perf/core improvements and fixes

index fe3af9535e85..3df4178ba378 100644
@@ -130,7 +130,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__disassemble(sym, map, 0);
+	err = symbol__disassemble(sym, map, NULL, 0);
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;

index 4c18271c71c9..e6e9f7d80dbd 100644
@@ -1050,7 +1050,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		  (nr_pcnt - 1);
 	}
 
-	err = symbol__disassemble(sym, map, sizeof_bdl);
+	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), sizeof_bdl);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));

index 42d319927762..8c9308ac30b7 100644
@@ -167,7 +167,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__disassemble(sym, map, 0);
+	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));

240 lines not on this page · raw message

index 5bbcec173b82..8e490b5c91bc 100644
@@ -34,9 +34,11 @@ struct ins_operands {
 	};
 };
 
+struct arch;
+
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct ins_operands *ops, struct map *map);
+	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map *map);
 	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
 			 struct ins_operands *ops);
 };

@@ -156,7 +158,7 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__disassemble(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_name, size_t privsize);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,

index 1ba41a27214d..72769762ece9 100644
@@ -35,6 +35,7 @@ struct arch {
 	const char	*name;
 	struct		{
 		char comment_char;
+		char skip_functions_char;
 	} objdump;
 };
 

@@ -43,6 +44,7 @@ static struct arch architectures[] = {
 		.name = "arm",
 		.objdump =  {
 			.comment_char = ';',
+			.skip_functions_char = '+',
 		},
 	},
 	{

@@ -78,7 +80,7 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
 	return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
-static int call__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map)
+static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
 {
 	char *endptr, *tok, *name;
 

@@ -90,10 +92,9 @@ static int call__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 
 	name++;
 
-#ifdef __arm__
-	if (strchr(name, '+'))
+	if (arch->objdump.skip_functions_char &&
+	    strchr(name, arch->objdump.skip_functions_char))
 		return -1;
-#endif
 
 	tok = strchr(name, '>');
 	if (tok == NULL)

new file mode 100644
index 000000000000..d67b8aa26274
@@ -0,0 +1,90 @@
+static struct ins arm__instructions[] = {
+	{ .name = "add",	.ops = &mov_ops,  },
+	{ .name = "addl",	.ops = &mov_ops,  },
+	{ .name = "addq",	.ops = &mov_ops,  },
+	{ .name = "addw",	.ops = &mov_ops,  },
+	{ .name = "and",	.ops = &mov_ops,  },
+	{ .name = "b",		.ops = &jump_ops, }, // might also be a call
+	{ .name = "bcc",	.ops = &jump_ops, },
+	{ .name = "bcs",	.ops = &jump_ops, },
+	{ .name = "beq",	.ops = &jump_ops, },
+	{ .name = "bge",	.ops = &jump_ops, },
+	{ .name = "bgt",	.ops = &jump_ops, },
+	{ .name = "bhi",	.ops = &jump_ops, },
+	{ .name = "bl",		.ops = &call_ops, },
+	{ .name = "bls",	.ops = &jump_ops, },
+	{ .name = "blt",	.ops = &jump_ops, },
+	{ .name = "blx",	.ops = &call_ops, },
+	{ .name = "bne",	.ops = &jump_ops, },
+	{ .name = "bts",	.ops = &mov_ops,  },
+	{ .name = "call",	.ops = &call_ops, },
+	{ .name = "callq",	.ops = &call_ops, },
+	{ .name = "cmp",	.ops = &mov_ops,  },
+	{ .name = "cmpb",	.ops = &mov_ops,  },
+	{ .name = "cmpl",	.ops = &mov_ops,  },
+	{ .name = "cmpq",	.ops = &mov_ops,  },
+	{ .name = "cmpw",	.ops = &mov_ops,  },
+	{ .name = "cmpxch",	.ops = &mov_ops,  },
+	{ .name = "dec",	.ops = &dec_ops,  },
+	{ .name = "decl",	.ops = &dec_ops,  },
+	{ .name = "imul",	.ops = &mov_ops,  },
+	{ .name = "inc",	.ops = &dec_ops,  },
+	{ .name = "incl",	.ops = &dec_ops,  },
+	{ .name = "ja",		.ops = &jump_ops, },
+	{ .name = "jae",	.ops = &jump_ops, },
+	{ .name = "jb",		.ops = &jump_ops, },
+	{ .name = "jbe",	.ops = &jump_ops, },
+	{ .name = "jc",		.ops = &jump_ops, },
+	{ .name = "jcxz",	.ops = &jump_ops, },
+	{ .name = "je",		.ops = &jump_ops, },
+	{ .name = "jecxz",	.ops = &jump_ops, },
+	{ .name = "jg",		.ops = &jump_ops, },
+	{ .name = "jge",	.ops = &jump_ops, },
+	{ .name = "jl",		.ops = &jump_ops, },
+	{ .name = "jle",	.ops = &jump_ops, },
+	{ .name = "jmp",	.ops = &jump_ops, },
+	{ .name = "jmpq",	.ops = &jump_ops, },
+	{ .name = "jna",	.ops = &jump_ops, },
+	{ .name = "jnae",	.ops = &jump_ops, },
+	{ .name = "jnb",	.ops = &jump_ops, },
+	{ .name = "jnbe",	.ops = &jump_ops, },
+	{ .name = "jnc",	.ops = &jump_ops, },
+	{ .name = "jne",	.ops = &jump_ops, },
+	{ .name = "jng",	.ops = &jump_ops, },
+	{ .name = "jnge",	.ops = &jump_ops, },
+	{ .name = "jnl",	.ops = &jump_ops, },
+	{ .name = "jnle",	.ops = &jump_ops, },
+	{ .name = "jno",	.ops = &jump_ops, },
+	{ .name = "jnp",	.ops = &jump_ops, },
+	{ .name = "jns",	.ops = &jump_ops, },
+	{ .name = "jnz",	.ops = &jump_ops, },
+	{ .name = "jo",		.ops = &jump_ops, },
+	{ .name = "jp",		.ops = &jump_ops, },
+	{ .name = "jpe",	.ops = &jump_ops, },
+	{ .name = "jpo",	.ops = &jump_ops, },
+	{ .name = "jrcxz",	.ops = &jump_ops, },
+	{ .name = "js",		.ops = &jump_ops, },
+	{ .name = "jz",		.ops = &jump_ops, },
+	{ .name = "lea",	.ops = &mov_ops,  },
+	{ .name = "lock",	.ops = &lock_ops, },
+	{ .name = "mov",	.ops = &mov_ops,  },
+	{ .name = "movb",	.ops = &mov_ops,  },
+	{ .name = "movdqa",	.ops = &mov_ops,  },
+	{ .name = "movl",	.ops = &mov_ops,  },
+	{ .name = "movq",	.ops = &mov_ops,  },
+	{ .name = "movslq",	.ops = &mov_ops,  },
+	{ .name = "movzbl",	.ops = &mov_ops,  },
+	{ .name = "movzwl",	.ops = &mov_ops,  },
+	{ .name = "nop",	.ops = &nop_ops,  },
+	{ .name = "nopl",	.ops = &nop_ops,  },
+	{ .name = "nopw",	.ops = &nop_ops,  },
+	{ .name = "or",		.ops = &mov_ops,  },
+	{ .name = "orl",	.ops = &mov_ops,  },
+	{ .name = "test",	.ops = &mov_ops,  },
+	{ .name = "testb",	.ops = &mov_ops,  },
+	{ .name = "testl",	.ops = &mov_ops,  },
+	{ .name = "xadd",	.ops = &mov_ops,  },
+	{ .name = "xbeginl",	.ops = &jump_ops, },
+	{ .name = "xbeginq",	.ops = &jump_ops, },
+	{ .name = "retq",	.ops = &ret_ops,  },
+};

78 lines not on this page · raw message

193 lines not on this page · raw message

index 664c90c8e22b..c1ad1ffa7335 100644
@@ -33,6 +33,7 @@
 #include <stdint.h>
 #include <limits.h>
 #include <linux/string.h>
+#include <linux/time64.h>
 
 #include <netinet/in.h>
 #include "event-parse.h"

@@ -5424,8 +5425,8 @@ void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
 	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
 							use_trace_clock);
 	if (use_usec_format) {
-		secs = record->ts / NSECS_PER_SEC;
-		nsecs = record->ts - secs * NSECS_PER_SEC;
+		secs = record->ts / NSEC_PER_SEC;
+		nsecs = record->ts - secs * NSEC_PER_SEC;
 	}
 
 	if (pevent->latency_format) {

@@ -5437,10 +5438,10 @@ void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
 			usecs = nsecs;
 			p = 9;
 		} else {
-			usecs = (nsecs + 500) / NSECS_PER_USEC;
+			usecs = (nsecs + 500) / NSEC_PER_USEC;
 			/* To avoid usecs larger than 1 sec */
-			if (usecs >= 1000000) {
-				usecs -= 1000000;
+			if (usecs >= USEC_PER_SEC) {
+				usecs -= USEC_PER_SEC;
 				secs++;
 			}
 			p = 6;

index 9ffde377e89d..783c842d6517 100644
@@ -172,9 +172,6 @@ struct pevent_plugin_option {
 #define PEVENT_PLUGIN_OPTIONS_NAME MAKE_STR(PEVENT_PLUGIN_OPTIONS)
 #define PEVENT_PLUGIN_ALIAS_NAME MAKE_STR(PEVENT_PLUGIN_ALIAS)
 
-#define NSECS_PER_SEC		1000000000ULL
-#define NSECS_PER_USEC		1000ULL
-
 enum format_flags {
 	FIELD_IS_ARRAY		= 1,
 	FIELD_IS_POINTER	= 2,

index c1ad1ffa7335..14a4f623c1a5 100644
@@ -5192,11 +5192,11 @@ struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type
 }
 
 /**
- * pevent_data_pid - parse the PID from raw data
+ * pevent_data_pid - parse the PID from record
  * @pevent: a handle to the pevent
  * @rec: the record to parse
  *
- * This returns the PID from a raw data.
+ * This returns the PID from a record.
  */
 int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec)
 {

@@ -5204,6 +5204,32 @@ int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec)
 }
 
 /**
+ * pevent_data_prempt_count - parse the preempt count from the record
+ * @pevent: a handle to the pevent
+ * @rec: the record to parse
+ *
+ * This returns the preempt count from a record.
+ */
+int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec)
+{
+	return parse_common_pc(pevent, rec->data);
+}
+
+/**
+ * pevent_data_flags - parse the latency flags from the record
+ * @pevent: a handle to the pevent
+ * @rec: the record to parse
+ *
+ * This returns the latency flags from a record.
+ *
+ *  Use trace_flag_type enum for the flags (see event-parse.h).
+ */
+int pevent_data_flags(struct pevent *pevent, struct pevent_record *rec)
+{
+	return parse_common_flags(pevent, rec->data);
+}
+
+/**
  * pevent_data_comm_from_pid - return the command line from PID
  * @pevent: a handle to the pevent
  * @pid: the PID of the task to search for

index 783c842d6517..7aae746ec2fe 100644
@@ -709,6 +709,8 @@ void pevent_data_lat_fmt(struct pevent *pevent,
 int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
 struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type);
 int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec);
+int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec);
+int pevent_data_flags(struct pevent *pevent, struct pevent_record *rec);
 const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
 struct cmdline;
 struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *comm,

index e58a2fbf3b16..b2365a63db45 100644
@@ -1481,7 +1481,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
 				  pid, cpus->map[cpu], group_fd, flags);
 
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,

@@ -1490,11 +1490,13 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0) {
 				err = -errno;
-				pr_debug2("sys_perf_event_open failed, error %d\n",
+				pr_debug2("\nsys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}
 
+			pr_debug2(" = %d\n", FD(evsel, cpu, thread));
+
 			if (evsel->bpf_fd >= 0) {
 				int evt_fd = FD(evsel, cpu, thread);
 				int bpf_fd = evsel->bpf_fd;

index c6d0dda594d9..15addb06d611 100644
@@ -2535,13 +2535,6 @@ static int perf_c2c__report(int argc, const char **argv)
 	if (c2c.stats_only)
 		c2c.use_stdio = true;
 
-	if (c2c.use_stdio)
-		use_browser = 0;
-	else
-		use_browser = 1;
-
-	setup_browser(false);
-
 	if (!input_name || !strlen(input_name))
 		input_name = "perf.data";
 

@@ -2568,6 +2561,7 @@ static int perf_c2c__report(int argc, const char **argv)
 		pr_debug("No memory for session\n");
 		goto out;
 	}
+
 	err = setup_nodes(session);
 	if (err) {
 		pr_err("Failed setup nodes\n");

@@ -2587,6 +2581,13 @@ static int perf_c2c__report(int argc, const char **argv)
 		goto out_session;
 	}
 
+	if (c2c.use_stdio)
+		use_browser = 0;
+	else
+		use_browser = 1;
+
+	setup_browser(false);
+
 	err = perf_session__process_events(session);
 	if (err) {
 		pr_err("failed to process sample\n");

index 15addb06d611..d873977b8fb6 100644
@@ -2523,6 +2523,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	OPT_STRING('d', "display", &display, NULL, "lcl,rmt"),
 	OPT_STRING('c', "coalesce", &coalesce, "coalesce fields",
 		   "coalesce fields: pid,tid,iaddr,dso"),
+	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_END()
 	};
 	int err = 0;

@@ -2538,7 +2539,8 @@ static int perf_c2c__report(int argc, const char **argv)
 	if (!input_name || !strlen(input_name))
 		input_name = "perf.data";
 
-	file.path = input_name;
+	file.path  = input_name;
+	file.force = symbol_conf.force;
 
 	err = setup_display(display);
 	if (err)

index e50773286ef6..1d4ab53c60ca 100644
@@ -280,6 +280,12 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 	u64 lock   = data_src->mem_lock;
 	int err = 0;
 
+#define HITM_INC(__f)		\
+do {				\
+	stats->__f++;		\
+	stats->tot_hitm++;	\
+} while (0)
+
 #define P(a, b) PERF_MEM_##a##_##b
 
 	stats->nr_entries++;

@@ -303,7 +309,7 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 			if (lvl & P(LVL, L2 )) stats->ld_l2hit++;
 			if (lvl & P(LVL, L3 )) {
 				if (snoop & P(SNOOP, HITM))
-					stats->lcl_hitm++;
+					HITM_INC(lcl_hitm);
 				else
 					stats->ld_llchit++;
 			}

@@ -331,7 +337,7 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 			if (snoop & P(SNOOP, HIT))
 				stats->rmt_hit++;
 			else if (snoop & P(SNOOP, HITM))
-				stats->rmt_hitm++;
+				HITM_INC(rmt_hitm);
 		}
 
 		if ((lvl & P(LVL, MISS)))

@@ -364,6 +370,7 @@ int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
 	}
 
 #undef P
+#undef HITM_INC
 	return err;
 }
 

@@ -390,6 +397,7 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
 	stats->ld_llchit	+= add->ld_llchit;
 	stats->lcl_hitm		+= add->lcl_hitm;
 	stats->rmt_hitm		+= add->rmt_hitm;
+	stats->tot_hitm		+= add->tot_hitm;
 	stats->rmt_hit		+= add->rmt_hit;
 	stats->lcl_dram		+= add->lcl_dram;
 	stats->rmt_dram		+= add->rmt_dram;

index faf80403b519..40f72ee4f42a 100644
@@ -59,6 +59,7 @@ struct c2c_stats {
 	u32	ld_llchit;           /* count of loads that hit LLC */
 	u32	lcl_hitm;            /* count of loads with local HITM  */
 	u32	rmt_hitm;            /* count of loads with remote HITM */
+	u32	tot_hitm;            /* count of loads with local and remote HITM */
 	u32	rmt_hit;             /* count of loads with remote hit clean; */
 	u32	lcl_dram;            /* count of loads miss to local DRAM */
 	u32	rmt_dram;            /* count of loads miss to remote DRAM */

index d873977b8fb6..54924717ae8e 100644
@@ -91,6 +91,14 @@ struct perf_c2c {
 enum {
 	DISPLAY_LCL,
 	DISPLAY_RMT,
+	DISPLAY_TOT,
+	DISPLAY_MAX,
+};
+
+static const char *display_str[DISPLAY_MAX] = {
+	[DISPLAY_LCL] = "Local",
+	[DISPLAY_RMT] = "Remote",
+	[DISPLAY_TOT] = "Total",
 };
 
 static struct perf_c2c c2c;

@@ -745,6 +753,10 @@ static double percent_hitm(struct c2c_hist_entry *c2c_he)
 	case DISPLAY_LCL:
 		st  = stats->lcl_hitm;
 		tot = total->lcl_hitm;
+		break;
+	case DISPLAY_TOT:
+		st  = stats->tot_hitm;
+		tot = total->tot_hitm;
 	default:
 		break;
 	}

@@ -1044,6 +1056,9 @@ node_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 				break;
 			case DISPLAY_LCL:
 				DISPLAY_HITM(lcl_hitm);
+				break;
+			case DISPLAY_TOT:
+				DISPLAY_HITM(tot_hitm);
 			default:
 				break;
 			}

@@ -1351,6 +1366,7 @@ static struct c2c_dimension dim_tot_loads = {
 static struct c2c_header percent_hitm_header[] = {
 	[DISPLAY_LCL] = HEADER_BOTH("Lcl", "Hitm"),
 	[DISPLAY_RMT] = HEADER_BOTH("Rmt", "Hitm"),
+	[DISPLAY_TOT] = HEADER_BOTH("Tot", "Hitm"),
 };
 
 static struct c2c_dimension dim_percent_hitm = {

@@ -1794,6 +1810,9 @@ static bool he__display(struct hist_entry *he, struct c2c_stats *stats)
 		break;
 	case DISPLAY_RMT:
 		FILTER_HITM(rmt_hitm);
+		break;
+	case DISPLAY_TOT:
+		FILTER_HITM(tot_hitm);
 	default:
 		break;
 	};

@@ -1809,8 +1828,9 @@ static inline int valid_hitm_or_store(struct hist_entry *he)
 	bool has_hitm;
 
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
-	has_hitm = c2c.display == DISPLAY_LCL ?
-		   c2c_he->stats.lcl_hitm : c2c_he->stats.rmt_hitm;
+	has_hitm = c2c.display == DISPLAY_TOT ? c2c_he->stats.tot_hitm :
+		   c2c.display == DISPLAY_LCL ? c2c_he->stats.lcl_hitm :
+						c2c_he->stats.rmt_hitm;
 	return has_hitm || c2c_he->stats.store;
 }
 

@@ -2095,7 +2115,7 @@ static void print_c2c_info(FILE *out, struct perf_session *session)
 		first = false;
 	}
 	fprintf(out, "  Cachelines sort on                : %s HITMs\n",
-		c2c.display == DISPLAY_LCL ? "Local" : "Remote");
+		display_str[c2c.display]);
 	fprintf(out, "  Cacheline data grouping           : %s\n", c2c.cl_sort);
 }
 

@@ -2250,7 +2270,7 @@ static int perf_c2c_browser__title(struct hist_browser *browser,
 		  "Shared Data Cache Line Table     "
 		  "(%lu entries, sorted on %s HITMs)",
 		  browser->nr_non_filtered_entries,
-		  c2c.display == DISPLAY_LCL ? "local" : "remote");
+		  display_str[c2c.display]);
 	return 0;
 }
 

@@ -2387,9 +2407,11 @@ static int setup_callchain(struct perf_evlist *evlist)
 
 static int setup_display(const char *str)
 {
-	const char *display = str ?: "rmt";
+	const char *display = str ?: "tot";
 
-	if (!strcmp(display, "rmt"))
+	if (!strcmp(display, "tot"))
+		c2c.display = DISPLAY_TOT;
+	else if (!strcmp(display, "rmt"))
 		c2c.display = DISPLAY_RMT;
 	else if (!strcmp(display, "lcl"))
 		c2c.display = DISPLAY_LCL;

@@ -2474,6 +2496,8 @@ static int setup_coalesce(const char *coalesce, bool no_source)
 		return -1;
 
 	if (asprintf(&c2c.cl_resort, "offset,%s",
+		     c2c.display == DISPLAY_TOT ?
+		     "tot_hitm" :
 		     c2c.display == DISPLAY_RMT ?
 		     "rmt_hitm,lcl_hitm" :
 		     "lcl_hitm,rmt_hitm") < 0)

@@ -2520,7 +2544,7 @@ static int perf_c2c__report(int argc, const char **argv)
 			     "print_type,threshold[,print_limit],order,sort_key[,branch],value",
 			     callchain_help, &parse_callchain_opt,
 			     callchain_default_opt),
-	OPT_STRING('d', "display", &display, NULL, "lcl,rmt"),
+	OPT_STRING('d', "display", &display, "Switch HITM output type", "lcl,rmt"),
 	OPT_STRING('c', "coalesce", &coalesce, "coalesce fields",
 		   "coalesce fields: pid,tid,iaddr,dso"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),

@@ -2608,6 +2632,7 @@ static int perf_c2c__report(int argc, const char **argv)
 			"tot_loads,"
 			"ld_fbhit,ld_l1hit,ld_l2hit,"
 			"ld_lclhit,ld_rmthit",
+			c2c.display == DISPLAY_TOT ? "tot_hitm" :
 			c2c.display == DISPLAY_LCL ? "lcl_hitm" : "rmt_hitm"
 			);
 

index 54924717ae8e..4b419631753d 100644
@@ -101,6 +101,11 @@ static const char *display_str[DISPLAY_MAX] = {
 	[DISPLAY_TOT] = "Total",
 };
 
+static const struct option c2c_options[] = {
+	OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+};
+
 static struct perf_c2c c2c;
 
 static void *c2c_he_zalloc(size_t size)

@@ -2520,11 +2525,9 @@ static int perf_c2c__report(int argc, const char **argv)
 	const char *display = NULL;
 	const char *coalesce = NULL;
 	bool no_source = false;
-	const struct option c2c_options[] = {
+	const struct option options[] = {
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
-	OPT_INCR('v', "verbose", &verbose,
-		 "be more verbose (show counter open errors, etc)"),
 	OPT_STRING('i', "input", &input_name, "file",
 		   "the input file to process"),
 	OPT_INCR('N', "node-info", &c2c.node_info,

@@ -2548,14 +2551,15 @@ static int perf_c2c__report(int argc, const char **argv)
 	OPT_STRING('c', "coalesce", &coalesce, "coalesce fields",
 		   "coalesce fields: pid,tid,iaddr,dso"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+	OPT_PARENT(c2c_options),
 	OPT_END()
 	};
 	int err = 0;
 
-	argc = parse_options(argc, argv, c2c_options, report_c2c_usage,
+	argc = parse_options(argc, argv, options, report_c2c_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 	if (argc)
-		usage_with_options(report_c2c_usage, c2c_options);
+		usage_with_options(report_c2c_usage, options);
 
 	if (c2c.stats_only)
 		c2c.use_stdio = true;

@@ -2683,11 +2687,10 @@ static int perf_c2c__record(int argc, const char **argv)
 	OPT_CALLBACK('e', "event", &event_set, "event",
 		     "event selector. Use 'perf mem record -e list' to list available events",
 		     parse_record_events),
-	OPT_INCR('v', "verbose", &verbose,
-		 "be more verbose (show counter open errors, etc)"),
 	OPT_BOOLEAN('u', "all-user", &all_user, "collect only user level data"),
 	OPT_BOOLEAN('k', "all-kernel", &all_kernel, "collect only kernel level data"),
 	OPT_UINTEGER('l', "ldlat", &perf_mem_events__loads_ldlat, "setup mem-loads latency"),
+	OPT_PARENT(c2c_options),
 	OPT_END()
 	};
 

@@ -2759,11 +2762,6 @@ static int perf_c2c__record(int argc, const char **argv)
 
 int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	const struct option c2c_options[] = {
-	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
-	OPT_END()
-	};
-
 	argc = parse_options(argc, argv, c2c_options, c2c_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 

index 662a0a6182e7..ccb602397b60 100644
@@ -137,7 +137,8 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 
 				if (print_symoffset) {
 					printed += __symbol__fprintf_symname_offs(node->sym, &node_al,
-										  print_unknown_as_addr, fp);
+										  print_unknown_as_addr,
+										  true, fp);
 				} else {
 					printed += __symbol__fprintf_symname(node->sym, &node_al,
 									     print_unknown_as_addr, fp);

@@ -188,7 +189,8 @@ int sample__fprintf_sym(struct perf_sample *sample, struct addr_location *al,
 			printed += fprintf(fp, " ");
 			if (print_symoffset) {
 				printed += __symbol__fprintf_symname_offs(al->sym, al,
-									  print_unknown_as_addr, fp);
+									  print_unknown_as_addr,
+									  true, fp);
 			} else {
 				printed += __symbol__fprintf_symname(al->sym, al,
 								     print_unknown_as_addr, fp);

index 2d0a905c879a..dec7e2d44885 100644
@@ -282,7 +282,8 @@ int symbol__annotation_init(void);
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
 size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 				      const struct addr_location *al,
-				      bool unknown_as_addr, FILE *fp);
+				      bool unknown_as_addr,
+				      bool print_offsets, FILE *fp);
 size_t symbol__fprintf_symname_offs(const struct symbol *sym,
 				    const struct addr_location *al, FILE *fp);
 size_t __symbol__fprintf_symname(const struct symbol *sym,

index a680bdaa65dc..7c6b33e8e2d2 100644
@@ -15,14 +15,15 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp)
 
 size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 				      const struct addr_location *al,
-				      bool unknown_as_addr, FILE *fp)
+				      bool unknown_as_addr,
+				      bool print_offsets, FILE *fp)
 {
 	unsigned long offset;
 	size_t length;
 
 	if (sym && sym->name) {
 		length = fprintf(fp, "%s", sym->name);
-		if (al) {
+		if (al && print_offsets) {
 			if (al->addr < sym->end)
 				offset = al->addr - sym->start;
 			else

@@ -40,19 +41,19 @@ size_t symbol__fprintf_symname_offs(const struct symbol *sym,
 				    const struct addr_location *al,
 				    FILE *fp)
 {
-	return __symbol__fprintf_symname_offs(sym, al, false, fp);
+	return __symbol__fprintf_symname_offs(sym, al, false, true, fp);
 }
 
 size_t __symbol__fprintf_symname(const struct symbol *sym,
 				 const struct addr_location *al,
 				 bool unknown_as_addr, FILE *fp)
 {
-	return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, fp);
+	return __symbol__fprintf_symname_offs(sym, al, unknown_as_addr, false, fp);
 }
 
 size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
 {
-	return __symbol__fprintf_symname_offs(sym, NULL, false, fp);
+	return __symbol__fprintf_symname_offs(sym, NULL, false, false, fp);
 }
 
 size_t dso__fprintf_symbols_by_name(struct dso *dso,

index 8cd7cd227483..27fa3a343577 100644
@@ -391,6 +391,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 #define EVSEL__PRINT_ONELINE		(1<<4)
 #define EVSEL__PRINT_SRCLINE		(1<<5)
 #define EVSEL__PRINT_UNKNOWN_AS_ADDR	(1<<6)
+#define EVSEL__PRINT_CALLCHAIN_ARROW	(1<<7)
 
 struct callchain_cursor;
 

index ccb602397b60..53bb614feafb 100644
@@ -108,7 +108,9 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 	int print_oneline = print_opts & EVSEL__PRINT_ONELINE;
 	int print_srcline = print_opts & EVSEL__PRINT_SRCLINE;
 	int print_unknown_as_addr = print_opts & EVSEL__PRINT_UNKNOWN_AS_ADDR;
+	int print_arrow = print_opts & EVSEL__PRINT_CALLCHAIN_ARROW;
 	char s = print_oneline ? ' ' : '\t';
+	bool first = true;
 
 	if (sample->callchain) {
 		struct addr_location node_al;

@@ -124,6 +126,9 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 
 			printed += fprintf(fp, "%-*.*s", left_alignment, left_alignment, " ");
 
+			if (print_arrow && !first)
+				printed += fprintf(fp, " <-");
+
 			if (print_ip)
 				printed += fprintf(fp, "%c%16" PRIx64, s, node->ip);
 

@@ -158,6 +163,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 				printed += fprintf(fp, "\n");
 
 			callchain_cursor_advance(cursor);
+			first = false;
 		}
 	}
 

649 lines not on this page · raw message

index c0ac0c9557e8..1e7d81ad5ec6 100644
@@ -194,6 +194,11 @@ struct perf_sched {
 	bool force;
 	bool skip_merge;
 	struct perf_sched_map map;
+
+	/* options for timehist command */
+	bool		summary;
+	bool		summary_only;
+	u64		skipped_samples;
 };
 
 /* per thread run time data */

@@ -2010,12 +2015,15 @@ static struct thread *timehist_get_thread(struct perf_sample *sample,
 	return thread;
 }
 
-static bool timehist_skip_sample(struct thread *thread)
+static bool timehist_skip_sample(struct perf_sched *sched,
+				 struct thread *thread)
 {
 	bool rc = false;
 
-	if (thread__is_filtered(thread))
+	if (thread__is_filtered(thread)) {
 		rc = true;
+		sched->skipped_samples++;
+	}
 
 	return rc;
 }

@@ -2045,7 +2053,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int timehist_sched_change_event(struct perf_tool *tool __maybe_unused,
+static int timehist_sched_change_event(struct perf_tool *tool,
 				       union perf_event *event,
 				       struct perf_evsel *evsel,
 				       struct perf_sample *sample,

@@ -2056,6 +2064,7 @@ static int timehist_sched_change_event(struct perf_tool *tool __maybe_unused,
 	struct thread_runtime *tr = NULL;
 	u64 tprev;
 	int rc = 0;
+	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event. skipping it\n",

@@ -2070,7 +2079,7 @@ static int timehist_sched_change_event(struct perf_tool *tool __maybe_unused,
 		goto out;
 	}
 
-	if (timehist_skip_sample(thread))
+	if (timehist_skip_sample(sched, thread))
 		goto out;
 
 	tr = thread__get_runtime(thread);

@@ -2082,7 +2091,8 @@ static int timehist_sched_change_event(struct perf_tool *tool __maybe_unused,
 	tprev = perf_evsel__get_time(evsel, sample->cpu);
 
 	timehist_update_runtime_stats(tr, sample->time, tprev);
-	timehist_print_sample(sample, thread);
+	if (!sched->summary_only)
+		timehist_print_sample(sample, thread);
 
 out:
 	if (tr) {

@@ -2122,6 +2132,131 @@ static int process_lost(struct perf_tool *tool __maybe_unused,
 }
 
 
+static void print_thread_runtime(struct thread *t,
+				 struct thread_runtime *r)
+{
+	double mean = avg_stats(&r->run_stats);
+	float stddev;
+
+	printf("%*s   %5d  %9" PRIu64 " ",
+	       comm_width, timehist_get_commstr(t), t->ppid,
+	       (u64) r->run_stats.n);
+
+	print_sched_time(r->total_run_time, 8);
+	stddev = rel_stddev_stats(stddev_stats(&r->run_stats), mean);
+	print_sched_time(r->run_stats.min, 6);
+	printf(" ");
+	print_sched_time((u64) mean, 6);
+	printf(" ");
+	print_sched_time(r->run_stats.max, 6);
+	printf("  ");
+	printf("%5.2f", stddev);
+	printf("\n");
+}
+
+struct total_run_stats {
+	u64  sched_count;
+	u64  task_count;
+	u64  total_run_time;
+};
+
+static int __show_thread_runtime(struct thread *t, void *priv)
+{
+	struct total_run_stats *stats = priv;
+	struct thread_runtime *r;
+
+	if (thread__is_filtered(t))
+		return 0;
+
+	r = thread__priv(t);
+	if (r && r->run_stats.n) {
+		stats->task_count++;
+		stats->sched_count += r->run_stats.n;
+		stats->total_run_time += r->total_run_time;
+		print_thread_runtime(t, r);
+	}
+
+	return 0;
+}
+
+static int show_thread_runtime(struct thread *t, void *priv)
+{
+	if (t->dead)
+		return 0;
+
+	return __show_thread_runtime(t, priv);
+}
+
+static int show_deadthread_runtime(struct thread *t, void *priv)
+{
+	if (!t->dead)
+		return 0;
+
+	return __show_thread_runtime(t, priv);
+}
+
+static void timehist_print_summary(struct perf_sched *sched,
+				   struct perf_session *session)
+{
+	struct machine *m = &session->machines.host;
+	struct total_run_stats totals;
+	u64 task_count;
+	struct thread *t;
+	struct thread_runtime *r;
+	int i;
+
+	memset(&totals, 0, sizeof(totals));
+
+	if (comm_width < 30)
+		comm_width = 30;
+
+	printf("\nRuntime summary\n");
+	printf("%*s  parent   sched-in  ", comm_width, "comm");
+	printf("   run-time    min-run     avg-run     max-run  stddev\n");
+	printf("%*s            (count)  ", comm_width, "");
+	printf("     (msec)     (msec)      (msec)      (msec)       %%\n");
+	printf("%.105s\n", graph_dotted_line);
+
+	machine__for_each_thread(m, show_thread_runtime, &totals);
+	task_count = totals.task_count;
+	if (!task_count)
+		printf("<no still running tasks>\n");
+
+	printf("\nTerminated tasks:\n");
+	machine__for_each_thread(m, show_deadthread_runtime, &totals);
+	if (task_count == totals.task_count)
+		printf("<no terminated tasks>\n");
+
+	/* CPU idle stats not tracked when samples were skipped */
+	if (sched->skipped_samples)
+		return;
+
+	printf("\nIdle stats:\n");
+	for (i = 0; i <= idle_max_cpu; ++i) {
+		t = idle_threads[i];
+		if (!t)
+			continue;
+
+		r = thread__priv(t);
+		if (r && r->run_stats.n) {
+			totals.sched_count += r->run_stats.n;
+			printf("    CPU %2d idle for ", i);
+			print_sched_time(r->total_run_time, 6);
+			printf(" msec\n");
+		} else
+			printf("    CPU %2d idle entire time window\n", i);
+	}
+
+	printf("\n"
+	       "    Total number of unique tasks: %" PRIu64 "\n"
+	       "Total number of context switches: %" PRIu64 "\n"
+	       "           Total run time (msec): ",
+	       totals.task_count, totals.sched_count);
+
+	print_sched_time(totals.total_run_time, 2);
+	printf("\n");
+}
+
 typedef int (*sched_handler)(struct perf_tool *tool,
 			  union perf_event *event,
 			  struct perf_evsel *evsel,

@@ -2163,6 +2298,7 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	};
 
 	struct perf_session *session;
+	struct perf_evlist *evlist;
 	int err = -1;
 
 	/*

@@ -2185,6 +2321,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	if (session == NULL)
 		return -ENOMEM;
 
+	evlist = session->evlist;
+
 	symbol__init(&session->header.env);
 
 	setup_pager();

@@ -2203,7 +2341,12 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	if (init_idle_threads(sched->max_cpu))
 		goto out;
 
-	timehist_header();
+	/* summary_only implies summary option, but don't overwrite summary if set */
+	if (sched->summary_only)
+		sched->summary = sched->summary_only;
+
+	if (!sched->summary_only)
+		timehist_header();
 
 	err = perf_session__process_events(session);
 	if (err) {

@@ -2211,6 +2354,13 @@ static int perf_sched__timehist(struct perf_sched *sched)
 		goto out;
 	}
 
+	sched->nr_events      = evlist->stats.nr_events[0];
+	sched->nr_lost_events = evlist->stats.total_lost;
+	sched->nr_lost_chunks = evlist->stats.nr_events[PERF_RECORD_LOST];
+
+	if (sched->summary)
+		timehist_print_summary(sched, session);
+
 out:
 	free_idle_threads();
 	perf_session__delete(session);

@@ -2569,6 +2719,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "file", "kallsyms pathname"),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
+	OPT_BOOLEAN('s', "summary", &sched.summary_only,
+		    "Show only syscall summary with statistics"),
+	OPT_BOOLEAN('S', "with-summary", &sched.summary,
+		    "Show all syscalls and summary with statistics"),
 	OPT_PARENT(sched_options)
 	};
 

122 lines not on this page · raw message

178 lines not on this page · raw message

100 lines not on this page · raw message