Merge tag 'perf-core-for-mingo-20161123' of...

Merge tag 'perf-core-for-mingo-20161123' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

New tool:

- 'perf sched timehist' provides an analysis of scheduling events.

  Example usage:
      perf sched record -- sleep 1
      perf sched timehist

  By default it shows the individual schedule events, including the wait
  time (time between sched-out and next sched-in events for the task), the
  task scheduling delay (time between wakeup and actually running) and run
  time for the task:

        time    cpu  task name         wait time  sch delay  run time
                     [tid/pid]            (msec)     (msec)    (msec)
    -------- ------  ----------------  ---------  ---------  --------
    1.874569 [0011]  gcc[31949]            0.014      0.000     1.148
    1.874591 [0010]  gcc[31951]            0.000      0.000     0.024
    1.874603 [0010]  migration/10[59]      3.350      0.004     0.011
    1.874604 [0011]  <idle>                1.148      0.000     0.035
    1.874723 [0005]  <idle>                0.016      0.000     1.383
    1.874746 [0005]  gcc[31949]            0.153      0.078     0.022
  ...

  Times are in msec.usec. (David Ahern, Namhyung Kim)

Improvements:

- Make 'perf c2c report' support -f/--force, to allow skipping the
  ownership check for root users, for instance, just like the other
  tools (Jiri Olsa)

- Allow sorting cachelines by total number of HITMs, in addition to
  local and remote numbers (Jiri Olsa)

Fixes:

- Make sure errors aren't suppressed by the TUI reset at the end of
  a 'perf c2c report' session (Jiri Olsa)

Infrastructure changes:

- Initial work on having the annotate code better support multiple
  architectures, including the ability to cross-annotate, i.e. to
  annotate perf.data files collected on an ARM system on a x86_64
  workstation (Arnaldo Carvalho de Melo, Ravi Bangoria, Kim Phillips)

- Use USECS_PER_SEC instead of hard coded number in libtraceevent (Steven Rostedt)

- Add retrieval of preempt count and latency flags in libtraceevent (Steven Rostedt)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/lib/traceevent/event-parse.c

@@ -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"
@@ -5191,17 +5192,43 @@ 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)
 {
 	return parse_common_pid(pevent, rec->data);
 }
 
+/**
+ * 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
@@ -5424,8 +5451,8 @@ 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 +5464,10 @@ 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;

tools/lib/traceevent/event-parse.h

@@ -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,
@@ -712,6 +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,

tools/perf/Documentation/perf-c2c.txt

@@ -100,6 +100,14 @@ REPORT OPTIONS
 --show-all::
 	Show all captured HITM lines, with no regard to HITM % 0.0005 limit.
 
+-f::
+--force::
+	Don't do ownership validation.
+
+-d::
+--display::
+	Siwtch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default.
+
 C2C RECORD
 ----------
 The perf c2c record command setup options related to HITM cacheline analysis

tools/perf/Documentation/perf-sched.txt

@@ -8,11 +8,11 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|map|replay|script}
+'perf sched' {record|latency|map|replay|script|timehist}
 
 DESCRIPTION
 -----------
-There are five variants of perf sched:
+There are several variants of 'perf sched':
 
   'perf sched record <command>' to record the scheduling events
   of an arbitrary workload.
@@ -36,6 +36,30 @@ There are five variants of perf sched:
   are running on a CPU. A '*' denotes the CPU that had the event, and
   a dot signals an idle CPU.
 
+  'perf sched timehist' provides an analysis of scheduling events.
+    
+    Example usage:
+        perf sched record -- sleep 1
+        perf sched timehist
+    
+   By default it shows the individual schedule events, including the wait
+   time (time between sched-out and next sched-in events for the task), the
+   task scheduling delay (time between wakeup and actually running) and run
+   time for the task:
+    
+                time    cpu  task name             wait time  sch delay   run time
+                             [tid/pid]                (msec)     (msec)     (msec)
+      -------------- ------  --------------------  ---------  ---------  ---------
+        79371.874569 [0011]  gcc[31949]                0.014      0.000      1.148
+        79371.874591 [0010]  gcc[31951]                0.000      0.000      0.024
+        79371.874603 [0010]  migration/10[59]          3.350      0.004      0.011
+        79371.874604 [0011]  <idle>                    1.148      0.000      0.035
+        79371.874723 [0005]  <idle>                    0.016      0.000      1.383
+        79371.874746 [0005]  gcc[31949]                0.153      0.078      0.022
+    ...
+    
+   Times are in msec.usec.
+
 OPTIONS
 -------
 -i::
@@ -66,6 +90,44 @@ OPTIONS for 'perf sched map'
 --color-pids::
 	Highlight the given pids.
 
+OPTIONS for 'perf sched timehist'
+---------------------------------
+-k::
+--vmlinux=<file>::
+    vmlinux pathname
+
+--kallsyms=<file>::
+    kallsyms pathname
+
+-g::
+--no-call-graph::
+	Do not display call chains if present.
+
+--max-stack::
+	Maximum number of functions to display in backtrace, default 5.
+
+-s::
+--summary::
+    Show only a summary of scheduling by thread with min, max, and average
+    run times (in sec) and relative stddev.
+
+-S::
+--with-summary::
+    Show all scheduling events followed by a summary by thread with min,
+    max, and average run times (in sec) and relative stddev.
+
+--symfs=<directory>::
+    Look for files with symbols relative to this directory.
+
+-V::
+--cpu-visual::
+	Show visual aid for sched switches by CPU: 'i' marks idle time,
+	's' are scheduler events.
+
+-w::
+--wakeups::
+	Show wakeup events.
+
 SEE ALSO
 --------
 linkperf:perf-record[1]

tools/perf/arch/arm/annotate/instructions.c

+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,  },
+};

tools/perf/arch/x86/annotate/instructions.c

+static struct ins x86__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 = "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,  },
+};

tools/perf/builtin-c2c.c

@@ -91,6 +91,19 @@ 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 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;
@@ -745,6 +758,10 @@ 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 +1061,9 @@ 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 +1371,7 @@ 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 +1815,9 @@ 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 +1833,9 @@ 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 +2120,7 @@ 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 +2275,7 @@ 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 +2412,11 @@ 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 +2501,8 @@ 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)
@@ -2496,11 +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,
@@ -2520,32 +2547,28 @@ 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"),
+	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;
 
-	if (c2c.use_stdio)
-		use_browser = 0;
-	else
-		use_browser = 1;
-
-	setup_browser(false);
-
 	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)
@@ -2568,6 +2591,7 @@ 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 +2611,13 @@ 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");
@@ -2605,6 +2636,7 @@ 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"
 			);
 
@@ -2655,11 +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()
 	};
 
@@ -2731,11 +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);
 

tools/perf/builtin-top.c

@@ -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;

tools/perf/ui/browsers/annotate.c

@@ -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));

tools/perf/ui/gtk/annotate.c

@@ -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));

tools/perf/util/annotate.h

@@ -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,

tools/perf/util/evsel.c

@@ -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;

tools/perf/util/evsel.h

@@ -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;
 

tools/perf/util/evsel_fprintf.c

@@ -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);
 
@@ -137,7 +142,8 @@ 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);
@@ -157,6 +163,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 				printed += fprintf(fp, "\n");
 
 			callchain_cursor_advance(cursor);
+			first = false;
 		}
 	}
 
@@ -188,7 +195,8 @@ 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);

tools/perf/util/mem-events.c

@@ -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;

tools/perf/util/mem-events.h

@@ -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 */

tools/perf/util/symbol.h

@@ -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,

tools/perf/util/symbol_fprintf.c

@@ -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,