Merge tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Namhyung Kim:
 "perf stat:

   - Support new 'cluster' aggregation mode for shared resources
     depending on the hardware configuration:

        $ sudo perf stat -a --per-cluster -e cycles,instructions sleep 1

         Performance counter stats for 'system wide':

        S0-D0-CLS0    2         85,051,822      cycles
        S0-D0-CLS0    2         73,909,908      instructions      #    0.87  insn per cycle
        S0-D0-CLS2    2         93,365,918      cycles
        S0-D0-CLS2    2         83,006,158      instructions      #    0.89  insn per cycle
        S0-D0-CLS4    2        104,157,523      cycles
        S0-D0-CLS4    2         53,234,396      instructions      #    0.51  insn per cycle
        S0-D0-CLS6    2         65,891,079      cycles
        S0-D0-CLS6    2         41,478,273      instructions      #    0.63  insn per cycle

               1.002407989 seconds time elapsed

   - Various fixes and cleanups for event metrics including NaN handling

  perf script:

   - Use libcapstone if available to disassemble the instructions. This
     enables 'perf script -F disasm' and 'perf script --insn-trace=disasm'
     (for Intel-PT):

        $ perf script -F event,ip,disasm
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa9839d25             movq %rax, %r14
        cycles:P:  ffffffffa9cdcaf0             endbr64
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa99c4de5             movq 0x30(%rcx), %r8
        cycles:P:  ffffffffa988d428             wrmsr
        cycles:P:  ffffffffaa401f86             iretq
        cycles:P:  ffffffffa9907983             movl 0x68(%rbx), %eax
        cycles:P:  ffffffffa988d428             wrmsr

   - Expose sample ID / stream ID to python scripts

  perf test:

   - Add more perf test cases from Redhat internal test suites. This
     time it adds the base infra and a few perf probe tests. More to
     come. :)

   - Add 'perf test -p' for parallel execution and fix some issues found
     by the parallel test

   - Support symbol test to print symbols in given (active) module:

        $ perf test -F -v Symbols --dso /lib/modules/$(uname -r)/kernel/fs/ext4/ext4.ko
        --- start ---
        Testing /lib/modules/6.5.13-1rodete2-amd64/kernel/fs/ext4/ext4.ko
        Overlapping symbols:
         7a990-7a9a0 l __pfx_ext4_exit_fs
         7a990-7a9a0 g __pfx_cleanup_module
        Overlapping symbols:
         7a9a0-7aa1c l ext4_exit_fs
         7a9a0-7aa1c g cleanup_module
        ...

  JSON metric updates:

   - A new round of Intel metric updates

   - Support Power11 PVR (compatible to Power10)

   - Fix cache latency events on Zen 4 to set SliceId properly

  Internal:

   - Fix reference counting for 'map' data structure, tireless work from
     Ian!

   - More memory optimization for struct thread and annotate histogram.
     Now, 'perf report' (TUI) and 'perf annotate' should be much
     lighter-weight in terms of memory footprint

   - Support cross-arch perf register access. Clean up the build
     configuration so that it can detect arch-register support at
     runtime. This can allow to parse register data in sample which was
     recorded in a different arch

  Others:

   - Sync task state in 'perf sched' to kernel using trace event fields.
     The task states have been changed so tools cannot assume a fixed
     encoding

   - Clean up 'perf mem' to generalize the arch-specific events

   - Add support for local and global variables to data type profiling.
     This would increase the success rate of type resolution with DWARF

   - Add short option -H for --hierarchy in 'perf report' and 'perf top'"

* tag 'perf-tools-for-v6.9-2024-03-13' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (154 commits)
  perf annotate: Add comments in the data structures
  perf annotate: Remove sym_hist.addr[] array
  perf annotate: Calculate instruction overhead using hashmap
  perf annotate: Add a hashmap for symbol histogram
  perf threads: Reduce table size from 256 to 8
  perf threads: Switch from rbtree to hashmap
  perf threads: Move threads to its own files
  perf machine: Move machine's threads into its own abstraction
  perf machine: Move fprintf to for_each loop and a callback
  perf trace: Ignore thread hashing in summary
  perf report: Sort child tasks by tid
  perf vendor events amd: Fix Zen 4 cache latency events
  perf version: Display availability of OpenCSD support
  perf vendor events intel: Add umasks/occ_sel to PCU events.
  perf map: Fix map reference count issues
  libperf evlist: Avoid out-of-bounds access
  perf lock contention: Account contending locks too
  perf metrics: Fix segv for metrics with no events
  perf metrics: Fix metric matching
  perf pmu: Fix a potential memory leak in perf_pmu__lookup()
  ...

1 files changed, 53 insertions, 13 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b1f57401ff23..37088cc0ff1b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -34,6 +34,7 @@
 #include "util/event.h"
 #include "ui/ui.h"
 #include "print_binary.h"
+#include "print_insn.h"
 #include "archinsn.h"
 #include <linux/bitmap.h>
 #include <linux/kernel.h>
@@ -134,6 +135,7 @@ enum perf_output_field {
 	PERF_OUTPUT_CGROUP          = 1ULL << 39,
 	PERF_OUTPUT_RETIRE_LAT      = 1ULL << 40,
 	PERF_OUTPUT_DSOFF           = 1ULL << 41,
+	PERF_OUTPUT_DISASM          = 1ULL << 42,
 };
 
 struct perf_script {
@@ -189,6 +191,7 @@ struct output_option {
 	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
+	{.str = "disasm", .field = PERF_OUTPUT_DISASM},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
@@ -1162,7 +1165,8 @@ out:
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
 			    int insn, FILE *fp, int *total_cycles,
-			    struct perf_event_attr *attr)
+			    struct perf_event_attr *attr,
+			    struct thread *thread)
 {
 	int ilen = 0;
 	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t", ip,
@@ -1171,6 +1175,16 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 	if (PRINT_FIELD(BRSTACKINSNLEN))
 		printed += fprintf(fp, "ilen: %d\t", ilen);
 
+	if (PRINT_FIELD(SRCLINE)) {
+		struct addr_location al;
+
+		addr_location__init(&al);
+		thread__find_map(thread, x->cpumode, ip, &al);
+		printed += map__fprintf_srcline(al.map, al.addr, " srcline: ", fp);
+		printed += fprintf(fp, "\t");
+		addr_location__exit(&al);
+	}
+
 	printed += fprintf(fp, "#%s%s%s%s",
 			      en->flags.predicted ? " PRED" : "",
 			      en->flags.mispred ? " MISPRED" : "",
@@ -1182,6 +1196,7 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 		if (insn)
 			printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles);
 	}
+
 	return printed + fprintf(fp, "\n");
 }
 
@@ -1260,7 +1275,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
 		printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
 					    &x, buffer, len, 0, fp, &total_cycles,
-					    attr);
+					    attr, thread);
 		if (PRINT_FIELD(SRCCODE))
 			printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
 	}
@@ -1291,7 +1306,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
 				printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
-							    &total_cycles, attr);
+							    &total_cycles, attr, thread);
 				if (PRINT_FIELD(SRCCODE))
 					printed += print_srccode(thread, x.cpumode, ip);
 				break;
@@ -1511,11 +1526,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 	if (PRINT_FIELD(INSNLEN))
 		printed += fprintf(fp, " ilen: %d", sample->insn_len);
 	if (PRINT_FIELD(INSN) && sample->insn_len) {
-		int i;
-
-		printed += fprintf(fp, " insn:");
-		for (i = 0; i < sample->insn_len; i++)
-			printed += fprintf(fp, " %02x", (unsigned char)sample->insn[i]);
+		printed += fprintf(fp, " insn: ");
+		printed += sample__fprintf_insn_raw(sample, fp);
+	}
+	if (PRINT_FIELD(DISASM) && sample->insn_len) {
+		printed += fprintf(fp, "\t\t");
+		printed += sample__fprintf_insn_asm(sample, thread, machine, fp);
 	}
 	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
@@ -3108,6 +3124,13 @@ parse:
 			rc = -EINVAL;
 			goto out;
 		}
+#ifndef HAVE_LIBCAPSTONE_SUPPORT
+		if (change != REMOVE && strcmp(tok, "disasm") == 0) {
+			fprintf(stderr, "Field \"disasm\" requires perf to be built with libcapstone support.\n");
+			rc = -EINVAL;
+			goto out;
+		}
+#endif
 
 		if (type == -1) {
 			/* add user option to all events types for
@@ -3765,10 +3788,24 @@ static int perf_script__process_auxtrace_info(struct perf_session *session,
 #endif
 
 static int parse_insn_trace(const struct option *opt __maybe_unused,
-			    const char *str __maybe_unused,
-			    int unset __maybe_unused)
+			    const char *str, int unset __maybe_unused)
 {
-	parse_output_fields(NULL, "+insn,-event,-period", 0);
+	const char *fields = "+insn,-event,-period";
+	int ret;
+
+	if (str) {
+		if (strcmp(str, "disasm") == 0)
+			fields = "+disasm,-event,-period";
+		else if (strlen(str) != 0 && strcmp(str, "raw") != 0) {
+			fprintf(stderr, "Only accept raw|disasm\n");
+			return -EINVAL;
+		}
+	}
+
+	ret = parse_output_fields(NULL, fields, 0);
+	if (ret < 0)
+		return ret;
+
 	itrace_parse_synth_opts(opt, "i0ns", 0);
 	symbol_conf.nanosecs = true;
 	return 0;
@@ -3902,7 +3939,7 @@ int cmd_script(int argc, const char **argv)
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
-		     "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth,"
+		     "brstackinsnlen,brstackoff,callindent,insn,disasm,insnlen,synth,"
 		     "phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
 		     "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat",
 		     parse_output_fields),
@@ -3914,7 +3951,7 @@ int cmd_script(int argc, const char **argv)
 		   "only consider these symbols"),
 	OPT_INTEGER(0, "addr-range", &symbol_conf.addr_range,
 		    "Use with -S to list traced records within address range"),
-	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
+	OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, "raw|disasm",
 			"Decode instructions from itrace", parse_insn_trace),
 	OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL,
 			"Run xed disassembler on output", parse_xed),
@@ -4366,6 +4403,9 @@ script_found:
 
 	flush_scripting();
 
+	if (verbose > 2 || debug_kmaps)
+		perf_session__dump_kmaps(session);
+
 out_delete:
 	if (script.ptime_range) {
 		itrace_synth_opts__clear_time_range(&itrace_synth_opts);