = cpu_map__trim_new(k, tmp_cpus);
+	free(tmp_cpus);
+	perf_cpu_map__put(orig);
+	return merged;
+}
diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c
index 205ddbb80bc1..ae9e65aa2491 100644
--- a/tools/perf/lib/evlist.c
+++ b/tools/perf/lib/evlist.c
@@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 
 	perf_thread_map__put(evsel->threads);
 	evsel->threads = perf_thread_map__get(evlist->threads);
+	evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
 }
 
 static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c
index 5a89857b0381..4dc06289f4c7 100644
--- a/tools/perf/lib/evsel.c
+++ b/tools/perf/lib/evsel.c
@@ -114,16 +114,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	return err;
 }
 
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+{
+	int thread;
+
+	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
+		if (FD(evsel, cpu, thread) >= 0)
+			close(FD(evsel, cpu, thread));
+		FD(evsel, cpu, thread) = -1;
+	}
+}
+
 void perf_evsel__close_fd(struct perf_evsel *evsel)
 {
-	int cpu, thread;
+	int cpu;
 
 	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
-		for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-			if (FD(evsel, cpu, thread) >= 0)
-				close(FD(evsel, cpu, thread));
-			FD(evsel, cpu, thread) = -1;
-		}
+		perf_evsel__close_fd_cpu(evsel, cpu);
 }
 
 void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -141,6 +148,14 @@ void perf_evsel__close(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 }
 
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+{
+	if (evsel->fd == NULL)
+		return;
+
+	perf_evsel__close_fd_cpu(evsel, cpu);
+}
+
 int perf_evsel__read_size(struct perf_evsel *evsel)
 {
 	u64 read_format = evsel->attr.read_format;
@@ -183,38 +198,61 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 }
 
 static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
-				 int ioc,  void *arg)
+				 int ioc,  void *arg,
+				 int cpu)
 {
-	int cpu, thread;
+	int thread;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
-		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int fd = FD(evsel, cpu, thread),
-			    err = ioctl(fd, ioc, arg);
+	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+		int fd = FD(evsel, cpu, thread),
+		    err = ioctl(fd, ioc, arg);
 
-			if (err)
-				return err;
-		}
+		if (err)
+			return err;
 	}
 
 	return 0;
 }
 
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+{
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+}
+
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+	int i;
+	int err = 0;
+
+	for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++)
+		err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, i);
+	return err;
+}
+
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+{
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+	int i;
+	int err = 0;
+
+	for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++)
+		err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, i);
+	return err;
 }
 
 int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
 {
-	return perf_evsel__run_ioctl(evsel,
+	int err = 0, i;
+
+	for (i = 0; i < evsel->cpus->nr && !err; i++)
+		err = perf_evsel__run_ioctl(evsel,
 				     PERF_EVENT_IOC_SET_FILTER,
-				     (void *)filter);
+				     (void *)filter, i);
+	return err;
 }
 
 struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h
index a2fbccf1922f..74dc8c3f0b66 100644
--- a/tools/perf/lib/include/internal/evlist.h
+++ b/tools/perf/lib/include/internal/evlist.h
@@ -18,6 +18,7 @@ struct perf_evlist {
 	int			 nr_entries;
 	bool			 has_user_cpus;
 	struct perf_cpu_map	*cpus;
+	struct perf_cpu_map	*all_cpus;
 	struct perf_thread_map	*threads;
 	int			 nr_mmaps;
 	size_t			 mmap_len;
diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h
index ac9aa497f84a..6a17ad730cbc 100644
--- a/tools/perf/lib/include/perf/cpumap.h
+++ b/tools/perf/lib/include/perf/cpumap.h
@@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+						     struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h
index 557f5815a9c9..c82ec39a4ad0 100644
--- a/tools/perf/lib/include/perf/evsel.h
+++ b/tools/perf/lib/include/perf/evsel.h
@@ -26,10 +26,13 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
 LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 				 struct perf_thread_map *threads);
 LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);
+LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
 LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 				 struct perf_counts_values *count);
 LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
 LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
 LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
 LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
 LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 436ce33f1182..5da8296b667e 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -32,7 +32,7 @@
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
-		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
 		"Unit": "CPU-M-CF",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index 68618152ea2c..89e070727e1b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -4,7 +4,7 @@
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
-		"PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
 		"Unit": "CPU-M-CF",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index bc7151d639d7..45a34ce4fe89 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -297,7 +297,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
index 49c5f123d811..961fe4395758 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
@@ -115,7 +115,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 113d19e92678..746734ce09be 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -297,7 +297,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 2ba32af9bc36..f94653229dd4 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -315,7 +315,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
index c80f16fde6d0..5402cd3120f9 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index e501729c3dd1..832f3cb40b34 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -267,7 +267,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index e2446966b651..d69b2a8fc0bc 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -285,7 +285,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
index 9294769dec64..5f465fd81315 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -285,7 +285,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
index 603ff9c2e9a1..3e909b306003 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
index c6b485b3a2cb..50c053235752 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -171,7 +171,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index 0ca539bb60f6..e7feb60f9fa9 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -303,7 +303,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 047d7e11aa6f..21d7a0c2c2e8 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -315,7 +315,7 @@
     },
     {
         "BriefDescription": "Fraction of cycles spent in Kernel mode",
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:k / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index a3c595fba943..1692529639b0 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -54,6 +54,7 @@ perf-y += unit_number__scnprintf.o
 perf-y += mem2node.o
 perf-y += maps.o
 perf-y += time-utils-test.o
+perf-y += genelf.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 7115aa32a51e..5f05db75cdd8 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -260,6 +260,11 @@ static struct test generic_tests[] = {
 		.func = test__cpu_map_print,
 	},
 	{
+		.desc = "Merge cpu map",
+		.func = test__cpu_map_merge,
+	},
+
+	{
 		.desc = "Probe SDT events",
 		.func = test__sdt_event,
 	},
@@ -297,6 +302,10 @@ static struct test generic_tests[] = {
 		.func = test__time_utils,
 	},
 	{
+		.desc = "Test jit_write_elf",
+		.func = test__jit_write_elf,
+	},
+	{
 		.desc = "maps__merge_in",
 		.func = test__maps__merge_in,
 	},
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 8a0d236202b0..4ac56741ac5f 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un
 	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
 	return 0;
 }
+
+int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	struct perf_cpu_map *a = perf_cpu_map__new("4,2,1");
+	struct perf_cpu_map *b = perf_cpu_map__new("4,5,7");
+	struct perf_cpu_map *c = perf_cpu_map__merge(a, b);
+	char buf[100];
+
+	TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5);
+	cpu_map__snprint(c, buf, sizeof(buf));
+	TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7"));
+	perf_cpu_map__put(a);
+	perf_cpu_map__put(b);
+	perf_cpu_map__put(c);
+	return 0;
+}
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 1ee8704e2284..1e8a9f5c356d 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -125,7 +125,7 @@ static int attach__cpu_disabled(struct evlist *evlist)
 
 	evsel->core.attr.disabled = 1;
 
-	err = perf_evsel__open_per_cpu(evsel, cpus);
+	err = perf_evsel__open_per_cpu(evsel, cpus, -1);
 	if (err) {
 		if (err == -EACCES)
 			return TEST_SKIP;
@@ -152,7 +152,7 @@ static int attach__cpu_enabled(struct evlist *evlist)
 		return -1;
 	}
 
-	err = perf_evsel__open_per_cpu(evsel, cpus);
+	err = perf_evsel__open_per_cpu(evsel, cpus, -1);
 	if (err == -EACCES)
 		return TEST_SKIP;
 
diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c
new file mode 100644
index 000000000000..f797f9823e89
--- /dev/null
+++ b/tools/perf/tests/genelf.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+
+#include "debug.h"
+#include "tests.h"
+
+#ifdef HAVE_JITDUMP
+#include <libelf.h>
+#include "../util/genelf.h"
+#endif
+
+#define TEMPL "/tmp/perf-test-XXXXXX"
+
+int test__jit_write_elf(struct test *test __maybe_unused,
+			int subtest __maybe_unused)
+{
+#ifdef HAVE_JITDUMP
+	static unsigned char x86_code[] = {
+		0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
+		0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
+		0xCD, 0x80            /* int $0x80 */
+	};
+	char path[PATH_MAX];
+	int fd, ret;
+
+	strcpy(path, TEMPL);
+
+	fd = mkstemp(path);
+	if (fd < 0) {
+		perror("mkstemp failed");
+		return TEST_FAIL;
+	}
+
+	pr_info("Writing jit code to: %s\n", path);
+
+	ret = jit_write_elf(fd, 0, "main", x86_code, sizeof(x86_code),
+			NULL, 0, NULL, 0, 0);
+	close(fd);
+
+	unlink(path);
+
+	return ret ? TEST_FAIL : 0;
+#else
+	return TEST_SKIP;
+#endif
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 25aea387e2bf..9a160fef47c9 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest);
 int test__event_times(struct test *test, int subtest);
 int test__backward_ring_buffer(struct test *test, int subtest);
 int test__cpu_map_print(struct test *test, int subtest);
+int test__cpu_map_merge(struct test *test, int subtest);
 int test__sdt_event(struct test *test, int subtest);
 int test__is_printable_array(struct test *test, int subtest);
 int test__bitmap_print(struct test *test, int subtest);
@@ -109,6 +110,7 @@ int test__unit_number__scnprint(struct test *test, int subtest);
 int test__mem2node(struct test *t, int subtest);
 int test__maps__merge_in(struct test *t, int subtest);
 int test__time_utils(struct test *t, int subtest);
+int test__jit_write_elf(struct test *test, int subtest);
 
 bool test__bp_signal_is_supported(void);
 bool test__bp_account_is_supported(void);
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index 1a8d3be2030e..062ca849c8fd 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -45,6 +45,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size,
 	P_FLAG(NEWPID);
 	P_FLAG(NEWNET);
 	P_FLAG(IO);
+	P_FLAG(CLEAR_SIGHAND);
 #undef P_FLAG
 
 	if (flags)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 57943f3685f8..3a442f021468 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -63,4 +63,5 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
 
 int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
 bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
+
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index fdce590d2278..1548237b6558 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,6 +18,7 @@
 #include "debug.h"
 #include "units.h"
 #include <internal/lib.h> // page_size
+#include "affinity.h"
 #include "../perf.h"
 #include "asm/bug.h"
 #include "bpf-event.h"
@@ -342,14 +343,63 @@ static int perf_evlist__nr_threads(struct evlist *evlist,
 		return perf_thread_map__nr(evlist->core.threads);
 }
 
+void evlist__cpu_iter_start(struct evlist *evlist)
+{
+	struct evsel *pos;
+
+	/*
+	 * Reset the per evsel cpu_iter. This is needed because
+	 * each evsel's cpumap may have a different index space,
+	 * and some operations need the index to modify
+	 * the FD xyarray (e.g. open, close)
+	 */
+	evlist__for_each_entry(evlist, pos)
+		pos->cpu_iter = 0;
+}
+
+bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu)
+{
+	if (ev->cpu_iter >= ev->core.cpus->nr)
+		return true;
+	if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu)
+		return true;
+	return false;
+}
+
+bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
+{
+	if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) {
+		ev->cpu_iter++;
+		return false;
+	}
+	return true;
+}
+
 void evlist__disable(struct evlist *evlist)
 {
 	struct evsel *pos;
+	struct affinity affinity;
+	int cpu, i;
+
+	if (affinity__setup(&affinity) < 0)
+		return;
 
+	evlist__for_each_cpu(evlist, i, cpu) {
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evlist, pos) {
+			if (evsel__cpu_iter_skip(pos, cpu))
+				continue;
+			if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			evsel__disable_cpu(pos, pos->cpu_iter - 1);
+		}
+	}
+	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
-		if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		evsel__disable(pos);
+		pos->disabled = true;
 	}
 
 	evlist->enabled = false;
@@ -358,11 +408,28 @@ void evlist__disable(struct evlist *evlist)
 void evlist__enable(struct evlist *evlist)
 {
 	struct evsel *pos;
+	struct affinity affinity;
+	int cpu, i;
+
+	if (affinity__setup(&affinity) < 0)
+		return;
 
+	evlist__for_each_cpu(evlist, i, cpu) {
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry(evlist, pos) {
+			if (evsel__cpu_iter_skip(pos, cpu))
+				continue;
+			if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			evsel__enable_cpu(pos, pos->cpu_iter - 1);
+		}
+	}
+	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
 		if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
 			continue;
-		evsel__enable(pos);
+		pos->disabled = false;
 	}
 
 	evlist->enabled = true;
@@ -1137,9 +1204,35 @@ void perf_evlist__set_selected(struct evlist *evlist,
 void evlist__close(struct evlist *evlist)
 {
 	struct evsel *evsel;
+	struct affinity affinity;
+	int cpu, i;
 
-	evlist__for_each_entry_reverse(evlist, evsel)
-		evsel__close(evsel);
+	/*
+	 * With perf record core.cpus is usually NULL.
+	 * Use the old method to handle this for now.
+	 */
+	if (!evlist->core.cpus) {
+		evlist__for_each_entry_reverse(evlist, evsel)
+			evsel__close(evsel);
+		return;
+	}
+
+	if (affinity__setup(&affinity) < 0)
+		return;
+	evlist__for_each_cpu(evlist, i, cpu) {
+		affinity__set(&affinity, cpu);
+
+		evlist__for_each_entry_reverse(evlist, evsel) {
+			if (evsel__cpu_iter_skip(evsel, cpu))
+			    continue;
+			perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1);
+		}
+	}
+	affinity__cleanup(&affinity);
+	evlist__for_each_entry_reverse(evlist, evsel) {
+		perf_evsel__free_fd(&evsel->core);
+		perf_evsel__free_id(&evsel->core);
+	}
 }
 
 static int perf_evlist__create_syswide_maps(struct evlist *evlist)
@@ -1577,7 +1670,8 @@ void perf_evlist__force_leader(struct evlist *evlist)
 }
 
 struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
-						 struct evsel *evsel)
+						 struct evsel *evsel,
+						bool close)
 {
 	struct evsel *c2, *leader;
 	bool is_open = true;
@@ -1594,10 +1688,15 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
 		if (c2 == evsel)
 			is_open = false;
 		if (c2->leader == leader) {
-			if (is_open)
+			if (is_open && close)
 				perf_evsel__close(&c2->core);
 			c2->leader = c2;
 			c2->core.nr_members = 0;
+			/*
+			 * Set this for all former members of the group
+			 * to indicate they get reopened.
+			 */
+			c2->reset_group = true;
 		}
 	}
 	return leader;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 3655b9ebb147..f5bd5c386df1 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -334,9 +334,17 @@ void perf_evlist__to_front(struct evlist *evlist,
 #define evlist__for_each_entry_safe(evlist, tmp, evsel) \
 	__evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel)
 
+#define evlist__for_each_cpu(evlist, index, cpu)	\
+	evlist__cpu_iter_start(evlist);			\
+	perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
+
 void perf_evlist__set_tracking_event(struct evlist *evlist,
 				     struct evsel *tracking_evsel);
 
+void evlist__cpu_iter_start(struct evlist *evlist);
+bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
+bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
+
 struct evsel *
 perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
 
@@ -348,5 +356,6 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist);
 void perf_evlist__force_leader(struct evlist *evlist);
 
 struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
-						 struct evsel *evsel);
+						 struct evsel *evsel,
+						bool close);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f4dea055b080..a69e64236120 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1223,16 +1223,27 @@ int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
 	return perf_evsel__append_filter(evsel, "%s,%s", filter);
 }
 
+/* Caller has to clear disabled after going through all CPUs. */
+int evsel__enable_cpu(struct evsel *evsel, int cpu)
+{
+	return perf_evsel__enable_cpu(&evsel->core, cpu);
+}
+
 int evsel__enable(struct evsel *evsel)
 {
 	int err = perf_evsel__enable(&evsel->core);
 
 	if (!err)
 		evsel->disabled = false;
-
 	return err;
 }
 
+/* Caller has to set disabled after going through all CPUs. */
+int evsel__disable_cpu(struct evsel *evsel, int cpu)
+{
+	return perf_evsel__disable_cpu(&evsel->core, cpu);
+}
+
 int evsel__disable(struct evsel *evsel)
 {
 	int err = perf_evsel__disable(&evsel->core);
@@ -1587,8 +1598,9 @@ static int perf_event_open(struct evsel *evsel,
 	return fd;
 }
 
-int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
-		struct perf_thread_map *threads)
+static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
+		struct perf_thread_map *threads,
+		int start_cpu, int end_cpu)
 {
 	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
@@ -1665,7 +1677,7 @@ retry_sample_id:
 
 	display_attr(&evsel->core.attr);
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	for (cpu = start_cpu; cpu < end_cpu; cpu++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd, group_fd;
@@ -1843,6 +1855,12 @@ out_close:
 	return err;
 }
 
+int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
+		struct perf_thread_map *threads)
+{
+	return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1);
+}
+
 void evsel__close(struct evsel *evsel)
 {
 	perf_evsel__close(&evsel->core);
@@ -1850,9 +1868,14 @@ void evsel__close(struct evsel *evsel)
 }
 
 int perf_evsel__open_per_cpu(struct evsel *evsel,
-			     struct perf_cpu_map *cpus)
+			     struct perf_cpu_map *cpus,
+			     int cpu)
 {
-	return evsel__open(evsel, cpus, NULL);
+	if (cpu == -1)
+		return evsel__open_cpu(evsel, cpus, NULL, 0,
+					cpus ? cpus->nr : 1);
+
+	return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
 }
 
 int perf_evsel__open_per_thread(struct evsel *evsel,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ddc5ee6f6592..dc14f4a823cd 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -86,6 +86,7 @@ struct evsel {
 	struct list_head	config_terms;
 	struct bpf_object	*bpf_obj;
 	int			bpf_fd;
+	int			err;
 	bool			auto_merge_stats;
 	bool			merged_stat;
 	const char *		metric_expr;
@@ -94,7 +95,10 @@ struct evsel {
 	struct evsel		*metric_leader;
 	bool			collect_stat;
 	bool			weak_group;
+	bool			reset_group;
+	bool			errored;
 	bool			percore;
+	int			cpu_iter;
 	const char		*pmu_name;
 	struct {
 		perf_evsel__sb_cb_t	*cb;
@@ -218,11 +222,14 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter);
 int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter);
 int perf_evsel__append_addr_filter(struct evsel *evsel,
 				   const char *filter);
+int evsel__enable_cpu(struct evsel *evsel, int cpu);
 int evsel__enable(struct evsel *evsel);
 int evsel__disable(struct evsel *evsel);
+int evsel__disable_cpu(struct evsel *evsel, int cpu);
 
 int perf_evsel__open_per_cpu(struct evsel *evsel,
-			     struct perf_cpu_map *cpus);
+			     struct perf_cpu_map *cpus,
+			     int cpu);
 int perf_evsel__open_per_thread(struct evsel *evsel,
 				struct perf_thread_map *threads);
 int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index f9f18b8b1df9..aed49806a09b 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -8,15 +8,12 @@
  */
 
 #include <sys/types.h>
-#include <stdio.h>
-#include <getopt.h>
 #include <stddef.h>
 #include <libelf.h>
 #include <string.h>
 #include <stdlib.h>
 #include <unistd.h>
 #include <inttypes.h>
-#include <limits.h>
 #include <fcntl.h>
 #include <err.h>
 #ifdef HAVE_DWARF_SUPPORT
@@ -31,8 +28,6 @@
 #define NT_GNU_BUILD_ID 3
 #endif
 
-#define JVMTI
-
 #define BUILD_ID_URANDOM /* different uuid for each run */
 
 #ifdef HAVE_LIBCRYPTO
@@ -511,44 +506,3 @@ error:
 
 	return retval;
 }
-
-#ifndef JVMTI
-
-static unsigned char x86_code[] = {
-    0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
-    0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
-    0xCD, 0x80            /* int $0x80 */
-};
-
-static struct options options;
-
-int main(int argc, char **argv)
-{
-	int c, fd, ret;
-
-	while ((c = getopt(argc, argv, "o:h")) != -1) {
-		switch (c) {
-		case 'o':
-			options.output = optarg;
-			break;
-		case 'h':
-			printf("Usage: genelf -o output_file [-h]\n");
-			return 0;
-		default:
-			errx(1, "unknown option");
-		}
-	}
-
-	fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666);
-	if (fd == -1)
-		err(1, "cannot create file %s", options.output);
-
-	ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code));
-	close(fd);
-
-	if (ret != 0)
-		unlink(options.output);
-
-	return ret;
-}
-#endif
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index becc2d109423..93ad27830e2b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -850,7 +850,7 @@ int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
  */
 int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
 {
-	return -1;
+	return ENOSYS; /* Not implemented */
 }
 
 static int write_cpuid(struct feat_fd *ff,
@@ -1089,21 +1089,18 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
 	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
 }
 
-static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+#define MAX_CACHE_LVL 4
+
+static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
 {
 	u32 i, cnt = 0;
-	long ncpus;
 	u32 nr, cpu;
 	u16 level;
 
-	ncpus = sysconf(_SC_NPROCESSORS_CONF);
-	if (ncpus < 0)
-		return -1;
-
-	nr = (u32)(ncpus & UINT_MAX);
+	nr = cpu__max_cpu();
 
 	for (cpu = 0; cpu < nr; cpu++) {
-		for (level = 0; level < 10; level++) {
+		for (level = 0; level < MAX_CACHE_LVL; level++) {
 			struct cpu_cache_level c;
 			int err;
 
@@ -1123,18 +1120,12 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
 				caches[cnt++] = c;
 			else
 				cpu_cache_level__free(&c);
-
-			if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
-				goto out;
 		}
 	}
- out:
 	*cntp = cnt;
 	return 0;
 }
 
-#define MAX_CACHE_LVL 4
-
 static int write_cache(struct feat_fd *ff,
 		       struct evlist *evlist __maybe_unused)
 {
@@ -1143,7 +1134,7 @@ static int write_cache(struct feat_fd *ff,
 	u32 cnt = 0, i, version = 1;
 	int ret;
 
-	ret = build_caches(caches, max_caches, &cnt);
+	ret = build_caches(caches, &cnt);
 	if (ret)
 		goto out;
 
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index f01d48a8d707..b8a5159361b4 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -5,10 +5,93 @@
 
 /* linkage.h ... for including arch/x86/lib/memcpy_64.S */
 
-#define ENTRY(name)				\
-	.globl name;				\
+/* Some toolchains use other characters (e.g. '`') to mark new line in macro */
+#ifndef ASM_NL
+#define ASM_NL		 ;
+#endif
+
+#ifndef __ALIGN
+#define __ALIGN		.align 4,0x90
+#define __ALIGN_STR	".align 4,0x90"
+#endif
+
+/* SYM_T_FUNC -- type used by assembler to mark functions */
+#ifndef SYM_T_FUNC
+#define SYM_T_FUNC				STT_FUNC
+#endif
+
+/* SYM_A_* -- align the symbol? */
+#define SYM_A_ALIGN				ALIGN
+
+/* SYM_L_* -- linkage of symbols */
+#define SYM_L_GLOBAL(name)			.globl name
+#define SYM_L_LOCAL(name)			/* nothing */
+
+#define ALIGN __ALIGN
+
+/* === generic annotations === */
+
+/* SYM_ENTRY -- use only if you have to for non-paired symbols */
+#ifndef SYM_ENTRY
+#define SYM_ENTRY(name, linkage, align...)		\
+	linkage(name) ASM_NL				\
+	align ASM_NL					\
 	name:
+#endif
+
+/* SYM_START -- use only if you have to */
+#ifndef SYM_START
+#define SYM_START(name, linkage, align...)		\
+	SYM_ENTRY(name, linkage, align)
+#endif
+
+/* SYM_END -- use only if you have to */
+#ifndef SYM_END
+#define SYM_END(name, sym_type)				\
+	.type name sym_type ASM_NL			\
+	.size name, .-name
+#endif
+
+/*
+ * SYM_FUNC_START_ALIAS -- use where there are two global names for one
+ * function
+ */
+#ifndef SYM_FUNC_START_ALIAS
+#define SYM_FUNC_START_ALIAS(name)			\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START -- use for global functions */
+#ifndef SYM_FUNC_START
+/*
+ * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two
+ * later.
+ */
+#define SYM_FUNC_START(name)				\
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START_LOCAL -- use for local functions */
+#ifndef SYM_FUNC_START_LOCAL
+/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_START_LOCAL(name)			\
+	SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */
+#ifndef SYM_FUNC_END_ALIAS
+#define SYM_FUNC_END_ALIAS(name)			\
+	SYM_END(name, SYM_T_FUNC)
+#endif
 
-#define ENDPROC(name)
+/*
+ * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
+ * SYM_FUNC_START_WEAK, ...
+ */
+#ifndef SYM_FUNC_END
+/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_END(name)				\
+	SYM_END(name, SYM_T_FUNC)
+#endif
 
 #endif	/* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 416d174d223c..c8c5410315e8 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2446,6 +2446,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms
 
 	list_for_each_entry(ilist, &inline_node->val, list) {
 		struct map_symbol ilist_ms = {
+			.maps = ms->maps,
 			.map = map,
 			.sym = ilist->symbol,
 		};
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 6a4d350d5cdb..02aee946b6c1 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -103,8 +103,11 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 		if (!strcmp(ev->name, ids[i])) {
 			if (!metric_events[i])
 				metric_events[i] = ev;
+			i++;
+			if (i == idnum)
+				break;
 		} else {
-			if (++i == idnum) {
+			if (i + 1 == idnum) {
 				/* Discard the whole match and start again */
 				i = 0;
 				memset(metric_events, 0,
@@ -124,7 +127,7 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 		}
 	}
 
-	if (i != idnum - 1) {
+	if (i != idnum) {
 		/* Not whole match */
 		return NULL;
 	}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 345b5ccc90f6..9fcba2872130 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2681,12 +2681,12 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
 				if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
-					pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
+					ui__error("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
 				else
-					pr_err("Invalid --sort key: `%s'", tok);
+					ui__error("Invalid --sort key: `%s'", tok);
 				break;
 			} else if (ret == -ESRCH) {
-				pr_err("Unknown --sort key: `%s'", tok);
+				ui__error("Unknown --sort key: `%s'", tok);
 				break;
 			}
 		}
@@ -2743,7 +2743,7 @@ static int setup_sort_order(struct evlist *evlist)
 		return 0;
 
 	if (sort_order[1] == '\0') {
-		pr_err("Invalid --sort key: `+'");
+		ui__error("Invalid --sort key: `+'");
 		return -EINVAL;
 	}
 
@@ -2959,6 +2959,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
+		if (sort__mode != SORT_MODE__MEMORY)
+			return -EINVAL;
+
 		return __sort_dimension__add_output(list, sd);
 	}
 
@@ -2968,6 +2971,9 @@ int output_field_add(struct perf_hpp_list *list, char *tok)
 		if (strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
+		if (sort__mode != SORT_MODE__BRANCH)
+			return -EINVAL;
+
 		return __sort_dimension__add_output(list, sd);
 	}
 
@@ -3034,7 +3040,7 @@ static int __setup_output_field(void)
 		strp++;
 
 	if (!strlen(strp)) {
-		pr_err("Invalid --fields key: `+'");
+		ui__error("Invalid --fields key: `+'");
 		goto out;
 	}
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 332cb730785b..5f26137b8d60 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -464,7 +464,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 
 int create_perf_stat_counter(struct evsel *evsel,
 			     struct perf_stat_config *config,
-			     struct target *target)
+			     struct target *target,
+			     int cpu)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	struct evsel *leader = evsel->leader;
@@ -518,7 +519,7 @@ int create_perf_stat_counter(struct evsel *evsel,
 	}
 
 	if (target__has_cpu(target) && !target__has_per_thread(target))
-		return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel));
+		return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
 
 	return perf_evsel__open_per_thread(evsel, evsel->core.threads);
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index bfa9aaf36ce6..fb990efa54a8 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -214,7 +214,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
 
 int create_perf_stat_counter(struct evsel *evsel,
 			     struct perf_stat_config *config,
-			     struct target *target);
+			     struct target *target,
+			     int cpu);
 void
 perf_evlist__print_counters(struct evlist *evlist,
 			    struct perf_stat_config *config,