[PATCH v1 3/3] perf parse-events: Add 'X' modifier to exclude an event from being regrouped

[Ian Rogers <irogers@google.com>]

The function parse_events__sort_events_and_fix_groups is needed to fix
uncore events like:
```
$ perf stat -e '{data_read,data_write}' ...
```
so that the multiple uncore PMUs have a group each of data_read and
data_write events.

The same function will perform architecture sorting and group fixing,
in particular for Intel topdown/perf-metric events. Grouping multiple
perf metric events together causes perf_event_open to fail as the
group can only support one. This means command lines like:
```
$ perf stat -e 'slots,slots' ...
```
fail as the slots events are forced into a group together to try to
satisfy the perf-metric event constraints.

As the user may know better than
parse_events__sort_events_and_fix_groups add a 'X' modifier to skip
its regrouping behavior. This allows the following to succeed rather
than fail on the second slots event being opened:
```
$ perf stat -e 'slots,slots:X' -a sleep 1

 Performance counter stats for 'system wide':

     6,834,154,071      cpu_core/slots/                                                         (50.13%)
     5,548,629,453      cpu_core/slots/X                                                        (49.87%)

       1.002634606 seconds time elapsed
```

Reported-by: Xudong Hao <xudong.hao@intel.com>
Reported-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Closes: https://lore.kernel.org/lkml/20250822082233.1850417-1-dapeng1.mi@linux.intel.com/
Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/Documentation/perf-list.txt | 1 +
 tools/perf/util/evsel.h                | 1 +
 tools/perf/util/parse-events.c         | 5 +++--
 tools/perf/util/parse-events.h         | 1 +
 tools/perf/util/parse-events.l         | 5 +++--
 5 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 28215306a78a..a5039d1614f9 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -73,6 +73,7 @@ counted. The following modifiers exist:
  e - group or event are exclusive and do not share the PMU
  b - use BPF aggregration (see perf stat --bpf-counters)
  R - retire latency value of the event
+ X - don't regroup the event to match PMUs
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e927a3a4fe0e..03f9f22e3a0c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -89,6 +89,7 @@ struct evsel {
 		bool			use_config_name;
 		bool			skippable;
 		bool			retire_lat;
+		bool			dont_regroup;
 		int			bpf_fd;
 		struct bpf_object	*bpf_obj;
 		struct list_head	config_terms;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 8282ddf68b98..43de19551c81 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1892,6 +1892,8 @@ static int parse_events__modifier_list(struct parse_events_state *parse_state,
 			evsel->bpf_counter = true;
 		if (mod.retire_lat)
 			evsel->retire_lat = true;
+		if (mod.dont_regroup)
+			evsel->dont_regroup = true;
 	}
 	return 0;
 }
@@ -2188,13 +2190,12 @@ static int parse_events__sort_events_and_fix_groups(struct list_head *list)
 		 * Set the group leader respecting the given groupings and that
 		 * groups can't span PMUs.
 		 */
-		if (!cur_leader) {
+		if (!cur_leader || pos->dont_regroup) {
 			cur_leader = pos;
 			cur_leaders_grp = &pos->core;
 			if (pos_force_grouped)
 				force_grouped_leader = pos;
 		}
-
 		cur_leader_pmu_name = cur_leader->group_pmu_name;
 		if (strcmp(cur_leader_pmu_name, pos_pmu_name)) {
 			/* PMU changed so the group/leader must change. */
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 62dc7202e3ba..a5c5fc39fd6f 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -216,6 +216,7 @@ struct parse_events_modifier {
 	bool guest : 1;		/* 'G' */
 	bool host : 1;		/* 'H' */
 	bool retire_lat : 1;	/* 'R' */
+	bool dont_regroup : 1;	/* 'X' */
 };
 
 int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 2034590eb789..294e943bcdb4 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -206,6 +206,7 @@ static int modifiers(struct parse_events_state *parse_state, yyscan_t scanner)
 		CASE('e', exclusive);
 		CASE('b', bpf);
 		CASE('R', retire_lat);
+		CASE('X', dont_regroup);
 		default:
 			return PE_ERROR;
 		}
@@ -251,10 +252,10 @@ term_name	{name_start}[a-zA-Z0-9_*?.\[\]!\-:]*
 quoted_name	[\']{name_start}[a-zA-Z0-9_*?.\[\]!\-:,\.=]*[\']
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /*
- * If you add a modifier you need to update check_modifier().
+ * If you add a modifier you need to update modifiers().
  * Also, the letters in modifier_event must not be in modifier_bp.
  */
-modifier_event	[ukhpPGHSDIWebR]{1,16}
+modifier_event	[ukhpPGHSDIWebRX]{1,17}
 modifier_bp	[rwx]{1,3}
 lc_type 	(L1-dcache|l1-d|l1d|L1-data|L1-icache|l1-i|l1i|L1-instruction|LLC|L2|dTLB|d-tlb|Data-TLB|iTLB|i-tlb|Instruction-TLB|branch|branches|bpu|btb|bpc|node)
 lc_op_result	(load|loads|read|store|stores|write|prefetch|prefetches|speculative-read|speculative-load|refs|Reference|ops|access|misses|miss)
-- 
2.51.0.261.g7ce5a0a67e-goog