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
  ...

Author: torvalds

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.