Merge tag 'perf-tools-for-v5.14-2021-07-01' of...

Merge tag 'perf-tools-for-v5.14-2021-07-01' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "Tools:

   - Add cgroup support for 'perf top' (-G).

   - Add support for KVM MSRs in 'perf kvm stat'

   - Support probes on init functions in 'perf probe', to support the
     bootconfig format.

   - Improve error reporting in 'perf probe'.

   - No need to synthesize BUILD_ID records in 'perf inject' if the
     MMAP2 records have build ids already.

   - Allow toggling source code ('s' hotkey) in 'perf annotate' in all
     lines.

   - Add itrace options support to 'perf annotate'.

   - Support to custom DSO filters for 'perf script'.

  Hardware enablement:

   - Support the HYBRID_TOPOLOGY and HYBRID_CPU_PMU_CAPS features in the
     perf.data file header.

   - Support PMU prefix for mem-load and mem-store events, to support
     hybrid (BIG little) CPUs such as Intel's Alderlake.

   - Support hybrid CPUs in 'perf mem' and 'perf c2c'.

  Hardware tracing:

   - Intel PT now supports tracing KVM guests.

   - Timestamp improvements for ARM's Coresight.

  Build:

   - Add 'make -C tools/perf build-test' entries for
     libopencsd/CORESIGHT=1 and libbpf/LIBBPF_DYNAMIC=1.

   - Use bison's --file-prefix-map option to avoid storing full paths
     when using O= in the perf build.

  Tests:

   - Improve the 'perf test' entries for libpfm4 and BPF counters.

  Misc:

   - Sync msr-index.h, mount.h, kvm headers with the kernel originals.

   - Add vendor events and metrics for Intel's Icelake Server & Client"

* tag 'perf-tools-for-v5.14-2021-07-01' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (123 commits)
  perf session: Add missing evlist__delete when deleting a session
  perf annotate: Allow 's' on source code lines
  perf dlfilter: Add object_code() to perf_dlfilter_fns
  perf dlfilter: Add attr() to perf_dlfilter_fns
  perf dlfilter: Add srcline() to perf_dlfilter_fns
  perf dlfilter: Add insn() to perf_dlfilter_fns
  perf dlfilter: Add resolve_address() to perf_dlfilter_fns
  perf build: Install perf_dlfilter.h
  perf script: Add option to pass arguments to dlfilters
  perf script: Add option to list dlfilters
  perf script: Add dlfilter__filter_event_early()
  perf script: Add API for filtering via dynamically loaded shared object
  perf llvm: Return -ENOMEM when asprintf() fails
  perf cs-etm: Delay decode of non-timeless data until cs_etm__flush_events()
  tools headers UAPI: Synch KVM's svm.h header with the kernel
  tools kvm headers arm64: Update KVM headers from the kernel sources
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  tools include UAPI: Update linux/mount.h copy
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  ...

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -184,6 +184,17 @@ struct kvm_vcpu_events {
 	__u32 reserved[12];
 };
 
+struct kvm_arm_copy_mte_tags {
+	__u64 guest_ipa;
+	__u64 length;
+	void __user *addr;
+	__u64 flags;
+	__u64 reserved[2];
+};
+
+#define KVM_ARM_TAGS_TO_GUEST		0
+#define KVM_ARM_TAGS_FROM_GUEST		1
+
 /* If you need to interpret the index values, here is the key: */
 #define KVM_REG_ARM_COPROC_MASK		0x000000000FFF0000
 #define KVM_REG_ARM_COPROC_SHIFT	16

tools/arch/x86/include/asm/cpufeatures.h

@@ -108,7 +108,7 @@
 #define X86_FEATURE_EXTD_APICID		( 3*32+26) /* Extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM		( 3*32+27) /* AMD multi-node processor */
 #define X86_FEATURE_APERFMPERF		( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
-/* free					( 3*32+29) */
+#define X86_FEATURE_RAPL		( 3*32+29) /* AMD/Hygon RAPL interface */
 #define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
 #define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
 
@@ -378,6 +378,7 @@
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_SRBDS_CTRL		(18*32+ 9) /* "" SRBDS mitigation MSR available */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
+#define X86_FEATURE_RTM_ALWAYS_ABORT	(18*32+11) /* "" RTM transaction always aborts */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
 #define X86_FEATURE_HYBRID_CPU		(18*32+15) /* "" This part has CPUs of more than one type */

tools/arch/x86/include/asm/msr-index.h

@@ -772,6 +772,10 @@
 
 #define MSR_TFA_RTM_FORCE_ABORT_BIT	0
 #define MSR_TFA_RTM_FORCE_ABORT		BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT)
+#define MSR_TFA_TSX_CPUID_CLEAR_BIT	1
+#define MSR_TFA_TSX_CPUID_CLEAR		BIT_ULL(MSR_TFA_TSX_CPUID_CLEAR_BIT)
+#define MSR_TFA_SDV_ENABLE_RTM_BIT	2
+#define MSR_TFA_SDV_ENABLE_RTM		BIT_ULL(MSR_TFA_SDV_ENABLE_RTM_BIT)
 
 /* P4/Xeon+ specific */
 #define MSR_IA32_MCG_EAX		0x00000180

tools/arch/x86/include/uapi/asm/kvm.h

@@ -159,6 +159,19 @@ struct kvm_sregs {
 	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
 };
 
+struct kvm_sregs2 {
+	/* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */
+	struct kvm_segment cs, ds, es, fs, gs, ss;
+	struct kvm_segment tr, ldt;
+	struct kvm_dtable gdt, idt;
+	__u64 cr0, cr2, cr3, cr4, cr8;
+	__u64 efer;
+	__u64 apic_base;
+	__u64 flags;
+	__u64 pdptrs[4];
+};
+#define KVM_SREGS2_FLAGS_PDPTRS_VALID 1
+
 /* for KVM_GET_FPU and KVM_SET_FPU */
 struct kvm_fpu {
 	__u8  fpr[8][16];

tools/arch/x86/include/uapi/asm/svm.h

@@ -110,6 +110,9 @@
 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE		1
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
 
+/* Exit code reserved for hypervisor/software use */
+#define SVM_EXIT_SW				0xf0000000
+
 #define SVM_EXIT_ERR           -1
 
 #define SVM_EXIT_REASONS \

tools/include/linux/bitmap.h

@@ -18,6 +18,8 @@ int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 int __bitmap_equal(const unsigned long *bitmap1,
 		   const unsigned long *bitmap2, unsigned int bits);
 void bitmap_clear(unsigned long *map, unsigned int start, int len);
+int __bitmap_intersects(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, unsigned int bits);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
@@ -170,4 +172,13 @@ static inline int bitmap_equal(const unsigned long *src1,
 	return __bitmap_equal(src1, src2, nbits);
 }
 
+static inline int bitmap_intersects(const unsigned long *src1,
+			const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+	else
+		return __bitmap_intersects(src1, src2, nbits);
+}
+
 #endif /* _PERF_BITOPS_H */

tools/include/uapi/linux/kvm.h

@@ -280,6 +280,9 @@ struct kvm_xen_exit {
 /* Encounter unexpected vm-exit reason */
 #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
+/* Flags that describe what fields in emulation_failure hold valid data. */
+#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0)
+
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
 	/* in */
@@ -383,6 +386,25 @@ struct kvm_run {
 			__u32 ndata;
 			__u64 data[16];
 		} internal;
+		/*
+		 * KVM_INTERNAL_ERROR_EMULATION
+		 *
+		 * "struct emulation_failure" is an overlay of "struct internal"
+		 * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of
+		 * KVM_EXIT_INTERNAL_ERROR.  Note, unlike other internal error
+		 * sub-types, this struct is ABI!  It also needs to be backwards
+		 * compatible with "struct internal".  Take special care that
+		 * "ndata" is correct, that new fields are enumerated in "flags",
+		 * and that each flag enumerates fields that are 64-bit aligned
+		 * and sized (so that ndata+internal.data[] is valid/accurate).
+		 */
+		struct {
+			__u32 suberror;
+			__u32 ndata;
+			__u64 flags;
+			__u8  insn_size;
+			__u8  insn_bytes[15];
+		} emulation_failure;
 		/* KVM_EXIT_OSI */
 		struct {
 			__u64 gprs[32];
@@ -1083,6 +1105,13 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SGX_ATTRIBUTE 196
 #define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197
 #define KVM_CAP_PTP_KVM 198
+#define KVM_CAP_HYPERV_ENFORCE_CPUID 199
+#define KVM_CAP_SREGS2 200
+#define KVM_CAP_EXIT_HYPERCALL 201
+#define KVM_CAP_PPC_RPT_INVALIDATE 202
+#define KVM_CAP_BINARY_STATS_FD 203
+#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
+#define KVM_CAP_ARM_MTE 205
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1428,6 +1457,7 @@ struct kvm_s390_ucas_mapping {
 /* 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)
+#define KVM_ARM_MTE_COPY_TAGS	  _IOR(KVMIO,  0xb4, struct kvm_arm_copy_mte_tags)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)
@@ -1621,6 +1651,9 @@ struct kvm_xen_hvm_attr {
 #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
 #define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
 
+#define KVM_GET_SREGS2             _IOR(KVMIO,  0xcc, struct kvm_sregs2)
+#define KVM_SET_SREGS2             _IOW(KVMIO,  0xcd, struct kvm_sregs2)
+
 struct kvm_xen_vcpu_attr {
 	__u16 type;
 	__u16 pad[3];
@@ -1899,4 +1932,76 @@ struct kvm_dirty_gfn {
 #define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
 #define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
 
+/**
+ * struct kvm_stats_header - Header of per vm/vcpu binary statistics data.
+ * @flags: Some extra information for header, always 0 for now.
+ * @name_size: The size in bytes of the memory which contains statistics
+ *             name string including trailing '\0'. The memory is allocated
+ *             at the send of statistics descriptor.
+ * @num_desc: The number of statistics the vm or vcpu has.
+ * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed
+ *             by vm/vcpu stats fd.
+ * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file
+ *               pointd by vm/vcpu stats fd.
+ * @data_offset: The offset of the vm/vcpu stats' data block in the file
+ *               pointed by vm/vcpu stats fd.
+ *
+ * This is the header userspace needs to read from stats fd before any other
+ * readings. It is used by userspace to discover all the information about the
+ * vm/vcpu's binary statistics.
+ * Userspace reads this header from the start of the vm/vcpu's stats fd.
+ */
+struct kvm_stats_header {
+	__u32 flags;
+	__u32 name_size;
+	__u32 num_desc;
+	__u32 id_offset;
+	__u32 desc_offset;
+	__u32 data_offset;
+};
+
+#define KVM_STATS_TYPE_SHIFT		0
+#define KVM_STATS_TYPE_MASK		(0xF << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_CUMULATIVE	(0x0 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_INSTANT		(0x1 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_PEAK		(0x2 << KVM_STATS_TYPE_SHIFT)
+#define KVM_STATS_TYPE_MAX		KVM_STATS_TYPE_PEAK
+
+#define KVM_STATS_UNIT_SHIFT		4
+#define KVM_STATS_UNIT_MASK		(0xF << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_NONE		(0x0 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_BYTES		(0x1 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_SECONDS		(0x2 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_CYCLES		(0x3 << KVM_STATS_UNIT_SHIFT)
+#define KVM_STATS_UNIT_MAX		KVM_STATS_UNIT_CYCLES
+
+#define KVM_STATS_BASE_SHIFT		8
+#define KVM_STATS_BASE_MASK		(0xF << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW10		(0x0 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_POW2		(0x1 << KVM_STATS_BASE_SHIFT)
+#define KVM_STATS_BASE_MAX		KVM_STATS_BASE_POW2
+
+/**
+ * struct kvm_stats_desc - Descriptor of a KVM statistics.
+ * @flags: Annotations of the stats, like type, unit, etc.
+ * @exponent: Used together with @flags to determine the unit.
+ * @size: The number of data items for this stats.
+ *        Every data item is of type __u64.
+ * @offset: The offset of the stats to the start of stat structure in
+ *          struture kvm or kvm_vcpu.
+ * @unused: Unused field for future usage. Always 0 for now.
+ * @name: The name string for the stats. Its size is indicated by the
+ *        &kvm_stats_header->name_size.
+ */
+struct kvm_stats_desc {
+	__u32 flags;
+	__s16 exponent;
+	__u16 size;
+	__u32 offset;
+	__u32 unused;
+	char name[];
+};
+
+#define KVM_GET_STATS_FD  _IO(KVMIO,  0xce)
+
 #endif /* __LINUX_KVM_H */

tools/include/uapi/linux/mount.h

@@ -120,6 +120,7 @@ enum fsconfig_command {
 #define MOUNT_ATTR_STRICTATIME	0x00000020 /* - Always perform atime updates */
 #define MOUNT_ATTR_NODIRATIME	0x00000080 /* Do not update directory access times */
 #define MOUNT_ATTR_IDMAP	0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+#define MOUNT_ATTR_NOSYMFOLLOW	0x00200000 /* Do not follow symlinks */
 
 /*
  * mount_setattr()

tools/lib/bitmap.c

@@ -86,3 +86,17 @@ int __bitmap_equal(const unsigned long *bitmap1,
 
 	return 1;
 }
+
+int __bitmap_intersects(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, unsigned int bits)
+{
+	unsigned int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & bitmap2[k])
+			return 1;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 1;
+	return 0;
+}

tools/perf/Documentation/itrace.txt

@@ -20,6 +20,7 @@
 		L	synthesize last branch entries on existing event records
 		s       skip initial number of events
 		q	quicker (less detailed) decoding
+		Z	prefer to ignore timestamps (so-called "timeless" decoding)
 
 	The default is all events i.e. the same as --itrace=ibxwpe,
 	except for perf script where it is --itrace=ce

tools/perf/Documentation/perf-annotate.txt

@@ -58,6 +58,13 @@ OPTIONS
 --ignore-vmlinux::
 	Ignore vmlinux files.
 
+--itrace::
+	Options for decoding instruction tracing data. The options are:
+
+include::itrace.txt[]
+
+	To disable decoding entirely, use --no-itrace.
+
 -m::
 --modules::
         Load module symbols. WARNING: use only with -k and LIVE kernel.

tools/perf/Documentation/perf-dlfilter.txt

+perf-dlfilter(1)
+================
+
+NAME
+----
+perf-dlfilter - Filter sample events using a dynamically loaded shared
+object file
+
+SYNOPSIS
+--------
+[verse]
+'perf script' [--dlfilter file.so ] [ --dlarg arg ]...
+
+DESCRIPTION
+-----------
+
+This option is used to process data through a custom filter provided by a
+dynamically loaded shared object file. Arguments can be passed using --dlarg
+and retrieved using perf_dlfilter_fns.args().
+
+If 'file.so' does not contain "/", then it will be found either in the current
+directory, or perf tools exec path which is ~/libexec/perf-core/dlfilters for
+a local build and install (refer perf --exec-path), or the dynamic linker
+paths.
+
+API
+---
+
+The API for filtering consists of the following:
+
+[source,c]
+----
+#include <perf/perf_dlfilter.h>
+
+const struct perf_dlfilter_fns perf_dlfilter_fns;
+
+int start(void **data, void *ctx);
+int stop(void *data, void *ctx);
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
+int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
+const char *filter_description(const char **long_description);
+----
+
+If implemented, 'start' will be called at the beginning, before any
+calls to 'filter_event' or 'filter_event_early'. Return 0 to indicate success,
+or return a negative error code. '*data' can be assigned for use by other
+functions. 'ctx' is needed for calls to perf_dlfilter_fns, but most
+perf_dlfilter_fns are not valid when called from 'start'.
+
+If implemented, 'stop' will be called at the end, after any calls to
+'filter_event' or 'filter_event_early'. Return 0 to indicate success, or
+return a negative error code. 'data' is set by 'start'. 'ctx' is needed
+for calls to perf_dlfilter_fns, but most perf_dlfilter_fns are not valid
+when called from 'stop'.
+
+If implemented, 'filter_event' will be called for each sample event.
+Return 0 to keep the sample event, 1 to filter it out, or return a negative
+error code. 'data' is set by 'start'. 'ctx' is needed for calls to
+'perf_dlfilter_fns'.
+
+'filter_event_early' is the same as 'filter_event' except it is called before
+internal filtering.
+
+If implemented, 'filter_description' should return a one-line description
+of the filter, and optionally a longer description.
+
+The perf_dlfilter_sample structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+'filter_event' and 'filter_event_early' are passed a perf_dlfilter_sample
+structure, which contains the following fields:
+[source,c]
+----
+/*
+ * perf sample event information (as per perf script and <linux/perf_event.h>)
+ */
+struct perf_dlfilter_sample {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u16 ins_lat;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u16 p_stage_cyc;	/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 ip;
+	__s32 pid;
+	__s32 tid;
+	__u64 time;
+	__u64 addr;
+	__u64 id;
+	__u64 stream_id;
+	__u64 period;
+	__u64 weight;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 transaction;	/* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */
+	__u64 insn_cnt;	/* For instructions-per-cycle (IPC) */
+	__u64 cyc_cnt;		/* For instructions-per-cycle (IPC) */
+	__s32 cpu;
+	__u32 flags;		/* Refer PERF_DLFILTER_FLAG_* above */
+	__u64 data_src;		/* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */
+	__u64 phys_addr;	/* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */
+	__u64 data_page_size;	/* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 code_page_size;	/* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 cgroup;		/* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */
+	__u8  cpumode;		/* Refer CPUMODE_MASK etc in <linux/perf_event.h> */
+	__u8  addr_correlates_sym; /* True => resolve_addr() can be called */
+	__u16 misc;		/* Refer perf_event_header in <linux/perf_event.h> */
+	__u32 raw_size;		/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	const void *raw_data;	/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	__u64 brstack_nr;	/* Number of brstack entries */
+	const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */
+	__u64 raw_callchain_nr;	/* Number of raw_callchain entries */
+	const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */
+	const char *event;
+};
+----
+
+The perf_dlfilter_fns structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'perf_dlfilter_fns' structure is populated with function pointers when the
+file is loaded. The functions can be called by 'filter_event' or
+'filter_event_early'.
+
+[source,c]
+----
+struct perf_dlfilter_fns {
+	const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);
+	const struct perf_dlfilter_al *(*resolve_addr)(void *ctx);
+	char **(*args)(void *ctx, int *dlargc);
+	__s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al);
+	const __u8 *(*insn)(void *ctx, __u32 *length);
+	const char *(*srcline)(void *ctx, __u32 *line_number);
+	struct perf_event_attr *(*attr)(void *ctx);
+	__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
+	void *(*reserved[120])(void *);
+};
+----
+
+'resolve_ip' returns information about ip.
+
+'resolve_addr' returns information about addr (if addr_correlates_sym).
+
+'args' returns arguments from --dlarg options.
+
+'resolve_address' provides information about 'address'. al->size must be set
+before calling. Returns 0 on success, -1 otherwise.
+
+'insn' returns instruction bytes and length.
+
+'srcline' return source file name and line number.
+
+'attr' returns perf_event_attr, refer <linux/perf_event.h>.
+
+'object_code' reads object code and returns the number of bytes read.
+
+The perf_dlfilter_al structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'perf_dlfilter_al' structure contains information about an address.
+
+[source,c]
+----
+/*
+ * Address location (as per perf script)
+ */
+struct perf_dlfilter_al {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u32 symoff;
+	const char *sym;
+	__u64 addr; /* Mapped address (from dso) */
+	__u64 sym_start;
+	__u64 sym_end;
+	const char *dso;
+	__u8  sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */
+	__u8  is_64_bit; /* Only valid if dso is not NULL */
+	__u8  is_kernel_ip; /* True if in kernel space */
+	__u32 buildid_size;
+	__u8 *buildid;
+	/* Below members are only populated by resolve_ip() */
+	__u8 filtered; /* true if this sample event will be filtered out */
+	const char *comm;
+};
+----
+
+perf_dlfilter_sample flags
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'flags' member of 'perf_dlfilter_sample' corresponds with the flags field
+of perf script. The bits of the flags are as follows:
+
+[source,c]
+----
+/* Definitions for perf_dlfilter_sample flags */
+enum {
+	PERF_DLFILTER_FLAG_BRANCH	= 1ULL << 0,
+	PERF_DLFILTER_FLAG_CALL		= 1ULL << 1,
+	PERF_DLFILTER_FLAG_RETURN	= 1ULL << 2,
+	PERF_DLFILTER_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_DLFILTER_FLAG_SYSCALLRET	= 1ULL << 4,
+	PERF_DLFILTER_FLAG_ASYNC	= 1ULL << 5,
+	PERF_DLFILTER_FLAG_INTERRUPT	= 1ULL << 6,
+	PERF_DLFILTER_FLAG_TX_ABORT	= 1ULL << 7,
+	PERF_DLFILTER_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_DLFILTER_FLAG_TRACE_END	= 1ULL << 9,
+	PERF_DLFILTER_FLAG_IN_TX	= 1ULL << 10,
+	PERF_DLFILTER_FLAG_VMENTRY	= 1ULL << 11,
+	PERF_DLFILTER_FLAG_VMEXIT	= 1ULL << 12,
+};
+----
+
+EXAMPLE
+-------
+
+Filter out everything except branches from "foo" to "bar":
+
+[source,c]
+----
+#include <perf/perf_dlfilter.h>
+#include <string.h>
+
+const struct perf_dlfilter_fns perf_dlfilter_fns;
+
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
+{
+	const struct perf_dlfilter_al *al;
+	const struct perf_dlfilter_al *addr_al;
+
+	if (!sample->ip || !sample->addr_correlates_sym)
+		return 1;
+
+	al = perf_dlfilter_fns.resolve_ip(ctx);
+	if (!al || !al->sym || strcmp(al->sym, "foo"))
+		return 1;
+
+	addr_al = perf_dlfilter_fns.resolve_addr(ctx);
+	if (!addr_al || !addr_al->sym || strcmp(addr_al->sym, "bar"))
+		return 1;
+
+	return 0;
+}
+----
+
+To build the shared object, assuming perf has been installed for the local user
+i.e. perf_dlfilter.h is in ~/include/perf :
+
+	gcc -c -I ~/include -fpic dlfilter-example.c
+	gcc -shared -o dlfilter-example.so dlfilter-example.o
+
+To use the filter with perf script:
+
+	perf script --dlfilter dlfilter-example.so
+
+SEE ALSO
+--------
+linkperf:perf-script[1]

tools/perf/Documentation/perf-inject.txt

@@ -68,6 +68,16 @@ include::itrace.txt[]
 --force::
 	Don't complain, do it.
 
+--vm-time-correlation[=OPTIONS]::
+	Some architectures may capture AUX area data which contains timestamps
+	affected by virtualization. This option will update those timestamps
+	in place, to correlate with host timestamps. The in-place update means
+	that an output file is not specified, and instead the input file is
+	modified.  The options are architecture specific, except that they may
+	start with "dry-run" which will cause the file to be processed but
+	without updating it. Currently this option is supported only by
+	Intel PT, refer linkperf:perf-intel-pt[1]
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1],

tools/perf/Documentation/perf-intel-pt.txt

@@ -174,7 +174,11 @@ Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
 and to script exported-sql-viewer.py for an example of using the database.
 
 There is also script intel-pt-events.py which provides an example of how to
-unpack the raw data for power events and PTWRITE.
+unpack the raw data for power events and PTWRITE. The script also displays
+branches, and supports 2 additional modes selected by option:
+
+ --insn-trace - instruction trace
+ --src-trace - source trace
 
 As mentioned above, it is easy to capture too much data.  One way to limit the
 data captured is to use 'snapshot' mode which is explained further below.
@@ -869,6 +873,7 @@ The letters are:
 	L	synthesize last branch entries on existing event records
 	s	skip initial number of events
 	q	quicker (less detailed) decoding
+	Z	prefer to ignore timestamps (so-called "timeless" decoding)
 
 "Instructions" events look like they were recorded by "perf record -e
 instructions".
@@ -1062,6 +1067,10 @@ What *will* be decoded with the qq option:
 
 	- instruction pointer associated with PSB packets
 
+The Z option is equivalent to having recorded a trace without TSC
+(i.e. config term tsc=0). It can be useful to avoid timestamp issues when
+decoding a trace of a virtual machine.
+
 
 dump option
 ~~~~~~~~~~~
@@ -1150,8 +1159,9 @@ include::build-xed.txt[]
 Tracing Virtual Machines
 ------------------------
 
-Currently, only kernel tracing is supported and only with "timeless" decoding
-i.e. no TSC timestamps
+Currently, only kernel tracing is supported and only with either "timeless" decoding
+(i.e. no TSC timestamps) or VM Time Correlation. VM Time Correlation is an extra step
+using 'perf inject' and requires unchanging VMX TSC Offset and no VMX TSC Scaling.
 
 Other limitations and caveats
 
@@ -1162,7 +1172,7 @@ Other limitations and caveats
  Guest VCPU is unknown but may be able to be inferred from the host thread
  Callchains are not supported
 
-Example
+Example using "timeless" decoding
 
 Start VM
 
@@ -1226,6 +1236,107 @@ perf script can be used to provide an instruction trace
            :1440  1440  ffffffffbb74603c clockevents_program_event+0x4c ([guest.kernel.kallsyms])               popq  %rbx
            :1440  1440  ffffffffbb74603d clockevents_program_event+0x4d ([guest.kernel.kallsyms])               popq  %r12
 
+Example using VM Time Correlation
+
+Start VM
+
+ $ sudo virsh start kubuntu20.04
+ Domain kubuntu20.04 started
+
+Mount the guest file system.  Note sshfs needs -o direct_io to enable reading of proc files.  root access is needed to read /proc/kcore.
+
+ $ mkdir -p vm0
+ $ sshfs -o direct_io root@vm0:/ vm0
+
+Copy the guest /proc/kallsyms, /proc/modules and /proc/kcore
+
+ $ perf buildid-cache -v --kcore vm0/proc/kcore
+ same kcore found in /home/user/.debug/[kernel.kcore]/cc9c55a98c5e4ec0aeda69302554aabed5cd6491/2021021312450777
+ $ KALLSYMS=/home/user/.debug/\[kernel.kcore\]/cc9c55a98c5e4ec0aeda69302554aabed5cd6491/2021021312450777/kallsyms
+
+Find the VM process
+
+ $ ps -eLl | grep 'KVM\|PID'
+ F S   UID     PID    PPID     LWP  C PRI  NI ADDR SZ WCHAN  TTY          TIME CMD
+ 3 S 64055   16998       1   17005 13  80   0 - 1818189 -    ?        00:00:16 CPU 0/KVM
+ 3 S 64055   16998       1   17006  4  80   0 - 1818189 -    ?        00:00:05 CPU 1/KVM
+ 3 S 64055   16998       1   17007  3  80   0 - 1818189 -    ?        00:00:04 CPU 2/KVM
+ 3 S 64055   16998       1   17008  4  80   0 - 1818189 -    ?        00:00:05 CPU 3/KVM
+
+Start an open-ended perf record, tracing the VM process, do something on the VM, and then ctrl-C to stop.
+IPC can be determined, hence cyc=1 can be added.
+Only kernel decoding is supported, so 'k' must be specified.
+Intel PT traces both the host and the guest so --guest and --host need to be specified.
+
+ $ sudo perf kvm --guest --host --guestkallsyms $KALLSYMS record --kcore -e intel_pt/cyc=1/k -p 16998
+ ^C[ perf record: Woken up 1 times to write data ]
+ [ perf record: Captured and wrote 9.041 MB perf.data.kvm ]
+
+Now 'perf inject' can be used to determine the VMX TCS Offset. Note, Intel PT TSC packets are
+only 7-bytes, so the TSC Offset might differ from the actual value in the 8th byte. That will
+have no effect i.e. the resulting timestamps will be correct anyway.
+
+ $ perf inject -i perf.data.kvm --vm-time-correlation=dry-run
+ ERROR: Unknown TSC Offset for VMCS 0x1bff6a
+ VMCS: 0x1bff6a  TSC Offset 0xffffe42722c64c41
+ ERROR: Unknown TSC Offset for VMCS 0x1cbc08
+ VMCS: 0x1cbc08  TSC Offset 0xffffe42722c64c41
+ ERROR: Unknown TSC Offset for VMCS 0x1c3ce8
+ VMCS: 0x1c3ce8  TSC Offset 0xffffe42722c64c41
+ ERROR: Unknown TSC Offset for VMCS 0x1cbce9
+ VMCS: 0x1cbce9  TSC Offset 0xffffe42722c64c41
+
+Each virtual CPU has a different Virtual Machine Control Structure (VMCS)
+shown above with the calculated TSC Offset. For an unchanging TSC Offset
+they should all be the same for the same virtual machine.
+
+Now that the TSC Offset is known, it can be provided to 'perf inject'
+
+ $ perf inject -i perf.data.kvm --vm-time-correlation="dry-run 0xffffe42722c64c41"
+
+Note the options for 'perf inject' --vm-time-correlation are:
+
+ [ dry-run ] [ <TSC Offset> [ : <VMCS> [ , <VMCS> ]... ]  ]...
+
+So it is possible to specify different TSC Offsets for different VMCS.
+The option "dry-run" will cause the file to be processed but without updating it.
+Note it is also possible to get a intel_pt.log file by adding option --itrace=d
+
+There were no errors so, do it for real
+
+ $ perf inject -i perf.data.kvm --vm-time-correlation=0xffffe42722c64c41 --force
+
+'perf script' can be used to see if there are any decoder errors
+
+ $ perf script -i perf.data.kvm --guestkallsyms $KALLSYMS --itrace=e-o
+
+There were none.
+
+'perf script' can be used to provide an instruction trace showing timestamps
+
+ $ perf script -i perf.data.kvm --guestkallsyms $KALLSYMS --insn-trace --xed -F+ipc | grep -C10 vmresume | head -21
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133cdd __vmx_vcpu_run+0x3d ([kernel.kallsyms])                 movq  0x48(%rax), %r9
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133ce1 __vmx_vcpu_run+0x41 ([kernel.kallsyms])                 movq  0x50(%rax), %r10
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133ce5 __vmx_vcpu_run+0x45 ([kernel.kallsyms])                 movq  0x58(%rax), %r11
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133ce9 __vmx_vcpu_run+0x49 ([kernel.kallsyms])                 movq  0x60(%rax), %r12
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133ced __vmx_vcpu_run+0x4d ([kernel.kallsyms])                 movq  0x68(%rax), %r13
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133cf1 __vmx_vcpu_run+0x51 ([kernel.kallsyms])                 movq  0x70(%rax), %r14
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133cf5 __vmx_vcpu_run+0x55 ([kernel.kallsyms])                 movq  0x78(%rax), %r15
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133cf9 __vmx_vcpu_run+0x59 ([kernel.kallsyms])                 movq  (%rax), %rax
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133cfc __vmx_vcpu_run+0x5c ([kernel.kallsyms])                 callq  0xffffffff82133c40
+       CPU 1/KVM 17006 [001] 11500.262865593:  ffffffff82133c40 vmx_vmenter+0x0 ([kernel.kallsyms])             jz 0xffffffff82133c46
+       CPU 1/KVM 17006 [001] 11500.262866075:  ffffffff82133c42 vmx_vmenter+0x2 ([kernel.kallsyms])             vmresume         IPC: 0.05 (40/769)
+          :17006 17006 [001] 11500.262869216:  ffffffff82200cb0 asm_sysvec_apic_timer_interrupt+0x0 ([guest.kernel.kallsyms])           clac
+          :17006 17006 [001] 11500.262869216:  ffffffff82200cb3 asm_sysvec_apic_timer_interrupt+0x3 ([guest.kernel.kallsyms])           pushq  $0xffffffffffffffff
+          :17006 17006 [001] 11500.262869216:  ffffffff82200cb5 asm_sysvec_apic_timer_interrupt+0x5 ([guest.kernel.kallsyms])           callq  0xffffffff82201160
+          :17006 17006 [001] 11500.262869216:  ffffffff82201160 error_entry+0x0 ([guest.kernel.kallsyms])               cld
+          :17006 17006 [001] 11500.262869216:  ffffffff82201161 error_entry+0x1 ([guest.kernel.kallsyms])               pushq  %rsi
+          :17006 17006 [001] 11500.262869216:  ffffffff82201162 error_entry+0x2 ([guest.kernel.kallsyms])               movq  0x8(%rsp), %rsi
+          :17006 17006 [001] 11500.262869216:  ffffffff82201167 error_entry+0x7 ([guest.kernel.kallsyms])               movq  %rdi, 0x8(%rsp)
+          :17006 17006 [001] 11500.262869216:  ffffffff8220116c error_entry+0xc ([guest.kernel.kallsyms])               pushq  %rdx
+          :17006 17006 [001] 11500.262869216:  ffffffff8220116d error_entry+0xd ([guest.kernel.kallsyms])               pushq  %rcx
+          :17006 17006 [001] 11500.262869216:  ffffffff8220116e error_entry+0xe ([guest.kernel.kallsyms])               pushq  %rax
+
 
 
 SEE ALSO

tools/perf/Documentation/perf-probe.txt

@@ -226,7 +226,7 @@ So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And
 
 LAZY MATCHING
 -------------
- The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).
+The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).
 
 e.g.
  'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.
@@ -235,8 +235,8 @@ This provides some sort of flexibility and robustness to probe point definitions
 
 FILTER PATTERN
 --------------
- The filter pattern is a glob matching pattern(s) to filter variables.
- In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
+The filter pattern is a glob matching pattern(s) to filter variables.
+In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
 
 e.g.
  With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
@@ -295,6 +295,19 @@ Add a probe in a source file using special characters by backslash escape
  ./perf probe -x /opt/test/a.out 'foo\+bar.c:4'
 
 
+PERMISSIONS AND SYSCTL
+----------------------
+Since perf probe depends on ftrace (tracefs) and kallsyms (/proc/kallsyms), you have to care about the permission and some sysctl knobs.
+
+ - Since tracefs and kallsyms requires root or privileged user to access it, the following perf probe commands also require it; --add, --del, --list (except for --cache option)
+
+ - The system admin can remount the tracefs with 755 (`sudo mount -o remount,mode=755 /sys/kernel/tracing/`) to allow unprivileged user to run the perf probe --list command.
+
+ - /proc/sys/kernel/kptr_restrict = 2 (restrict all users) also prevents perf probe to retrieve the important information from kallsyms. You also need to set to 1 (restrict non CAP_SYSLOG users) for the above commands. Since the user-space probe doesn't need to access kallsyms, this is only for probing the kernel function (kprobes).
+
+ - Since the perf probe commands read the vmlinux (for kernel) and/or the debuginfo file (including user-space application), you need to ensure that you can read those files.
+
+
 SEE ALSO
 --------
 linkperf:perf-trace[1], linkperf:perf-record[1], linkperf:perf-buildid-cache[1]

tools/perf/Documentation/perf-script-python.txt

@@ -550,6 +550,27 @@ def trace_unhandled(event_name, context, event_fields_dict):
     pass
 ----
 
+*process_event*, if defined, is called for any non-tracepoint event
+
+----
+def process_event(param_dict):
+    pass
+----
+
+*context_switch*, if defined, is called for any context switch
+
+----
+def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_preempt, *x):
+    pass
+----
+
+*auxtrace_error*, if defined, is called for any AUX area tracing error
+
+----
+def auxtrace_error(typ, code, cpu, pid, tid, ip, ts, msg, cpumode, *x):
+    pass
+----
+
 The remaining sections provide descriptions of each of the available
 built-in perf script Python modules and their associated functions.
 
@@ -592,12 +613,18 @@ common, but need to be made accessible to user scripts nonetheless.
 perf_trace_context defines a set of functions that can be used to
 access this data in the context of the current event.  Each of these
 functions expects a context variable, which is the same as the
-context variable passed into every event handler as the second
-argument.
+context variable passed into every tracepoint event handler as the second
+argument. For non-tracepoint events, the context variable is also present
+as perf_trace_context.perf_script_context .
 
  common_pc(context) - returns common_preempt count for the current event
  common_flags(context) - returns common_flags for the current event
  common_lock_depth(context) - returns common_lock_depth for the current event
+ perf_sample_insn(context) - returns the machine code instruction
+ perf_set_itrace_options(context, itrace_options) - set --itrace options if they have not been set already
+ perf_sample_srcline(context) - returns source_file_name, line_number
+ perf_sample_srccode(context) - returns source_file_name, line_number, source_line
+
 
 Util.py Module
 ~~~~~~~~~~~~~~
@@ -616,9 +643,20 @@ SUPPORTED FIELDS
 Currently supported fields:
 
 ev_name, comm, pid, tid, cpu, ip, time, period, phys_addr, addr,
-symbol, dso, time_enabled, time_running, values, callchain,
+symbol, symoff, dso, time_enabled, time_running, values, callchain,
 brstack, brstacksym, datasrc, datasrc_decode, iregs, uregs,
-weight, transaction, raw_buf, attr.
+weight, transaction, raw_buf, attr, cpumode.
+
+Fields that may also be present:
+
+ flags - sample flags
+ flags_disp - sample flags display
+ insn_cnt - instruction count for determining instructions-per-cycle (IPC)
+ cyc_cnt - cycle count for determining IPC
+ addr_correlates_sym - addr can correlate to a symbol
+ addr_dso - addr dso
+ addr_symbol - addr symbol
+ addr_symoff - addr symbol offset
 
 Some fields have sub items:
 

tools/perf/Documentation/perf-script.txt

@@ -98,6 +98,18 @@ OPTIONS
         Generate perf-script.[ext] starter script for given language,
         using current perf.data.
 
+--dlfilter=<file>::
+	Filter sample events using the given shared object file.
+	Refer linkperf:perf-dlfilter[1]
+
+--dlarg=<arg>::
+	Pass 'arg' as an argument to the dlfilter. --dlarg may be repeated
+	to add more arguments.
+
+--list-dlfilters=::
+        Display a list of available dlfilters. Use with option -v (must come
+        before option --list-dlfilters) to show long descriptions.
+
 -a::
         Force system-wide collection.  Scripts run without a <command>
         normally use -a by default, while scripts run with a <command>
@@ -483,4 +495,5 @@ include::itrace.txt[]
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
-linkperf:perf-script-python[1], linkperf:perf-intel-pt[1]
+linkperf:perf-script-python[1], linkperf:perf-intel-pt[1],
+linkperf:perf-dlfilter[1]

tools/perf/Documentation/perf-top.txt

@@ -277,6 +277,18 @@ Default is to monitor all CPUS.
 	Record events of type PERF_RECORD_NAMESPACES and display it with the
 	'cgroup_id' sort key.
 
+-G name::
+--cgroup name::
+monitor only in the container (cgroup) called "name". This option is available only
+in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
+container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
+can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
+to first event, second cgroup to second event and so on. It is possible to provide
+an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
+corresponding events, i.e., they always refer to events defined earlier on the command
+line. If the user wants to track multiple events for a specific cgroup, the user can
+use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
+
 --all-cgroups::
 	Record events of type PERF_RECORD_CGROUP and display it with the
 	'cgroup' sort key.

tools/perf/Documentation/perf.data-file-format.txt

@@ -402,6 +402,39 @@ struct {
 	u64 clockid_time_ns;
 };
 
+	HEADER_HYBRID_TOPOLOGY = 30,
+
+Indicate the hybrid CPUs. The format of data is as below.
+
+struct {
+	u32 nr;
+	struct {
+		char pmu_name[];
+		char cpus[];
+	} [nr]; /* Variable length records */
+};
+
+Example:
+  hybrid cpu system:
+  cpu_core cpu list : 0-15
+  cpu_atom cpu list : 16-23
+
+	HEADER_HYBRID_CPU_PMU_CAPS = 31,
+
+	A list of hybrid CPU PMU capabilities.
+
+struct {
+	u32 nr_pmu;
+	struct {
+		u32 nr_cpu_pmu_caps;
+		{
+			char	name[];
+			char	value[];
+		} [nr_cpu_pmu_caps];
+		char pmu_name[];
+	} [nr_pmu];
+};
+
 	other bits are reserved and should ignored for now
 	HEADER_FEAT_BITS	= 256,
 

tools/perf/Makefile.config

@@ -201,6 +201,12 @@ ifeq ($(call get-executable,$(BISON)),)
   dummy := $(error Error: $(BISON) is missing on this system, please install it)
 endif
 
+ifneq ($(OUTPUT),)
+  ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1)
+    BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)=
+  endif
+endif
+
 # Treat warnings as errors unless directed not to
 ifneq ($(WERROR),0)
   CORE_CFLAGS += -Werror
@@ -634,7 +640,7 @@ endif
 ifdef BUILD_BPF_SKEL
   $(call feature_check,clang-bpf-co-re)
   ifeq ($(feature-clang-bpf-co-re), 0)
-    dummy := $(error Error: clang too old. Please install recent clang)
+    dummy := $(error Error: clang too old/not installed. Please install recent clang to build with BUILD_BPF_SKEL)
   endif
   $(call detected,CONFIG_PERF_BPF_SKEL)
   CFLAGS += -DHAVE_BPF_SKEL
@@ -1111,6 +1117,8 @@ prefix ?= $(HOME)
 endif
 bindir_relative = bin
 bindir = $(abspath $(prefix)/$(bindir_relative))
+includedir_relative = include
+includedir = $(abspath $(prefix)/$(includedir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
@@ -1143,6 +1151,7 @@ ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG))
 STRACE_GROUPS_DIR_SQ = $(subst ','\'',$(STRACE_GROUPS_DIR))
 DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
 bindir_SQ = $(subst ','\'',$(bindir))
+includedir_SQ = $(subst ','\'',$(includedir))
 mandir_SQ = $(subst ','\'',$(mandir))
 infodir_SQ = $(subst ','\'',$(infodir))
 perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
@@ -1227,6 +1236,9 @@ $(call detected_var,LIBDIR)
 $(call detected_var,GTK_CFLAGS)
 $(call detected_var,PERL_EMBED_CCOPTS)
 $(call detected_var,PYTHON_EMBED_CCOPTS)
+ifneq ($(BISON_FILE_PREFIX_MAP),)
+$(call detected_var,BISON_FILE_PREFIX_MAP)
+endif
 
 # re-generate FEATURE-DUMP as we may have called feature_check, found out
 # extra libraries to add to LDFLAGS of some other test and then redo those

tools/perf/Makefile.perf

@@ -923,7 +923,9 @@ install-tools: all install-gtk
 	$(call QUIET_INSTALL, binaries) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
-		$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
+		$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(dir_SQ)/trace'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(includedir_SQ)/perf'; \
+		$(INSTALL) util/perf_dlfilter.h -t '$(DESTDIR_SQ)$(includedir_SQ)/perf'
 ifndef NO_PERF_READ_VDSO32
 	$(call QUIET_INSTALL, perf-read-vdso32) \
 		$(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';

tools/perf/arch/arm/include/arch-tests.h

@@ -2,11 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-#endif
-
 extern struct test arch_tests[];
 
 #endif

tools/perf/arch/arm/util/cs-etm.c

@@ -38,8 +38,6 @@ struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
 	struct evlist		*evlist;
-	int			wrapped_cnt;
-	bool			*wrapped;
 	bool			snapshot_mode;
 	size_t			snapshot_size;
 };
@@ -734,135 +732,6 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
-static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
-{
-	bool *wrapped;
-	int cnt = ptr->wrapped_cnt;
-
-	/* Make @ptr->wrapped as big as @idx */
-	while (cnt <= idx)
-		cnt++;
-
-	/*
-	 * Free'ed in cs_etm_recording_free().  Using realloc() to avoid
-	 * cross compilation problems where the host's system supports
-	 * reallocarray() but not the target.
-	 */
-	wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
-	if (!wrapped)
-		return -ENOMEM;
-
-	wrapped[cnt - 1] = false;
-	ptr->wrapped_cnt = cnt;
-	ptr->wrapped = wrapped;
-
-	return 0;
-}
-
-static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
-				      size_t buffer_size, u64 head)
-{
-	u64 i, watermark;
-	u64 *buf = (u64 *)buffer;
-	size_t buf_size = buffer_size;
-
-	/*
-	 * We want to look the very last 512 byte (chosen arbitrarily) in
-	 * the ring buffer.
-	 */
-	watermark = buf_size - 512;
-
-	/*
-	 * @head is continuously increasing - if its value is equal or greater
-	 * than the size of the ring buffer, it has wrapped around.
-	 */
-	if (head >= buffer_size)
-		return true;
-
-	/*
-	 * The value of @head is somewhere within the size of the ring buffer.
-	 * This can be that there hasn't been enough data to fill the ring
-	 * buffer yet or the trace time was so long that @head has numerically
-	 * wrapped around.  To find we need to check if we have data at the very
-	 * end of the ring buffer.  We can reliably do this because mmap'ed
-	 * pages are zeroed out and there is a fresh mapping with every new
-	 * session.
-	 */
-
-	/* @head is less than 512 byte from the end of the ring buffer */
-	if (head > watermark)
-		watermark = head;
-
-	/*
-	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
-	 */
-	watermark >>= 3;
-	buf_size >>= 3;
-
-	/*
-	 * If we find trace data at the end of the ring buffer, @head has
-	 * been there and has numerically wrapped around at least once.
-	 */
-	for (i = watermark; i < buf_size; i++)
-		if (buf[i])
-			return true;
-
-	return false;
-}
-
-static int cs_etm_find_snapshot(struct auxtrace_record *itr,
-				int idx, struct auxtrace_mmap *mm,
-				unsigned char *data,
-				u64 *head, u64 *old)
-{
-	int err;
-	bool wrapped;
-	struct cs_etm_recording *ptr =
-			container_of(itr, struct cs_etm_recording, itr);
-
-	/*
-	 * Allocate memory to keep track of wrapping if this is the first
-	 * time we deal with this *mm.
-	 */
-	if (idx >= ptr->wrapped_cnt) {
-		err = cs_etm_alloc_wrapped_array(ptr, idx);
-		if (err)
-			return err;
-	}
-
-	/*
-	 * Check to see if *head has wrapped around.  If it hasn't only the
-	 * amount of data between *head and *old is snapshot'ed to avoid
-	 * bloating the perf.data file with zeros.  But as soon as *head has
-	 * wrapped around the entire size of the AUX ring buffer it taken.
-	 */
-	wrapped = ptr->wrapped[idx];
-	if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
-		wrapped = true;
-		ptr->wrapped[idx] = true;
-	}
-
-	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
-		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
-
-	/* No wrap has occurred, we can just use *head and *old. */
-	if (!wrapped)
-		return 0;
-
-	/*
-	 * *head has wrapped around - adjust *head and *old to pickup the
-	 * entire content of the AUX buffer.
-	 */
-	if (*head >= mm->len) {
-		*old = *head - mm->len;
-	} else {
-		*head += mm->len;
-		*old = *head - mm->len;
-	}
-
-	return 0;
-}
-
 static int cs_etm_snapshot_start(struct auxtrace_record *itr)
 {
 	struct cs_etm_recording *ptr =
@@ -900,7 +769,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 
-	zfree(&ptr->wrapped);
 	free(ptr);
 }
 
@@ -928,7 +796,6 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	ptr->itr.recording_options	= cs_etm_recording_options;
 	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
 	ptr->itr.info_fill		= cs_etm_info_fill;
-	ptr->itr.find_snapshot		= cs_etm_find_snapshot;
 	ptr->itr.snapshot_start		= cs_etm_snapshot_start;
 	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
 	ptr->itr.reference		= cs_etm_reference;

tools/perf/arch/arm64/include/arch-tests.h

@@ -2,11 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-#endif
-
 extern struct test arch_tests[];
 
 #endif

tools/perf/arch/arm64/util/arm-spe.c

@@ -14,6 +14,7 @@
 #include "../../../util/cpumap.h"
 #include "../../../util/event.h"
 #include "../../../util/evsel.h"
+#include "../../../util/evsel_config.h"
 #include "../../../util/evlist.h"
 #include "../../../util/session.h"
 #include <internal/lib.h> // page_size
@@ -32,6 +33,29 @@ struct arm_spe_recording {
 	struct evlist		*evlist;
 };
 
+static void arm_spe_set_timestamp(struct auxtrace_record *itr,
+				  struct evsel *evsel)
+{
+	struct arm_spe_recording *ptr;
+	struct perf_pmu *arm_spe_pmu;
+	struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG);
+	u64 user_bits = 0, bit;
+
+	ptr = container_of(itr, struct arm_spe_recording, itr);
+	arm_spe_pmu = ptr->arm_spe_pmu;
+
+	if (term)
+		user_bits = term->val.cfg_chg;
+
+	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "ts_enable");
+
+	/* Skip if user has set it */
+	if (bit & user_bits)
+		return;
+
+	evsel->core.attr.config |= bit;
+}
+
 static size_t
 arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		       struct evlist *evlist __maybe_unused)
@@ -68,6 +92,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 	struct evsel *evsel, *arm_spe_evsel = NULL;
+	struct perf_cpu_map *cpus = evlist->core.cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
@@ -91,7 +116,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		return 0;
 
 	/* We are in full trace mode but '-m,xyz' wasn't specified */
-	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+	if (!opts->auxtrace_mmap_pages) {
 		if (privileged) {
 			opts->auxtrace_mmap_pages = MiB(4) / page_size;
 		} else {
@@ -120,9 +145,14 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 */
 	evlist__to_front(evlist, arm_spe_evsel);
 
-	evsel__set_sample_bit(arm_spe_evsel, CPU);
-	evsel__set_sample_bit(arm_spe_evsel, TIME);
-	evsel__set_sample_bit(arm_spe_evsel, TID);
+	/*
+	 * In the case of per-cpu mmaps, sample CPU for AUX event;
+	 * also enable the timestamp tracing for samples correlation.
+	 */
+	if (!perf_cpu_map__empty(cpus)) {
+		evsel__set_sample_bit(arm_spe_evsel, CPU);
+		arm_spe_set_timestamp(itr, arm_spe_evsel);
+	}
 
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
@@ -134,9 +164,10 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
-	evsel__set_sample_bit(tracking_evsel, TIME);
-	evsel__set_sample_bit(tracking_evsel, CPU);
-	evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+
+	/* In per-cpu case, always need the time of mmap events etc */
+	if (!perf_cpu_map__empty(cpus))
+		evsel__set_sample_bit(tracking_evsel, TIME);
 
 	return 0;
 }

tools/perf/arch/arm64/util/mem-events.c

@@ -20,7 +20,7 @@ struct perf_mem_event *perf_mem_events__ptr(int i)
 	return &perf_mem_events[i];
 }
 
-char *perf_mem_events__name(int i)
+char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 

tools/perf/arch/powerpc/include/arch-tests.h

@@ -2,13 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-int test__arch_unwind_sample(struct perf_sample *sample,
-			     struct thread *thread);
-#endif
-
 extern struct test arch_tests[];
 
 #endif

tools/perf/arch/powerpc/tests/dwarf-unwind.c

@@ -7,7 +7,6 @@
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
-#include "arch-tests.h"
 
 #define STACK_SIZE 8192
 

tools/perf/arch/powerpc/util/mem-events.c

@@ -3,7 +3,7 @@
 #include "mem-events.h"
 
 /* PowerPC does not support 'ldlat' parameter. */
-char *perf_mem_events__name(int i)
+char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
 {
 	if (i == PERF_MEM_EVENTS__LOAD)
 		return (char *) "cpu/mem-loads/";

tools/perf/arch/x86/include/arch-tests.h

@@ -2,23 +2,15 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#include <linux/compiler.h>
 struct test;
 
 /* Tests */
-int test__rdpmc(struct test *test __maybe_unused, int subtest);
-int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__rdpmc(struct test *test, int subtest);
+int test__insn_x86(struct test *test, int subtest);
 int test__intel_pt_pkt_decoder(struct test *test, int subtest);
 int test__bp_modify(struct test *test, int subtest);
 int test__x86_sample_parsing(struct test *test, int subtest);
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-int test__arch_unwind_sample(struct perf_sample *sample,
-			     struct thread *thread);
-#endif
-
 extern struct test arch_tests[];
 
 #endif

tools/perf/arch/x86/tests/dwarf-unwind.c

@@ -7,7 +7,6 @@
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
-#include "arch-tests.h"
 
 #define STACK_SIZE 8192
 

tools/perf/arch/x86/util/kvm-stat.c

@@ -133,11 +133,56 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
+ /* The time of emulation msr is from kvm_msr to kvm_entry. */
+static void msr_event_get_key(struct evsel *evsel,
+				 struct perf_sample *sample,
+				 struct event_key *key)
+{
+	key->key  = evsel__intval(evsel, sample, "ecx");
+	key->info = evsel__intval(evsel, sample, "write");
+}
+
+static bool msr_event_begin(struct evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	if (!strcmp(evsel->name, "kvm:kvm_msr")) {
+		msr_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool msr_event_end(struct evsel *evsel,
+			     struct perf_sample *sample __maybe_unused,
+			     struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static void msr_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				    struct event_key *key,
+				    char *decode)
+{
+	scnprintf(decode, decode_str_len, "%#llx:%s",
+		  (unsigned long long)key->key,
+		  key->info ? "W" : "R");
+}
+
+static struct kvm_events_ops msr_events = {
+	.is_begin_event = msr_event_begin,
+	.is_end_event = msr_event_end,
+	.decode_key = msr_event_decode_key,
+	.name = "MSR Access"
+};
+
 const char *kvm_events_tp[] = {
 	"kvm:kvm_entry",
 	"kvm:kvm_exit",
 	"kvm:kvm_mmio",
 	"kvm:kvm_pio",
+	"kvm:kvm_msr",
 	NULL,
 };
 
@@ -145,6 +190,7 @@ struct kvm_reg_events_ops kvm_reg_events_ops[] = {
 	{ .name = "vmexit", .ops = &exit_events },
 	{ .name = "mmio", .ops = &mmio_events },
 	{ .name = "ioport", .ops = &ioport_events },
+	{ .name = "msr", .ops = &msr_events },
 	{ NULL, NULL },
 };
 

tools/perf/arch/x86/util/mem-events.c

@@ -5,19 +5,41 @@
 
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
+static char mem_stores_name[100];
 
 #define MEM_LOADS_AUX		0x8203
-#define MEM_LOADS_AUX_NAME	"{cpu/mem-loads-aux/,cpu/mem-loads,ldlat=%u/pp}:S"
+#define MEM_LOADS_AUX_NAME     "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads"),
+	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores"),
+	E(NULL,			NULL,				NULL),
+};
+
+struct perf_mem_event *perf_mem_events__ptr(int i)
+{
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	return &perf_mem_events[i];
+}
 
 bool is_mem_loads_aux_event(struct evsel *leader)
 {
-	if (!pmu_have_event("cpu", "mem-loads-aux"))
-		return false;
+	if (perf_pmu__find("cpu")) {
+		if (!pmu_have_event("cpu", "mem-loads-aux"))
+			return false;
+	} else if (perf_pmu__find("cpu_core")) {
+		if (!pmu_have_event("cpu_core", "mem-loads-aux"))
+			return false;
+	}
 
 	return leader->core.attr.config == MEM_LOADS_AUX;
 }
 
-char *perf_mem_events__name(int i)
+char *perf_mem_events__name(int i, char *pmu_name)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 
@@ -25,20 +47,34 @@ char *perf_mem_events__name(int i)
 		return NULL;
 
 	if (i == PERF_MEM_EVENTS__LOAD) {
-		if (mem_loads_name__init)
+		if (mem_loads_name__init && !pmu_name)
 			return mem_loads_name;
 
-		mem_loads_name__init = true;
+		if (!pmu_name) {
+			mem_loads_name__init = true;
+			pmu_name = (char *)"cpu";
+		}
 
-		if (pmu_have_event("cpu", "mem-loads-aux")) {
+		if (pmu_have_event(pmu_name, "mem-loads-aux")) {
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  MEM_LOADS_AUX_NAME, perf_mem_events__loads_ldlat);
+				  MEM_LOADS_AUX_NAME, pmu_name, pmu_name,
+				  perf_mem_events__loads_ldlat);
 		} else {
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  e->name, perf_mem_events__loads_ldlat);
+				  e->name, pmu_name,
+				  perf_mem_events__loads_ldlat);
 		}
 		return mem_loads_name;
 	}
 
+	if (i == PERF_MEM_EVENTS__STORE) {
+		if (!pmu_name)
+			pmu_name = (char *)"cpu";
+
+		scnprintf(mem_stores_name, sizeof(mem_stores_name),
+			  e->name, pmu_name);
+		return mem_stores_name;
+	}
+
 	return (char *)e->name;
 }

tools/perf/builtin-annotate.c

@@ -474,6 +474,9 @@ int cmd_annotate(int argc, const char **argv)
 			.attr	= perf_event__process_attr,
 			.build_id = perf_event__process_build_id,
 			.tracing_data   = perf_event__process_tracing_data,
+			.id_index	= perf_event__process_id_index,
+			.auxtrace_info	= perf_event__process_auxtrace_info,
+			.auxtrace	= perf_event__process_auxtrace,
 			.feature	= process_feature_event,
 			.ordered_events = true,
 			.ordering_requires_timestamps = true,
@@ -483,6 +486,9 @@ int cmd_annotate(int argc, const char **argv)
 	struct perf_data data = {
 		.mode  = PERF_DATA_MODE_READ,
 	};
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = 0,
+	};
 	struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -547,6 +553,9 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period",
 		     "Set percent type local/global-period/hits",
 		     annotate_parse_percent_type),
+	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options\n" ITRACE_HELP,
+			    itrace_parse_synth_opts),
 
 	OPT_END()
 	};
@@ -591,6 +600,8 @@ int cmd_annotate(int argc, const char **argv)
 	if (IS_ERR(annotate.session))
 		return PTR_ERR(annotate.session);
 
+	annotate.session->itrace_synth_opts = &itrace_synth_opts;
+
 	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
 						      HEADER_BRANCH_STACK);
 

tools/perf/builtin-c2c.c

@@ -42,6 +42,8 @@
 #include "ui/ui.h"
 #include "ui/progress.h"
 #include "../perf.h"
+#include "pmu.h"
+#include "pmu-hybrid.h"
 
 struct c2c_hists {
 	struct hists		hists;
@@ -2907,8 +2909,9 @@ static const char * const *record_mem_usage = __usage_record;
 
 static int perf_c2c__record(int argc, const char **argv)
 {
-	int rec_argc, i = 0, j;
+	int rec_argc, i = 0, j, rec_tmp_nr = 0;
 	const char **rec_argv;
+	char **rec_tmp;
 	int ret;
 	bool all_user = false, all_kernel = false;
 	bool event_set = false;
@@ -2932,11 +2935,21 @@ static int perf_c2c__record(int argc, const char **argv)
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
-	rec_argc = argc + 11; /* max number of arguments */
+	if (!perf_pmu__has_hybrid())
+		rec_argc = argc + 11; /* max number of arguments */
+	else
+		rec_argc = argc + 11 * perf_pmu__hybrid_pmu_num();
+
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
 
+	rec_tmp = calloc(rec_argc + 1, sizeof(char *));
+	if (!rec_tmp) {
+		free(rec_argv);
+		return -1;
+	}
+
 	rec_argv[i++] = "record";
 
 	if (!event_set) {
@@ -2964,21 +2977,9 @@ static int perf_c2c__record(int argc, const char **argv)
 	rec_argv[i++] = "--phys-data";
 	rec_argv[i++] = "--sample-cpu";
 
-	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		e = perf_mem_events__ptr(j);
-		if (!e->record)
-			continue;
-
-		if (!e->supported) {
-			pr_err("failed: event '%s' not supported\n",
-			       perf_mem_events__name(j));
-			free(rec_argv);
-			return -1;
-		}
-
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = perf_mem_events__name(j);
-	}
+	ret = perf_mem_events__record_args(rec_argv, &i, rec_tmp, &rec_tmp_nr);
+	if (ret)
+		goto out;
 
 	if (all_user)
 		rec_argv[i++] = "--all-user";
@@ -3002,6 +3003,11 @@ static int perf_c2c__record(int argc, const char **argv)
 	}
 
 	ret = cmd_record(i, rec_argv);
+out:
+	for (i = 0; i < rec_tmp_nr; i++)
+		free(rec_tmp[i]);
+
+	free(rec_tmp);
 	free(rec_argv);
 	return ret;
 }

tools/perf/builtin-inject.c

@@ -31,6 +31,7 @@
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 
 #include <linux/list.h>
+#include <linux/string.h>
 #include <errno.h>
 #include <signal.h>
 
@@ -43,6 +44,8 @@ struct perf_inject {
 	bool			have_auxtrace;
 	bool			strip;
 	bool			jit_mode;
+	bool			in_place_update;
+	bool			in_place_update_dry_run;
 	const char		*input_name;
 	struct perf_data	output;
 	u64			bytes_written;
@@ -380,8 +383,8 @@ static int perf_event__repipe_buildid_mmap(struct perf_tool *tool,
 	if (dso && !dso->hit) {
 		dso->hit = 1;
 		dso__inject_build_id(dso, tool, machine, sample->cpumode, 0);
-		dso__put(dso);
 	}
+	dso__put(dso);
 
 	return perf_event__repipe(tool, event, sample, machine);
 }
@@ -396,6 +399,18 @@ static int perf_event__repipe_mmap2(struct perf_tool *tool,
 	err = perf_event__process_mmap2(tool, event, sample, machine);
 	perf_event__repipe(tool, event, sample, machine);
 
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) {
+		struct dso *dso;
+
+		dso = findnew_dso(event->mmap2.pid, event->mmap2.tid,
+				  event->mmap2.filename, NULL, machine);
+		if (dso) {
+			/* mark it not to inject build-id */
+			dso->hit = 1;
+		}
+		dso__put(dso);
+	}
+
 	return err;
 }
 
@@ -437,6 +452,18 @@ static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool,
 	};
 	struct dso *dso;
 
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) {
+		/* cannot use dso_id since it'd have invalid info */
+		dso = findnew_dso(event->mmap2.pid, event->mmap2.tid,
+				  event->mmap2.filename, NULL, machine);
+		if (dso) {
+			/* mark it not to inject build-id */
+			dso->hit = 1;
+		}
+		dso__put(dso);
+		return 0;
+	}
+
 	dso = findnew_dso(event->mmap2.pid, event->mmap2.tid,
 			  event->mmap2.filename, &dso_id, machine);
 
@@ -444,8 +471,8 @@ static int perf_event__repipe_buildid_mmap2(struct perf_tool *tool,
 		dso->hit = 1;
 		dso__inject_build_id(dso, tool, machine, sample->cpumode,
 				     event->mmap2.flags);
-		dso__put(dso);
 	}
+	dso__put(dso);
 
 	perf_event__repipe(tool, event, sample, machine);
 
@@ -696,12 +723,42 @@ static void strip_init(struct perf_inject *inject)
 		evsel->handler = drop_sample;
 }
 
+static int parse_vm_time_correlation(const struct option *opt, const char *str, int unset)
+{
+	struct perf_inject *inject = opt->value;
+	const char *args;
+	char *dry_run;
+
+	if (unset)
+		return 0;
+
+	inject->itrace_synth_opts.set = true;
+	inject->itrace_synth_opts.vm_time_correlation = true;
+	inject->in_place_update = true;
+
+	if (!str)
+		return 0;
+
+	dry_run = skip_spaces(str);
+	if (!strncmp(dry_run, "dry-run", strlen("dry-run"))) {
+		inject->itrace_synth_opts.vm_tm_corr_dry_run = true;
+		inject->in_place_update_dry_run = true;
+		args = dry_run + strlen("dry-run");
+	} else {
+		args = str;
+	}
+
+	inject->itrace_synth_opts.vm_tm_corr_args = strdup(args);
+
+	return inject->itrace_synth_opts.vm_tm_corr_args ? 0 : -ENOMEM;
+}
+
 static int __cmd_inject(struct perf_inject *inject)
 {
 	int ret = -EINVAL;
 	struct perf_session *session = inject->session;
 	struct perf_data *data_out = &inject->output;
-	int fd = perf_data__fd(data_out);
+	int fd = inject->in_place_update ? -1 : perf_data__fd(data_out);
 	u64 output_data_offset;
 
 	signal(SIGINT, sig_handler);
@@ -737,6 +794,15 @@ static int __cmd_inject(struct perf_inject *inject)
 			else if (!strncmp(name, "sched:sched_stat_", 17))
 				evsel->handler = perf_inject__sched_stat;
 		}
+	} else if (inject->itrace_synth_opts.vm_time_correlation) {
+		session->itrace_synth_opts = &inject->itrace_synth_opts;
+		memset(&inject->tool, 0, sizeof(inject->tool));
+		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.auxtrace_error = perf_event__process_auxtrace_error;
+		inject->tool.ordered_events = true;
+		inject->tool.ordering_requires_timestamps = true;
 	} else if (inject->itrace_synth_opts.set) {
 		session->itrace_synth_opts = &inject->itrace_synth_opts;
 		inject->itrace_synth_opts.inject = true;
@@ -759,14 +825,14 @@ static int __cmd_inject(struct perf_inject *inject)
 	if (!inject->itrace_synth_opts.set)
 		auxtrace_index__free(&session->auxtrace_index);
 
-	if (!data_out->is_pipe)
+	if (!data_out->is_pipe && !inject->in_place_update)
 		lseek(fd, output_data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session);
 	if (ret)
 		return ret;
 
-	if (!data_out->is_pipe) {
+	if (!data_out->is_pipe && !inject->in_place_update) {
 		if (inject->build_ids)
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
@@ -878,6 +944,9 @@ int cmd_inject(int argc, const char **argv)
 				    itrace_parse_synth_opts),
 		OPT_BOOLEAN(0, "strip", &inject.strip,
 			    "strip non-synthesized events (use with --itrace)"),
+		OPT_CALLBACK_OPTARG(0, "vm-time-correlation", &inject, NULL, "opts",
+				    "correlate time between VM guests and the host",
+				    parse_vm_time_correlation),
 		OPT_END()
 	};
 	const char * const inject_usage[] = {
@@ -900,7 +969,23 @@ int cmd_inject(int argc, const char **argv)
 		return -1;
 	}
 
-	if (perf_data__open(&inject.output)) {
+	if (inject.in_place_update) {
+		if (!strcmp(inject.input_name, "-")) {
+			pr_err("Input file name required for in-place updating\n");
+			return -1;
+		}
+		if (strcmp(inject.output.path, "-")) {
+			pr_err("Output file name must not be specified for in-place updating\n");
+			return -1;
+		}
+		if (!data.force && !inject.in_place_update_dry_run) {
+			pr_err("The input file would be updated in place, "
+				"the --force option is required.\n");
+			return -1;
+		}
+		if (!inject.in_place_update_dry_run)
+			data.in_place_update = true;
+	} else if (perf_data__open(&inject.output)) {
 		perror("failed to create output file");
 		return -1;
 	}
@@ -950,5 +1035,6 @@ int cmd_inject(int argc, const char **argv)
 out_delete:
 	zstd_fini(&(inject.session->zstd_data));
 	perf_session__delete(inject.session);
+	free(inject.itrace_synth_opts.vm_tm_corr_args);
 	return ret;
 }

tools/perf/builtin-mem.c

@@ -18,6 +18,8 @@
 #include "util/dso.h"
 #include "util/map.h"
 #include "util/symbol.h"
+#include "util/pmu.h"
+#include "util/pmu-hybrid.h"
 #include <linux/err.h>
 
 #define MEM_OPERATION_LOAD	0x1
@@ -62,8 +64,10 @@ static const char * const *record_mem_usage = __usage;
 
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
-	int rec_argc, i = 0, j;
+	int rec_argc, i = 0, j, tmp_nr = 0;
+	int start, end;
 	const char **rec_argv;
+	char **rec_tmp;
 	int ret;
 	bool all_user = false, all_kernel = false;
 	struct perf_mem_event *e;
@@ -87,11 +91,24 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
-	rec_argc = argc + 9; /* max number of arguments */
+	if (!perf_pmu__has_hybrid())
+		rec_argc = argc + 9; /* max number of arguments */
+	else
+		rec_argc = argc + 9 * perf_pmu__hybrid_pmu_num();
+
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
 
+	/*
+	 * Save the allocated event name strings.
+	 */
+	rec_tmp = calloc(rec_argc + 1, sizeof(char *));
+	if (!rec_tmp) {
+		free(rec_argv);
+		return -1;
+	}
+
 	rec_argv[i++] = "record";
 
 	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE);
@@ -128,21 +145,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (mem->data_page_size)
 		rec_argv[i++] = "--data-page-size";
 
-	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		e = perf_mem_events__ptr(j);
-		if (!e->record)
-			continue;
-
-		if (!e->supported) {
-			pr_err("failed: event '%s' not supported\n",
-			       perf_mem_events__name(j));
-			free(rec_argv);
-			return -1;
-		}
-
-		rec_argv[i++] = "-e";
-		rec_argv[i++] = perf_mem_events__name(j);
-	}
+	start = i;
+	ret = perf_mem_events__record_args(rec_argv, &i, rec_tmp, &tmp_nr);
+	if (ret)
+		goto out;
+	end = i;
 
 	if (all_user)
 		rec_argv[i++] = "--all-user";
@@ -156,14 +163,18 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	if (verbose > 0) {
 		pr_debug("calling: record ");
 
-		while (rec_argv[j]) {
+		for (j = start; j < end; j++)
 			pr_debug("%s ", rec_argv[j]);
-			j++;
-		}
+
 		pr_debug("\n");
 	}
 
 	ret = cmd_record(i, rec_argv);
+out:
+	for (i = 0; i < tmp_nr; i++)
+		free(rec_tmp[i]);
+
+	free(rec_tmp);
 	free(rec_argv);
 	return ret;
 }

tools/perf/builtin-probe.c

@@ -347,7 +347,10 @@ static int perf_add_probe_events(struct perf_probe_event *pevs, int npevs)
 		goto out_cleanup;
 
 	if (params.command == 'D') {	/* it shows definition */
-		ret = show_probe_trace_events(pevs, npevs);
+		if (probe_conf.bootconfig)
+			ret = show_bootconfig_events(pevs, npevs);
+		else
+			ret = show_probe_trace_events(pevs, npevs);
 		goto out_cleanup;
 	}
 
@@ -581,6 +584,8 @@ __cmd_probe(int argc, const char **argv)
 		   "Look for files with symbols relative to this directory"),
 	OPT_CALLBACK(0, "target-ns", NULL, "pid",
 		     "target pid for namespace contexts", opt_set_target_ns),
+	OPT_BOOLEAN(0, "bootconfig", &probe_conf.bootconfig,
+		    "Output probe definition with bootconfig format"),
 	OPT_END()
 	};
 	int ret;
@@ -692,6 +697,11 @@ __cmd_probe(int argc, const char **argv)
 		}
 		break;
 	case 'D':
+		if (probe_conf.bootconfig && params.uprobes) {
+			pr_err("  Error: --bootconfig doesn't support uprobes.\n");
+			return -EINVAL;
+		}
+		__fallthrough;
 	case 'a':
 
 		/* Ensure the last given target is used */

tools/perf/builtin-record.c

@@ -969,6 +969,15 @@ static int record__open(struct record *rec)
 	return rc;
 }
 
+static void set_timestamp_boundary(struct record *rec, u64 sample_time)
+{
+	if (rec->evlist->first_sample_time == 0)
+		rec->evlist->first_sample_time = sample_time;
+
+	if (sample_time)
+		rec->evlist->last_sample_time = sample_time;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -977,10 +986,7 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct record *rec = container_of(tool, struct record, tool);
 
-	if (rec->evlist->first_sample_time == 0)
-		rec->evlist->first_sample_time = sample->time;
-
-	rec->evlist->last_sample_time = sample->time;
+	set_timestamp_boundary(rec, sample->time);
 
 	if (rec->buildid_all)
 		return 0;
@@ -2402,6 +2408,17 @@ static int build_id__process_mmap2(struct perf_tool *tool, union perf_event *eve
 	return perf_event__process_mmap2(tool, event, sample, machine);
 }
 
+static int process_timestamp_boundary(struct perf_tool *tool,
+				      union perf_event *event __maybe_unused,
+				      struct perf_sample *sample,
+				      struct machine *machine __maybe_unused)
+{
+	struct record *rec = container_of(tool, struct record, tool);
+
+	set_timestamp_boundary(rec, sample->time);
+	return 0;
+}
+
 /*
  * XXX Ideally would be local to cmd_record() and passed to a record__new
  * because we need to have access to it in record__exit, that is called
@@ -2436,6 +2453,8 @@ static struct record record = {
 		.namespaces	= perf_event__process_namespaces,
 		.mmap		= build_id__process_mmap,
 		.mmap2		= build_id__process_mmap2,
+		.itrace_start	= process_timestamp_boundary,
+		.aux		= process_timestamp_boundary,
 		.ordered_events	= true,
 	},
 };

tools/perf/builtin-report.c

@@ -934,6 +934,8 @@ static int __cmd_report(struct report *rep)
 		return ret;
 	}
 
+	evlist__check_mem_load_aux(session->evlist);
+
 	if (rep->stats_mode)
 		return stats_print(rep);
 

tools/perf/builtin-top.c

@@ -22,6 +22,7 @@
 
 #include "util/annotate.h"
 #include "util/bpf-event.h"
+#include "util/cgroup.h"
 #include "util/config.h"
 #include "util/color.h"
 #include "util/dso.h"
@@ -1558,6 +1559,8 @@ int cmd_top(int argc, const char **argv)
 	OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
 			"number of thread to run event synthesize"),
+	OPT_CALLBACK('G', "cgroup", &top.evlist, "name",
+		     "monitor event in cgroup name only", parse_cgroups),
 	OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces,
 		    "Record namespaces events"),
 	OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup,
@@ -1646,6 +1649,11 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
+	if (nr_cgroups > 0 && opts->record_cgroup) {
+		pr_err("--cgroup and --all-cgroups cannot be used together\n");
+		goto out_delete_evlist;
+	}
+
 	if (opts->branch_stack && callchain_param.enabled)
 		symbol_conf.show_branchflag_count = true;
 

tools/perf/pmu-events/arch/x86/icelakex/floating-point.json

+[
+    {
+        "BriefDescription": "Counts all microcode FP assists.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc1",
+        "EventName": "ASSISTS.FP",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts all microcode Floating Point assists.",
+        "SampleAfterValue": "100003",
+        "Speculative": "1",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x4"
+    },
+    {
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "PublicDescription": "Counts number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "SampleAfterValue": "100003",
+        "UMask": "0x8"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 4 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB.  FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x10"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x20"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 8 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x40"
+    },
+    {
+        "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 16 computation operations, one for each element.  Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+        "CollectPEBSRecord": "2",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
+        "PEBScounters": "0,1,2,3,4,5,6,7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x80"
+    }
+]
\ No newline at end of file

tools/perf/pmu-events/arch/x86/icelakex/uncore-power.json

+[
+    {
+        "BriefDescription": "Clockticks of the power control unit (PCU)",
+        "Counter": "0,1,2,3",
+        "CounterType": "PGMABLE",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]