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

e6328a7a · Linus Torvalds <[email protected]> · 2017-09-12 11:28:13 -07:00

Pull perf tooling updates from Ingo Molnar:
 "Perf tooling updates and fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf annotate browser: Help for cycling thru hottest instructions with TAB/shift+TAB
  perf stat: Only auto-merge events that are PMU aliases
  perf test: Add test case for PERF_SAMPLE_PHYS_ADDR
  perf script: Support physical address
  perf mem: Support physical address
  perf sort: Add sort option for physical address
  perf tools: Support new sample type for physical address
  perf vendor events powerpc: Remove duplicate events
  perf intel-pt: Fix syntax in documentation of config option
  perf test powerpc: Fix 'Object code reading' test
  perf trace: Support syscall name globbing
  perf syscalltbl: Support glob matching on syscall names
  perf report: Calculate the average cycles of iterations

Commit: e6328a7abe7f8fcd32e9d3bcbd14ff2161bf71c9
Parents: 33f82bda · 770e9612

Merge commit. Changes below are compared with the first parent: 33f82bda.

Changes

37 files changed · +368 −268

File	Status	Add	Del	Content
tools/include/uapi/linux/perf_event.h	modified	+3	−1	View file
tools/perf/Documentation/intel-pt.txt	modified	+1	−1	View file
tools/perf/Documentation/perf-mem.txt	modified	+4	−0	View file
tools/perf/Documentation/perf-record.txt	modified	+4	−1	View file
tools/perf/Documentation/perf-report.txt	modified	+1	−0	View file
tools/perf/Documentation/perf-script.txt	modified	+1	−1	View file
tools/perf/Documentation/perf-trace.txt	modified	+1	−1	View file
tools/perf/builtin-mem.c	modified	+71	−26	View file
tools/perf/builtin-record.c	modified	+2	−0	View file
tools/perf/builtin-script.c	modified	+13	−2	View file
tools/perf/builtin-stat.c	modified	+1	−1	View file
tools/perf/builtin-trace.c	modified	+35	−4	View file
tools/perf/perf.h	modified	+1	−0	View file
tools/perf/pmu-events/arch/powerpc/power9/frontend.json	modified	+1	−6	View file
tools/perf/pmu-events/arch/powerpc/power9/other.json	modified	+0	−120	View file
tools/perf/pmu-events/arch/powerpc/power9/pipeline.json	modified	+1	−6	View file
tools/perf/pmu-events/arch/powerpc/power9/pmc.json	modified	+1	−6	View file
tools/perf/tests/code-reading.c	modified	+5	−0	View file
tools/perf/tests/sample-parsing.c	modified	+5	−1	View file
tools/perf/ui/browsers/annotate.c	modified	+2	−1	View file
tools/perf/ui/browsers/hists.c	modified	+2	−6	View file
tools/perf/ui/stdio/hist.c	modified	+3	−7	View file
tools/perf/util/callchain.c	modified	+23	−26	View file
tools/perf/util/callchain.h	modified	+4	−5	View file
tools/perf/util/event.h	modified	+1	−0	View file
tools/perf/util/evsel.c	modified	+18	−1	View file
tools/perf/util/evsel.h	modified	+1	−0	View file
tools/perf/util/hist.c	modified	+4	−0	View file
tools/perf/util/hist.h	modified	+1	−0	View file
tools/perf/util/machine.c	modified	+59	−37	View file
tools/perf/util/parse-events.c	modified	+16	−8	View file
tools/perf/util/session.c	modified	+3	−0	View file
tools/perf/util/sort.c	modified	+42	−0	View file
tools/perf/util/sort.h	modified	+1	−0	View file
tools/perf/util/symbol.h	modified	+1	−0	View file
tools/perf/util/syscalltbl.c	modified	+33	−0	View file
tools/perf/util/syscalltbl.h	modified	+3	−0	View file

Only the first 600 diff lines are shown. Download the complete patch.

tools/include/uapi/linux/perf_event.h

View file

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 2a37ae9..140ae63 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -139,8 +139,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
 	PERF_SAMPLE_REGS_INTR			= 1U << 18,
+	PERF_SAMPLE_PHYS_ADDR			= 1U << 19,
 
-	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 20,		/* non-ABI */
 };
 
 /*
@@ -814,6 +815,7 @@ enum perf_event_type {
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
 	 *	{ u64			abi; # enum perf_sample_regs_abi
 	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+	 *	{ u64			phys_addr;} && PERF_SAMPLE_PHYS_ADDR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,

tools/perf/Documentation/intel-pt.txt

View file

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index ab1b082..76971d2 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -873,7 +873,7 @@ amended to take the number of elements as a parameter.
 
 	$ cat ~/.perfconfig
 	[intel-pt]
-		mispred-all
+		mispred-all = on
 
 	$ perf record -e intel_pt//u ./sort 3000
 	Bubble sorting array of 3000 elements

tools/perf/Documentation/perf-mem.txt

View file

diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 7349632..4be08a1 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -59,6 +59,10 @@ OPTIONS
 --ldload::
 	Specify desired latency for loads event.
 
+-p::
+--phys-data::
+	Record/Report sample physical addresses
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]

tools/perf/Documentation/perf-record.txt

View file

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 9bdea04..e397453 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -249,7 +249,10 @@ OPTIONS
 
 -d::
 --data::
-	Record the sample addresses.
+	Record the sample virtual addresses.
+
+--phys-data::
+	Record the sample physical addresses.
 
 -T::
 --timestamp::

tools/perf/Documentation/perf-report.txt

View file

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9fa8461..383a98d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -137,6 +137,7 @@ OPTIONS
 	- mem: type of memory access for the data at the time of the sample
 	- snoop: type of snoop (if any) for the data at the time of the sample
 	- dcacheline: the cacheline the data address is on at the time of the sample
+	- phys_daddr: physical address of data being executed on at the time of sample
 
 	And the default sort keys are changed to local_weight, mem, sym, dso,
 	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.

tools/perf/Documentation/perf-script.txt

View file

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5ee8796..18dfcfa 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
         srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
-        callindent, insn, insnlen, synth.
+        callindent, insn, insnlen, synth, phys_addr.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace

tools/perf/Documentation/perf-trace.txt

View file

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index c1e3288..d53bea6 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -37,7 +37,7 @@ OPTIONS
 --expr::
 --event::
 	List of syscalls and other perf events (tracepoints, HW cache events,
-	etc) to show.
+	etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
 	See 'perf list' for a complete list of events.
 	Prefixing with ! shows all syscalls but the ones specified.  You may
 	need to escape it.

tools/perf/builtin-mem.c

View file

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e001c02..0f15634 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -23,6 +23,7 @@ struct perf_mem {
 	bool			hide_unresolved;
 	bool			dump_raw;
 	bool			force;
+	bool			phys_addr;
 	int			operation;
 	const char		*cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -101,6 +102,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "-d";
 
+	if (mem->phys_addr)
+		rec_argv[i++] = "--phys-data";
+
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		if (!perf_mem_events[j].record)
 			continue;
@@ -161,30 +165,60 @@ dump_raw_samples(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	if (symbol_conf.field_sep) {
-		fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
-		      "%s0x%"PRIx64"%s%s:%s\n";
+	if (mem->phys_addr) {
+		if (symbol_conf.field_sep) {
+			fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64
+			      "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+		} else {
+			fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+			      "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64
+			      "%s%s:%s\n";
+			symbol_conf.field_sep = " ";
+		}
+
+		printf(fmt,
+			sample->pid,
+			symbol_conf.field_sep,
+			sample->tid,
+			symbol_conf.field_sep,
+			sample->ip,
+			symbol_conf.field_sep,
+			sample->addr,
+			symbol_conf.field_sep,
+			sample->phys_addr,
+			symbol_conf.field_sep,
+			sample->weight,
+			symbol_conf.field_sep,
+			sample->data_src,
+			symbol_conf.field_sep,
+			al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+			al.sym ? al.sym->name : "???");
 	} else {
-		fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
-		      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
-		symbol_conf.field_sep = " ";
-	}
+		if (symbol_conf.field_sep) {
+			fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+			      "%s0x%"PRIx64"%s%s:%s\n";
+		} else {
+			fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+			      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+			symbol_conf.field_sep = " ";
+		}
 
-	printf(fmt,
-		sample->pid,
-		symbol_conf.field_sep,
-		sample->tid,
-		symbol_conf.field_sep,
-		sample->ip,
-		symbol_conf.field_sep,
-		sample->addr,
-		symbol_conf.field_sep,
-		sample->weight,
-		symbol_conf.field_sep,
-		sample->data_src,
-		symbol_conf.field_sep,
-		al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
-		al.sym ? al.sym->name : "???");
+		printf(fmt,
+			sample->pid,
+			symbol_conf.field_sep,
+			sample->tid,
+			symbol_conf.field_sep,
+			sample->ip,
+			symbol_conf.field_sep,
+			sample->addr,
+			symbol_conf.field_sep,
+			sample->weight,
+			symbol_conf.field_sep,
+			sample->data_src,
+			symbol_conf.field_sep,
+			al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+			al.sym ? al.sym->name : "???");
+	}
 out_put:
 	addr_location__put(&al);
 	return 0;
@@ -224,7 +258,10 @@ static int report_raw_events(struct perf_mem *mem)
 	if (ret < 0)
 		goto out_delete;
 
-	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+	if (mem->phys_addr)
+		printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+	else
+		printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
 	ret = perf_session__process_events(session);
 
@@ -254,9 +291,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
 	 * there is no weight (cost) associated with stores, so don't print
 	 * the column
 	 */
-	if (!(mem->operation & MEM_OPERATION_LOAD))
-		rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
-				"dso_daddr,tlb,locked";
+	if (!(mem->operation & MEM_OPERATION_LOAD)) {
+		if (mem->phys_addr)
+			rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+					"dso_daddr,tlb,locked,phys_daddr";
+		else
+			rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+					"dso_daddr,tlb,locked";
+	} else if (mem->phys_addr)
+		rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+				"dso_daddr,snoop,tlb,locked,phys_daddr";
 
 	for (j = 1; j < argc; j++, i++)
 		rep_argv[i] = argv[j];
@@ -373,6 +417,7 @@ int cmd_mem(int argc, const char **argv)
 		   "separator for columns, no spaces will be added"
 		   " between columns '.' is reserved."),
 	OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+	OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
 	OPT_END()
 	};
 	const char *const mem_subcommands[] = { "record", "report", NULL };

tools/perf/builtin-record.c

View file

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 36d7117..56f8142 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1604,6 +1604,8 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
 		    "per thread counts"),
 	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+	OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
+		    "Record the sample physical addresses"),
 	OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
 	OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
 			&record.opts.sample_time_set,

tools/perf/builtin-script.c

View file

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 378f76c..3d4c3b5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -87,6 +87,7 @@ enum perf_output_field {
 	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
 	PERF_OUTPUT_BRSTACKOFF	    = 1U << 24,
 	PERF_OUTPUT_SYNTH           = 1U << 25,
+	PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
 };
 
 struct output_option {
@@ -119,6 +120,7 @@ struct output_option {
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
 	{.str = "synth", .field = PERF_OUTPUT_SYNTH},
+	{.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
 };
 
 enum {
@@ -175,7 +177,8 @@ static struct {
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
 			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+			      PERF_OUTPUT_PHYS_ADDR,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -382,6 +385,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 					PERF_OUTPUT_IREGS))
 		return -EINVAL;
 
+	if (PRINT_FIELD(PHYS_ADDR) &&
+		perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+					PERF_OUTPUT_PHYS_ADDR))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1446,6 +1454,9 @@ static void process_event(struct perf_script *script,
 	if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		print_sample_bpf_output(sample);
 	print_insn(sample, attr, thread, machine);
+
+	if (PRINT_FIELD(PHYS_ADDR))
+		printf("%16" PRIx64, sample->phys_addr);
 	printf("\n");
 }
 
@@ -2729,7 +2740,7 @@ int cmd_script(int argc, const char **argv)
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),

tools/perf/builtin-stat.c

View file

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 866da7a..85e992d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1257,7 +1257,7 @@ static bool collect_data(struct perf_evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(counter, data, true);
-	if (!no_merge)
+	if (!no_merge && counter->auto_merge_stats)
 		collect_all_aliases(counter, cb, data);
 	return true;
 }

tools/perf/builtin-trace.c

View file

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d59cdad..771ddab 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1261,6 +1261,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 static int trace__validate_ev_qualifier(struct trace *trace)
 {
 	int err = 0, i;
+	size_t nr_allocated;
 	struct str_node *pos;
 
 	trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
@@ -1274,13 +1275,18 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 		goto out;
 	}
 
+	nr_allocated = trace->ev_qualifier_ids.nr;
 	i = 0;
 
 	strlist__for_each_entry(pos, trace->ev_qualifier) {
 		const char *sc = pos->s;
-		int id = syscalltbl__id(trace->sctbl, sc);
+		int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
 
 		if (id < 0) {
+			id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
+			if (id >= 0)
+				goto matches;
+
 			if (err == 0) {
 				fputs("Error:\tInvalid syscall ", trace->output);
 				err = -EINVAL;
@@ -1290,13 +1296,37 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
 			fputs(sc, trace->output);
 		}
-
+matches:
 		trace->ev_qualifier_ids.entries[i++] = id;
+		if (match_next == -1)
+			continue;
+
+		while (1) {
+			id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
+			if (id < 0)
+				break;
+			if (nr_allocated == trace->ev_qualifier_ids.nr) {
+				void *entries;
+
+				nr_allocated += 8;
+				entries = realloc(trace->ev_qualifier_ids.entries,
+						  nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
+				if (entries == NULL) {
+					err = -ENOMEM;
+					fputs("\nError:\t Not enough memory for parsing\n", trace->output);
+					goto out_free;
+				}
+				trace->ev_qualifier_ids.entries = entries;
+			}
+			trace->ev_qualifier_ids.nr++;
+			trace->ev_qualifier_ids.entries[i++] = id;
+		}
 	}
 
 	if (err < 0) {
 		fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
 		      "\nHint:\tand: 'man syscalls'\n", trace->output);
+out_free:
 		zfree(&trace->ev_qualifier_ids.entries);
 		trace->ev_qualifier_ids.nr = 0;
 	}
@@ -2814,7 +2844,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 	struct trace *trace = (struct trace *)opt->value;
 	const char *s = str;
 	char *sep = NULL, *lists[2] = { NULL, NULL, };
-	int len = strlen(str) + 1, err = -1, list;
+	int len = strlen(str) + 1, err = -1, list, idx;
 	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
 	char group_name[PATH_MAX];
 
@@ -2831,7 +2861,8 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 			*sep = '\0';
 
 		list = 0;
-		if (syscalltbl__id(trace->sctbl, s) >= 0) {
+		if (syscalltbl__id(trace->sctbl, s) >= 0 ||
+		    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
 			list = 1;
 		} else {
 			path__join(group_name, sizeof(group_name), strace_groups_dir, s);

tools/perf/perf.h

View file

diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2c010dd..dc442ba 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -43,6 +43,7 @@ struct record_opts {
 	bool	     no_samples;
 	bool	     raw_samples;
 	bool	     sample_address;
+	bool	     sample_phys_addr;
 	bool	     sample_weight;
 	bool	     sample_time;
 	bool	     sample_time_set;

tools/perf/pmu-events/arch/powerpc/power9/frontend.json

View file

diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
index 7e62c46..c63a919 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -80,11 +80,6 @@
     "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
   },
   {,
-    "EventCode": "0x400F0",
-    "EventName": "PM_LD_MISS_L1",
-    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
-  },
-  {,
     "EventCode": "0x2E01A",
     "EventName": "PM_CMPLU_STALL_LSU_FLUSH_NEXT",
     "BriefDescription": "Completion stall of one cycle because the LSU requested to flush the next iop in the sequence. It takes 1 cycle for the ISU to process this request before the LSU instruction is allowed to complete"
@@ -374,4 +369,4 @@
     "EventName": "PM_IPTEG_FROM_L31_ECO_MOD",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request"
   }
-]
\ No newline at end of file
+]

tools/perf/pmu-events/arch/powerpc/power9/other.json

View file

diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
index 00f3d2a..54cc3be 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -605,11 +605,6 @@
     "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)"
   },
   {,
-    "EventCode": "0x3689E",
-    "EventName": "PM_L2_RTY_LD",
-    "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)"
-  },
-  {,
     "EventCode": "0xE08C",
     "EventName": "PM_LSU0_ERAT_HIT",
     "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
@@ -715,11 +710,6 @@
     "BriefDescription": "Lifetime, sample of RD machine 0 valid"
   },
   {,
-    "EventCode": "0x468B4",
-    "EventName": "PM_L3_RD0_BUSY",
-    "BriefDescription": "Lifetime, sample of RD machine 0 valid"
-  },
-  {,
     "EventCode": "0x46080",
     "EventName": "PM_L2_DISP_ALL_L2MISS",
     "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
@@ -850,21 +840,11 @@
     "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
   },
   {,
-    "EventCode": "0x2608C",
-    "EventName": "PM_RC0_BUSY",
-    "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
-  },
-  {,
     "EventCode": "0x36082",
     "EventName": "PM_L2_LD_DISP",
     "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)."
   },
   {,
-    "EventCode": "0x1609E",
-    "EventName": "PM_L2_LD_DISP",
-    "BriefDescription": "All successful D side load dispatches for this thread (L2 miss + L2 hits)"
-  },
-  {,
     "EventCode": "0xF8B0",
     "EventName": "PM_L3_SW_PREF",
     "BriefDescription": "L3 load prefetch, sourced from a software prefetch stream, was sent to the nest"
@@ -1040,11 +1020,6 @@
     "BriefDescription": "L3 castouts in Mepf state for this thread"
   },
   {,
-    "EventCode": "0x168A0",
-    "EventName": "PM_L3_CO_MEPF",
-    "BriefDescription": "L3 CO of line in Mep state (includes casthrough to memory).  The Mepf state indicates that a line was brought in to satisfy an L3 prefetch request"
-  },
-  {,
     "EventCode": "0x460A2",
     "EventName": "PM_L3_LAT_CI_HIT",
     "BriefDescription": "L3 Lateral Castins Hit"
@@ -1150,11 +1125,6 @@
     "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)"
   },
   {,
-    "EventCode": "0x4689E",
-    "EventName": "PM_L2_RTY_ST",
-    "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)"
-  },
-  {,
     "EventCode": "0x24040",
     "EventName": "PM_INST_FROM_L2_MEPF",
     "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to an instruction fetch (not prefetch)"
@@ -1255,11 +1225,6 @@
     "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)"
   },
   {,
-    "EventCode": "0x4608C",
-    "EventName": "PM_CO0_BUSY",
-    "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)"
-  },
-  {,
     "EventCode": "0x2C122",
     "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT_CYC",
     "BriefDescription": "Duration in cycles to reload from local core's L3 with dispatch conflict due to a marked load"
@@ -1395,11 +1360,6 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a instruction side request"
   },
   {,
-    "EventCode": "0x40006",
-    "EventName": "PM_ISLB_MISS",
-    "BriefDescription": "Number of ISLB misses for this thread"
-  },
-  {,
     "EventCode": "0xD8A8",
     "EventName": "PM_ISLB_MISS",
     "BriefDescription": "Instruction SLB miss - Total of all segment sizes"
@@ -1515,11 +1475,6 @@
     "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)."
   },
   {,
-    "EventCode": "0x3609E",
-    "EventName": "PM_L2_INST",
-    "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
-  },
-  {,
     "EventCode": "0x3504C",
     "EventName": "PM_IPTEG_FROM_DL4",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a instruction side request"
@@ -1690,11 +1645,6 @@
     "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)"
   },
   {,
-    "EventCode": "0x2609E",
-    "EventName": "PM_L2_LD_HIT",
-    "BriefDescription": "All successful D side load dispatches for this thread that were L2 hits for this thread"
-  },
-  {,
     "EventCode": "0x168AC",
     "EventName": "PM_L3_CI_USAGE",
     "BriefDescription": "Rotating sample of 16 CI or CO actives"
@@ -1795,21 +1745,11 @@
     "BriefDescription": "Rotating sample of 8 WI valid"
   },
   {,
-    "EventCode": "0x260B6",
-    "EventName": "PM_L3_WI0_BUSY",
-    "BriefDescription": "Rotating sample of 8 WI valid (duplicate)"
-  },
-  {,
     "EventCode": "0x368AC",
     "EventName": "PM_L3_CO0_BUSY",
     "BriefDescription": "Lifetime, sample of CO machine 0 valid"
   },
   {,
-    "EventCode": "0x468AC",
-    "EventName": "PM_L3_CO0_BUSY",