Merge tag 'perf-tools-for-v6.0-2022-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Introduce 'perf lock contention' subtool, using new lock contention
   tracepoints and using BPF for in kernel aggregation and then
   userspace processing using the perf tooling infrastructure for
   resolving symbols, target specification, etc.

   Since the new lock contention tracepoints don't provide lock names,
   get up to 8 stack traces and display the first non-lock function
   symbol name as a caller:

    $ perf lock report -F acquired,contended,avg_wait,wait_total

                    Name   acquired  contended     avg wait    total wait

     update_blocked_a...         40         40      3.61 us     144.45 us
     kernfs_fop_open+...          5          5      3.64 us      18.18 us
      _nohz_idle_balance          3          3      2.65 us       7.95 us
     tick_do_update_j...          1          1      6.04 us       6.04 us
      ep_scan_ready_list          1          1      3.93 us       3.93 us

   Supports the usual 'perf record' + 'perf report' workflow as well as
   a BCC/bpftrace like mode where you start the tool and then press
   control+C to get results:

     $ sudo perf lock contention -b
    ^C
    contended   total wait     max wait     avg wait         type   caller

            42    192.67 us     13.64 us      4.59 us     spinlock   queue_work_on+0x20
            23     85.54 us     10.28 us      3.72 us     spinlock   worker_thread+0x14a
             6     13.92 us      6.51 us      2.32 us        mutex   kernfs_iop_permission+0x30
             3     11.59 us     10.04 us      3.86 us        mutex   kernfs_dop_revalidate+0x3c
             1      7.52 us      7.52 us      7.52 us     spinlock   kthread+0x115
             1      7.24 us      7.24 us      7.24 us     rwlock:W   sys_epoll_wait+0x148
             2      7.08 us      3.99 us      3.54 us     spinlock   delayed_work_timer_fn+0x1b
             1      6.41 us      6.41 us      6.41 us     spinlock   idle_balance+0xa06
             2      2.50 us      1.83 us      1.25 us        mutex   kernfs_iop_lookup+0x2f
             1      1.71 us      1.71 us      1.71 us        mutex   kernfs_iop_getattr+0x2c
    ...

 - Add new 'perf kwork' tool to trace time properties of kernel work
   (such as softirq, and workqueue), uses eBPF skeletons to collect info
   in kernel space, aggregating data that then gets processed by the
   userspace tool, e.g.:

    # perf kwork report

     Kwork Name      | Cpu | Total Runtime | Count | Max runtime | Max runtime start | Max runtime end |
    ----------------------------------------------------------------------------------------------------
     nvme0q5:130     | 004 |      1.101 ms |    49 |    0.051 ms |    26035.056403 s |  26035.056455 s |
     amdgpu:162      | 002 |      0.176 ms |     9 |    0.046 ms |    26035.268020 s |  26035.268066 s |
     nvme0q24:149    | 023 |      0.161 ms |    55 |    0.009 ms |    26035.655280 s |  26035.655288 s |
     nvme0q20:145    | 019 |      0.090 ms |    33 |    0.014 ms |    26035.939018 s |  26035.939032 s |
     nvme0q31:156    | 030 |      0.075 ms |    21 |    0.010 ms |    26035.052237 s |  26035.052247 s |
     nvme0q8:133     | 007 |      0.062 ms |    12 |    0.021 ms |    26035.416840 s |  26035.416861 s |
     nvme0q6:131     | 005 |      0.054 ms |    22 |    0.010 ms |    26035.199919 s |  26035.199929 s |
     nvme0q19:144    | 018 |      0.052 ms |    14 |    0.010 ms |    26035.110615 s |  26035.110625 s |
     nvme0q7:132     | 006 |      0.049 ms |    13 |    0.007 ms |    26035.125180 s |  26035.125187 s |
     nvme0q18:143    | 017 |      0.033 ms |    14 |    0.007 ms |    26035.169698 s |  26035.169705 s |
     nvme0q17:142    | 016 |      0.013 ms |     1 |    0.013 ms |    26035.565147 s |  26035.565160 s |
     enp5s0-rx-0:164 | 006 |      0.004 ms |     4 |    0.002 ms |    26035.928882 s |  26035.928884 s |
     enp5s0-tx-0:166 | 008 |      0.003 ms |     3 |    0.002 ms |    26035.870923 s |  26035.870925 s |
    --------------------------------------------------------------------------------------------------------

   See commit log messages for more examples with extra options to limit
   the events time window, etc.

 - Add support for new AMD IBS (Instruction Based Sampling) features:

   With the DataSrc extensions, the source of data can be decoded among:
     - Local L3 or other L1/L2 in CCX.
     - A peer cache in a near CCX.
     - Data returned from DRAM.
     - A peer cache in a far CCX.
     - DRAM address map with "long latency" bit set.
     - Data returned from MMIO/Config/PCI/APIC.
     - Extension Memory (S-Link, GenZ, etc - identified by the CS target
       and/or address map at DF's choice).
     - Peer Agent Memory.

 - Support hardware tracing with Intel PT on guest machines, combining
   the traces with the ones in the host machine.

 - Add a "-m" option to 'perf buildid-list' to show kernel and modules
   build-ids, to display all of the information needed to do external
   symbolization of kernel stack traces, such as those collected by
   bpf_get_stackid().

 - Add arch TSC frequency information to perf.data file headers.

 - Handle changes in the binutils disassembler function signatures in
   perf, bpftool and bpf_jit_disasm (Acked by the bpftool maintainer).

 - Fix building the perf perl binding with the newest gcc in distros
   such as fedora rawhide, where some new warnings were breaking the
   build as perf uses -Werror.

 - Add 'perf test' entry for branch stack sampling.

 - Add ARM SPE system wide 'perf test' entry.

 - Add user space counter reading tests to 'perf test'.

 - Build with python3 by default, if available.

 - Add python converter script for the vendor JSON event files.

 - Update vendor JSON files for most Intel cores.

 - Add vendor JSON File for Intel meteorlake.

 - Add Arm Cortex-A78C and X1C JSON vendor event files.

 - Add workaround to symbol address reading from ELF files without phdr,
   falling back to the previoous equation.

 - Convert legacy map definition to BTF-defined in the perf BPF script
   test.

 - Rework prologue generation code to stop using libbpf deprecated APIs.

 - Add default hybrid events for 'perf stat' on x86.

 - Add topdown metrics in the default 'perf stat' on the hybrid machines
   (big/little cores).

 - Prefer sampled CPU when exporting JSON in 'perf data convert'

 - Fix ('perf stat CSV output linter') and ("Check branch stack
   sampling") 'perf test' entries on s390.

* tag 'perf-tools-for-v6.0-2022-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (169 commits)
  perf stat: Refactor __run_perf_stat() common code
  perf lock: Print the number of lost entries for BPF
  perf lock: Add --map-nr-entries option
  perf lock: Introduce struct lock_contention
  perf scripting python: Do not build fail on deprecation warnings
  genelf: Use HAVE_LIBCRYPTO_SUPPORT, not the never defined HAVE_LIBCRYPTO
  perf build: Suppress openssl v3 deprecation warnings in libcrypto feature test
  perf parse-events: Break out tracepoint and printing
  perf parse-events: Don't #define YY_EXTRA_TYPE
  tools bpftool: Don't display disassembler-four-args feature test
  tools bpftool: Fix compilation error with new binutils
  tools bpf_jit_disasm: Don't display disassembler-four-args feature test
  tools bpf_jit_disasm: Fix compilation error with new binutils
  tools perf: Fix compilation error with new binutils
  tools include: add dis-asm-compat.h to handle version differences
  tools build: Don't display disassembler-four-args feature test
  tools build: Add feature test for init_disassemble_info API changes
  perf test: Add ARM SPE system wide test
  perf tools: Rework prologue generation code
  perf bpf: Convert legacy map definition to BTF-defined
  ...

68 files changed, 3379 insertions, 1032 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index a51267d88ca9..d8fe514c9ec9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -26,6 +26,8 @@ perf-y += mmap.o
 perf-y += memswap.o
 perf-y += parse-events.o
 perf-y += parse-events-hybrid.o
+perf-y += print-events.o
+perf-y += tracepoint.o
 perf-y += perf_regs.o
 perf-y += path.o
 perf-y += print_binary.o
@@ -148,6 +150,8 @@ perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o
+perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o
 perf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c
index d19d765195c5..238305868644 100644
--- a/tools/perf/util/amd-sample-raw.c
+++ b/tools/perf/util/amd-sample-raw.c
@@ -18,6 +18,7 @@
 #include "pmu-events/pmu-events.h"
 
 static u32 cpu_family, cpu_model, ibs_fetch_type, ibs_op_type;
+static bool zen4_ibs_extensions;
 
 static void pr_ibs_fetch_ctl(union ibs_fetch_ctl reg)
 {
@@ -39,6 +40,7 @@ static void pr_ibs_fetch_ctl(union ibs_fetch_ctl reg)
 	};
 	const char *ic_miss_str = NULL;
 	const char *l1tlb_pgsz_str = NULL;
+	char l3_miss_str[sizeof(" L3MissOnly _ FetchOcMiss _ FetchL3Miss _")] = "";
 
 	if (cpu_family == 0x19 && cpu_model < 0x10) {
 		/*
@@ -53,12 +55,19 @@ static void pr_ibs_fetch_ctl(union ibs_fetch_ctl reg)
 		ic_miss_str = ic_miss_strs[reg.ic_miss];
 	}
 
+	if (zen4_ibs_extensions) {
+		snprintf(l3_miss_str, sizeof(l3_miss_str),
+			 " L3MissOnly %d FetchOcMiss %d FetchL3Miss %d",
+			 reg.l3_miss_only, reg.fetch_oc_miss, reg.fetch_l3_miss);
+	}
+
 	printf("ibs_fetch_ctl:\t%016llx MaxCnt %7d Cnt %7d Lat %5d En %d Val %d Comp %d%s "
-	       "PhyAddrValid %d%s L1TlbMiss %d L2TlbMiss %d RandEn %d%s\n",
+		"PhyAddrValid %d%s L1TlbMiss %d L2TlbMiss %d RandEn %d%s%s\n",
 		reg.val, reg.fetch_maxcnt << 4, reg.fetch_cnt << 4, reg.fetch_lat,
 		reg.fetch_en, reg.fetch_val, reg.fetch_comp, ic_miss_str ? : "",
 		reg.phy_addr_valid, l1tlb_pgsz_str ? : "", reg.l1tlb_miss, reg.l2tlb_miss,
-		reg.rand_en, reg.fetch_comp ? (reg.fetch_l2_miss ? " L2Miss 1" : " L2Miss 0") : "");
+		reg.rand_en, reg.fetch_comp ? (reg.fetch_l2_miss ? " L2Miss 1" : " L2Miss 0") : "",
+		l3_miss_str);
 }
 
 static void pr_ic_ibs_extd_ctl(union ic_ibs_extd_ctl reg)
@@ -68,9 +77,15 @@ static void pr_ic_ibs_extd_ctl(union ic_ibs_extd_ctl reg)
 
 static void pr_ibs_op_ctl(union ibs_op_ctl reg)
 {
-	printf("ibs_op_ctl:\t%016llx MaxCnt %9d En %d Val %d CntCtl %d=%s CurCnt %9d\n",
-	       reg.val, ((reg.opmaxcnt_ext << 16) | reg.opmaxcnt) << 4, reg.op_en, reg.op_val,
-	       reg.cnt_ctl, reg.cnt_ctl ? "uOps" : "cycles", reg.opcurcnt);
+	char l3_miss_only[sizeof(" L3MissOnly _")] = "";
+
+	if (zen4_ibs_extensions)
+		snprintf(l3_miss_only, sizeof(l3_miss_only), " L3MissOnly %d", reg.l3_miss_only);
+
+	printf("ibs_op_ctl:\t%016llx MaxCnt %9d%s En %d Val %d CntCtl %d=%s CurCnt %9d\n",
+		reg.val, ((reg.opmaxcnt_ext << 16) | reg.opmaxcnt) << 4, l3_miss_only,
+		reg.op_en, reg.op_val, reg.cnt_ctl,
+		reg.cnt_ctl ? "uOps" : "cycles", reg.opcurcnt);
 }
 
 static void pr_ibs_op_data(union ibs_op_data reg)
@@ -84,7 +99,34 @@ static void pr_ibs_op_data(union ibs_op_data reg)
 		reg.op_brn_ret, reg.op_rip_invalid, reg.op_brn_fuse, reg.op_microcode);
 }
 
-static void pr_ibs_op_data2(union ibs_op_data2 reg)
+static void pr_ibs_op_data2_extended(union ibs_op_data2 reg)
+{
+	static const char * const data_src_str[] = {
+		"",
+		" DataSrc 1=Local L3 or other L1/L2 in CCX",
+		" DataSrc 2=A peer cache in a near CCX",
+		" DataSrc 3=Data returned from DRAM",
+		" DataSrc 4=(reserved)",
+		" DataSrc 5=A peer cache in a far CCX",
+		" DataSrc 6=DRAM address map with \"long latency\" bit set",
+		" DataSrc 7=Data returned from MMIO/Config/PCI/APIC",
+		" DataSrc 8=Extension Memory (S-Link, GenZ, etc)",
+		" DataSrc 9=(reserved)",
+		" DataSrc 10=(reserved)",
+		" DataSrc 11=(reserved)",
+		" DataSrc 12=Peer Agent Memory",
+		/* 13 to 31 are reserved. Avoid printing them. */
+	};
+	int data_src = (reg.data_src_hi << 3) | reg.data_src_lo;
+
+	printf("ibs_op_data2:\t%016llx %sRmtNode %d%s\n", reg.val,
+		(data_src == 1 || data_src == 2 || data_src == 5) ?
+			(reg.cache_hit_st ? "CacheHitSt 1=O-State " : "CacheHitSt 0=M-state ") : "",
+		reg.rmt_node,
+		data_src < (int)ARRAY_SIZE(data_src_str) ? data_src_str[data_src] : "");
+}
+
+static void pr_ibs_op_data2_default(union ibs_op_data2 reg)
 {
 	static const char * const data_src_str[] = {
 		"",
@@ -98,9 +140,16 @@ static void pr_ibs_op_data2(union ibs_op_data2 reg)
 	};
 
 	printf("ibs_op_data2:\t%016llx %sRmtNode %d%s\n", reg.val,
-	       reg.data_src == 2 ? (reg.cache_hit_st ? "CacheHitSt 1=O-State "
+	       reg.data_src_lo == 2 ? (reg.cache_hit_st ? "CacheHitSt 1=O-State "
 						     : "CacheHitSt 0=M-state ") : "",
-	       reg.rmt_node, data_src_str[reg.data_src]);
+	       reg.rmt_node, data_src_str[reg.data_src_lo]);
+}
+
+static void pr_ibs_op_data2(union ibs_op_data2 reg)
+{
+	if (zen4_ibs_extensions)
+		return pr_ibs_op_data2_extended(reg);
+	pr_ibs_op_data2_default(reg);
 }
 
 static void pr_ibs_op_data3(union ibs_op_data3 reg)
@@ -279,6 +328,9 @@ bool evlist__has_amd_ibs(struct evlist *evlist)
 		pmu_mapping += strlen(pmu_mapping) + 1 /* '\0' */;
 	}
 
+	if (perf_env__find_pmu_cap(env, "ibs_op", "zen4_ibs_extensions"))
+		zen4_ibs_extensions = 1;
+
 	if (ibs_fetch_type || ibs_op_type) {
 		if (!cpu_family)
 			parse_cpuid(env);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 82cc396ef516..2c6a485c3de5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1720,6 +1720,7 @@ fallback:
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
 #include <linux/btf.h>
+#include <tools/dis-asm-compat.h>
 
 static int symbol__disassemble_bpf(struct symbol *sym,
 				   struct annotate_args *args)
@@ -1762,9 +1763,9 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		ret = errno;
 		goto out;
 	}
-	init_disassemble_info(&info, s,
-			      (fprintf_ftype) fprintf);
-
+	init_disassemble_info_compat(&info, s,
+				     (fprintf_ftype) fprintf,
+				     fprintf_styled);
 	info.arch = bfd_get_arch(bfdf);
 	info.mach = bfd_get_mach(bfdf);
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 511dd3caa1bc..6edab8a16de6 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1189,9 +1189,10 @@ void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
 	free(buffer);
 }
 
-void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
-			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
-			  const char *msg, u64 timestamp)
+void auxtrace_synth_guest_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
+				int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+				const char *msg, u64 timestamp,
+				pid_t machine_pid, int vcpu)
 {
 	size_t size;
 
@@ -1207,12 +1208,26 @@ void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int
 	auxtrace_error->ip = ip;
 	auxtrace_error->time = timestamp;
 	strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
-
-	size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
-	       strlen(auxtrace_error->msg) + 1;
+	if (machine_pid) {
+		auxtrace_error->fmt = 2;
+		auxtrace_error->machine_pid = machine_pid;
+		auxtrace_error->vcpu = vcpu;
+		size = sizeof(*auxtrace_error);
+	} else {
+		size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+		       strlen(auxtrace_error->msg) + 1;
+	}
 	auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
 }
 
+void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg, u64 timestamp)
+{
+	auxtrace_synth_guest_error(auxtrace_error, type, code, cpu, pid, tid,
+				   ip, msg, timestamp, 0, -1);
+}
+
 int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
 					 struct perf_tool *tool,
 					 struct perf_session *session,
@@ -1662,6 +1677,9 @@ size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
 	if (!e->fmt)
 		msg = (const char *)&e->time;
 
+	if (e->fmt >= 2 && e->machine_pid)
+		ret += fprintf(fp, " machine_pid %d vcpu %d", e->machine_pid, e->vcpu);
+
 	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRI_lx64" code %u: %s\n",
 		       e->cpu, e->pid, e->tid, e->ip, e->code, msg);
 	return ret;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index cd0d25c2751c..6a4fbfd34c6b 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -595,6 +595,10 @@ int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
 			    bool needs_swap);
 void auxtrace_index__free(struct list_head *head);
 
+void auxtrace_synth_guest_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
+				int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+				const char *msg, u64 timestamp,
+				pid_t machine_pid, int vcpu);
 void auxtrace_synth_error(struct perf_record_auxtrace_error *auxtrace_error, int type,
 			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
 			  const char *msg, u64 timestamp);
diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c
new file mode 100644
index 000000000000..b629dd679d3f
--- /dev/null
+++ b/tools/perf/util/bpf_kwork.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * bpf_kwork.c
+ *
+ * Copyright (c) 2022  Huawei Inc,  Yang Jihong <yangjihong1@huawei.com>
+ */
+
+#include <time.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include <linux/time64.h>
+
+#include "util/debug.h"
+#include "util/kwork.h"
+
+#include <bpf/bpf.h>
+
+#include "util/bpf_skel/kwork_trace.skel.h"
+
+/*
+ * This should be in sync with "util/kwork_trace.bpf.c"
+ */
+#define MAX_KWORKNAME 128
+
+struct work_key {
+	u32 type;
+	u32 cpu;
+	u64 id;
+};
+
+struct report_data {
+	u64 nr;
+	u64 total_time;
+	u64 max_time;
+	u64 max_time_start;
+	u64 max_time_end;
+};
+
+struct kwork_class_bpf {
+	struct kwork_class *class;
+
+	void (*load_prepare)(struct perf_kwork *kwork);
+	int  (*get_work_name)(struct work_key *key, char **ret_name);
+};
+
+static struct kwork_trace_bpf *skel;
+
+static struct timespec ts_start;
+static struct timespec ts_end;
+
+void perf_kwork__trace_start(void)
+{
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+	skel->bss->enabled = 1;
+}
+
+void perf_kwork__trace_finish(void)
+{
+	clock_gettime(CLOCK_MONOTONIC, &ts_end);
+	skel->bss->enabled = 0;
+}
+
+static int get_work_name_from_map(struct work_key *key, char **ret_name)
+{
+	char name[MAX_KWORKNAME] = { 0 };
+	int fd = bpf_map__fd(skel->maps.perf_kwork_names);
+
+	*ret_name = NULL;
+
+	if (fd < 0) {
+		pr_debug("Invalid names map fd\n");
+		return 0;
+	}
+
+	if ((bpf_map_lookup_elem(fd, key, name) == 0) && (strlen(name) != 0)) {
+		*ret_name = strdup(name);
+		if (*ret_name == NULL) {
+			pr_err("Failed to copy work name\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static void irq_load_prepare(struct perf_kwork *kwork)
+{
+	if (kwork->report == KWORK_REPORT_RUNTIME) {
+		bpf_program__set_autoload(skel->progs.report_irq_handler_entry, true);
+		bpf_program__set_autoload(skel->progs.report_irq_handler_exit, true);
+	}
+}
+
+static struct kwork_class_bpf kwork_irq_bpf = {
+	.load_prepare  = irq_load_prepare,
+	.get_work_name = get_work_name_from_map,
+};
+
+static void softirq_load_prepare(struct perf_kwork *kwork)
+{
+	if (kwork->report == KWORK_REPORT_RUNTIME) {
+		bpf_program__set_autoload(skel->progs.report_softirq_entry, true);
+		bpf_program__set_autoload(skel->progs.report_softirq_exit, true);
+	} else if (kwork->report == KWORK_REPORT_LATENCY) {
+		bpf_program__set_autoload(skel->progs.latency_softirq_raise, true);
+		bpf_program__set_autoload(skel->progs.latency_softirq_entry, true);
+	}
+}
+
+static struct kwork_class_bpf kwork_softirq_bpf = {
+	.load_prepare  = softirq_load_prepare,
+	.get_work_name = get_work_name_from_map,
+};
+
+static void workqueue_load_prepare(struct perf_kwork *kwork)
+{
+	if (kwork->report == KWORK_REPORT_RUNTIME) {
+		bpf_program__set_autoload(skel->progs.report_workqueue_execute_start, true);
+		bpf_program__set_autoload(skel->progs.report_workqueue_execute_end, true);
+	} else if (kwork->report == KWORK_REPORT_LATENCY) {
+		bpf_program__set_autoload(skel->progs.latency_workqueue_activate_work, true);
+		bpf_program__set_autoload(skel->progs.latency_workqueue_execute_start, true);
+	}
+}
+
+static struct kwork_class_bpf kwork_workqueue_bpf = {
+	.load_prepare  = workqueue_load_prepare,
+	.get_work_name = get_work_name_from_map,
+};
+
+static struct kwork_class_bpf *
+kwork_class_bpf_supported_list[KWORK_CLASS_MAX] = {
+	[KWORK_CLASS_IRQ]       = &kwork_irq_bpf,
+	[KWORK_CLASS_SOFTIRQ]   = &kwork_softirq_bpf,
+	[KWORK_CLASS_WORKQUEUE] = &kwork_workqueue_bpf,
+};
+
+static bool valid_kwork_class_type(enum kwork_class_type type)
+{
+	return type >= 0 && type < KWORK_CLASS_MAX ? true : false;
+}
+
+static int setup_filters(struct perf_kwork *kwork)
+{
+	u8 val = 1;
+	int i, nr_cpus, key, fd;
+	struct perf_cpu_map *map;
+
+	if (kwork->cpu_list != NULL) {
+		fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+		if (fd < 0) {
+			pr_debug("Invalid cpu filter fd\n");
+			return -1;
+		}
+
+		map = perf_cpu_map__new(kwork->cpu_list);
+		if (map == NULL) {
+			pr_debug("Invalid cpu_list\n");
+			return -1;
+		}
+
+		nr_cpus = libbpf_num_possible_cpus();
+		for (i = 0; i < perf_cpu_map__nr(map); i++) {
+			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+
+			if (cpu.cpu >= nr_cpus) {
+				perf_cpu_map__put(map);
+				pr_err("Requested cpu %d too large\n", cpu.cpu);
+				return -1;
+			}
+			bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY);
+		}
+		perf_cpu_map__put(map);
+
+		skel->bss->has_cpu_filter = 1;
+	}
+
+	if (kwork->profile_name != NULL) {
+		if (strlen(kwork->profile_name) >= MAX_KWORKNAME) {
+			pr_err("Requested name filter %s too large, limit to %d\n",
+			       kwork->profile_name, MAX_KWORKNAME - 1);
+			return -1;
+		}
+
+		fd = bpf_map__fd(skel->maps.perf_kwork_name_filter);
+		if (fd < 0) {
+			pr_debug("Invalid name filter fd\n");
+			return -1;
+		}
+
+		key = 0;
+		bpf_map_update_elem(fd, &key, kwork->profile_name, BPF_ANY);
+
+		skel->bss->has_name_filter = 1;
+	}
+
+	return 0;
+}
+
+int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork)
+{
+	struct bpf_program *prog;
+	struct kwork_class *class;
+	struct kwork_class_bpf *class_bpf;
+	enum kwork_class_type type;
+
+	skel = kwork_trace_bpf__open();
+	if (!skel) {
+		pr_debug("Failed to open kwork trace skeleton\n");
+		return -1;
+	}
+
+	/*
+	 * set all progs to non-autoload,
+	 * then set corresponding progs according to config
+	 */
+	bpf_object__for_each_program(prog, skel->obj)
+		bpf_program__set_autoload(prog, false);
+
+	list_for_each_entry(class, &kwork->class_list, list) {
+		type = class->type;
+		if (!valid_kwork_class_type(type) ||
+		    (kwork_class_bpf_supported_list[type] == NULL)) {
+			pr_err("Unsupported bpf trace class %s\n", class->name);
+			goto out;
+		}
+
+		class_bpf = kwork_class_bpf_supported_list[type];
+		class_bpf->class = class;
+
+		if (class_bpf->load_prepare != NULL)
+			class_bpf->load_prepare(kwork);
+	}
+
+	if (kwork_trace_bpf__load(skel)) {
+		pr_debug("Failed to load kwork trace skeleton\n");
+		goto out;
+	}
+
+	if (setup_filters(kwork))
+		goto out;
+
+	if (kwork_trace_bpf__attach(skel)) {
+		pr_debug("Failed to attach kwork trace skeleton\n");
+		goto out;
+	}
+
+	return 0;
+
+out:
+	kwork_trace_bpf__destroy(skel);
+	return -1;
+}
+
+static int add_work(struct perf_kwork *kwork,
+		    struct work_key *key,
+		    struct report_data *data)
+{
+	struct kwork_work *work;
+	struct kwork_class_bpf *bpf_trace;
+	struct kwork_work tmp = {
+		.id = key->id,
+		.name = NULL,
+		.cpu = key->cpu,
+	};
+	enum kwork_class_type type = key->type;
+
+	if (!valid_kwork_class_type(type)) {
+		pr_debug("Invalid class type %d to add work\n", type);
+		return -1;
+	}
+
+	bpf_trace = kwork_class_bpf_supported_list[type];
+	tmp.class = bpf_trace->class;
+
+	if ((bpf_trace->get_work_name != NULL) &&
+	    (bpf_trace->get_work_name(key, &tmp.name)))
+		return -1;
+
+	work = perf_kwork_add_work(kwork, tmp.class, &tmp);
+	if (work == NULL)
+		return -1;
+
+	if (kwork->report == KWORK_REPORT_RUNTIME) {
+		work->nr_atoms = data->nr;
+		work->total_runtime = data->total_time;
+		work->max_runtime = data->max_time;
+		work->max_runtime_start = data->max_time_start;
+		work->max_runtime_end = data->max_time_end;
+	} else if (kwork->report == KWORK_REPORT_LATENCY) {
+		work->nr_atoms = data->nr;
+		work->total_latency = data->total_time;
+		work->max_latency = data->max_time;
+		work->max_latency_start = data->max_time_start;
+		work->max_latency_end = data->max_time_end;
+	} else {
+		pr_debug("Invalid bpf report type %d\n", kwork->report);
+		return -1;
+	}
+
+	kwork->timestart = (u64)ts_start.tv_sec * NSEC_PER_SEC + ts_start.tv_nsec;
+	kwork->timeend = (u64)ts_end.tv_sec * NSEC_PER_SEC + ts_end.tv_nsec;
+
+	return 0;
+}
+
+int perf_kwork__report_read_bpf(struct perf_kwork *kwork)
+{
+	struct report_data data;
+	struct work_key key = {
+		.type = 0,
+		.cpu  = 0,
+		.id   = 0,
+	};
+	struct work_key prev = {
+		.type = 0,
+		.cpu  = 0,
+		.id   = 0,
+	};
+	int fd = bpf_map__fd(skel->maps.perf_kwork_report);
+
+	if (fd < 0) {
+		pr_debug("Invalid report fd\n");
+		return -1;
+	}
+
+	while (!bpf_map_get_next_key(fd, &prev, &key)) {
+		if ((bpf_map_lookup_elem(fd, &key, &data)) != 0) {
+			pr_debug("Failed to lookup report elem\n");
+			return -1;
+		}
+
+		if ((data.nr != 0) && (add_work(kwork, &key, &data) != 0))
+			return -1;
+
+		prev = key;
+	}
+	return 0;
+}
+
+void perf_kwork__report_cleanup_bpf(void)
+{
+	kwork_trace_bpf__destroy(skel);
+}
diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
new file mode 100644
index 000000000000..c591a66733ef
--- /dev/null
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/map.h"
+#include "util/symbol.h"
+#include "util/target.h"
+#include "util/thread_map.h"
+#include "util/lock-contention.h"
+#include <linux/zalloc.h>
+#include <bpf/bpf.h>
+
+#include "bpf_skel/lock_contention.skel.h"
+
+static struct lock_contention_bpf *skel;
+
+/* should be same as bpf_skel/lock_contention.bpf.c */
+struct lock_contention_key {
+	s32 stack_id;
+};
+
+struct lock_contention_data {
+	u64 total_time;
+	u64 min_time;
+	u64 max_time;
+	u32 count;
+	u32 flags;
+};
+
+int lock_contention_prepare(struct lock_contention *con)
+{
+	int i, fd;
+	int ncpus = 1, ntasks = 1;
+	struct evlist *evlist = con->evlist;
+	struct target *target = con->target;
+
+	skel = lock_contention_bpf__open();
+	if (!skel) {
+		pr_err("Failed to open lock-contention BPF skeleton\n");
+		return -1;
+	}
+
+	bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries);
+	bpf_map__set_max_entries(skel->maps.lock_stat, con->map_nr_entries);
+
+	if (target__has_cpu(target))
+		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
+	if (target__has_task(target))
+		ntasks = perf_thread_map__nr(evlist->core.threads);
+
+	bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
+	bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+
+	if (lock_contention_bpf__load(skel) < 0) {
+		pr_err("Failed to load lock-contention BPF skeleton\n");
+		return -1;
+	}
+
+	if (target__has_cpu(target)) {
+		u32 cpu;
+		u8 val = 1;
+
+		skel->bss->has_cpu = 1;
+		fd = bpf_map__fd(skel->maps.cpu_filter);
+
+		for (i = 0; i < ncpus; i++) {
+			cpu = perf_cpu_map__cpu(evlist->core.user_requested_cpus, i).cpu;
+			bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
+		}
+	}
+
+	if (target__has_task(target)) {
+		u32 pid;
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+
+		for (i = 0; i < ntasks; i++) {
+			pid = perf_thread_map__pid(evlist->core.threads, i);
+			bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+		}
+	}
+
+	if (target__none(target) && evlist->workload.pid > 0) {
+		u32 pid = evlist->workload.pid;
+		u8 val = 1;
+
+		skel->bss->has_task = 1;
+		fd = bpf_map__fd(skel->maps.task_filter);
+		bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+	}
+
+	lock_contention_bpf__attach(skel);
+	return 0;
+}
+
+int lock_contention_start(void)
+{
+	skel->bss->enabled = 1;
+	return 0;
+}
+
+int lock_contention_stop(void)
+{
+	skel->bss->enabled = 0;
+	return 0;
+}
+
+int lock_contention_read(struct lock_contention *con)
+{
+	int fd, stack;
+	s32 prev_key, key;
+	struct lock_contention_data data;
+	struct lock_stat *st;
+	struct machine *machine = con->machine;
+	u64 stack_trace[CONTENTION_STACK_DEPTH];
+
+	fd = bpf_map__fd(skel->maps.lock_stat);
+	stack = bpf_map__fd(skel->maps.stacks);
+
+	con->lost = skel->bss->lost;
+
+	prev_key = 0;
+	while (!bpf_map_get_next_key(fd, &prev_key, &key)) {
+		struct map *kmap;
+		struct symbol *sym;
+		int idx;
+
+		bpf_map_lookup_elem(fd, &key, &data);
+		st = zalloc(sizeof(*st));
+		if (st == NULL)
+			return -1;
+
+		st->nr_contended = data.count;
+		st->wait_time_total = data.total_time;
+		st->wait_time_max = data.max_time;
+		st->wait_time_min = data.min_time;
+
+		if (data.count)
+			st->avg_wait_time = data.total_time / data.count;
+
+		st->flags = data.flags;
+
+		bpf_map_lookup_elem(stack, &key, stack_trace);
+
+		/* skip BPF + lock internal functions */
+		idx = CONTENTION_STACK_SKIP;
+		while (is_lock_function(machine, stack_trace[idx]) &&
+		       idx < CONTENTION_STACK_DEPTH - 1)
+			idx++;
+
+		st->addr = stack_trace[idx];
+		sym = machine__find_kernel_symbol(machine, st->addr, &kmap);
+
+		if (sym) {
+			unsigned long offset;
+			int ret = 0;
+
+			offset = kmap->map_ip(kmap, st->addr) - sym->start;
+
+			if (offset)
+				ret = asprintf(&st->name, "%s+%#lx", sym->name, offset);
+			else
+				st->name = strdup(sym->name);
+
+			if (ret < 0 || st->name == NULL)
+				return -1;
+		} else if (asprintf(&st->name, "%#lx", (unsigned long)st->addr) < 0) {
+			free(st);
+			return -1;
+		}
+
+		hlist_add_head(&st->hash_entry, con->result);
+		prev_key = key;
+	}
+
+	return 0;
+}
+
+int lock_contention_finish(void)
+{
+	if (skel) {
+		skel->bss->enabled = 0;
+		lock_contention_bpf__destroy(skel);
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/bpf_skel/kwork_trace.bpf.c b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
new file mode 100644
index 000000000000..063c124e0999
--- /dev/null
+++ b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
@@ -0,0 +1,383 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2022, Huawei
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define KWORK_COUNT 100
+#define MAX_KWORKNAME 128
+
+/*
+ * This should be in sync with "util/kwork.h"
+ */
+enum kwork_class_type {
+	KWORK_CLASS_IRQ,
+	KWORK_CLASS_SOFTIRQ,
+	KWORK_CLASS_WORKQUEUE,
+	KWORK_CLASS_MAX,
+};
+
+struct work_key {
+	__u32 type;
+	__u32 cpu;
+	__u64 id;
+};
+
+struct report_data {
+	__u64 nr;
+	__u64 total_time;
+	__u64 max_time;
+	__u64 max_time_start;
+	__u64 max_time_end;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct work_key));
+	__uint(value_size, MAX_KWORKNAME);
+	__uint(max_entries, KWORK_COUNT);
+} perf_kwork_names SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct work_key));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, KWORK_COUNT);
+} perf_kwork_time SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct work_key));
+	__uint(value_size, sizeof(struct report_data));
+	__uint(max_entries, KWORK_COUNT);
+} perf_kwork_report SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} perf_kwork_cpu_filter SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, MAX_KWORKNAME);
+	__uint(max_entries, 1);
+} perf_kwork_name_filter SEC(".maps");
+
+int enabled = 0;
+int has_cpu_filter = 0;
+int has_name_filter = 0;
+
+static __always_inline int local_strncmp(const char *s1,
+					 unsigned int sz, const char *s2)
+{
+	int ret = 0;
+	unsigned int i;
+
+	for (i = 0; i < sz; i++) {
+		ret = (unsigned char)s1[i] - (unsigned char)s2[i];
+		if (ret || !s1[i] || !s2[i])
+			break;
+	}
+
+	return ret;
+}
+
+static __always_inline int trace_event_match(struct work_key *key, char *name)
+{
+	__u8 *cpu_val;
+	char *name_val;
+	__u32 zero = 0;
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	if (!enabled)
+		return 0;
+
+	if (has_cpu_filter) {
+		cpu_val = bpf_map_lookup_elem(&perf_kwork_cpu_filter, &cpu);
+		if (!cpu_val)
+			return 0;
+	}
+
+	if (has_name_filter && (name != NULL)) {
+		name_val = bpf_map_lookup_elem(&perf_kwork_name_filter, &zero);
+		if (name_val &&
+		    (local_strncmp(name_val, MAX_KWORKNAME, name) != 0)) {
+			return 0;
+		}
+	}
+
+	return 1;
+}
+
+static __always_inline void do_update_time(void *map, struct work_key *key,
+					   __u64 time_start, __u64 time_end)
+{
+	struct report_data zero, *data;
+	__s64 delta = time_end - time_start;
+
+	if (delta < 0)
+		return;
+
+	data = bpf_map_lookup_elem(map, key);
+	if (!data) {
+		__builtin_memset(&zero, 0, sizeof(zero));
+		bpf_map_update_elem(map, key, &zero, BPF_NOEXIST);
+		data = bpf_map_lookup_elem(map, key);
+		if (!data)
+			return;
+	}
+
+	if ((delta > data->max_time) ||
+	    (data->max_time == 0)) {
+		data->max_time       = delta;
+		data->max_time_start = time_start;
+		data->max_time_end   = time_end;
+	}
+
+	data->total_time += delta;
+	data->nr++;
+}
+
+static __always_inline void do_update_timestart(void *map, struct work_key *key)
+{
+	__u64 ts = bpf_ktime_get_ns();
+
+	bpf_map_update_elem(map, key, &ts, BPF_ANY);
+}
+
+static __always_inline void do_update_timeend(void *report_map, void *time_map,
+					      struct work_key *key)
+{
+	__u64 *time = bpf_map_lookup_elem(time_map, key);
+
+	if (time) {
+		bpf_map_delete_elem(time_map, key);
+		do_update_time(report_map, key, *time, bpf_ktime_get_ns());
+	}
+}
+
+static __always_inline void do_update_name(void *map,
+					   struct work_key *key, char *name)
+{
+	if (!bpf_map_lookup_elem(map, key))
+		bpf_map_update_elem(map, key, name, BPF_ANY);
+}
+
+static __always_inline int update_timestart(void *map, struct work_key *key)
+{
+	if (!trace_event_match(key, NULL))
+		return 0;
+
+	do_update_timestart(map, key);
+	return 0;
+}
+
+static __always_inline int update_timestart_and_name(void *time_map,
+						     void *names_map,
+						     struct work_key *key,
+						     char *name)
+{
+	if (!trace_event_match(key, name))
+		return 0;
+
+	do_update_timestart(time_map, key);
+	do_update_name(names_map, key, name);
+
+	return 0;
+}
+
+static __always_inline int update_timeend(void *report_map,
+					  void *time_map, struct work_key *key)
+{
+	if (!trace_event_match(key, NULL))
+		return 0;
+
+	do_update_timeend(report_map, time_map, key);
+
+	return 0;
+}
+
+static __always_inline int update_timeend_and_name(void *report_map,
+						   void *time_map,
+						   void *names_map,
+						   struct work_key *key,
+						   char *name)
+{
+	if (!trace_event_match(key, name))
+		return 0;
+
+	do_update_timeend(report_map, time_map, key);
+	do_update_name(names_map, key, name);
+
+	return 0;
+}
+
+SEC("tracepoint/irq/irq_handler_entry")
+int report_irq_handler_entry(struct trace_event_raw_irq_handler_entry *ctx)
+{
+	char name[MAX_KWORKNAME];
+	struct work_key key = {
+		.type = KWORK_CLASS_IRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->irq,
+	};
+	void *name_addr = (void *)ctx + (ctx->__data_loc_name & 0xffff);
+
+	bpf_probe_read_kernel_str(name, sizeof(name), name_addr);
+
+	return update_timestart_and_name(&perf_kwork_time,
+					 &perf_kwork_names, &key, name);
+}
+
+SEC("tracepoint/irq/irq_handler_exit")
+int report_irq_handler_exit(struct trace_event_raw_irq_handler_exit *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_IRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->irq,
+	};
+
+	return update_timeend(&perf_kwork_report, &perf_kwork_time, &key);
+}
+
+static char softirq_name_list[NR_SOFTIRQS][MAX_KWORKNAME] = {
+	{ "HI"       },
+	{ "TIMER"    },
+	{ "NET_TX"   },
+	{ "NET_RX"   },
+	{ "BLOCK"    },
+	{ "IRQ_POLL" },
+	{ "TASKLET"  },
+	{ "SCHED"    },
+	{ "HRTIMER"  },
+	{ "RCU"      },
+};
+
+SEC("tracepoint/irq/softirq_entry")
+int report_softirq_entry(struct trace_event_raw_softirq *ctx)
+{
+	unsigned int vec = ctx->vec;
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)vec,
+	};
+
+	if (vec < NR_SOFTIRQS) {
+		return update_timestart_and_name(&perf_kwork_time,
+						 &perf_kwork_names, &key,
+						 softirq_name_list[vec]);
+	}
+
+	return 0;
+}
+
+SEC("tracepoint/irq/softirq_exit")
+int report_softirq_exit(struct trace_event_raw_softirq *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->vec,
+	};
+
+	return update_timeend(&perf_kwork_report, &perf_kwork_time, &key);
+}
+
+SEC("tracepoint/irq/softirq_raise")
+int latency_softirq_raise(struct trace_event_raw_softirq *ctx)
+{
+	unsigned int vec = ctx->vec;
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)vec,
+	};
+
+	if (vec < NR_SOFTIRQS) {
+		return update_timestart_and_name(&perf_kwork_time,
+						 &perf_kwork_names, &key,
+						 softirq_name_list[vec]);
+	}
+
+	return 0;
+}
+
+SEC("tracepoint/irq/softirq_entry")
+int latency_softirq_entry(struct trace_event_raw_softirq *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_SOFTIRQ,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->vec,
+	};
+
+	return update_timeend(&perf_kwork_report, &perf_kwork_time, &key);
+}
+
+SEC("tracepoint/workqueue/workqueue_execute_start")
+int report_workqueue_execute_start(struct trace_event_raw_workqueue_execute_start *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_WORKQUEUE,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->work,
+	};
+
+	return update_timestart(&perf_kwork_time, &key);
+}
+
+SEC("tracepoint/workqueue/workqueue_execute_end")
+int report_workqueue_execute_end(struct trace_event_raw_workqueue_execute_end *ctx)
+{
+	char name[MAX_KWORKNAME];
+	struct work_key key = {
+		.type = KWORK_CLASS_WORKQUEUE,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->work,
+	};
+	unsigned long long func_addr = (unsigned long long)ctx->function;
+
+	__builtin_memset(name, 0, sizeof(name));
+	bpf_snprintf(name, sizeof(name), "%ps", &func_addr, sizeof(func_addr));
+
+	return update_timeend_and_name(&perf_kwork_report, &perf_kwork_time,
+				       &perf_kwork_names, &key, name);
+}
+
+SEC("tracepoint/workqueue/workqueue_activate_work")
+int latency_workqueue_activate_work(struct trace_event_raw_workqueue_activate_work *ctx)
+{
+	struct work_key key = {
+		.type = KWORK_CLASS_WORKQUEUE,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->work,
+	};
+
+	return update_timestart(&perf_kwork_time, &key);
+}
+
+SEC("tracepoint/workqueue/workqueue_execute_start")
+int latency_workqueue_execute_start(struct trace_event_raw_workqueue_execute_start *ctx)
+{
+	char name[MAX_KWORKNAME];
+	struct work_key key = {
+		.type = KWORK_CLASS_WORKQUEUE,
+		.cpu  = bpf_get_smp_processor_id(),
+		.id   = (__u64)ctx->work,
+	};
+	unsigned long long func_addr = (unsigned long long)ctx->function;
+
+	__builtin_memset(name, 0, sizeof(name));
+	bpf_snprintf(name, sizeof(name), "%ps", &func_addr, sizeof(func_addr));
+
+	return update_timeend_and_name(&perf_kwork_report, &perf_kwork_time,
+				       &perf_kwork_names, &key, name);
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
new file mode 100644
index 000000000000..9e8b94eb6320
--- /dev/null
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2022 Google
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+/* maximum stack trace depth */
+#define MAX_STACKS   8
+
+/* default buffer size */
+#define MAX_ENTRIES  10240
+
+struct contention_key {
+	__s32 stack_id;
+};
+
+struct contention_data {
+	__u64 total_time;
+	__u64 min_time;
+	__u64 max_time;
+	__u32 count;
+	__u32 flags;
+};
+
+struct tstamp_data {
+	__u64 timestamp;
+	__u64 lock;
+	__u32 flags;
+	__s32 stack_id;
+};
+
+/* callstack storage  */
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, MAX_STACKS * sizeof(__u64));
+	__uint(max_entries, MAX_ENTRIES);
+} stacks SEC(".maps");
+
+/* maintain timestamp at the beginning of contention */
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct tstamp_data);
+} tstamp SEC(".maps");
+
+/* actual lock contention statistics */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct contention_key));
+	__uint(value_size, sizeof(struct contention_data));
+	__uint(max_entries, MAX_ENTRIES);
+} lock_stat SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} cpu_filter SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u8));
+	__uint(max_entries, 1);
+} task_filter SEC(".maps");
+
+/* control flags */
+int enabled;
+int has_cpu;
+int has_task;
+
+/* error stat */
+unsigned long lost;
+
+static inline int can_record(void)
+{
+	if (has_cpu) {
+		__u32 cpu = bpf_get_smp_processor_id();
+		__u8 *ok;
+
+		ok = bpf_map_lookup_elem(&cpu_filter, &cpu);
+		if (!ok)
+			return 0;
+	}
+
+	if (has_task) {
+		__u8 *ok;
+		__u32 pid = bpf_get_current_pid_tgid();
+
+		ok = bpf_map_lookup_elem(&task_filter, &pid);
+		if (!ok)
+			return 0;
+	}
+
+	return 1;
+}
+
+SEC("tp_btf/contention_begin")
+int contention_begin(u64 *ctx)
+{
+	struct task_struct *curr;
+	struct tstamp_data *pelem;
+
+	if (!enabled || !can_record())
+		return 0;
+
+	curr = bpf_get_current_task_btf();
+	pelem = bpf_task_storage_get(&tstamp, curr, NULL,
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!pelem || pelem->lock)
+		return 0;
+
+	pelem->timestamp = bpf_ktime_get_ns();
+	pelem->lock = (__u64)ctx[0];
+	pelem->flags = (__u32)ctx[1];
+	pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP);
+
+	if (pelem->stack_id < 0)
+		lost++;
+	return 0;
+}
+
+SEC("tp_btf/contention_end")
+int contention_end(u64 *ctx)
+{
+	struct task_struct *curr;
+	struct tstamp_data *pelem;
+	struct contention_key key;
+	struct contention_data *data;
+	__u64 duration;
+
+	if (!enabled)
+		return 0;
+
+	curr = bpf_get_current_task_btf();
+	pelem = bpf_task_storage_get(&tstamp, curr, NULL, 0);
+	if (!pelem || pelem->lock != ctx[0])
+		return 0;
+
+	duration = bpf_ktime_get_ns() - pelem->timestamp;
+
+	key.stack_id = pelem->stack_id;
+	data = bpf_map_lookup_elem(&lock_stat, &key);
+	if (!data) {
+		struct contention_data first = {
+			.total_time = duration,
+			.max_time = duration,
+			.min_time = duration,
+			.count = 1,
+			.flags = pelem->flags,
+		};
+
+		bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST);
+		pelem->lock = 0;
+		return 0;
+	}
+
+	__sync_fetch_and_add(&data->total_time, duration);
+	__sync_fetch_and_add(&data->count, 1);
+
+	/* FIXME: need atomic operations */
+	if (data->max_time < duration)
+		data->max_time = duration;
+	if (data->min_time > duration)
+		data->min_time = duration;
+
+	pelem->lock = 0;
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 328668f38c69..9e176146eb10 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -300,12 +300,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size,
 	return __dso__build_id_filename(dso, bf, size, is_debug, is_kallsyms);
 }
 
-#define dsos__for_each_with_build_id(pos, head)	\
-	list_for_each_entry(pos, head, node)	\
-		if (!pos->has_build_id)		\
-			continue;		\
-		else
-
 static int write_buildid(const char *name, size_t name_len, struct build_id *bid,
 			 pid_t pid, u16 misc, struct feat_fd *fd)
 {
@@ -567,14 +561,11 @@ char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
 	char *realname = (char *)name, *filename;
 	bool slash = is_kallsyms || is_vdso;
 
-	if (!slash) {
+	if (!slash)
 		realname = nsinfo__realpath(name, nsi);
-		if (!realname)
-			return NULL;
-	}
 
 	if (asprintf(&filename, "%s%s%s%s%s", buildid_dir, slash ? "/" : "",
-		     is_vdso ? DSO__NAME_VDSO : realname,
+		     is_vdso ? DSO__NAME_VDSO : (realname ? realname : name),
 		     sbuild_id ? "/" : "", sbuild_id ?: "") < 0)
 		filename = NULL;
 
@@ -631,9 +622,12 @@ static int build_id_cache__add_sdt_cache(const char *sbuild_id,
 #endif
 
 static char *build_id_cache__find_debug(const char *sbuild_id,
-					struct nsinfo *nsi)
+					struct nsinfo *nsi,
+					const char *root_dir)
 {
+	const char *dirname = "/usr/lib/debug/.build-id/";
 	char *realname = NULL;
+	char dirbuf[PATH_MAX];
 	char *debugfile;
 	struct nscookie nsc;
 	size_t len = 0;
@@ -642,8 +636,12 @@ static char *build_id_cache__find_debug(const char *sbuild_id,
 	if (!debugfile)
 		goto out;
 
-	len = __symbol__join_symfs(debugfile, PATH_MAX,
-				   "/usr/lib/debug/.build-id/");
+	if (root_dir) {
+		path__join(dirbuf, PATH_MAX, root_dir, dirname);
+		dirname = dirbuf;
+	}
+
+	len = __symbol__join_symfs(debugfile, PATH_MAX, dirname);
 	snprintf(debugfile + len, PATH_MAX - len, "%.2s/%s.debug", sbuild_id,
 		 sbuild_id + 2);
 
@@ -674,14 +672,18 @@ out:
 
 int
 build_id_cache__add(const char *sbuild_id, const char *name, const char *realname,
-		    struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
+		    struct nsinfo *nsi, bool is_kallsyms, bool is_vdso,
+		    const char *proper_name, const char *root_dir)
 {
 	const size_t size = PATH_MAX;
 	char *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp;
 	char *debugfile = NULL;
 	int err = -1;
 
-	dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms,
+	if (!proper_name)
+		proper_name = name;
+
+	dir_name = build_id_cache__cachedir(sbuild_id, proper_name, nsi, is_kallsyms,
 					    is_vdso);
 	if (!dir_name)
 		goto out_free;
@@ -721,7 +723,7 @@ build_id_cache__add(const char *sbuild_id, const char *name, const char *realnam
 	 */
 	if (!is_kallsyms && !is_vdso &&
 	    strncmp(".ko", name + strlen(name) - 3, 3)) {
-		debugfile = build_id_cache__find_debug(sbuild_id, nsi);
+		debugfile = build_id_cache__find_debug(sbuild_id, nsi, root_dir);
 		if (debugfile) {
 			zfree(&filename);
 			if (asprintf(&filename, "%s/%s", dir_name,
@@ -787,8 +789,9 @@ out_free:
 	return err;
 }
 
-int build_id_cache__add_s(const char *sbuild_id, const char *name,
-			  struct nsinfo *nsi, bool is_kallsyms, bool is_vdso)
+int __build_id_cache__add_s(const char *sbuild_id, const char *name,
+			    struct nsinfo *nsi, bool is_kallsyms, bool is_vdso,
+			    const char *proper_name, const char *root_dir)
 {
 	char *realname = NULL;
 	int err = -1;
@@ -802,8 +805,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
 			goto out_free;
 	}
 
-	err = build_id_cache__add(sbuild_id, name, realname, nsi, is_kallsyms, is_vdso);
-
+	err = build_id_cache__add(sbuild_id, name, realname, nsi,
+				  is_kallsyms, is_vdso, proper_name, root_dir);
 out_free:
 	if (!is_kallsyms)
 		free(realname);
@@ -812,14 +815,16 @@ out_free:
 
 static int build_id_cache__add_b(const struct build_id *bid,
 				 const char *name, struct nsinfo *nsi,
-				 bool is_kallsyms, bool is_vdso)
+				 bool is_kallsyms, bool is_vdso,
+				 const char *proper_name,
+				 const char *root_dir)
 {
 	char sbuild_id[SBUILD_ID_SIZE];
 
 	build_id__sprintf(bid, sbuild_id);
 
-	return build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms,
-				     is_vdso);
+	return __build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms,
+				       is_vdso, proper_name, root_dir);
 }
 
 bool build_id_cache__cached(const char *sbuild_id)
@@ -902,6 +907,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 	bool is_kallsyms = dso__is_kallsyms(dso);
 	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
+	const char *proper_name = NULL;
+	const char *root_dir = NULL;
+	char *allocated_name = NULL;
+	int ret = 0;
 
 	if (!dso->has_build_id)
 		return 0;
@@ -911,11 +920,28 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 		name = machine->mmap_name;
 	}
 
+	if (!machine__is_host(machine)) {
+		if (*machine->root_dir) {
+			root_dir = machine->root_dir;
+			ret = asprintf(&allocated_name, "%s/%s", root_dir, name);
+			if (ret < 0)
+				return ret;
+			proper_name = name;
+			name = allocated_name;
+		} else if (is_kallsyms) {
+			/* Cannot get guest kallsyms */
+			return 0;
+		}
+	}
+
 	if (!is_kallsyms && dso__build_id_mismatch(dso, name))
-		return 0;
+		goto out_free;
 
-	return build_id_cache__add_b(&dso->bid, name, dso->nsinfo,
-				     is_kallsyms, is_vdso);
+	ret = build_id_cache__add_b(&dso->bid, name, dso->nsinfo,
+				    is_kallsyms, is_vdso, proper_name, root_dir);
+out_free:
+	free(allocated_name);
+	return ret;
 }
 
 static int
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index c19617151670..4e3a1169379b 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -66,10 +66,18 @@ int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi,
 				   struct strlist **result);
 bool build_id_cache__cached(const char *sbuild_id);
 int build_id_cache__add(const char *sbuild_id, const char *name, const char *realname,
-			struct nsinfo *nsi, bool is_kallsyms, bool is_vdso);
-int build_id_cache__add_s(const char *sbuild_id,
-			  const char *name, struct nsinfo *nsi,
-			  bool is_kallsyms, bool is_vdso);
+			struct nsinfo *nsi, bool is_kallsyms, bool is_vdso,
+			const char *proper_name, const char *root_dir);
+int __build_id_cache__add_s(const char *sbuild_id,
+			    const char *name, struct nsinfo *nsi,
+			    bool is_kallsyms, bool is_vdso,
+			    const char *proper_name, const char *root_dir);
+static inline int build_id_cache__add_s(const char *sbuild_id,
+					const char *name, struct nsinfo *nsi,
+					bool is_kallsyms, bool is_vdso)
+{
+	return __build_id_cache__add_s(sbuild_id, name, nsi, is_kallsyms, is_vdso, NULL, NULL);
+}
 int build_id_cache__remove_s(const char *sbuild_id);
 
 extern char buildid_dir[];
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 5c27a4b2e7a7..7e663673f79f 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -31,6 +31,7 @@
 #include "callchain.h"
 #include "branch.h"
 #include "symbol.h"
+#include "util.h"
 #include "../perf.h"
 
 #define CALLCHAIN_PARAM_DEFAULT			\
@@ -266,12 +267,17 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
 	do {
 		/* Framepointer style */
 		if (!strncmp(name, "fp", sizeof("fp"))) {
-			if (!strtok_r(NULL, ",", &saveptr)) {
-				param->record_mode = CALLCHAIN_FP;
-				ret = 0;
-			} else
-				pr_err("callchain: No more arguments "
-				       "needed for --call-graph fp\n");
+			ret = 0;
+			param->record_mode = CALLCHAIN_FP;
+
+			tok = strtok_r(NULL, ",", &saveptr);
+			if (tok) {
+				unsigned long size;
+
+				size = strtoul(tok, &name, 0);
+				if (size < (unsigned) sysctl__max_stack())
+					param->max_stack = size;
+			}
 			break;
 
 		/* Dwarf style */
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 8b95fb3c4d7b..16db965ac995 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1451,7 +1451,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		 * tidq->packet->instr_count represents the number of
 		 * instructions in the current etm packet.
 		 *
-		 * Period instructions (Pi) contains the the number of
+		 * Period instructions (Pi) contains the number of
 		 * instructions executed after the sample point(n) from the
 		 * previous etm packet.  This will always be less than
 		 * etm->instructions_sample_period.
diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c
index f1ab6edba446..613d6ae82663 100644
--- a/tools/perf/util/data-convert-json.c
+++ b/tools/perf/util/data-convert-json.c
@@ -149,6 +149,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct convert_json *c = container_of(tool, struct convert_json, tool);
 	FILE *out = c->out;
 	struct addr_location al, tal;
+	u64 sample_type = __evlist__combined_sample_type(evsel->evlist);
 	u8 cpumode = PERF_RECORD_MISC_USER;
 
 	if (machine__resolve(machine, &al, sample) < 0) {
@@ -168,7 +169,9 @@ static int process_sample_event(struct perf_tool *tool,
 	output_json_key_format(out, true, 3, "pid", "%i", al.thread->pid_);
 	output_json_key_format(out, true, 3, "tid", "%i", al.thread->tid);
 
-	if (al.thread->cpu >= 0)
+	if ((sample_type & PERF_SAMPLE_CPU))
+		output_json_key_format(out, true, 3, "cpu", "%i", sample->cpu);
+	else if (al.thread->cpu >= 0)
 		output_json_key_format(out, true, 3, "cpu", "%i", al.thread->cpu);
 
 	output_json_key_string(out, true, 3, "comm", thread__comm_str(al.thread));
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index caabeac24c69..a7f68c309545 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -3,6 +3,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
+#include <linux/err.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
@@ -481,16 +482,21 @@ int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz)
 
 bool has_kcore_dir(const char *path)
 {
-	char *kcore_dir;
-	int ret;
-
-	if (asprintf(&kcore_dir, "%s/kcore_dir", path) < 0)
-		return false;
-
-	ret = access(kcore_dir, F_OK);
+	struct dirent *d = ERR_PTR(-EINVAL);
+	const char *name = "kcore_dir";
+	DIR *dir = opendir(path);
+	size_t n = strlen(name);
+	bool result = false;
+
+	if (dir) {
+		while (d && !result) {
+			d = readdir(dir);
+			result = d ? strncmp(d->d_name, name, n) : false;
+		}
+		closedir(dir);
+	}
 
-	free(kcore_dir);
-	return !ret;
+	return result;
 }
 
 char *perf_data__kallsyms_name(struct perf_data *data)
@@ -512,6 +518,25 @@ char *perf_data__kallsyms_name(struct perf_data *data)
 	return kallsyms_name;
 }
 
+char *perf_data__guest_kallsyms_name(struct perf_data *data, pid_t machine_pid)
+{
+	char *kallsyms_name;
+	struct stat st;
+
+	if (!data->is_dir)
+		return NULL;
+
+	if (asprintf(&kallsyms_name, "%s/kcore_dir__%d/kallsyms", data->path, machine_pid) < 0)
+		return NULL;
+
+	if (stat(kallsyms_name, &st)) {
+		free(kallsyms_name);
+		return NULL;
+	}
+
+	return kallsyms_name;
+}
+
 bool is_perf_data(const char *path)
 {
 	bool ret = false;
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 7de53d6e2d7f..effcc195d7e9 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -4,6 +4,7 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <unistd.h>
 #include <linux/types.h>
 
 enum perf_data_mode {
@@ -101,5 +102,6 @@ unsigned long perf_data__size(struct perf_data *data);
 int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz);
 bool has_kcore_dir(const char *path);
 char *perf_data__kallsyms_name(struct perf_data *data);
+char *perf_data__guest_kallsyms_name(struct perf_data *data, pid_t machine_pid);
 bool is_perf_data(const char *path);
 #endif /* __PERF_DATA_H */
diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index db964d5a52af..54e4d4495e00 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -495,6 +495,8 @@ int dlfilter__do_filter_event(struct dlfilter *d,
 	ASSIGN(misc);
 	ASSIGN(raw_size);
 	ASSIGN(raw_data);
+	ASSIGN(machine_pid);
+	ASSIGN(vcpu);
 
 	if (sample->branch_stack) {
 		d_sample.brstack_nr = sample->branch_stack->nr;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 97047a11282b..66981c7a9a18 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -227,6 +227,12 @@ struct dso {
 #define dso__for_each_symbol(dso, pos, n)	\
 	symbols__for_each_entry(&(dso)->symbols, pos, n)
 
+#define dsos__for_each_with_build_id(pos, head)	\
+	list_for_each_entry(pos, head, node)	\
+		if (!pos->has_build_id)		\
+			continue;		\
+		else
+
 static inline void dso__set_loaded(struct dso *dso)
 {
 	dso->loaded = true;
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index b97366f77bbf..2bd23e4cf19e 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -23,8 +23,19 @@ static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
 	if (a->ino > b->ino) return -1;
 	if (a->ino < b->ino) return 1;
 
-	if (a->ino_generation > b->ino_generation) return -1;
-	if (a->ino_generation < b->ino_generation) return 1;
+	/*
+	 * Synthesized MMAP events have zero ino_generation, avoid comparing
+	 * them with MMAP events with actual ino_generation.
+	 *
+	 * I found it harmful because the mismatch resulted in a new
+	 * dso that did not have a build ID whereas the original dso did have a
+	 * build ID. The build ID was essential because the object was not found
+	 * otherwise. - Adrian
+	 */
+	if (a->ino_generation && b->ino_generation) {
+		if (a->ino_generation > b->ino_generation) return -1;
+		if (a->ino_generation < b->ino_generation) return 1;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 579e44c59914..5b8cf6a421a4 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -179,7 +179,7 @@ static void perf_env__purge_bpf(struct perf_env *env __maybe_unused)
 
 void perf_env__exit(struct perf_env *env)
 {
-	int i;
+	int i, j;
 
 	perf_env__purge_bpf(env);
 	perf_env__purge_cgroups(env);
@@ -196,6 +196,8 @@ void perf_env__exit(struct perf_env *env)
 	zfree(&env->sibling_threads);
 	zfree(&env->pmu_mappings);
 	zfree(&env->cpu);
+	for (i = 0; i < env->nr_cpu_pmu_caps; i++)
+		zfree(&env->cpu_pmu_caps[i]);
 	zfree(&env->cpu_pmu_caps);
 	zfree(&env->numa_map);
 
@@ -217,11 +219,13 @@ void perf_env__exit(struct perf_env *env)
 	}
 	zfree(&env->hybrid_nodes);
 
-	for (i = 0; i < env->nr_hybrid_cpc_nodes; i++) {
-		zfree(&env->hybrid_cpc_nodes[i].cpu_pmu_caps);
-		zfree(&env->hybrid_cpc_nodes[i].pmu_name);
+	for (i = 0; i < env->nr_pmus_with_caps; i++) {
+		for (j = 0; j < env->pmu_caps[i].nr_caps; j++)
+			zfree(&env->pmu_caps[i].caps[j]);
+		zfree(&env->pmu_caps[i].caps);
+		zfree(&env->pmu_caps[i].pmu_name);
 	}
-	zfree(&env->hybrid_cpc_nodes);
+	zfree(&env->pmu_caps);
 }
 
 void perf_env__init(struct perf_env *env)
@@ -527,3 +531,51 @@ int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 
 	return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
 }
+
+char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
+			     const char *cap)
+{
+	char *cap_eq;
+	int cap_size;
+	char **ptr;
+	int i, j;
+
+	if (!pmu_name || !cap)
+		return NULL;
+
+	cap_size = strlen(cap);
+	cap_eq = zalloc(cap_size + 2);
+	if (!cap_eq)
+		return NULL;
+
+	memcpy(cap_eq, cap, cap_size);
+	cap_eq[cap_size] = '=';
+
+	if (!strcmp(pmu_name, "cpu")) {
+		for (i = 0; i < env->nr_cpu_pmu_caps; i++) {
+			if (!strncmp(env->cpu_pmu_caps[i], cap_eq, cap_size + 1)) {
+				free(cap_eq);
+				return &env->cpu_pmu_caps[i][cap_size + 1];
+			}
+		}
+		goto out;
+	}
+
+	for (i = 0; i < env->nr_pmus_with_caps; i++) {
+		if (strcmp(env->pmu_caps[i].pmu_name, pmu_name))
+			continue;
+
+		ptr = env->pmu_caps[i].caps;
+
+		for (j = 0; j < env->pmu_caps[i].nr_caps; j++) {
+			if (!strncmp(ptr[j], cap_eq, cap_size + 1)) {
+				free(cap_eq);
+				return &ptr[j][cap_size + 1];
+			}
+		}
+	}
+
+out:
+	free(cap_eq);
+	return NULL;
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index a3541f98e1fc..4566c51f2fd9 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -43,10 +43,10 @@ struct hybrid_node {
 	char	*cpus;
 };
 
-struct hybrid_cpc_node {
-	int		nr_cpu_pmu_caps;
+struct pmu_caps {
+	int		nr_caps;
 	unsigned int    max_branches;
-	char            *cpu_pmu_caps;
+	char            **caps;
 	char            *pmu_name;
 };
 
@@ -74,14 +74,14 @@ struct perf_env {
 	int			nr_groups;
 	int			nr_cpu_pmu_caps;
 	int			nr_hybrid_nodes;
-	int			nr_hybrid_cpc_nodes;
+	int			nr_pmus_with_caps;
 	char			*cmdline;
 	const char		**cmdline_argv;
 	char			*sibling_cores;
 	char			*sibling_dies;
 	char			*sibling_threads;
 	char			*pmu_mappings;
-	char			*cpu_pmu_caps;
+	char			**cpu_pmu_caps;
 	struct cpu_topology_map	*cpu;
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
@@ -94,7 +94,7 @@ struct perf_env {
 	struct memory_node	*memory_nodes;
 	unsigned long long	 memory_bsize;
 	struct hybrid_node	*hybrid_nodes;
-	struct hybrid_cpc_node	*hybrid_cpc_nodes;
+	struct pmu_caps		*pmu_caps;
 #ifdef HAVE_LIBBPF_SUPPORT
 	/*
 	 * bpf_info_lock protects bpf rbtrees. This is needed because the
@@ -172,4 +172,6 @@ bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
+char *perf_env__find_pmu_cap(struct perf_env *env, const char *pmu_name,
+			     const char *cap);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0476bb3a4188..1fa14598b916 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -76,6 +76,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
 	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
 	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
+	[PERF_RECORD_FINISHED_INIT]		= "FINISHED_INIT",
 };
 
 const char *perf_event__name(unsigned int id)
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index cdd72e05fd28..a7b0931d5137 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -148,6 +148,8 @@ struct perf_sample {
 	u64 code_page_size;
 	u64 cgroup;
 	u32 flags;
+	u32 machine_pid;
+	u32 vcpu;
 	u16 insn_len;
 	u8  cpumode;
 	u16 misc;
@@ -482,4 +484,25 @@ void arch_perf_synthesize_sample_weight(const struct perf_sample *data, __u64 *a
 const char *arch_perf_header_entry(const char *se_header);
 int arch_support_sort_key(const char *sort_key);
 
+static inline bool perf_event_header__cpumode_is_guest(u8 cpumode)
+{
+	return cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
+	       cpumode == PERF_RECORD_MISC_GUEST_USER;
+}
+
+static inline bool perf_event_header__misc_is_guest(u16 misc)
+{
+	return perf_event_header__cpumode_is_guest(misc & PERF_RECORD_MISC_CPUMODE_MASK);
+}
+
+static inline bool perf_event_header__is_guest(const struct perf_event_header *header)
+{
+	return perf_event_header__misc_is_guest(header->misc);
+}
+
+static inline bool perf_event__is_guest(const union perf_event *event)
+{
+	return perf_event_header__is_guest(&event->header);
+}
+
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 48af7d379d82..48167f3941a6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -309,7 +309,7 @@ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide)
 	return evsel;
 }
 
-static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
+int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs)
 {
 	struct evsel *evsel, *n;
 	LIST_HEAD(head);
@@ -342,9 +342,14 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a
 	return evlist__add_attrs(evlist, attrs, nr_attrs);
 }
 
-__weak int arch_evlist__add_default_attrs(struct evlist *evlist __maybe_unused)
+__weak int arch_evlist__add_default_attrs(struct evlist *evlist,
+					  struct perf_event_attr *attrs,
+					  size_t nr_attrs)
 {
-	return 0;
+	if (!nr_attrs)
+		return 0;
+
+	return __evlist__add_default_attrs(evlist, attrs, nr_attrs);
 }
 
 struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id)
@@ -1244,34 +1249,8 @@ bool evlist__valid_read_format(struct evlist *evlist)
 u16 evlist__id_hdr_size(struct evlist *evlist)
 {
 	struct evsel *first = evlist__first(evlist);
-	struct perf_sample *data;
-	u64 sample_type;
-	u16 size = 0;
-
-	if (!first->core.attr.sample_id_all)
-		goto out;
-
-	sample_type = first->core.attr.sample_type;
-
-	if (sample_type & PERF_SAMPLE_TID)
-		size += sizeof(data->tid) * 2;
-
-       if (sample_type & PERF_SAMPLE_TIME)
-		size += sizeof(data->time);
-
-	if (sample_type & PERF_SAMPLE_ID)
-		size += sizeof(data->id);
 
-	if (sample_type & PERF_SAMPLE_STREAM_ID)
-		size += sizeof(data->stream_id);
-
-	if (sample_type & PERF_SAMPLE_CPU)
-		size += sizeof(data->cpu) * 2;
-
-	if (sample_type & PERF_SAMPLE_IDENTIFIER)
-		size += sizeof(data->id);
-out:
-	return size;
+	return first->core.attr.sample_id_all ? evsel__id_hdr_size(first) : 0;
 }
 
 bool evlist__valid_sample_id_all(struct evlist *evlist)
@@ -1533,10 +1512,22 @@ int evlist__start_workload(struct evlist *evlist)
 int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample)
 {
 	struct evsel *evsel = evlist__event2evsel(evlist, event);
+	int ret;
 
 	if (!evsel)
 		return -EFAULT;
-	return evsel__parse_sample(evsel, event, sample);
+	ret = evsel__parse_sample(evsel, event, sample);
+	if (ret)
+		return ret;
+	if (perf_guest && sample->id) {
+		struct perf_sample_id *sid = evlist__id2sid(evlist, sample->id);
+
+		if (sid) {
+			sample->machine_pid = sid->machine_pid;
+			sample->vcpu = sid->vcpu.cpu;
+		}
+	}
+	return 0;
 }
 
 int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 1bde9ccf4e7d..351ba2887a79 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -104,13 +104,18 @@ static inline int evlist__add_default(struct evlist *evlist)
 	return __evlist__add_default(evlist, true);
 }
 
+int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs);
+
 int __evlist__add_default_attrs(struct evlist *evlist,
 				     struct perf_event_attr *attrs, size_t nr_attrs);
 
+int arch_evlist__add_default_attrs(struct evlist *evlist,
+				   struct perf_event_attr *attrs,
+				   size_t nr_attrs);
+
 #define evlist__add_default_attrs(evlist, array) \
-	__evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
+	arch_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
-int arch_evlist__add_default_attrs(struct evlist *evlist);
 struct evsel *arch_evlist__leader(struct list_head *list);
 
 int evlist__add_dummy(struct evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 094b0a9c0bc0..4852089e1d79 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -594,9 +594,14 @@ static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size)
 	return r;
 }
 
+int __weak arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
+{
+	return scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config));
+}
+
 static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 {
-	int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config));
+	int r = arch_evsel__hw_name(evsel, bf, size);
 	return r + evsel__add_modifiers(evsel, bf + r, size - r);
 }
 
@@ -1092,6 +1097,11 @@ void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_un
 {
 }
 
+void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused,
+				    struct perf_event_attr *attr __maybe_unused)
+{
+}
+
 static void evsel__set_default_freq_period(struct record_opts *opts,
 					   struct perf_event_attr *attr)
 {
@@ -1375,6 +1385,8 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 
 	if (evsel__is_offcpu_event(evsel))
 		evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES;
+
+	arch__post_evsel_config(evsel, attr);
 }
 
 int evsel__set_filter(struct evsel *evsel, const char *filter)
@@ -2358,6 +2370,7 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 	data->misc    = event->header.misc;
 	data->id = -1ULL;
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
+	data->vcpu = -1;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->core.attr.sample_id_all)
@@ -2717,6 +2730,32 @@ int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
 	return 0;
 }
 
+u16 evsel__id_hdr_size(struct evsel *evsel)
+{
+	u64 sample_type = evsel->core.attr.sample_type;
+	u16 size = 0;
+
+	if (sample_type & PERF_SAMPLE_TID)
+		size += sizeof(u64);
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		size += sizeof(u64);
+
+	if (sample_type & PERF_SAMPLE_ID)
+		size += sizeof(u64);
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		size += sizeof(u64);
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		size += sizeof(u64);
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(u64);
+
+	return size;
+}
+
 struct tep_format_field *evsel__field(struct evsel *evsel, const char *name)
 {
 	return tep_find_field(evsel->tp_format, name);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 73ea48e94079..d927713b513e 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -271,6 +271,7 @@ extern const char *const evsel__hw_names[PERF_COUNT_HW_MAX];
 extern const char *const evsel__sw_names[PERF_COUNT_SW_MAX];
 extern char *evsel__bpf_counter_events;
 bool evsel__match_bpf_counter_events(const char *name);
+int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size);
 
 int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size);
 const char *evsel__name(struct evsel *evsel);
@@ -297,6 +298,7 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
 
 void arch_evsel__set_sample_weight(struct evsel *evsel);
 void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr);
+void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr);
 
 int evsel__set_filter(struct evsel *evsel, const char *filter);
 int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
@@ -380,6 +382,8 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event,
 				  u64 *timestamp);
 
+u16 evsel__id_hdr_size(struct evsel *evsel);
+
 static inline struct evsel *evsel__next(struct evsel *evsel)
 {
 	return list_entry(evsel->core.node.next, struct evsel, core.node);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 675f318ce7c1..c15a9852fa41 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -12,6 +12,7 @@
 #include "expr-bison.h"
 #include "expr-flex.h"
 #include "smt.h"
+#include "tsc.h"
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
@@ -402,6 +403,13 @@ double expr_id_data__source_count(const struct expr_id_data *data)
 	return data->val.source_count;
 }
 
+#if !defined(__i386__) && !defined(__x86_64__)
+double arch_get_tsc_freq(void)
+{
+	return 0.0;
+}
+#endif
+
 double expr__get_literal(const char *literal)
 {
 	static struct cpu_topology *topology;
@@ -417,6 +425,11 @@ double expr__get_literal(const char *literal)
 		goto out;
 	}
 
+	if (!strcasecmp("#system_tsc_freq", literal)) {
+		result = arch_get_tsc_freq();
+		goto out;
+	}
+
 	/*
 	 * Assume that topology strings are consistent, such as CPUs "0-1"
 	 * wouldn't be listed as "0,1", and so after deduplication the number of
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index aed49806a09b..953338b9e887 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -30,7 +30,11 @@
 
 #define BUILD_ID_URANDOM /* different uuid for each run */
 
-#ifdef HAVE_LIBCRYPTO
+// FIXME, remove this and fix the deprecation warnings before its removed and
+// We'll break for good here...
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+
+#ifdef HAVE_LIBCRYPTO_SUPPORT
 
 #define BUILD_ID_MD5
 #undef BUILD_ID_SHA	/* does not seem to work well when linked with Java */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6ad629db63b7..c30c29c51410 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1512,18 +1512,13 @@ static int write_compressed(struct feat_fd *ff __maybe_unused,
 	return do_write(ff, &(ff->ph->env.comp_mmap_len), sizeof(ff->ph->env.comp_mmap_len));
 }
 
-static int write_per_cpu_pmu_caps(struct feat_fd *ff, struct perf_pmu *pmu,
-				  bool write_pmu)
+static int __write_pmu_caps(struct feat_fd *ff, struct perf_pmu *pmu,
+			    bool write_pmu)
 {
 	struct perf_pmu_caps *caps = NULL;
-	int nr_caps;
 	int ret;
 
-	nr_caps = perf_pmu__caps_parse(pmu);
-	if (nr_caps < 0)
-		return nr_caps;
-
-	ret = do_write(ff, &nr_caps, sizeof(nr_caps));
+	ret = do_write(ff, &pmu->nr_caps, sizeof(pmu->nr_caps));
 	if (ret < 0)
 		return ret;
 
@@ -1550,33 +1545,60 @@ static int write_cpu_pmu_caps(struct feat_fd *ff,
 			      struct evlist *evlist __maybe_unused)
 {
 	struct perf_pmu *cpu_pmu = perf_pmu__find("cpu");
+	int ret;
 
 	if (!cpu_pmu)
 		return -ENOENT;
 
-	return write_per_cpu_pmu_caps(ff, cpu_pmu, false);
+	ret = perf_pmu__caps_parse(cpu_pmu);
+	if (ret < 0)
+		return ret;
+
+	return __write_pmu_caps(ff, cpu_pmu, false);
 }
 
-static int write_hybrid_cpu_pmu_caps(struct feat_fd *ff,
-				     struct evlist *evlist __maybe_unused)
+static int write_pmu_caps(struct feat_fd *ff,
+			  struct evlist *evlist __maybe_unused)
 {
-	struct perf_pmu *pmu;
-	u32 nr_pmu = perf_pmu__hybrid_pmu_num();
+	struct perf_pmu *pmu = NULL;
+	int nr_pmu = 0;
 	int ret;
 
-	if (nr_pmu == 0)
-		return -ENOENT;
+	while ((pmu = perf_pmu__scan(pmu))) {
+		if (!pmu->name || !strcmp(pmu->name, "cpu") ||
+		    perf_pmu__caps_parse(pmu) <= 0)
+			continue;
+		nr_pmu++;
+	}
 
 	ret = do_write(ff, &nr_pmu, sizeof(nr_pmu));
 	if (ret < 0)
 		return ret;
 
+	if (!nr_pmu)
+		return 0;
+
+	/*
+	 * Write hybrid pmu caps first to maintain compatibility with
+	 * older perf tool.
+	 */
+	pmu = NULL;
 	perf_pmu__for_each_hybrid_pmu(pmu) {
-		ret = write_per_cpu_pmu_caps(ff, pmu, true);
+		ret = __write_pmu_caps(ff, pmu, true);
 		if (ret < 0)
 			return ret;
 	}
 
+	pmu = NULL;
+	while ((pmu = perf_pmu__scan(pmu))) {
+		if (!pmu->name || !strcmp(pmu->name, "cpu") ||
+		    !pmu->nr_caps || perf_pmu__is_hybrid(pmu->name))
+			continue;
+
+		ret = __write_pmu_caps(ff, pmu, true);
+		if (ret < 0)
+			return ret;
+	}
 	return 0;
 }
 
@@ -2051,32 +2073,20 @@ static void print_compressed(struct feat_fd *ff, FILE *fp)
 		ff->ph->env.comp_level, ff->ph->env.comp_ratio);
 }
 
-static void print_per_cpu_pmu_caps(FILE *fp, int nr_caps, char *cpu_pmu_caps,
-				   char *pmu_name)
+static void __print_pmu_caps(FILE *fp, int nr_caps, char **caps, char *pmu_name)
 {
-	const char *delimiter;
-	char *str, buf[128];
+	const char *delimiter = "";
+	int i;
 
 	if (!nr_caps) {
-		if (!pmu_name)
-			fprintf(fp, "# cpu pmu capabilities: not available\n");
-		else
-			fprintf(fp, "# %s pmu capabilities: not available\n", pmu_name);
+		fprintf(fp, "# %s pmu capabilities: not available\n", pmu_name);
 		return;
 	}
 
-	if (!pmu_name)
-		scnprintf(buf, sizeof(buf), "# cpu pmu capabilities: ");
-	else
-		scnprintf(buf, sizeof(buf), "# %s pmu capabilities: ", pmu_name);
-
-	delimiter = buf;
-
-	str = cpu_pmu_caps;
-	while (nr_caps--) {
-		fprintf(fp, "%s%s", delimiter, str);
+	fprintf(fp, "# %s pmu capabilities: ", pmu_name);
+	for (i = 0; i < nr_caps; i++) {
+		fprintf(fp, "%s%s", delimiter, caps[i]);
 		delimiter = ", ";
-		str += strlen(str) + 1;
 	}
 
 	fprintf(fp, "\n");
@@ -2084,19 +2094,18 @@ static void print_per_cpu_pmu_caps(FILE *fp, int nr_caps, char *cpu_pmu_caps,
 
 static void print_cpu_pmu_caps(struct feat_fd *ff, FILE *fp)
 {
-	print_per_cpu_pmu_caps(fp, ff->ph->env.nr_cpu_pmu_caps,
-			       ff->ph->env.cpu_pmu_caps, NULL);
+	__print_pmu_caps(fp, ff->ph->env.nr_cpu_pmu_caps,
+			 ff->ph->env.cpu_pmu_caps, (char *)"cpu");
 }
 
-static void print_hybrid_cpu_pmu_caps(struct feat_fd *ff, FILE *fp)
+static void print_pmu_caps(struct feat_fd *ff, FILE *fp)
 {
-	struct hybrid_cpc_node *n;
+	struct pmu_caps *pmu_caps;
 
-	for (int i = 0; i < ff->ph->env.nr_hybrid_cpc_nodes; i++) {
-		n = &ff->ph->env.hybrid_cpc_nodes[i];
-		print_per_cpu_pmu_caps(fp, n->nr_cpu_pmu_caps,
-				       n->cpu_pmu_caps,
-				       n->pmu_name);
+	for (int i = 0; i < ff->ph->env.nr_pmus_with_caps; i++) {
+		pmu_caps = &ff->ph->env.pmu_caps[i];
+		__print_pmu_caps(fp, pmu_caps->nr_caps, pmu_caps->caps,
+				 pmu_caps->pmu_name);
 	}
 }
 
@@ -3207,28 +3216,26 @@ static int process_compressed(struct feat_fd *ff,
 	return 0;
 }
 
-static int process_per_cpu_pmu_caps(struct feat_fd *ff, int *nr_cpu_pmu_caps,
-				    char **cpu_pmu_caps,
-				    unsigned int *max_branches)
+static int __process_pmu_caps(struct feat_fd *ff, int *nr_caps,
+			      char ***caps, unsigned int *max_branches)
 {
-	char *name, *value;
-	struct strbuf sb;
-	u32 nr_caps;
+	char *name, *value, *ptr;
+	u32 nr_pmu_caps, i;
+
+	*nr_caps = 0;
+	*caps = NULL;
 
-	if (do_read_u32(ff, &nr_caps))
+	if (do_read_u32(ff, &nr_pmu_caps))
 		return -1;
 
-	if (!nr_caps) {
-		pr_debug("cpu pmu capabilities not available\n");
+	if (!nr_pmu_caps)
 		return 0;
-	}
-
-	*nr_cpu_pmu_caps = nr_caps;
 
-	if (strbuf_init(&sb, 128) < 0)
+	*caps = zalloc(sizeof(char *) * nr_pmu_caps);
+	if (!*caps)
 		return -1;
 
-	while (nr_caps--) {
+	for (i = 0; i < nr_pmu_caps; i++) {
 		name = do_read_string(ff);
 		if (!name)
 			goto error;
@@ -3237,12 +3244,10 @@ static int process_per_cpu_pmu_caps(struct feat_fd *ff, int *nr_cpu_pmu_caps,
 		if (!value)
 			goto free_name;
 
-		if (strbuf_addf(&sb, "%s=%s", name, value) < 0)
+		if (asprintf(&ptr, "%s=%s", name, value) < 0)
 			goto free_value;
 
-		/* include a NULL character at the end */
-		if (strbuf_add(&sb, "", 1) < 0)
-			goto free_value;
+		(*caps)[i] = ptr;
 
 		if (!strcmp(name, "branches"))
 			*max_branches = atoi(value);
@@ -3250,7 +3255,7 @@ static int process_per_cpu_pmu_caps(struct feat_fd *ff, int *nr_cpu_pmu_caps,
 		free(value);
 		free(name);
 	}
-	*cpu_pmu_caps = strbuf_detach(&sb, NULL);
+	*nr_caps = nr_pmu_caps;
 	return 0;
 
 free_value:
@@ -3258,64 +3263,76 @@ free_value:
 free_name:
 	free(name);
 error:
-	strbuf_release(&sb);
+	for (; i > 0; i--)
+		free((*caps)[i - 1]);
+	free(*caps);
+	*caps = NULL;
+	*nr_caps = 0;
 	return -1;
 }
 
 static int process_cpu_pmu_caps(struct feat_fd *ff,
 				void *data __maybe_unused)
 {
-	return process_per_cpu_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps,
-					&ff->ph->env.cpu_pmu_caps,
-					&ff->ph->env.max_branches);
+	int ret = __process_pmu_caps(ff, &ff->ph->env.nr_cpu_pmu_caps,
+				     &ff->ph->env.cpu_pmu_caps,
+				     &ff->ph->env.max_branches);
+
+	if (!ret && !ff->ph->env.cpu_pmu_caps)
+		pr_debug("cpu pmu capabilities not available\n");
+	return ret;
 }
 
-static int process_hybrid_cpu_pmu_caps(struct feat_fd *ff,
-				       void *data __maybe_unused)
+static int process_pmu_caps(struct feat_fd *ff, void *data __maybe_unused)
 {
-	struct hybrid_cpc_node *nodes;
+	struct pmu_caps *pmu_caps;
 	u32 nr_pmu, i;
 	int ret;
+	int j;
 
 	if (do_read_u32(ff, &nr_pmu))
 		return -1;
 
 	if (!nr_pmu) {
-		pr_debug("hybrid cpu pmu capabilities not available\n");
+		pr_debug("pmu capabilities not available\n");
 		return 0;
 	}
 
-	nodes = zalloc(sizeof(*nodes) * nr_pmu);
-	if (!nodes)
+	pmu_caps = zalloc(sizeof(*pmu_caps) * nr_pmu);
+	if (!pmu_caps)
 		return -ENOMEM;
 
 	for (i = 0; i < nr_pmu; i++) {
-		struct hybrid_cpc_node *n = &nodes[i];
-
-		ret = process_per_cpu_pmu_caps(ff, &n->nr_cpu_pmu_caps,
-					       &n->cpu_pmu_caps,
-					       &n->max_branches);
+		ret = __process_pmu_caps(ff, &pmu_caps[i].nr_caps,
+					 &pmu_caps[i].caps,
+					 &pmu_caps[i].max_branches);
 		if (ret)
 			goto err;
 
-		n->pmu_name = do_read_string(ff);
-		if (!n->pmu_name) {
+		pmu_caps[i].pmu_name = do_read_string(ff);
+		if (!pmu_caps[i].pmu_name) {
 			ret = -1;
 			goto err;
 		}
+		if (!pmu_caps[i].nr_caps) {
+			pr_debug("%s pmu capabilities not available\n",
+				 pmu_caps[i].pmu_name);
+		}
 	}
 
-	ff->ph->env.nr_hybrid_cpc_nodes = nr_pmu;
-	ff->ph->env.hybrid_cpc_nodes = nodes;
+	ff->ph->env.nr_pmus_with_caps = nr_pmu;
+	ff->ph->env.pmu_caps = pmu_caps;
 	return 0;
 
 err:
 	for (i = 0; i < nr_pmu; i++) {
-		free(nodes[i].cpu_pmu_caps);
-		free(nodes[i].pmu_name);
+		for (j = 0; j < pmu_caps[i].nr_caps; j++)
+			free(pmu_caps[i].caps[j]);
+		free(pmu_caps[i].caps);
+		free(pmu_caps[i].pmu_name);
 	}
 
-	free(nodes);
+	free(pmu_caps);
 	return ret;
 }
 
@@ -3381,7 +3398,7 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(CPU_PMU_CAPS,	cpu_pmu_caps,	false),
 	FEAT_OPR(CLOCK_DATA,	clock_data,	false),
 	FEAT_OPN(HYBRID_TOPOLOGY,	hybrid_topology,	true),
-	FEAT_OPR(HYBRID_CPU_PMU_CAPS,	hybrid_cpu_pmu_caps,	false),
+	FEAT_OPR(PMU_CAPS,	pmu_caps,	false),
 };
 
 struct header_print_data {
@@ -4363,6 +4380,9 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 	struct evsel *evsel;
 	struct perf_cpu_map *map;
 
+	if (dump_trace)
+		perf_event__fprintf_event_update(event, stdout);
+
 	if (!pevlist || *pevlist == NULL)
 		return -EINVAL;
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 56916dabce7b..2d5e601ba60f 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -46,7 +46,7 @@ enum {
 	HEADER_CPU_PMU_CAPS,
 	HEADER_CLOCK_DATA,
 	HEADER_HYBRID_TOPOLOGY,
-	HEADER_HYBRID_CPU_PMU_CAPS,
+	HEADER_PMU_CAPS,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 62b2f375a94d..d5e9fc8106dd 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -74,10 +74,12 @@ struct intel_pt {
 	bool data_queued;
 	bool est_tsc;
 	bool sync_switch;
+	bool sync_switch_not_supported;
 	bool mispred_all;
 	bool use_thread_stack;
 	bool callstack;
 	bool cap_event_trace;
+	bool have_guest_sideband;
 	unsigned int br_stack_sz;
 	unsigned int br_stack_sz_plus;
 	int have_sched_switch;
@@ -195,6 +197,9 @@ struct intel_pt_queue {
 	struct thread *guest_thread;
 	struct thread *unknown_guest_thread;
 	pid_t guest_machine_pid;
+	pid_t guest_pid;
+	pid_t guest_tid;
+	int vcpu;
 	bool exclude_kernel;
 	bool have_sample;
 	u64 time;
@@ -685,7 +690,7 @@ static int intel_pt_get_guest(struct intel_pt_queue *ptq)
 	struct machine *machine;
 	pid_t pid = ptq->pid <= 0 ? DEFAULT_GUEST_KERNEL_ID : ptq->pid;
 
-	if (ptq->guest_machine && pid == ptq->guest_machine_pid)
+	if (ptq->guest_machine && pid == ptq->guest_machine->pid)
 		return 0;
 
 	ptq->guest_machine = NULL;
@@ -705,7 +710,6 @@ static int intel_pt_get_guest(struct intel_pt_queue *ptq)
 		return -1;
 
 	ptq->guest_machine = machine;
-	ptq->guest_machine_pid = pid;
 
 	return 0;
 }
@@ -759,28 +763,44 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	cpumode = intel_pt_nr_cpumode(ptq, *ip, nr);
 
 	if (nr) {
-		if ((!symbol_conf.guest_code && cpumode != PERF_RECORD_MISC_GUEST_KERNEL) ||
-		    intel_pt_get_guest(ptq))
+		if (ptq->pt->have_guest_sideband) {
+			if (!ptq->guest_machine || ptq->guest_machine_pid != ptq->pid) {
+				intel_pt_log("ERROR: guest sideband but no guest machine\n");
+				return -EINVAL;
+			}
+		} else if ((!symbol_conf.guest_code && cpumode != PERF_RECORD_MISC_GUEST_KERNEL) ||
+			   intel_pt_get_guest(ptq)) {
+			intel_pt_log("ERROR: no guest machine\n");
 			return -EINVAL;
+		}
 		machine = ptq->guest_machine;
 		thread = ptq->guest_thread;
 		if (!thread) {
-			if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL)
+			if (cpumode != PERF_RECORD_MISC_GUEST_KERNEL) {
+				intel_pt_log("ERROR: no guest thread\n");
 				return -EINVAL;
+			}
 			thread = ptq->unknown_guest_thread;
 		}
 	} else {
 		thread = ptq->thread;
 		if (!thread) {
-			if (cpumode != PERF_RECORD_MISC_KERNEL)
+			if (cpumode != PERF_RECORD_MISC_KERNEL) {
+				intel_pt_log("ERROR: no thread\n");
 				return -EINVAL;
+			}
 			thread = ptq->pt->unknown_thread;
 		}
 	}
 
 	while (1) {
-		if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso)
+		if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso) {
+			if (al.map)
+				intel_pt_log("ERROR: thread has no dso for %#" PRIx64 "\n", *ip);
+			else
+				intel_pt_log("ERROR: thread has no map for %#" PRIx64 "\n", *ip);
 			return -EINVAL;
+		}
 
 		if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
 		    dso__data_status_seen(al.map->dso,
@@ -821,8 +841,12 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 			len = dso__data_read_offset(al.map->dso, machine,
 						    offset, buf,
 						    INTEL_PT_INSN_BUF_SZ);
-			if (len <= 0)
+			if (len <= 0) {
+				intel_pt_log("ERROR: failed to read at %" PRIu64 " ", offset);
+				if (intel_pt_enable_logging)
+					dso__fprintf(al.map->dso, intel_pt_log_fp());
 				return -EINVAL;
+			}
 
 			if (intel_pt_get_insn(buf, len, x86_64, intel_pt_insn))
 				return -EINVAL;
@@ -1370,6 +1394,55 @@ static void intel_pt_first_timestamp(struct intel_pt *pt, u64 timestamp)
 	}
 }
 
+static int intel_pt_get_guest_from_sideband(struct intel_pt_queue *ptq)
+{
+	struct machines *machines = &ptq->pt->session->machines;
+	struct machine *machine;
+	pid_t machine_pid = ptq->pid;
+	pid_t tid;
+	int vcpu;
+
+	if (machine_pid <= 0)
+		return 0; /* Not a guest machine */
+
+	machine = machines__find(machines, machine_pid);
+	if (!machine)
+		return 0; /* Not a guest machine */
+
+	if (ptq->guest_machine != machine) {
+		ptq->guest_machine = NULL;
+		thread__zput(ptq->guest_thread);
+		thread__zput(ptq->unknown_guest_thread);
+
+		ptq->unknown_guest_thread = machine__find_thread(machine, 0, 0);
+		if (!ptq->unknown_guest_thread)
+			return -1;
+		ptq->guest_machine = machine;
+	}
+
+	vcpu = ptq->thread ? ptq->thread->guest_cpu : -1;
+	if (vcpu < 0)
+		return -1;
+
+	tid = machine__get_current_tid(machine, vcpu);
+
+	if (ptq->guest_thread && ptq->guest_thread->tid != tid)
+		thread__zput(ptq->guest_thread);
+
+	if (!ptq->guest_thread) {
+		ptq->guest_thread = machine__find_thread(machine, -1, tid);
+		if (!ptq->guest_thread)
+			return -1;
+	}
+
+	ptq->guest_machine_pid = machine_pid;
+	ptq->guest_pid = ptq->guest_thread->pid_;
+	ptq->guest_tid = tid;
+	ptq->vcpu = vcpu;
+
+	return 0;
+}
+
 static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
 				     struct auxtrace_queue *queue)
 {
@@ -1390,6 +1463,13 @@ static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
 		if (queue->cpu == -1)
 			ptq->cpu = ptq->thread->cpu;
 	}
+
+	if (pt->have_guest_sideband && intel_pt_get_guest_from_sideband(ptq)) {
+		ptq->guest_machine_pid = 0;
+		ptq->guest_pid = -1;
+		ptq->guest_tid = -1;
+		ptq->vcpu = -1;
+	}
 }
 
 static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
@@ -1577,6 +1657,17 @@ static void intel_pt_prep_a_sample(struct intel_pt_queue *ptq,
 
 	sample->pid = ptq->pid;
 	sample->tid = ptq->tid;
+
+	if (ptq->pt->have_guest_sideband) {
+		if ((ptq->state->from_ip && ptq->state->from_nr) ||
+		    (ptq->state->to_ip && ptq->state->to_nr)) {
+			sample->pid = ptq->guest_pid;
+			sample->tid = ptq->guest_tid;
+			sample->machine_pid = ptq->guest_machine_pid;
+			sample->vcpu = ptq->vcpu;
+		}
+	}
+
 	sample->cpu = ptq->cpu;
 	sample->insn_len = ptq->insn_len;
 	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
@@ -2324,7 +2415,8 @@ static int intel_pt_synth_iflag_chg_sample(struct intel_pt_queue *ptq)
 }
 
 static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
-				pid_t pid, pid_t tid, u64 ip, u64 timestamp)
+				pid_t pid, pid_t tid, u64 ip, u64 timestamp,
+				pid_t machine_pid, int vcpu)
 {
 	union perf_event event;
 	char msg[MAX_AUXTRACE_ERROR_MSG];
@@ -2341,8 +2433,9 @@ static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
 
 	intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG);
 
-	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
-			     code, cpu, pid, tid, ip, msg, timestamp);
+	auxtrace_synth_guest_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+				   code, cpu, pid, tid, ip, msg, timestamp,
+				   machine_pid, vcpu);
 
 	err = perf_session__deliver_synth_event(pt->session, &event, NULL);
 	if (err)
@@ -2357,11 +2450,22 @@ static int intel_ptq_synth_error(struct intel_pt_queue *ptq,
 {
 	struct intel_pt *pt = ptq->pt;
 	u64 tm = ptq->timestamp;
+	pid_t machine_pid = 0;
+	pid_t pid = ptq->pid;
+	pid_t tid = ptq->tid;
+	int vcpu = -1;
 
 	tm = pt->timeless_decoding ? 0 : tsc_to_perf_time(tm, &pt->tc);
 
-	return intel_pt_synth_error(pt, state->err, ptq->cpu, ptq->pid,
-				    ptq->tid, state->from_ip, tm);
+	if (pt->have_guest_sideband && state->from_nr) {
+		machine_pid = ptq->guest_machine_pid;
+		vcpu = ptq->vcpu;
+		pid = ptq->guest_pid;
+		tid = ptq->guest_tid;
+	}
+
+	return intel_pt_synth_error(pt, state->err, ptq->cpu, pid, tid,
+				    state->from_ip, tm, machine_pid, vcpu);
 }
 
 static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
@@ -2624,6 +2728,9 @@ static void intel_pt_enable_sync_switch(struct intel_pt *pt)
 {
 	unsigned int i;
 
+	if (pt->sync_switch_not_supported)
+		return;
+
 	pt->sync_switch = true;
 
 	for (i = 0; i < pt->queues.nr_queues; i++) {
@@ -2635,6 +2742,23 @@ static void intel_pt_enable_sync_switch(struct intel_pt *pt)
 	}
 }
 
+static void intel_pt_disable_sync_switch(struct intel_pt *pt)
+{
+	unsigned int i;
+
+	pt->sync_switch = false;
+
+	for (i = 0; i < pt->queues.nr_queues; i++) {
+		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+		struct intel_pt_queue *ptq = queue->priv;
+
+		if (ptq) {
+			ptq->sync_switch = false;
+			intel_pt_next_tid(pt, ptq);
+		}
+	}
+}
+
 /*
  * To filter against time ranges, it is only necessary to look at the next start
  * or end time.
@@ -2928,7 +3052,8 @@ static int intel_pt_process_timeless_sample(struct intel_pt *pt,
 static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
 {
 	return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu,
-				    sample->pid, sample->tid, 0, sample->time);
+				    sample->pid, sample->tid, 0, sample->time,
+				    sample->machine_pid, sample->vcpu);
 }
 
 static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
@@ -3066,6 +3191,33 @@ static int intel_pt_context_switch_in(struct intel_pt *pt,
 	return machine__set_current_tid(pt->machine, cpu, pid, tid);
 }
 
+static int intel_pt_guest_context_switch(struct intel_pt *pt,
+					 union perf_event *event,
+					 struct perf_sample *sample)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	struct machines *machines = &pt->session->machines;
+	struct machine *machine = machines__find(machines, sample->machine_pid);
+
+	pt->have_guest_sideband = true;
+
+	/*
+	 * sync_switch cannot handle guest machines at present, so just disable
+	 * it.
+	 */
+	pt->sync_switch_not_supported = true;
+	if (pt->sync_switch)
+		intel_pt_disable_sync_switch(pt);
+
+	if (out)
+		return 0;
+
+	if (!machine)
+		return -EINVAL;
+
+	return machine__set_current_tid(machine, sample->vcpu, sample->pid, sample->tid);
+}
+
 static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
 				   struct perf_sample *sample)
 {
@@ -3073,6 +3225,9 @@ static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
 	pid_t pid, tid;
 	int cpu, ret;
 
+	if (perf_event__is_guest(event))
+		return intel_pt_guest_context_switch(pt, event, sample);
+
 	cpu = sample->cpu;
 
 	if (pt->have_sched_switch == 3) {
diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h
new file mode 100644
index 000000000000..320c0a6d2e08
--- /dev/null
+++ b/tools/perf/util/kwork.h
@@ -0,0 +1,257 @@
+#ifndef PERF_UTIL_KWORK_H
+#define PERF_UTIL_KWORK_H
+
+#include "perf.h"
+
+#include "util/tool.h"
+#include "util/event.h"
+#include "util/evlist.h"
+#include "util/session.h"
+#include "util/time-utils.h"
+
+#include <linux/list.h>
+#include <linux/bitmap.h>
+
+enum kwork_class_type {
+	KWORK_CLASS_IRQ,
+	KWORK_CLASS_SOFTIRQ,
+	KWORK_CLASS_WORKQUEUE,
+	KWORK_CLASS_MAX,
+};
+
+enum kwork_report_type {
+	KWORK_REPORT_RUNTIME,
+	KWORK_REPORT_LATENCY,
+	KWORK_REPORT_TIMEHIST,
+};
+
+enum kwork_trace_type {
+	KWORK_TRACE_RAISE,
+	KWORK_TRACE_ENTRY,
+	KWORK_TRACE_EXIT,
+	KWORK_TRACE_MAX,
+};
+
+/*
+ * data structure:
+ *
+ *                 +==================+ +============+ +======================+
+ *                 |      class       | |    work    | |         atom         |
+ *                 +==================+ +============+ +======================+
+ * +------------+  |  +-----+         | |  +------+  | |  +-------+   +-----+ |
+ * | perf_kwork | +-> | irq | --------|+-> | eth0 | --+-> | raise | - | ... | --+   +-----------+
+ * +-----+------+ ||  +-----+         |||  +------+  |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  |||            |||                      | +-> | atom_page |
+ *       |        ||                  |||            |||  +-------+   +-----+ |     |           |
+ *       |  class_list                |||            |+-> | entry | - | ... | ----> |           |
+ *       |        ||                  |||            |||  +-------+   +-----+ |     |           |
+ *       |        ||                  |||            |||                      | +-> |           |
+ *       |        ||                  |||            |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  |||            |+-> | exit  | - | ... | --+   +-----+-----+
+ *       |        ||                  |||            | |  +-------+   +-----+ |           |
+ *       |        ||                  |||            | |                      |           |
+ *       |        ||                  |||  +-----+   | |                      |           |
+ *       |        ||                  |+-> | ... |   | |                      |           |
+ *       |        ||                  | |  +-----+   | |                      |           |
+ *       |        ||                  | |            | |                      |           |
+ *       |        ||  +---------+     | |  +-----+   | |  +-------+   +-----+ |           |
+ *       |        +-> | softirq | -------> | RCU | ---+-> | raise | - | ... | --+   +-----+-----+
+ *       |        ||  +---------+     | |  +-----+   |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  | |            |||                      | +-> | atom_page |
+ *       |        ||                  | |            |||  +-------+   +-----+ |     |           |
+ *       |        ||                  | |            |+-> | entry | - | ... | ----> |           |
+ *       |        ||                  | |            |||  +-------+   +-----+ |     |           |
+ *       |        ||                  | |            |||                      | +-> |           |
+ *       |        ||                  | |            |||  +-------+   +-----+ | |   |           |
+ *       |        ||                  | |            |+-> | exit  | - | ... | --+   +-----+-----+
+ *       |        ||                  | |            | |  +-------+   +-----+ |           |
+ *       |        ||                  | |            | |                      |           |
+ *       |        ||  +-----------+   | |  +-----+   | |                      |           |
+ *       |        +-> | workqueue | -----> | ... |   | |                      |           |
+ *       |         |  +-----------+   | |  +-----+   | |                      |           |
+ *       |         +==================+ +============+ +======================+           |
+ *       |                                                                                |
+ *       +---->  atom_page_list  ---------------------------------------------------------+
+ *
+ */
+
+struct kwork_atom {
+	struct list_head list;
+	u64 time;
+	struct kwork_atom *prev;
+
+	void *page_addr;
+	unsigned long bit_inpage;
+};
+
+#define NR_ATOM_PER_PAGE 128
+struct kwork_atom_page {
+	struct list_head list;
+	struct kwork_atom atoms[NR_ATOM_PER_PAGE];
+	DECLARE_BITMAP(bitmap, NR_ATOM_PER_PAGE);
+};
+
+struct kwork_class;
+struct kwork_work {
+	/*
+	 * class field
+	 */
+	struct rb_node node;
+	struct kwork_class *class;
+
+	/*
+	 * work field
+	 */
+	u64 id;
+	int cpu;
+	char *name;
+
+	/*
+	 * atom field
+	 */
+	u64 nr_atoms;
+	struct list_head atom_list[KWORK_TRACE_MAX];
+
+	/*
+	 * runtime report
+	 */
+	u64 max_runtime;
+	u64 max_runtime_start;
+	u64 max_runtime_end;
+	u64 total_runtime;
+
+	/*
+	 * latency report
+	 */
+	u64 max_latency;
+	u64 max_latency_start;
+	u64 max_latency_end;
+	u64 total_latency;
+};
+
+struct kwork_class {
+	struct list_head list;
+	const char *name;
+	enum kwork_class_type type;
+
+	unsigned int nr_tracepoints;
+	const struct evsel_str_handler *tp_handlers;
+
+	struct rb_root_cached work_root;
+
+	int (*class_init)(struct kwork_class *class,
+			  struct perf_session *session);
+
+	void (*work_init)(struct kwork_class *class,
+			  struct kwork_work *work,
+			  struct evsel *evsel,
+			  struct perf_sample *sample,
+			  struct machine *machine);
+
+	void (*work_name)(struct kwork_work *work,
+			  char *buf, int len);
+};
+
+struct perf_kwork;
+struct trace_kwork_handler {
+	int (*raise_event)(struct perf_kwork *kwork,
+			   struct kwork_class *class, struct evsel *evsel,
+			   struct perf_sample *sample, struct machine *machine);
+
+	int (*entry_event)(struct perf_kwork *kwork,
+			   struct kwork_class *class, struct evsel *evsel,
+			   struct perf_sample *sample, struct machine *machine);
+
+	int (*exit_event)(struct perf_kwork *kwork,
+			  struct kwork_class *class, struct evsel *evsel,
+			  struct perf_sample *sample, struct machine *machine);
+};
+
+struct perf_kwork {
+	/*
+	 * metadata
+	 */
+	struct perf_tool tool;
+	struct list_head class_list;
+	struct list_head atom_page_list;
+	struct list_head sort_list, cmp_id;
+	struct rb_root_cached sorted_work_root;
+	const struct trace_kwork_handler *tp_handler;
+
+	/*
+	 * profile filters
+	 */
+	const char *profile_name;
+
+	const char *cpu_list;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
+	const char *time_str;
+	struct perf_time_interval ptime;
+
+	/*
+	 * options for command
+	 */
+	bool force;
+	const char *event_list_str;
+	enum kwork_report_type report;
+
+	/*
+	 * options for subcommand
+	 */
+	bool summary;
+	const char *sort_order;
+	bool show_callchain;
+	unsigned int max_stack;
+	bool use_bpf;
+
+	/*
+	 * statistics
+	 */
+	u64 timestart;
+	u64 timeend;
+
+	unsigned long nr_events;
+	unsigned long nr_lost_chunks;
+	unsigned long nr_lost_events;
+
+	u64 all_runtime;
+	u64 all_count;
+	u64 nr_skipped_events[KWORK_TRACE_MAX + 1];
+};
+
+struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork,
+				       struct kwork_class *class,
+				       struct kwork_work *key);
+
+#ifdef HAVE_BPF_SKEL
+
+int perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork);
+int perf_kwork__report_read_bpf(struct perf_kwork *kwork);
+void perf_kwork__report_cleanup_bpf(void);
+
+void perf_kwork__trace_start(void);
+void perf_kwork__trace_finish(void);
+
+#else  /* !HAVE_BPF_SKEL */
+
+static inline int
+perf_kwork__trace_prepare_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_kwork__report_read_bpf(struct perf_kwork *kwork __maybe_unused)
+{
+	return -1;
+}
+
+static inline void perf_kwork__report_cleanup_bpf(void) {}
+
+static inline void perf_kwork__trace_start(void) {}
+static inline void perf_kwork__trace_finish(void) {}
+
+#endif  /* HAVE_BPF_SKEL */
+
+#endif  /* PERF_UTIL_KWORK_H */
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 96c8ef60f4f8..2dc797007419 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -25,7 +25,7 @@
 		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
+		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
 
 struct llvm_param llvm_param = {
 	.clang_path = "clang",
diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h
new file mode 100644
index 000000000000..2146efc33396
--- /dev/null
+++ b/tools/perf/util/lock-contention.h
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef PERF_LOCK_CONTENTION_H
+#define PERF_LOCK_CONTENTION_H
+
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+struct lock_stat {
+	struct hlist_node	hash_entry;
+	struct rb_node		rb;		/* used for sorting */
+
+	u64			addr;		/* address of lockdep_map, used as ID */
+	char			*name;		/* for strcpy(), we cannot use const */
+
+	unsigned int		nr_acquire;
+	unsigned int		nr_acquired;
+	unsigned int		nr_contended;
+	unsigned int		nr_release;
+
+	union {
+		unsigned int	nr_readlock;
+		unsigned int	flags;
+	};
+	unsigned int		nr_trylock;
+
+	/* these times are in nano sec. */
+	u64                     avg_wait_time;
+	u64			wait_time_total;
+	u64			wait_time_min;
+	u64			wait_time_max;
+
+	int			broken; /* flag of blacklist */
+	int			combined;
+};
+
+/*
+ * States of lock_seq_stat
+ *
+ * UNINITIALIZED is required for detecting first event of acquire.
+ * As the nature of lock events, there is no guarantee
+ * that the first event for the locks are acquire,
+ * it can be acquired, contended or release.
+ */
+#define SEQ_STATE_UNINITIALIZED      0	       /* initial state */
+#define SEQ_STATE_RELEASED	1
+#define SEQ_STATE_ACQUIRING	2
+#define SEQ_STATE_ACQUIRED	3
+#define SEQ_STATE_READ_ACQUIRED	4
+#define SEQ_STATE_CONTENDED	5
+
+/*
+ * MAX_LOCK_DEPTH
+ * Imported from include/linux/sched.h.
+ * Should this be synchronized?
+ */
+#define MAX_LOCK_DEPTH 48
+
+/*
+ * struct lock_seq_stat:
+ * Place to put on state of one lock sequence
+ * 1) acquire -> acquired -> release
+ * 2) acquire -> contended -> acquired -> release
+ * 3) acquire (with read or try) -> release
+ * 4) Are there other patterns?
+ */
+struct lock_seq_stat {
+	struct list_head        list;
+	int			state;
+	u64			prev_event_time;
+	u64                     addr;
+
+	int                     read_count;
+};
+
+struct thread_stat {
+	struct rb_node		rb;
+
+	u32                     tid;
+	struct list_head        seq_list;
+};
+
+/*
+ * CONTENTION_STACK_DEPTH
+ * Number of stack trace entries to find callers
+ */
+#define CONTENTION_STACK_DEPTH  8
+
+/*
+ * CONTENTION_STACK_SKIP
+ * Number of stack trace entries to skip when finding callers.
+ * The first few entries belong to the locking implementation itself.
+ */
+#define CONTENTION_STACK_SKIP  3
+
+/*
+ * flags for lock:contention_begin
+ * Imported from include/trace/events/lock.h.
+ */
+#define LCB_F_SPIN	(1U << 0)
+#define LCB_F_READ	(1U << 1)
+#define LCB_F_WRITE	(1U << 2)
+#define LCB_F_RT	(1U << 3)
+#define LCB_F_PERCPU	(1U << 4)
+#define LCB_F_MUTEX	(1U << 5)
+
+struct evlist;
+struct machine;
+struct target;
+
+struct lock_contention {
+	struct evlist *evlist;
+	struct target *target;
+	struct machine *machine;
+	struct hlist_head *result;
+	unsigned long map_nr_entries;
+	unsigned long lost;
+};
+
+#ifdef HAVE_BPF_SKEL
+
+int lock_contention_prepare(struct lock_contention *con);
+int lock_contention_start(void);
+int lock_contention_stop(void);
+int lock_contention_read(struct lock_contention *con);
+int lock_contention_finish(void);
+
+#else  /* !HAVE_BPF_SKEL */
+
+static inline int lock_contention_prepare(struct lock_contention *con __maybe_unused)
+{
+	return 0;
+}
+
+static inline int lock_contention_start(void) { return 0; }
+static inline int lock_contention_stop(void) { return 0; }
+static inline int lock_contention_finish(void) { return 0; }
+
+static inline int lock_contention_read(struct lock_contention *con __maybe_unused)
+{
+	return 0;
+}
+
+#endif  /* HAVE_BPF_SKEL */
+
+bool is_lock_function(struct machine *machine, u64 addr);
+
+#endif  /* PERF_LOCK_CONTENTION_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 009061852808..facc13fbf16e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1742,6 +1742,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 	struct map *map;
 	enum dso_space_type dso_space;
 	bool is_kernel_mmap;
+	const char *mmap_name = machine->mmap_name;
 
 	/* If we have maps from kcore then we do not need or want any others */
 	if (machine__uses_kcore(machine))
@@ -1752,8 +1753,16 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 	else
 		dso_space = DSO_SPACE__KERNEL_GUEST;
 
-	is_kernel_mmap = memcmp(xm->name, machine->mmap_name,
-				strlen(machine->mmap_name) - 1) == 0;
+	is_kernel_mmap = memcmp(xm->name, mmap_name, strlen(mmap_name) - 1) == 0;
+	if (!is_kernel_mmap && !machine__is_host(machine)) {
+		/*
+		 * If the event was recorded inside the guest and injected into
+		 * the host perf.data file, then it will match a host mmap_name,
+		 * so try that - see machine__set_mmap_name().
+		 */
+		mmap_name = "[kernel.kallsyms]";
+		is_kernel_mmap = memcmp(xm->name, mmap_name, strlen(mmap_name) - 1) == 0;
+	}
 	if (xm->name[0] == '/' ||
 	    (!is_kernel_mmap && xm->name[0] == '[')) {
 		map = machine__addnew_module_map(machine, xm->start,
@@ -1767,7 +1776,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			dso__set_build_id(map->dso, bid);
 
 	} else if (is_kernel_mmap) {
-		const char *symbol_name = (xm->name + strlen(machine->mmap_name));
+		const char *symbol_name = xm->name + strlen(mmap_name);
 		/*
 		 * Should be there already, from the build-id table in
 		 * the header.
@@ -3174,9 +3183,7 @@ int machines__for_each_thread(struct machines *machines,
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu)
 {
-	int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
-
-	if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
+	if (cpu < 0 || (size_t)cpu >= machine->current_tid_sz)
 		return -1;
 
 	return machine->current_tid[cpu];
@@ -3186,26 +3193,16 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 			     pid_t tid)
 {
 	struct thread *thread;
-	int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
+	const pid_t init_val = -1;
 
 	if (cpu < 0)
 		return -EINVAL;
 
-	if (!machine->current_tid) {
-		int i;
-
-		machine->current_tid = calloc(nr_cpus, sizeof(pid_t));
-		if (!machine->current_tid)
-			return -ENOMEM;
-		for (i = 0; i < nr_cpus; i++)
-			machine->current_tid[i] = -1;
-	}
-
-	if (cpu >= nr_cpus) {
-		pr_err("Requested CPU %d too large. ", cpu);
-		pr_err("Consider raising MAX_NR_CPUS\n");
-		return -EINVAL;
-	}
+	if (realloc_array_as_needed(machine->current_tid,
+				    machine->current_tid_sz,
+				    (unsigned int)cpu,
+				    &init_val))
+		return -ENOMEM;
 
 	machine->current_tid[cpu] = tid;
 
@@ -3327,3 +3324,18 @@ int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv
 	}
 	return err;
 }
+
+int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
+{
+	struct maps *maps = machine__kernel_maps(machine);
+	struct map *map;
+	int err = 0;
+
+	for (map = maps__first(maps); map != NULL; map = map__next(map)) {
+		err = fn(map, priv);
+		if (err != 0) {
+			break;
+		}
+	}
+	return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 5d7daf7cb7bc..74935dfaa937 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -48,6 +48,7 @@ struct machine {
 	bool		  single_address_space;
 	char		  *root_dir;
 	char		  *mmap_name;
+	char		  *kallsyms_filename;
 	struct threads    threads[THREADS__TABLE_SIZE];
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
@@ -56,6 +57,7 @@ struct machine {
 	struct map	  *vmlinux_map;
 	u64		  kernel_start;
 	pid_t		  *current_tid;
+	size_t		  current_tid_sz;
 	union { /* Tool specific area */
 		void	  *priv;
 		u64	  db_id;
@@ -262,6 +264,11 @@ typedef int (*machine__dso_t)(struct dso *dso, struct machine *machine, void *pr
 
 int machine__for_each_dso(struct machine *machine, machine__dso_t fn,
 			  void *priv);
+
+typedef int (*machine__map_t)(struct map *map, void *priv);
+int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn,
+				 void *priv);
+
 int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
index 0b05c3c0aeaa..8febbd7c98ca 100644
--- a/tools/perf/util/ordered-events.h
+++ b/tools/perf/util/ordered-events.h
@@ -75,4 +75,10 @@ void ordered_events__set_copy_on_queue(struct ordered_events *oe, bool copy)
 {
 	oe->copy_on_queue = copy;
 }
+
+static inline u64 ordered_events__last_flush_time(struct ordered_events *oe)
+{
+	return oe->last_flush;
+}
+
 #endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7ed235740431..206c76623c06 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -5,18 +5,12 @@
 #include <dirent.h>
 #include <errno.h>
 #include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
 #include <sys/param.h>
 #include "term.h"
-#include "build-id.h"
 #include "evlist.h"
 #include "evsel.h"
-#include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "parse-events.h"
-#include <subcmd/exec-cmd.h>
 #include "string2.h"
 #include "strlist.h"
 #include "bpf-loader.h"
@@ -24,23 +18,24 @@
 #include <api/fs/tracing_path.h>
 #include <perf/cpumap.h>
 #include "parse-events-bison.h"
-#define YY_EXTRA_TYPE void*
 #include "parse-events-flex.h"
 #include "pmu.h"
-#include "thread_map.h"
-#include "probe-file.h"
 #include "asm/bug.h"
 #include "util/parse-branch-options.h"
-#include "metricgroup.h"
 #include "util/evsel_config.h"
 #include "util/event.h"
-#include "util/pfm.h"
+#include "perf.h"
 #include "util/parse-events-hybrid.h"
 #include "util/pmu-hybrid.h"
-#include "perf.h"
+#include "tracepoint.h"
 
 #define MAX_NAME_LEN 100
 
+struct perf_pmu_event_symbol {
+	char	*symbol;
+	enum perf_pmu_event_symbol_type	type;
+};
+
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
@@ -154,21 +149,6 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 	},
 };
 
-struct event_symbol event_symbols_tool[PERF_TOOL_MAX] = {
-	[PERF_TOOL_DURATION_TIME] = {
-		.symbol = "duration_time",
-		.alias  = "",
-	},
-	[PERF_TOOL_USER_TIME] = {
-		.symbol = "user_time",
-		.alias  = "",
-	},
-	[PERF_TOOL_SYSTEM_TIME] = {
-		.symbol = "system_time",
-		.alias  = "",
-	},
-};
-
 #define __PERF_EVENT_FIELD(config, name) \
 	((config & PERF_EVENT_##name##_MASK) >> PERF_EVENT_##name##_SHIFT)
 
@@ -177,121 +157,6 @@ struct event_symbol event_symbols_tool[PERF_TOOL_MAX] = {
 #define PERF_EVENT_TYPE(config)		__PERF_EVENT_FIELD(config, TYPE)
 #define PERF_EVENT_ID(config)		__PERF_EVENT_FIELD(config, EVENT)
 
-#define for_each_subsystem(sys_dir, sys_dirent)			\
-	while ((sys_dirent = readdir(sys_dir)) != NULL)		\
-		if (sys_dirent->d_type == DT_DIR &&		\
-		    (strcmp(sys_dirent->d_name, ".")) &&	\
-		    (strcmp(sys_dirent->d_name, "..")))
-
-static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
-{
-	char evt_path[MAXPATHLEN];
-	int fd;
-
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name);
-	fd = open(evt_path, O_RDONLY);
-	if (fd < 0)
-		return -EINVAL;
-	close(fd);
-
-	return 0;
-}
-
-#define for_each_event(dir_path, evt_dir, evt_dirent)		\
-	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
-		if (evt_dirent->d_type == DT_DIR &&		\
-		    (strcmp(evt_dirent->d_name, ".")) &&	\
-		    (strcmp(evt_dirent->d_name, "..")) &&	\
-		    (!tp_event_has_id(dir_path, evt_dirent)))
-
-#define MAX_EVENT_LENGTH 512
-
-struct tracepoint_path *tracepoint_id_to_path(u64 config)
-{
-	struct tracepoint_path *path = NULL;
-	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_dirent, *evt_dirent;
-	char id_buf[24];
-	int fd;
-	u64 id;
-	char evt_path[MAXPATHLEN];
-	char *dir_path;
-
-	sys_dir = tracing_events__opendir();
-	if (!sys_dir)
-		return NULL;
-
-	for_each_subsystem(sys_dir, sys_dirent) {
-		dir_path = get_events_file(sys_dirent->d_name);
-		if (!dir_path)
-			continue;
-		evt_dir = opendir(dir_path);
-		if (!evt_dir)
-			goto next;
-
-		for_each_event(dir_path, evt_dir, evt_dirent) {
-
-			scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
-				  evt_dirent->d_name);
-			fd = open(evt_path, O_RDONLY);
-			if (fd < 0)
-				continue;
-			if (read(fd, id_buf, sizeof(id_buf)) < 0) {
-				close(fd);
-				continue;
-			}
-			close(fd);
-			id = atoll(id_buf);
-			if (id == config) {
-				put_events_file(dir_path);
-				closedir(evt_dir);
-				closedir(sys_dir);
-				path = zalloc(sizeof(*path));
-				if (!path)
-					return NULL;
-				if (asprintf(&path->system, "%.*s", MAX_EVENT_LENGTH, sys_dirent->d_name) < 0) {
-					free(path);
-					return NULL;
-				}
-				if (asprintf(&path->name, "%.*s", MAX_EVENT_LENGTH, evt_dirent->d_name) < 0) {
-					zfree(&path->system);
-					free(path);
-					return NULL;
-				}
-				return path;
-			}
-		}
-		closedir(evt_dir);
-next:
-		put_events_file(dir_path);
-	}
-
-	closedir(sys_dir);
-	return NULL;
-}
-
-struct tracepoint_path *tracepoint_name_to_path(const char *name)
-{
-	struct tracepoint_path *path = zalloc(sizeof(*path));
-	char *str = strchr(name, ':');
-
-	if (path == NULL || str == NULL) {
-		free(path);
-		return NULL;
-	}
-
-	path->system = strndup(name, str - name);
-	path->name = strdup(str+1);
-
-	if (path->system == NULL || path->name == NULL) {
-		zfree(&path->system);
-		zfree(&path->name);
-		zfree(&path);
-	}
-
-	return path;
-}
-
 const char *event_type(int type)
 {
 	switch (type) {
@@ -2666,571 +2531,6 @@ int exclude_perf(const struct option *opt,
 					  NULL);
 }
 
-static const char * const event_type_descriptors[] = {
-	"Hardware event",
-	"Software event",
-	"Tracepoint event",
-	"Hardware cache event",
-	"Raw hardware event descriptor",
-	"Hardware breakpoint",
-};
-
-static int cmp_string(const void *a, const void *b)
-{
-	const char * const *as = a;
-	const char * const *bs = b;
-
-	return strcmp(*as, *bs);
-}
-
-/*
- * Print the events from <debugfs_mount_point>/tracing/events
- */
-
-void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
-			     bool name_only)
-{
-	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_dirent, *evt_dirent;
-	char evt_path[MAXPATHLEN];
-	char *dir_path;
-	char **evt_list = NULL;
-	unsigned int evt_i = 0, evt_num = 0;
-	bool evt_num_known = false;
-
-restart:
-	sys_dir = tracing_events__opendir();
-	if (!sys_dir)
-		return;
-
-	if (evt_num_known) {
-		evt_list = zalloc(sizeof(char *) * evt_num);
-		if (!evt_list)
-			goto out_close_sys_dir;
-	}
-
-	for_each_subsystem(sys_dir, sys_dirent) {
-		if (subsys_glob != NULL &&
-		    !strglobmatch(sys_dirent->d_name, subsys_glob))
-			continue;
-
-		dir_path = get_events_file(sys_dirent->d_name);
-		if (!dir_path)
-			continue;
-		evt_dir = opendir(dir_path);
-		if (!evt_dir)
-			goto next;
-
-		for_each_event(dir_path, evt_dir, evt_dirent) {
-			if (event_glob != NULL &&
-			    !strglobmatch(evt_dirent->d_name, event_glob))
-				continue;
-
-			if (!evt_num_known) {
-				evt_num++;
-				continue;
-			}
-
-			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent->d_name, evt_dirent->d_name);
-
-			evt_list[evt_i] = strdup(evt_path);
-			if (evt_list[evt_i] == NULL) {
-				put_events_file(dir_path);
-				goto out_close_evt_dir;
-			}
-			evt_i++;
-		}
-		closedir(evt_dir);
-next:
-		put_events_file(dir_path);
-	}
-	closedir(sys_dir);
-
-	if (!evt_num_known) {
-		evt_num_known = true;
-		goto restart;
-	}
-	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
-	evt_i = 0;
-	while (evt_i < evt_num) {
-		if (name_only) {
-			printf("%s ", evt_list[evt_i++]);
-			continue;
-		}
-		printf("  %-50s [%s]\n", evt_list[evt_i++],
-				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
-	}
-	if (evt_num && pager_in_use())
-		printf("\n");
-
-out_free:
-	evt_num = evt_i;
-	for (evt_i = 0; evt_i < evt_num; evt_i++)
-		zfree(&evt_list[evt_i]);
-	zfree(&evt_list);
-	return;
-
-out_close_evt_dir:
-	closedir(evt_dir);
-out_close_sys_dir:
-	closedir(sys_dir);
-
-	printf("FATAL: not enough memory to print %s\n",
-			event_type_descriptors[PERF_TYPE_TRACEPOINT]);
-	if (evt_list)
-		goto out_free;
-}
-
-/*
- * Check whether event is in <debugfs_mount_point>/tracing/events
- */
-
-int is_valid_tracepoint(const char *event_string)
-{
-	DIR *sys_dir, *evt_dir;
-	struct dirent *sys_dirent, *evt_dirent;
-	char evt_path[MAXPATHLEN];
-	char *dir_path;
-
-	sys_dir = tracing_events__opendir();
-	if (!sys_dir)
-		return 0;
-
-	for_each_subsystem(sys_dir, sys_dirent) {
-		dir_path = get_events_file(sys_dirent->d_name);
-		if (!dir_path)
-			continue;
-		evt_dir = opendir(dir_path);
-		if (!evt_dir)
-			goto next;
-
-		for_each_event(dir_path, evt_dir, evt_dirent) {
-			snprintf(evt_path, MAXPATHLEN, "%s:%s",
-				 sys_dirent->d_name, evt_dirent->d_name);
-			if (!strcmp(evt_path, event_string)) {
-				closedir(evt_dir);
-				closedir(sys_dir);
-				return 1;
-			}
-		}
-		closedir(evt_dir);
-next:
-		put_events_file(dir_path);
-	}
-	closedir(sys_dir);
-	return 0;
-}
-
-static bool is_event_supported(u8 type, u64 config)
-{
-	bool ret = true;
-	int open_return;
-	struct evsel *evsel;
-	struct perf_event_attr attr = {
-		.type = type,
-		.config = config,
-		.disabled = 1,
-	};
-	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
-
-	if (tmap == NULL)
-		return false;
-
-	evsel = evsel__new(&attr);
-	if (evsel) {
-		open_return = evsel__open(evsel, NULL, tmap);
-		ret = open_return >= 0;
-
-		if (open_return == -EACCES) {
-			/*
-			 * This happens if the paranoid value
-			 * /proc/sys/kernel/perf_event_paranoid is set to 2
-			 * Re-run with exclude_kernel set; we don't do that
-			 * by default as some ARM machines do not support it.
-			 *
-			 */
-			evsel->core.attr.exclude_kernel = 1;
-			ret = evsel__open(evsel, NULL, tmap) >= 0;
-		}
-		evsel__delete(evsel);
-	}
-
-	perf_thread_map__put(tmap);
-	return ret;
-}
-
-void print_sdt_events(const char *subsys_glob, const char *event_glob,
-		      bool name_only)
-{
-	struct probe_cache *pcache;
-	struct probe_cache_entry *ent;
-	struct strlist *bidlist, *sdtlist;
-	struct strlist_config cfg = {.dont_dupstr = true};
-	struct str_node *nd, *nd2;
-	char *buf, *path, *ptr = NULL;
-	bool show_detail = false;
-	int ret;
-
-	sdtlist = strlist__new(NULL, &cfg);
-	if (!sdtlist) {
-		pr_debug("Failed to allocate new strlist for SDT\n");
-		return;
-	}
-	bidlist = build_id_cache__list_all(true);
-	if (!bidlist) {
-		pr_debug("Failed to get buildids: %d\n", errno);
-		return;
-	}
-	strlist__for_each_entry(nd, bidlist) {
-		pcache = probe_cache__new(nd->s, NULL);
-		if (!pcache)
-			continue;
-		list_for_each_entry(ent, &pcache->entries, node) {
-			if (!ent->sdt)
-				continue;
-			if (subsys_glob &&
-			    !strglobmatch(ent->pev.group, subsys_glob))
-				continue;
-			if (event_glob &&
-			    !strglobmatch(ent->pev.event, event_glob))
-				continue;
-			ret = asprintf(&buf, "%s:%s@%s", ent->pev.group,
-					ent->pev.event, nd->s);
-			if (ret > 0)
-				strlist__add(sdtlist, buf);
-		}
-		probe_cache__delete(pcache);
-	}
-	strlist__delete(bidlist);
-
-	strlist__for_each_entry(nd, sdtlist) {
-		buf = strchr(nd->s, '@');
-		if (buf)
-			*(buf++) = '\0';
-		if (name_only) {
-			printf("%s ", nd->s);
-			continue;
-		}
-		nd2 = strlist__next(nd);
-		if (nd2) {
-			ptr = strchr(nd2->s, '@');
-			if (ptr)
-				*ptr = '\0';
-			if (strcmp(nd->s, nd2->s) == 0)
-				show_detail = true;
-		}
-		if (show_detail) {
-			path = build_id_cache__origname(buf);
-			ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf);
-			if (ret > 0) {
-				printf("  %-50s [%s]\n", buf, "SDT event");
-				free(buf);
-			}
-			free(path);
-		} else
-			printf("  %-50s [%s]\n", nd->s, "SDT event");
-		if (nd2) {
-			if (strcmp(nd->s, nd2->s) != 0)
-				show_detail = false;
-			if (ptr)
-				*ptr = '@';
-		}
-	}
-	strlist__delete(sdtlist);
-}
-
-int print_hwcache_events(const char *event_glob, bool name_only)
-{
-	unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;
-	char name[64], new_name[128];
-	char **evt_list = NULL, **evt_pmus = NULL;
-	bool evt_num_known = false;
-	struct perf_pmu *pmu = NULL;
-
-	if (perf_pmu__has_hybrid()) {
-		npmus = perf_pmu__hybrid_pmu_num();
-		evt_pmus = zalloc(sizeof(char *) * npmus);
-		if (!evt_pmus)
-			goto out_enomem;
-	}
-
-restart:
-	if (evt_num_known) {
-		evt_list = zalloc(sizeof(char *) * evt_num);
-		if (!evt_list)
-			goto out_enomem;
-	}
-
-	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
-		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
-			/* skip invalid cache type */
-			if (!evsel__is_cache_op_valid(type, op))
-				continue;
-
-			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
-				unsigned int hybrid_supported = 0, j;
-				bool supported;
-
-				__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
-				if (event_glob != NULL && !strglobmatch(name, event_glob))
-					continue;
-
-				if (!perf_pmu__has_hybrid()) {
-					if (!is_event_supported(PERF_TYPE_HW_CACHE,
-								type | (op << 8) | (i << 16))) {
-						continue;
-					}
-				} else {
-					perf_pmu__for_each_hybrid_pmu(pmu) {
-						if (!evt_num_known) {
-							evt_num++;
-							continue;
-						}
-
-						supported = is_event_supported(
-									PERF_TYPE_HW_CACHE,
-									type | (op << 8) | (i << 16) |
-									((__u64)pmu->type << PERF_PMU_TYPE_SHIFT));
-						if (supported) {
-							snprintf(new_name, sizeof(new_name), "%s/%s/",
-								 pmu->name, name);
-							evt_pmus[hybrid_supported] = strdup(new_name);
-							hybrid_supported++;
-						}
-					}
-
-					if (hybrid_supported == 0)
-						continue;
-				}
-
-				if (!evt_num_known) {
-					evt_num++;
-					continue;
-				}
-
-				if ((hybrid_supported == 0) ||
-				    (hybrid_supported == npmus)) {
-					evt_list[evt_i] = strdup(name);
-					if (npmus > 0) {
-						for (j = 0; j < npmus; j++)
-							zfree(&evt_pmus[j]);
-					}
-				} else {
-					for (j = 0; j < hybrid_supported; j++) {
-						evt_list[evt_i++] = evt_pmus[j];
-						evt_pmus[j] = NULL;
-					}
-					continue;
-				}
-
-				if (evt_list[evt_i] == NULL)
-					goto out_enomem;
-				evt_i++;
-			}
-		}
-	}
-
-	if (!evt_num_known) {
-		evt_num_known = true;
-		goto restart;
-	}
-
-	for (evt_i = 0; evt_i < evt_num; evt_i++) {
-		if (!evt_list[evt_i])
-			break;
-	}
-
-	evt_num = evt_i;
-	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
-	evt_i = 0;
-	while (evt_i < evt_num) {
-		if (name_only) {
-			printf("%s ", evt_list[evt_i++]);
-			continue;
-		}
-		printf("  %-50s [%s]\n", evt_list[evt_i++],
-				event_type_descriptors[PERF_TYPE_HW_CACHE]);
-	}
-	if (evt_num && pager_in_use())
-		printf("\n");
-
-out_free:
-	evt_num = evt_i;
-	for (evt_i = 0; evt_i < evt_num; evt_i++)
-		zfree(&evt_list[evt_i]);
-	zfree(&evt_list);
-
-	for (evt_i = 0; evt_i < npmus; evt_i++)
-		zfree(&evt_pmus[evt_i]);
-	zfree(&evt_pmus);
-	return evt_num;
-
-out_enomem:
-	printf("FATAL: not enough memory to print %s\n", event_type_descriptors[PERF_TYPE_HW_CACHE]);
-	if (evt_list)
-		goto out_free;
-	return evt_num;
-}
-
-static void print_tool_event(const struct event_symbol *syms, const char *event_glob,
-			     bool name_only)
-{
-	if (syms->symbol == NULL)
-		return;
-
-	if (event_glob && !(strglobmatch(syms->symbol, event_glob) ||
-	      (syms->alias && strglobmatch(syms->alias, event_glob))))
-		return;
-
-	if (name_only)
-		printf("%s ", syms->symbol);
-	else {
-		char name[MAX_NAME_LEN];
-		if (syms->alias && strlen(syms->alias))
-			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
-		else
-			strlcpy(name, syms->symbol, MAX_NAME_LEN);
-		printf("  %-50s [%s]\n", name, "Tool event");
-	}
-}
-
-void print_tool_events(const char *event_glob, bool name_only)
-{
-	// Start at 1 because the first enum entry symbols no tool event
-	for (int i = 1; i < PERF_TOOL_MAX; ++i) {
-		print_tool_event(event_symbols_tool + i, event_glob, name_only);
-	}
-	if (pager_in_use())
-		printf("\n");
-}
-
-void print_symbol_events(const char *event_glob, unsigned type,
-				struct event_symbol *syms, unsigned max,
-				bool name_only)
-{
-	unsigned int i, evt_i = 0, evt_num = 0;
-	char name[MAX_NAME_LEN];
-	char **evt_list = NULL;
-	bool evt_num_known = false;
-
-restart:
-	if (evt_num_known) {
-		evt_list = zalloc(sizeof(char *) * evt_num);
-		if (!evt_list)
-			goto out_enomem;
-		syms -= max;
-	}
-
-	for (i = 0; i < max; i++, syms++) {
-		/*
-		 * New attr.config still not supported here, the latest
-		 * example was PERF_COUNT_SW_CGROUP_SWITCHES
-		 */
-		if (syms->symbol == NULL)
-			continue;
-
-		if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) ||
-		      (syms->alias && strglobmatch(syms->alias, event_glob))))
-			continue;
-
-		if (!is_event_supported(type, i))
-			continue;
-
-		if (!evt_num_known) {
-			evt_num++;
-			continue;
-		}
-
-		if (!name_only && strlen(syms->alias))
-			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
-		else
-			strlcpy(name, syms->symbol, MAX_NAME_LEN);
-
-		evt_list[evt_i] = strdup(name);
-		if (evt_list[evt_i] == NULL)
-			goto out_enomem;
-		evt_i++;
-	}
-
-	if (!evt_num_known) {
-		evt_num_known = true;
-		goto restart;
-	}
-	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
-	evt_i = 0;
-	while (evt_i < evt_num) {
-		if (name_only) {
-			printf("%s ", evt_list[evt_i++]);
-			continue;
-		}
-		printf("  %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]);
-	}
-	if (evt_num && pager_in_use())
-		printf("\n");
-
-out_free:
-	evt_num = evt_i;
-	for (evt_i = 0; evt_i < evt_num; evt_i++)
-		zfree(&evt_list[evt_i]);
-	zfree(&evt_list);
-	return;
-
-out_enomem:
-	printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]);
-	if (evt_list)
-		goto out_free;
-}
-
-/*
- * Print the help text for the event symbols:
- */
-void print_events(const char *event_glob, bool name_only, bool quiet_flag,
-			bool long_desc, bool details_flag, bool deprecated,
-			const char *pmu_name)
-{
-	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
-			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
-
-	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
-			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
-	print_tool_events(event_glob, name_only);
-
-	print_hwcache_events(event_glob, name_only);
-
-	print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
-			details_flag, deprecated, pmu_name);
-
-	if (event_glob != NULL)
-		return;
-
-	if (!name_only) {
-		printf("  %-50s [%s]\n",
-		       "rNNN",
-		       event_type_descriptors[PERF_TYPE_RAW]);
-		printf("  %-50s [%s]\n",
-		       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
-		       event_type_descriptors[PERF_TYPE_RAW]);
-		if (pager_in_use())
-			printf("   (see 'man perf-list' on how to encode it)\n\n");
-
-		printf("  %-50s [%s]\n",
-		       "mem:<addr>[/len][:access]",
-			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
-		if (pager_in_use())
-			printf("\n");
-	}
-
-	print_tracepoint_events(NULL, NULL, name_only);
-
-	print_sdt_events(NULL, NULL, name_only);
-
-	metricgroup__print(true, true, NULL, name_only, details_flag,
-			   pmu_name);
-
-	print_libpfm_events(name_only, long_desc);
-}
-
 int parse_events__is_hardcoded_term(struct parse_events_term *term)
 {
 	return term->type_term != PARSE_EVENTS__TERM_TYPE_USER;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index a38b8b160e80..ba9fa3ddaf6e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -11,7 +11,6 @@
 #include <linux/perf_event.h>
 #include <string.h>
 
-struct list_head;
 struct evsel;
 struct evlist;
 struct parse_events_error;
@@ -19,14 +18,6 @@ struct parse_events_error;
 struct option;
 struct perf_pmu;
 
-struct tracepoint_path {
-	char *system;
-	char *name;
-	struct tracepoint_path *next;
-};
-
-struct tracepoint_path *tracepoint_id_to_path(u64 config);
-struct tracepoint_path *tracepoint_name_to_path(const char *name);
 bool have_tracepoints(struct list_head *evlist);
 
 const char *event_type(int type);
@@ -46,8 +37,6 @@ int parse_events_terms(struct list_head *terms, const char *str);
 int parse_filter(const struct option *opt, const char *str, int unset);
 int exclude_perf(const struct option *opt, const char *arg, int unset);
 
-#define EVENTS_HELP_MAX (128*1024)
-
 enum perf_pmu_event_symbol_type {
 	PMU_EVENT_SYMBOL_ERR,		/* not a PMU EVENT */
 	PMU_EVENT_SYMBOL,		/* normal style PMU event */
@@ -56,11 +45,6 @@ enum perf_pmu_event_symbol_type {
 	PMU_EVENT_SYMBOL_SUFFIX2,	/* suffix of pre-suf2 style event */
 };
 
-struct perf_pmu_event_symbol {
-	char	*symbol;
-	enum perf_pmu_event_symbol_type	type;
-};
-
 enum {
 	PARSE_EVENTS__TERM_TYPE_NUM,
 	PARSE_EVENTS__TERM_TYPE_STR,
@@ -219,28 +203,13 @@ void parse_events_update_lists(struct list_head *list_event,
 void parse_events_evlist_error(struct parse_events_state *parse_state,
 			       int idx, const char *str);
 
-void print_events(const char *event_glob, bool name_only, bool quiet,
-		  bool long_desc, bool details_flag, bool deprecated,
-		  const char *pmu_name);
-
 struct event_symbol {
 	const char	*symbol;
 	const char	*alias;
 };
 extern struct event_symbol event_symbols_hw[];
 extern struct event_symbol event_symbols_sw[];
-void print_symbol_events(const char *event_glob, unsigned type,
-				struct event_symbol *syms, unsigned max,
-				bool name_only);
-void print_tool_events(const char *event_glob, bool name_only);
-void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
-			     bool name_only);
-int print_hwcache_events(const char *event_glob, bool name_only);
-void print_sdt_events(const char *subsys_glob, const char *event_glob,
-		      bool name_only);
-int is_valid_tracepoint(const char *event_string);
 
-int valid_event_mount(const char *eventfs);
 char *parse_events_formats_error_string(char *additional_terms);
 
 void parse_events_error__init(struct parse_events_error *err);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 9a1c7e63e663..0112e1c36418 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1890,7 +1890,11 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 	const char *sysfs = sysfs__mountpoint();
 	DIR *caps_dir;
 	struct dirent *evt_ent;
-	int nr_caps = 0;
+
+	if (pmu->caps_initialized)
+		return pmu->nr_caps;
+
+	pmu->nr_caps = 0;
 
 	if (!sysfs)
 		return -1;
@@ -1898,8 +1902,10 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 	snprintf(caps_path, PATH_MAX,
 		 "%s" EVENT_SOURCE_DEVICE_PATH "%s/caps", sysfs, pmu->name);
 
-	if (stat(caps_path, &st) < 0)
+	if (stat(caps_path, &st) < 0) {
+		pmu->caps_initialized = true;
 		return 0;	/* no error if caps does not exist */
+	}
 
 	caps_dir = opendir(caps_path);
 	if (!caps_dir)
@@ -1926,13 +1932,14 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu)
 			continue;
 		}
 
-		nr_caps++;
+		pmu->nr_caps++;
 		fclose(file);
 	}
 
 	closedir(caps_dir);
 
-	return nr_caps;
+	pmu->caps_initialized = true;
+	return pmu->nr_caps;
 }
 
 void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 541889fa9f9c..4b45fd8da5a3 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -46,6 +46,8 @@ struct perf_pmu {
 	struct perf_cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
 	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+	bool caps_initialized;
+	u32 nr_caps;
 	struct list_head caps;    /* HEAD struct perf_pmu_caps -> list */
 	struct list_head list;    /* ELEM */
 	struct list_head hybrid_list;
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
new file mode 100644
index 000000000000..ba1ab5134685
--- /dev/null
+++ b/tools/perf/util/print-events.c
@@ -0,0 +1,572 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <dirent.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/param.h>
+
+#include <api/fs/tracing_path.h>
+#include <linux/stddef.h>
+#include <linux/perf_event.h>
+#include <linux/zalloc.h>
+#include <subcmd/pager.h>
+
+#include "build-id.h"
+#include "debug.h"
+#include "evsel.h"
+#include "metricgroup.h"
+#include "parse-events.h"
+#include "pmu.h"
+#include "print-events.h"
+#include "probe-file.h"
+#include "string2.h"
+#include "strlist.h"
+#include "thread_map.h"
+#include "tracepoint.h"
+#include "pfm.h"
+#include "pmu-hybrid.h"
+
+#define MAX_NAME_LEN 100
+
+static const char * const event_type_descriptors[] = {
+	"Hardware event",
+	"Software event",
+	"Tracepoint event",
+	"Hardware cache event",
+	"Raw hardware event descriptor",
+	"Hardware breakpoint",
+};
+
+static const struct event_symbol event_symbols_tool[PERF_TOOL_MAX] = {
+	[PERF_TOOL_DURATION_TIME] = {
+		.symbol = "duration_time",
+		.alias  = "",
+	},
+	[PERF_TOOL_USER_TIME] = {
+		.symbol = "user_time",
+		.alias  = "",
+	},
+	[PERF_TOOL_SYSTEM_TIME] = {
+		.symbol = "system_time",
+		.alias  = "",
+	},
+};
+
+static int cmp_string(const void *a, const void *b)
+{
+	const char * const *as = a;
+	const char * const *bs = b;
+
+	return strcmp(*as, *bs);
+}
+
+/*
+ * Print the events from <debugfs_mount_point>/tracing/events
+ */
+void print_tracepoint_events(const char *subsys_glob,
+			     const char *event_glob, bool name_only)
+{
+	DIR *sys_dir, *evt_dir;
+	struct dirent *sys_dirent, *evt_dirent;
+	char evt_path[MAXPATHLEN];
+	char *dir_path;
+	char **evt_list = NULL;
+	unsigned int evt_i = 0, evt_num = 0;
+	bool evt_num_known = false;
+
+restart:
+	sys_dir = tracing_events__opendir();
+	if (!sys_dir)
+		return;
+
+	if (evt_num_known) {
+		evt_list = zalloc(sizeof(char *) * evt_num);
+		if (!evt_list)
+			goto out_close_sys_dir;
+	}
+
+	for_each_subsystem(sys_dir, sys_dirent) {
+		if (subsys_glob != NULL &&
+		    !strglobmatch(sys_dirent->d_name, subsys_glob))
+			continue;
+
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
+		evt_dir = opendir(dir_path);
+		if (!evt_dir)
+			goto next;
+
+		for_each_event(dir_path, evt_dir, evt_dirent) {
+			if (event_glob != NULL &&
+			    !strglobmatch(evt_dirent->d_name, event_glob))
+				continue;
+
+			if (!evt_num_known) {
+				evt_num++;
+				continue;
+			}
+
+			snprintf(evt_path, MAXPATHLEN, "%s:%s",
+				 sys_dirent->d_name, evt_dirent->d_name);
+
+			evt_list[evt_i] = strdup(evt_path);
+			if (evt_list[evt_i] == NULL) {
+				put_events_file(dir_path);
+				goto out_close_evt_dir;
+			}
+			evt_i++;
+		}
+		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
+	}
+	closedir(sys_dir);
+
+	if (!evt_num_known) {
+		evt_num_known = true;
+		goto restart;
+	}
+	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
+	evt_i = 0;
+	while (evt_i < evt_num) {
+		if (name_only) {
+			printf("%s ", evt_list[evt_i++]);
+			continue;
+		}
+		printf("  %-50s [%s]\n", evt_list[evt_i++],
+				event_type_descriptors[PERF_TYPE_TRACEPOINT]);
+	}
+	if (evt_num && pager_in_use())
+		printf("\n");
+
+out_free:
+	evt_num = evt_i;
+	for (evt_i = 0; evt_i < evt_num; evt_i++)
+		zfree(&evt_list[evt_i]);
+	zfree(&evt_list);
+	return;
+
+out_close_evt_dir:
+	closedir(evt_dir);
+out_close_sys_dir:
+	closedir(sys_dir);
+
+	printf("FATAL: not enough memory to print %s\n",
+			event_type_descriptors[PERF_TYPE_TRACEPOINT]);
+	if (evt_list)
+		goto out_free;
+}
+
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+		      bool name_only)
+{
+	struct probe_cache *pcache;
+	struct probe_cache_entry *ent;
+	struct strlist *bidlist, *sdtlist;
+	struct strlist_config cfg = {.dont_dupstr = true};
+	struct str_node *nd, *nd2;
+	char *buf, *path, *ptr = NULL;
+	bool show_detail = false;
+	int ret;
+
+	sdtlist = strlist__new(NULL, &cfg);
+	if (!sdtlist) {
+		pr_debug("Failed to allocate new strlist for SDT\n");
+		return;
+	}
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		pr_debug("Failed to get buildids: %d\n", errno);
+		return;
+	}
+	strlist__for_each_entry(nd, bidlist) {
+		pcache = probe_cache__new(nd->s, NULL);
+		if (!pcache)
+			continue;
+		list_for_each_entry(ent, &pcache->entries, node) {
+			if (!ent->sdt)
+				continue;
+			if (subsys_glob &&
+			    !strglobmatch(ent->pev.group, subsys_glob))
+				continue;
+			if (event_glob &&
+			    !strglobmatch(ent->pev.event, event_glob))
+				continue;
+			ret = asprintf(&buf, "%s:%s@%s", ent->pev.group,
+					ent->pev.event, nd->s);
+			if (ret > 0)
+				strlist__add(sdtlist, buf);
+		}
+		probe_cache__delete(pcache);
+	}
+	strlist__delete(bidlist);
+
+	strlist__for_each_entry(nd, sdtlist) {
+		buf = strchr(nd->s, '@');
+		if (buf)
+			*(buf++) = '\0';
+		if (name_only) {
+			printf("%s ", nd->s);
+			continue;
+		}
+		nd2 = strlist__next(nd);
+		if (nd2) {
+			ptr = strchr(nd2->s, '@');
+			if (ptr)
+				*ptr = '\0';
+			if (strcmp(nd->s, nd2->s) == 0)
+				show_detail = true;
+		}
+		if (show_detail) {
+			path = build_id_cache__origname(buf);
+			ret = asprintf(&buf, "%s@%s(%.12s)", nd->s, path, buf);
+			if (ret > 0) {
+				printf("  %-50s [%s]\n", buf, "SDT event");
+				free(buf);
+			}
+			free(path);
+		} else
+			printf("  %-50s [%s]\n", nd->s, "SDT event");
+		if (nd2) {
+			if (strcmp(nd->s, nd2->s) != 0)
+				show_detail = false;
+			if (ptr)
+				*ptr = '@';
+		}
+	}
+	strlist__delete(sdtlist);
+}
+
+static bool is_event_supported(u8 type, unsigned int config)
+{
+	bool ret = true;
+	int open_return;
+	struct evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.disabled = 1,
+	};
+	struct perf_thread_map *tmap = thread_map__new_by_tid(0);
+
+	if (tmap == NULL)
+		return false;
+
+	evsel = evsel__new(&attr);
+	if (evsel) {
+		open_return = evsel__open(evsel, NULL, tmap);
+		ret = open_return >= 0;
+
+		if (open_return == -EACCES) {
+			/*
+			 * This happens if the paranoid value
+			 * /proc/sys/kernel/perf_event_paranoid is set to 2
+			 * Re-run with exclude_kernel set; we don't do that
+			 * by default as some ARM machines do not support it.
+			 *
+			 */
+			evsel->core.attr.exclude_kernel = 1;
+			ret = evsel__open(evsel, NULL, tmap) >= 0;
+		}
+		evsel__delete(evsel);
+	}
+
+	perf_thread_map__put(tmap);
+	return ret;
+}
+
+int print_hwcache_events(const char *event_glob, bool name_only)
+{
+	unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus = 0;
+	char name[64], new_name[128];
+	char **evt_list = NULL, **evt_pmus = NULL;
+	bool evt_num_known = false;
+	struct perf_pmu *pmu = NULL;
+
+	if (perf_pmu__has_hybrid()) {
+		npmus = perf_pmu__hybrid_pmu_num();
+		evt_pmus = zalloc(sizeof(char *) * npmus);
+		if (!evt_pmus)
+			goto out_enomem;
+	}
+
+restart:
+	if (evt_num_known) {
+		evt_list = zalloc(sizeof(char *) * evt_num);
+		if (!evt_list)
+			goto out_enomem;
+	}
+
+	for (type = 0; type < PERF_COUNT_HW_CACHE_MAX; type++) {
+		for (op = 0; op < PERF_COUNT_HW_CACHE_OP_MAX; op++) {
+			/* skip invalid cache type */
+			if (!evsel__is_cache_op_valid(type, op))
+				continue;
+
+			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+				unsigned int hybrid_supported = 0, j;
+				bool supported;
+
+				__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
+				if (event_glob != NULL && !strglobmatch(name, event_glob))
+					continue;
+
+				if (!perf_pmu__has_hybrid()) {
+					if (!is_event_supported(PERF_TYPE_HW_CACHE,
+								type | (op << 8) | (i << 16))) {
+						continue;
+					}
+				} else {
+					perf_pmu__for_each_hybrid_pmu(pmu) {
+						if (!evt_num_known) {
+							evt_num++;
+							continue;
+						}
+
+						supported = is_event_supported(
+							PERF_TYPE_HW_CACHE,
+							type | (op << 8) | (i << 16) |
+							((__u64)pmu->type << PERF_PMU_TYPE_SHIFT));
+						if (supported) {
+							snprintf(new_name, sizeof(new_name),
+								 "%s/%s/", pmu->name, name);
+							evt_pmus[hybrid_supported] =
+								strdup(new_name);
+							hybrid_supported++;
+						}
+					}
+
+					if (hybrid_supported == 0)
+						continue;
+				}
+
+				if (!evt_num_known) {
+					evt_num++;
+					continue;
+				}
+
+				if ((hybrid_supported == 0) ||
+				    (hybrid_supported == npmus)) {
+					evt_list[evt_i] = strdup(name);
+					if (npmus > 0) {
+						for (j = 0; j < npmus; j++)
+							zfree(&evt_pmus[j]);
+					}
+				} else {
+					for (j = 0; j < hybrid_supported; j++) {
+						evt_list[evt_i++] = evt_pmus[j];
+						evt_pmus[j] = NULL;
+					}
+					continue;
+				}
+
+				if (evt_list[evt_i] == NULL)
+					goto out_enomem;
+				evt_i++;
+			}
+		}
+	}
+
+	if (!evt_num_known) {
+		evt_num_known = true;
+		goto restart;
+	}
+
+	for (evt_i = 0; evt_i < evt_num; evt_i++) {
+		if (!evt_list[evt_i])
+			break;
+	}
+
+	evt_num = evt_i;
+	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
+	evt_i = 0;
+	while (evt_i < evt_num) {
+		if (name_only) {
+			printf("%s ", evt_list[evt_i++]);
+			continue;
+		}
+		printf("  %-50s [%s]\n", evt_list[evt_i++],
+				event_type_descriptors[PERF_TYPE_HW_CACHE]);
+	}
+	if (evt_num && pager_in_use())
+		printf("\n");
+
+out_free:
+	evt_num = evt_i;
+	for (evt_i = 0; evt_i < evt_num; evt_i++)
+		zfree(&evt_list[evt_i]);
+	zfree(&evt_list);
+
+	for (evt_i = 0; evt_i < npmus; evt_i++)
+		zfree(&evt_pmus[evt_i]);
+	zfree(&evt_pmus);
+	return evt_num;
+
+out_enomem:
+	printf("FATAL: not enough memory to print %s\n",
+		event_type_descriptors[PERF_TYPE_HW_CACHE]);
+	if (evt_list)
+		goto out_free;
+	return evt_num;
+}
+
+static void print_tool_event(const struct event_symbol *syms, const char *event_glob,
+			     bool name_only)
+{
+	if (syms->symbol == NULL)
+		return;
+
+	if (event_glob && !(strglobmatch(syms->symbol, event_glob) ||
+	      (syms->alias && strglobmatch(syms->alias, event_glob))))
+		return;
+
+	if (name_only)
+		printf("%s ", syms->symbol);
+	else {
+		char name[MAX_NAME_LEN];
+
+		if (syms->alias && strlen(syms->alias))
+			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
+		else
+			strlcpy(name, syms->symbol, MAX_NAME_LEN);
+		printf("  %-50s [%s]\n", name, "Tool event");
+	}
+}
+
+void print_tool_events(const char *event_glob, bool name_only)
+{
+	// Start at 1 because the first enum entry means no tool event.
+	for (int i = 1; i < PERF_TOOL_MAX; ++i)
+		print_tool_event(event_symbols_tool + i, event_glob, name_only);
+
+	if (pager_in_use())
+		printf("\n");
+}
+
+void print_symbol_events(const char *event_glob, unsigned int type,
+			 struct event_symbol *syms, unsigned int max,
+			 bool name_only)
+{
+	unsigned int i, evt_i = 0, evt_num = 0;
+	char name[MAX_NAME_LEN];
+	char **evt_list = NULL;
+	bool evt_num_known = false;
+
+restart:
+	if (evt_num_known) {
+		evt_list = zalloc(sizeof(char *) * evt_num);
+		if (!evt_list)
+			goto out_enomem;
+		syms -= max;
+	}
+
+	for (i = 0; i < max; i++, syms++) {
+		/*
+		 * New attr.config still not supported here, the latest
+		 * example was PERF_COUNT_SW_CGROUP_SWITCHES
+		 */
+		if (syms->symbol == NULL)
+			continue;
+
+		if (event_glob != NULL && !(strglobmatch(syms->symbol, event_glob) ||
+		      (syms->alias && strglobmatch(syms->alias, event_glob))))
+			continue;
+
+		if (!is_event_supported(type, i))
+			continue;
+
+		if (!evt_num_known) {
+			evt_num++;
+			continue;
+		}
+
+		if (!name_only && strlen(syms->alias))
+			snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
+		else
+			strlcpy(name, syms->symbol, MAX_NAME_LEN);
+
+		evt_list[evt_i] = strdup(name);
+		if (evt_list[evt_i] == NULL)
+			goto out_enomem;
+		evt_i++;
+	}
+
+	if (!evt_num_known) {
+		evt_num_known = true;
+		goto restart;
+	}
+	qsort(evt_list, evt_num, sizeof(char *), cmp_string);
+	evt_i = 0;
+	while (evt_i < evt_num) {
+		if (name_only) {
+			printf("%s ", evt_list[evt_i++]);
+			continue;
+		}
+		printf("  %-50s [%s]\n", evt_list[evt_i++], event_type_descriptors[type]);
+	}
+	if (evt_num && pager_in_use())
+		printf("\n");
+
+out_free:
+	evt_num = evt_i;
+	for (evt_i = 0; evt_i < evt_num; evt_i++)
+		zfree(&evt_list[evt_i]);
+	zfree(&evt_list);
+	return;
+
+out_enomem:
+	printf("FATAL: not enough memory to print %s\n", event_type_descriptors[type]);
+	if (evt_list)
+		goto out_free;
+}
+
+/*
+ * Print the help text for the event symbols:
+ */
+void print_events(const char *event_glob, bool name_only, bool quiet_flag,
+			bool long_desc, bool details_flag, bool deprecated,
+			const char *pmu_name)
+{
+	print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
+			    event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
+
+	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
+			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
+	print_tool_events(event_glob, name_only);
+
+	print_hwcache_events(event_glob, name_only);
+
+	print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
+			details_flag, deprecated, pmu_name);
+
+	if (event_glob != NULL)
+		return;
+
+	if (!name_only) {
+		printf("  %-50s [%s]\n",
+		       "rNNN",
+		       event_type_descriptors[PERF_TYPE_RAW]);
+		printf("  %-50s [%s]\n",
+		       "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
+		       event_type_descriptors[PERF_TYPE_RAW]);
+		if (pager_in_use())
+			printf("   (see 'man perf-list' on how to encode it)\n\n");
+
+		printf("  %-50s [%s]\n",
+		       "mem:<addr>[/len][:access]",
+			event_type_descriptors[PERF_TYPE_BREAKPOINT]);
+		if (pager_in_use())
+			printf("\n");
+	}
+
+	print_tracepoint_events(NULL, NULL, name_only);
+
+	print_sdt_events(NULL, NULL, name_only);
+
+	metricgroup__print(true, true, NULL, name_only, details_flag,
+			   pmu_name);
+
+	print_libpfm_events(name_only, long_desc);
+}
diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h
new file mode 100644
index 000000000000..1da9910d83a6
--- /dev/null
+++ b/tools/perf/util/print-events.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_PRINT_EVENTS_H
+#define __PERF_PRINT_EVENTS_H
+
+#include <stdbool.h>
+
+struct event_symbol;
+
+void print_events(const char *event_glob, bool name_only, bool quiet_flag,
+		  bool long_desc, bool details_flag, bool deprecated,
+		  const char *pmu_name);
+int print_hwcache_events(const char *event_glob, bool name_only);
+void print_sdt_events(const char *subsys_glob, const char *event_glob,
+		      bool name_only);
+void print_symbol_events(const char *event_glob, unsigned int type,
+			 struct event_symbol *syms, unsigned int max,
+			 bool name_only);
+void print_tool_events(const char *event_glob, bool name_only);
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
+			     bool name_only);
+
+#endif /* __PERF_PRINT_EVENTS_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 062b5cbe67af..67c12d5303e7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1349,7 +1349,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 				/*
 				 * Adjust the number of lines here.
 				 * If the number of lines == 1, the
-				 * the end of line should be equal to
+				 * end of line should be equal to
 				 * the start of line.
 				 */
 				lr->end--;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 5b09ecbb05dc..b529636ab3ea 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -121,7 +121,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call
 	evlist__for_each_entry(evlist, evsel)
 		evsel__config_leader_sampling(evsel, evlist);
 
-	if (opts->full_auxtrace) {
+	if (opts->full_auxtrace || opts->sample_identifier) {
 		/*
 		 * Need to be able to synthesize and parse selected events with
 		 * arbitrary sample types, which requires always being able to
diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h
index be9a957501f4..4269e916f450 100644
--- a/tools/perf/util/record.h
+++ b/tools/perf/util/record.h
@@ -28,6 +28,7 @@ struct record_opts {
 	bool	      sample_time;
 	bool	      sample_time_set;
 	bool	      sample_cpu;
+	bool	      sample_identifier;
 	bool	      period;
 	bool	      period_set;
 	bool	      running_time;
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 7b342ce38d99..c92326c2233a 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,6 +1,6 @@
 perf-$(CONFIG_LIBPERL)   += trace-event-perl.o
 perf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
-CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
+CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum
 
-CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow
+CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-error=deprecated-declarations
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index adba01b7d9dd..5bbc1b16f368 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -861,6 +861,13 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	brstacksym = python_process_brstacksym(sample, al->thread);
 	pydict_set_item_string_decref(dict, "brstacksym", brstacksym);
 
+	if (sample->machine_pid) {
+		pydict_set_item_string_decref(dict_sample, "machine_pid",
+				_PyLong_FromLong(sample->machine_pid));
+		pydict_set_item_string_decref(dict_sample, "vcpu",
+				_PyLong_FromLong(sample->vcpu));
+	}
+
 	pydict_set_item_string_decref(dict_sample, "cpumode",
 			_PyLong_FromLong((unsigned long)sample->cpumode));
 
@@ -1509,7 +1516,7 @@ static void python_do_process_switch(union perf_event *event,
 		np_tid = event->context_switch.next_prev_tid;
 	}
 
-	t = tuple_new(9);
+	t = tuple_new(11);
 	if (!t)
 		return;
 
@@ -1522,6 +1529,8 @@ static void python_do_process_switch(union perf_event *event,
 	tuple_set_s32(t, 6, machine->pid);
 	tuple_set_bool(t, 7, out);
 	tuple_set_bool(t, 8, out_preempt);
+	tuple_set_s32(t, 9, sample->machine_pid);
+	tuple_set_s32(t, 10, sample->vcpu);
 
 	call_object(handler, t, handler_name);
 
@@ -1559,7 +1568,7 @@ static void python_process_auxtrace_error(struct perf_session *session __maybe_u
 		msg = (const char *)&e->time;
 	}
 
-	t = tuple_new(9);
+	t = tuple_new(11);
 
 	tuple_set_u32(t, 0, e->type);
 	tuple_set_u32(t, 1, e->code);
@@ -1570,6 +1579,8 @@ static void python_process_auxtrace_error(struct perf_session *session __maybe_u
 	tuple_set_u64(t, 6, tm);
 	tuple_set_string(t, 7, msg);
 	tuple_set_u32(t, 8, cpumode);
+	tuple_set_s32(t, 9, e->machine_pid);
+	tuple_set_s32(t, 10, e->vcpu);
 
 	call_object(handler, t, handler_name);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0aa818977d2b..98e16659a149 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -374,10 +374,6 @@ static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int process_finished_round(struct perf_tool *tool,
-				  union perf_event *event,
-				  struct ordered_events *oe);
-
 static int skipn(int fd, off_t n)
 {
 	char buf[4096];
@@ -534,7 +530,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->build_id = process_event_op2_stub;
 	if (tool->finished_round == NULL) {
 		if (tool->ordered_events)
-			tool->finished_round = process_finished_round;
+			tool->finished_round = perf_event__process_finished_round;
 		else
 			tool->finished_round = process_finished_round_stub;
 	}
@@ -562,6 +558,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->feature = process_event_op2_stub;
 	if (tool->compressed == NULL)
 		tool->compressed = perf_session__process_compressed_event;
+	if (tool->finished_init == NULL)
+		tool->finished_init = process_event_op2_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -897,6 +895,10 @@ static void perf_event__auxtrace_error_swap(union perf_event *event,
 	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
 	if (event->auxtrace_error.fmt)
 		event->auxtrace_error.time = bswap_64(event->auxtrace_error.time);
+	if (event->auxtrace_error.fmt >= 2) {
+		event->auxtrace_error.machine_pid = bswap_32(event->auxtrace_error.machine_pid);
+		event->auxtrace_error.vcpu = bswap_32(event->auxtrace_error.vcpu);
+	}
 }
 
 static void perf_event__thread_map_swap(union perf_event *event,
@@ -1067,9 +1069,9 @@ static perf_event__swap_op perf_event__swap_ops[] = {
  *      Flush every events below timestamp 7
  *      etc...
  */
-static int process_finished_round(struct perf_tool *tool __maybe_unused,
-				  union perf_event *event __maybe_unused,
-				  struct ordered_events *oe)
+int perf_event__process_finished_round(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event __maybe_unused,
+				       struct ordered_events *oe)
 {
 	if (dump_trace)
 		fprintf(stdout, "\n");
@@ -1420,7 +1422,9 @@ static struct machine *machines__find_for_cpumode(struct machines *machines,
 	     (sample->cpumode == PERF_RECORD_MISC_GUEST_USER))) {
 		u32 pid;
 
-		if (event->header.type == PERF_RECORD_MMAP
+		if (sample->machine_pid)
+			pid = sample->machine_pid;
+		else if (event->header.type == PERF_RECORD_MMAP
 		    || event->header.type == PERF_RECORD_MMAP2)
 			pid = event->mmap.pid;
 		else
@@ -1706,6 +1710,8 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		if (err)
 			dump_event(session->evlist, event, file_offset, &sample, file_path);
 		return err;
+	case PERF_RECORD_FINISHED_INIT:
+		return tool->finished_init(session, event);
 	default:
 		return -EINVAL;
 	}
@@ -2751,39 +2757,120 @@ void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
 	fprintf(fp, "# ========\n#\n");
 }
 
+static int perf_session__register_guest(struct perf_session *session, pid_t machine_pid)
+{
+	struct machine *machine = machines__findnew(&session->machines, machine_pid);
+	struct thread *thread;
+
+	if (!machine)
+		return -ENOMEM;
+
+	machine->single_address_space = session->machines.host.single_address_space;
+
+	thread = machine__idle_thread(machine);
+	if (!thread)
+		return -ENOMEM;
+	thread__put(thread);
+
+	machine->kallsyms_filename = perf_data__guest_kallsyms_name(session->data, machine_pid);
+
+	return 0;
+}
+
+static int perf_session__set_guest_cpu(struct perf_session *session, pid_t pid,
+				       pid_t tid, int guest_cpu)
+{
+	struct machine *machine = &session->machines.host;
+	struct thread *thread = machine__findnew_thread(machine, pid, tid);
+
+	if (!thread)
+		return -ENOMEM;
+	thread->guest_cpu = guest_cpu;
+	thread__put(thread);
+
+	return 0;
+}
+
 int perf_event__process_id_index(struct perf_session *session,
 				 union perf_event *event)
 {
 	struct evlist *evlist = session->evlist;
 	struct perf_record_id_index *ie = &event->id_index;
+	size_t sz = ie->header.size - sizeof(*ie);
 	size_t i, nr, max_nr;
+	size_t e1_sz = sizeof(struct id_index_entry);
+	size_t e2_sz = sizeof(struct id_index_entry_2);
+	size_t etot_sz = e1_sz + e2_sz;
+	struct id_index_entry_2 *e2;
+	pid_t last_pid = 0;
 
-	max_nr = (ie->header.size - sizeof(struct perf_record_id_index)) /
-		 sizeof(struct id_index_entry);
+	max_nr = sz / e1_sz;
 	nr = ie->nr;
-	if (nr > max_nr)
+	if (nr > max_nr) {
+		printf("Too big: nr %zu max_nr %zu\n", nr, max_nr);
 		return -EINVAL;
+	}
+
+	if (sz >= nr * etot_sz) {
+		max_nr = sz / etot_sz;
+		if (nr > max_nr) {
+			printf("Too big2: nr %zu max_nr %zu\n", nr, max_nr);
+			return -EINVAL;
+		}
+		e2 = (void *)ie + sizeof(*ie) + nr * e1_sz;
+	} else {
+		e2 = NULL;
+	}
 
 	if (dump_trace)
 		fprintf(stdout, " nr: %zu\n", nr);
 
-	for (i = 0; i < nr; i++) {
+	for (i = 0; i < nr; i++, (e2 ? e2++ : 0)) {
 		struct id_index_entry *e = &ie->entries[i];
 		struct perf_sample_id *sid;
+		int ret;
 
 		if (dump_trace) {
 			fprintf(stdout,	" ... id: %"PRI_lu64, e->id);
 			fprintf(stdout,	"  idx: %"PRI_lu64, e->idx);
 			fprintf(stdout,	"  cpu: %"PRI_ld64, e->cpu);
-			fprintf(stdout,	"  tid: %"PRI_ld64"\n", e->tid);
+			fprintf(stdout, "  tid: %"PRI_ld64, e->tid);
+			if (e2) {
+				fprintf(stdout, "  machine_pid: %"PRI_ld64, e2->machine_pid);
+				fprintf(stdout, "  vcpu: %"PRI_lu64"\n", e2->vcpu);
+			} else {
+				fprintf(stdout, "\n");
+			}
 		}
 
 		sid = evlist__id2sid(evlist, e->id);
 		if (!sid)
 			return -ENOENT;
+
 		sid->idx = e->idx;
 		sid->cpu.cpu = e->cpu;
 		sid->tid = e->tid;
+
+		if (!e2)
+			continue;
+
+		sid->machine_pid = e2->machine_pid;
+		sid->vcpu.cpu = e2->vcpu;
+
+		if (!sid->machine_pid)
+			continue;
+
+		if (sid->machine_pid != last_pid) {
+			ret = perf_session__register_guest(session, sid->machine_pid);
+			if (ret)
+				return ret;
+			last_pid = sid->machine_pid;
+			perf_guest = true;
+		}
+
+		ret = perf_session__set_guest_cpu(session, sid->machine_pid, e->tid, e2->vcpu);
+		if (ret)
+			return ret;
 	}
 	return 0;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 34500a3da735..be5871ea558f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -155,4 +155,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 int perf_event__process_id_index(struct perf_session *session,
 				 union perf_event *event);
 
+int perf_event__process_finished_round(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct ordered_events *oe);
+
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index c255a2c90cd6..5b1e6468d5e8 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -11,7 +11,7 @@ def clang_has_option(option):
     return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ]
 
 if cc_is_clang:
-    from distutils.sysconfig import get_config_vars
+    from sysconfig import get_config_vars
     vars = get_config_vars()
     for var in ('CFLAGS', 'OPT'):
         vars[var] = sub("-specs=[^ ]+", "", vars[var])
@@ -28,10 +28,10 @@ if cc_is_clang:
         if not clang_has_option("-ffat-lto-objects"):
             vars[var] = sub("-ffat-lto-objects", "", vars[var])
 
-from distutils.core import setup, Extension
+from setuptools import setup, Extension
 
-from distutils.command.build_ext   import build_ext   as _build_ext
-from distutils.command.install_lib import install_lib as _install_lib
+from setuptools.command.build_ext   import build_ext   as _build_ext
+from setuptools.command.install_lib import install_lib as _install_lib
 
 class build_ext(_build_ext):
     def finalize_options(self):
@@ -48,7 +48,9 @@ class install_lib(_install_lib):
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter', '-Wno-redundant-decls', '-DPYTHON_PERF' ]
-if not cc_is_clang:
+if cc_is_clang:
+    cflags += ["-Wno-unused-command-line-argument" ]
+else:
     cflags += ['-Wno-cast-function-type' ]
 
 src_perf  = getenv('srctree') + '/tools/perf'
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 606f09b09226..44045565c8f8 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -374,7 +374,7 @@ static void abs_printout(struct perf_stat_config *config,
 			config->csv_output ? 0 : config->unit_width,
 			evsel->unit, config->csv_sep);
 
-	fprintf(output, "%-*s", config->csv_output ? 0 : 25, evsel__name(evsel));
+	fprintf(output, "%-*s", config->csv_output ? 0 : 32, evsel__name(evsel));
 
 	print_cgroup(config, evsel);
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index b3be5b1d9dbb..75bec32d4f57 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1305,16 +1305,29 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 			if (elf_read_program_header(syms_ss->elf,
 						    (u64)sym.st_value, &phdr)) {
-				pr_warning("%s: failed to find program header for "
+				pr_debug4("%s: failed to find program header for "
 					   "symbol: %s st_value: %#" PRIx64 "\n",
 					   __func__, elf_name, (u64)sym.st_value);
-				continue;
+				pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+					"sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n",
+					__func__, (u64)sym.st_value, (u64)shdr.sh_addr,
+					(u64)shdr.sh_offset);
+				/*
+				 * Fail to find program header, let's rollback
+				 * to use shdr.sh_addr and shdr.sh_offset to
+				 * calibrate symbol's file address, though this
+				 * is not necessary for normal C ELF file, we
+				 * still need to handle java JIT symbols in this
+				 * case.
+				 */
+				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+			} else {
+				pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+					"p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
+					__func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
+					(u64)phdr.p_offset);
+				sym.st_value -= phdr.p_vaddr - phdr.p_offset;
 			}
-			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
-				  "p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
-				  __func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
-				  (u64)phdr.p_offset);
-			sym.st_value -= phdr.p_vaddr - phdr.p_offset;
 		}
 
 		demangled = demangle_sym(dso, kmodule, elf_name);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index f72baf636724..a4b22caa7c24 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2300,11 +2300,13 @@ do_kallsyms:
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 {
 	int err;
-	const char *kallsyms_filename = NULL;
+	const char *kallsyms_filename;
 	struct machine *machine = map__kmaps(map)->machine;
 	char path[PATH_MAX];
 
-	if (machine__is_default_guest(machine)) {
+	if (machine->kallsyms_filename) {
+		kallsyms_filename = machine->kallsyms_filename;
+	} else if (machine__is_default_guest(machine)) {
 		/*
 		 * if the user specified a vmlinux filename, use it and only
 		 * it, reporting errors to the user if it cannot be used.
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 84d17bd4efae..2ae59c03ae77 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1712,48 +1712,112 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 	return 0;
 }
 
-int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
-				    struct evlist *evlist, struct machine *machine)
+int perf_event__synthesize_id_sample(__u64 *array, u64 type, const struct perf_sample *sample)
+{
+	__u64 *start = array;
+
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union u64_swap u;
+
+	if (type & PERF_SAMPLE_TID) {
+		u.val32[0] = sample->pid;
+		u.val32[1] = sample->tid;
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_TIME) {
+		*array = sample->time;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_ID) {
+		*array = sample->id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_STREAM_ID) {
+		*array = sample->stream_id;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_CPU) {
+		u.val32[0] = sample->cpu;
+		u.val32[1] = 0;
+		*array = u.val64;
+		array++;
+	}
+
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		*array = sample->id;
+		array++;
+	}
+
+	return (void *)array - (void *)start;
+}
+
+int __perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
+				      struct evlist *evlist, struct machine *machine, size_t from)
 {
 	union perf_event *ev;
 	struct evsel *evsel;
-	size_t nr = 0, i = 0, sz, max_nr, n;
+	size_t nr = 0, i = 0, sz, max_nr, n, pos;
+	size_t e1_sz = sizeof(struct id_index_entry);
+	size_t e2_sz = sizeof(struct id_index_entry_2);
+	size_t etot_sz = e1_sz + e2_sz;
+	bool e2_needed = false;
 	int err;
 
-	pr_debug2("Synthesizing id index\n");
-
-	max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) /
-		 sizeof(struct id_index_entry);
+	max_nr = (UINT16_MAX - sizeof(struct perf_record_id_index)) / etot_sz;
 
-	evlist__for_each_entry(evlist, evsel)
+	pos = 0;
+	evlist__for_each_entry(evlist, evsel) {
+		if (pos++ < from)
+			continue;
 		nr += evsel->core.ids;
+	}
+
+	if (!nr)
+		return 0;
+
+	pr_debug2("Synthesizing id index\n");
 
 	n = nr > max_nr ? max_nr : nr;
-	sz = sizeof(struct perf_record_id_index) + n * sizeof(struct id_index_entry);
+	sz = sizeof(struct perf_record_id_index) + n * etot_sz;
 	ev = zalloc(sz);
 	if (!ev)
 		return -ENOMEM;
 
+	sz = sizeof(struct perf_record_id_index) + n * e1_sz;
+
 	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
-	ev->id_index.header.size = sz;
 	ev->id_index.nr = n;
 
+	pos = 0;
 	evlist__for_each_entry(evlist, evsel) {
 		u32 j;
 
-		for (j = 0; j < evsel->core.ids; j++) {
+		if (pos++ < from)
+			continue;
+		for (j = 0; j < evsel->core.ids; j++, i++) {
 			struct id_index_entry *e;
+			struct id_index_entry_2 *e2;
 			struct perf_sample_id *sid;
 
 			if (i >= n) {
+				ev->id_index.header.size = sz + (e2_needed ? n * e2_sz : 0);
 				err = process(tool, ev, NULL, machine);
 				if (err)
 					goto out_err;
 				nr -= n;
 				i = 0;
+				e2_needed = false;
 			}
 
-			e = &ev->id_index.entries[i++];
+			e = &ev->id_index.entries[i];
 
 			e->id = evsel->core.id[j];
 
@@ -1766,11 +1830,18 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
 			e->idx = sid->idx;
 			e->cpu = sid->cpu.cpu;
 			e->tid = sid->tid;
+
+			if (sid->machine_pid)
+				e2_needed = true;
+
+			e2 = (void *)ev + sz;
+			e2[i].machine_pid = sid->machine_pid;
+			e2[i].vcpu        = sid->vcpu.cpu;
 		}
 	}
 
-	sz = sizeof(struct perf_record_id_index) + nr * sizeof(struct id_index_entry);
-	ev->id_index.header.size = sz;
+	sz = sizeof(struct perf_record_id_index) + nr * e1_sz;
+	ev->id_index.header.size = sz + (e2_needed ? nr * e2_sz : 0);
 	ev->id_index.nr = nr;
 
 	err = process(tool, ev, NULL, machine);
@@ -1780,6 +1851,12 @@ out_err:
 	return err;
 }
 
+int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process,
+				    struct evlist *evlist, struct machine *machine)
+{
+	return __perf_event__synthesize_id_index(tool, process, evlist, machine, 0);
+}
+
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct perf_thread_map *threads,
 				  perf_event__handler_t process, bool needs_mmap,
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index 78a0450db164..81cb3d6af0b9 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -55,6 +55,8 @@ int perf_event__synthesize_extra_attr(struct perf_tool *tool, struct evlist *evs
 int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_features(struct perf_tool *tool, struct perf_session *session, struct evlist *evlist, perf_event__handler_t process);
 int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine);
+int __perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_t process, struct evlist *evlist, struct machine *machine, size_t from);
+int perf_event__synthesize_id_sample(__u64 *array, u64 type, const struct perf_sample *sample);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, perf_event__handler_t process, struct machine *machine, bool mmap_data);
 int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 665e5c0618ed..e3e5427e1c3c 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -47,6 +47,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->tid = tid;
 		thread->ppid = -1;
 		thread->cpu = -1;
+		thread->guest_cpu = -1;
 		thread->lbr_stitch_enable = false;
 		INIT_LIST_HEAD(&thread->namespaces_list);
 		INIT_LIST_HEAD(&thread->comm_list);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index b066fb30d203..241f300d7d6e 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -39,6 +39,7 @@ struct thread {
 	pid_t			tid;
 	pid_t			ppid;
 	int			cpu;
+	int			guest_cpu; /* For QEMU thread */
 	refcount_t		refcnt;
 	bool			comm_set;
 	int			comm_len;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index f2352dba1875..c957fb849ac6 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -76,7 +76,8 @@ struct perf_tool {
 			stat_config,
 			stat,
 			stat_round,
-			feature;
+			feature,
+			finished_init;
 	event_op4	compressed;
 	event_op3	auxtrace;
 	bool		ordered_events;
diff --git a/tools/perf/util/topdown.c b/tools/perf/util/topdown.c
index a369f84ceb6a..1090841550f7 100644
--- a/tools/perf/util/topdown.c
+++ b/tools/perf/util/topdown.c
@@ -65,3 +65,10 @@ __weak bool arch_topdown_sample_read(struct evsel *leader __maybe_unused)
 {
 	return false;
 }
+
+__weak const char *arch_get_topdown_pmu_name(struct evlist *evlist
+					     __maybe_unused,
+					     bool warn __maybe_unused)
+{
+	return "cpu";
+}
diff --git a/tools/perf/util/topdown.h b/tools/perf/util/topdown.h
index 118e75281f93..f9531528c559 100644
--- a/tools/perf/util/topdown.h
+++ b/tools/perf/util/topdown.h
@@ -2,11 +2,12 @@
 #ifndef TOPDOWN_H
 #define TOPDOWN_H 1
 #include "evsel.h"
+#include "evlist.h"
 
 bool arch_topdown_check_group(bool *warn);
 void arch_topdown_group_warn(void);
 bool arch_topdown_sample_read(struct evsel *leader);
-
+const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn);
 int topdown_filter_events(const char **attr, char **str, bool use_group,
 			  const char *pmu_name);
 
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index a65f65d0857e..892c323b4ac9 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -19,16 +19,24 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <internal/lib.h> // page_size
+#include <sys/param.h>
 
 #include "trace-event.h"
+#include "tracepoint.h"
 #include <api/fs/tracing_path.h>
 #include "evsel.h"
 #include "debug.h"
 
 #define VERSION "0.6"
+#define MAX_EVENT_LENGTH 512
 
 static int output_fd;
 
+struct tracepoint_path {
+	char *system;
+	char *name;
+	struct tracepoint_path *next;
+};
 
 int bigendian(void)
 {
@@ -400,6 +408,94 @@ put_tracepoints_path(struct tracepoint_path *tps)
 	}
 }
 
+static struct tracepoint_path *tracepoint_id_to_path(u64 config)
+{
+	struct tracepoint_path *path = NULL;
+	DIR *sys_dir, *evt_dir;
+	struct dirent *sys_dirent, *evt_dirent;
+	char id_buf[24];
+	int fd;
+	u64 id;
+	char evt_path[MAXPATHLEN];
+	char *dir_path;
+
+	sys_dir = tracing_events__opendir();
+	if (!sys_dir)
+		return NULL;
+
+	for_each_subsystem(sys_dir, sys_dirent) {
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
+		evt_dir = opendir(dir_path);
+		if (!evt_dir)
+			goto next;
+
+		for_each_event(dir_path, evt_dir, evt_dirent) {
+
+			scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
+				  evt_dirent->d_name);
+			fd = open(evt_path, O_RDONLY);
+			if (fd < 0)
+				continue;
+			if (read(fd, id_buf, sizeof(id_buf)) < 0) {
+				close(fd);
+				continue;
+			}
+			close(fd);
+			id = atoll(id_buf);
+			if (id == config) {
+				put_events_file(dir_path);
+				closedir(evt_dir);
+				closedir(sys_dir);
+				path = zalloc(sizeof(*path));
+				if (!path)
+					return NULL;
+				if (asprintf(&path->system, "%.*s",
+					     MAX_EVENT_LENGTH, sys_dirent->d_name) < 0) {
+					free(path);
+					return NULL;
+				}
+				if (asprintf(&path->name, "%.*s",
+					     MAX_EVENT_LENGTH, evt_dirent->d_name) < 0) {
+					zfree(&path->system);
+					free(path);
+					return NULL;
+				}
+				return path;
+			}
+		}
+		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
+	}
+
+	closedir(sys_dir);
+	return NULL;
+}
+
+static struct tracepoint_path *tracepoint_name_to_path(const char *name)
+{
+	struct tracepoint_path *path = zalloc(sizeof(*path));
+	char *str = strchr(name, ':');
+
+	if (path == NULL || str == NULL) {
+		free(path);
+		return NULL;
+	}
+
+	path->system = strndup(name, str - name);
+	path->name = strdup(str+1);
+
+	if (path->system == NULL || path->name == NULL) {
+		zfree(&path->system);
+		zfree(&path->name);
+		zfree(&path);
+	}
+
+	return path;
+}
+
 static struct tracepoint_path *
 get_tracepoints_path(struct list_head *pattrs)
 {
diff --git a/tools/perf/util/tracepoint.c b/tools/perf/util/tracepoint.c
new file mode 100644
index 000000000000..89ef56c43311
--- /dev/null
+++ b/tools/perf/util/tracepoint.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "tracepoint.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <sys/param.h>
+#include <unistd.h>
+
+#include <api/fs/tracing_path.h>
+
+int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
+{
+	char evt_path[MAXPATHLEN];
+	int fd;
+
+	snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name);
+	fd = open(evt_path, O_RDONLY);
+	if (fd < 0)
+		return -EINVAL;
+	close(fd);
+
+	return 0;
+}
+
+/*
+ * Check whether event is in <debugfs_mount_point>/tracing/events
+ */
+int is_valid_tracepoint(const char *event_string)
+{
+	DIR *sys_dir, *evt_dir;
+	struct dirent *sys_dirent, *evt_dirent;
+	char evt_path[MAXPATHLEN];
+	char *dir_path;
+
+	sys_dir = tracing_events__opendir();
+	if (!sys_dir)
+		return 0;
+
+	for_each_subsystem(sys_dir, sys_dirent) {
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
+		evt_dir = opendir(dir_path);
+		if (!evt_dir)
+			goto next;
+
+		for_each_event(dir_path, evt_dir, evt_dirent) {
+			snprintf(evt_path, MAXPATHLEN, "%s:%s",
+				 sys_dirent->d_name, evt_dirent->d_name);
+			if (!strcmp(evt_path, event_string)) {
+				closedir(evt_dir);
+				closedir(sys_dir);
+				return 1;
+			}
+		}
+		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
+	}
+	closedir(sys_dir);
+	return 0;
+}
diff --git a/tools/perf/util/tracepoint.h b/tools/perf/util/tracepoint.h
new file mode 100644
index 000000000000..c4a110fe87d7
--- /dev/null
+++ b/tools/perf/util/tracepoint.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_TRACEPOINT_H
+#define __PERF_TRACEPOINT_H
+
+#include <dirent.h>
+#include <string.h>
+
+int tp_event_has_id(const char *dir_path, struct dirent *evt_dir);
+
+#define for_each_event(dir_path, evt_dir, evt_dirent)		\
+	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
+		if (evt_dirent->d_type == DT_DIR &&		\
+		    (strcmp(evt_dirent->d_name, ".")) &&	\
+		    (strcmp(evt_dirent->d_name, "..")) &&	\
+		    (!tp_event_has_id(dir_path, evt_dirent)))
+
+#define for_each_subsystem(sys_dir, sys_dirent)			\
+	while ((sys_dirent = readdir(sys_dir)) != NULL)		\
+		if (sys_dirent->d_type == DT_DIR &&		\
+		    (strcmp(sys_dirent->d_name, ".")) &&	\
+		    (strcmp(sys_dirent->d_name, "..")))
+
+int is_valid_tracepoint(const char *event_string);
+
+#endif /* __PERF_TRACEPOINT_H */
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index 7d83a31732a7..88fd1c4c1cb8 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -25,6 +25,7 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
 u64 rdtsc(void);
+double arch_get_tsc_freq(void);
 
 size_t perf_event__fprintf_time_conv(union perf_event *event, FILE *fp);
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eeb83c80f458..391c1e928bd7 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/time64.h>
+#include <linux/overflow.h>
 #include <unistd.h>
 #include "cap.h"
 #include "strlist.h"
@@ -200,7 +201,7 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat)
 	return rmdir(path);
 }
 
-static int rm_rf_kcore_dir(const char *path)
+static int rm_rf_a_kcore_dir(const char *path, const char *name)
 {
 	char kcore_dir_path[PATH_MAX];
 	const char *pat[] = {
@@ -210,11 +211,44 @@ static int rm_rf_kcore_dir(const char *path)
 		NULL,
 	};
 
-	snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/kcore_dir", path);
+	snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/%s", path, name);
 
 	return rm_rf_depth_pat(kcore_dir_path, 0, pat);
 }
 
+static bool kcore_dir_filter(const char *name __maybe_unused, struct dirent *d)
+{
+	const char *pat[] = {
+		"kcore_dir",
+		"kcore_dir__[1-9]*",
+		NULL,
+	};
+
+	return match_pat(d->d_name, pat);
+}
+
+static int rm_rf_kcore_dir(const char *path)
+{
+	struct strlist *kcore_dirs;
+	struct str_node *nd;
+	int ret;
+
+	kcore_dirs = lsdir(path, kcore_dir_filter);
+
+	if (!kcore_dirs)
+		return 0;
+
+	strlist__for_each_entry(nd, kcore_dirs) {
+		ret = rm_rf_a_kcore_dir(path, nd->s);
+		if (ret)
+			return ret;
+	}
+
+	strlist__delete(kcore_dirs);
+
+	return 0;
+}
+
 int rm_rf_perf_data(const char *path)
 {
 	const char *pat[] = {
@@ -467,3 +501,35 @@ char *filename_with_chroot(int pid, const char *filename)
 
 	return new_name;
 }
+
+/*
+ * Reallocate an array *arr of size *arr_sz so that it is big enough to contain
+ * x elements of size msz, initializing new entries to *init_val or zero if
+ * init_val is NULL
+ */
+int do_realloc_array_as_needed(void **arr, size_t *arr_sz, size_t x, size_t msz, const void *init_val)
+{
+	size_t new_sz = *arr_sz;
+	void *new_arr;
+	size_t i;
+
+	if (!new_sz)
+		new_sz = msz >= 64 ? 1 : roundup(64, msz); /* Start with at least 64 bytes */
+	while (x >= new_sz) {
+		if (check_mul_overflow(new_sz, (size_t)2, &new_sz))
+			return -ENOMEM;
+	}
+	if (new_sz == *arr_sz)
+		return 0;
+	new_arr = calloc(new_sz, msz);
+	if (!new_arr)
+		return -ENOMEM;
+	memcpy(new_arr, *arr, *arr_sz * msz);
+	if (init_val) {
+		for (i = *arr_sz; i < new_sz; i++)
+			memcpy(new_arr + (i * msz), init_val, msz);
+	}
+	*arr = new_arr;
+	*arr_sz = new_sz;
+	return 0;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0f78f1e7782d..c1f2d423a9ec 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -79,4 +79,19 @@ struct perf_debuginfod {
 void perf_debuginfod_setup(struct perf_debuginfod *di);
 
 char *filename_with_chroot(int pid, const char *filename);
+
+int do_realloc_array_as_needed(void **arr, size_t *arr_sz, size_t x,
+			       size_t msz, const void *init_val);
+
+#define realloc_array_as_needed(a, n, x, v) ({			\
+	typeof(x) __x = (x);					\
+	__x >= (n) ?						\
+		do_realloc_array_as_needed((void **)&(a),	\
+					   &(n),		\
+					   __x,			\
+					   sizeof(*(a)),	\
+					   (const void *)(v)) :	\
+		0;						\
+	})
+
 #endif /* GIT_COMPAT_UTIL_H */