perf parse-events: Avoid scanning PMUs before parsing

The event parser needs to handle two special cases:
1) legacy events like L1-dcache-load-miss. These event names don't
   appear in JSON or sysfs, and lookup tables are used for the config
   value.
2) raw events where 'r0xead' is the same as 'read' unless the PMU has
   an event called 'read' in which case the event has priority.

The previous parser to handle these cases would scan all PMUs for
components of event names. These components would then be used to
classify in the lexer whether the token should be part of a legacy
event, a raw event or an event. The grammar would handle legacy event
tokens or recombining the tokens back into a regular event name.  The
code wasn't PMU specific and had issues around events like AMD's
branch-brs that would fail to parse as it expects brs to be a suffix
on a legacy event style name:

$ perf stat -e branch-brs true
event syntax error: 'branch-brs'
                           \___ parser error

This change removes processing all PMUs by using the lexer in the form
of a regular expression matcher. The lexer will return the token for
the longest matched sequence of characters, and in the event of a tie
the first. The legacy events are a fixed number of regular
expressions, and by matching these before a name token its possible to
generate an accurate legacy event token with everything else matching
as a name. Because of the lexer change the handling of hyphens in the
grammar can be removed as hyphens just become a part of the name.

To handle raw events and terms the parser is changed to defer trying
to evaluate whether something is a raw event until the PMU is known in
the grammar. Once the PMU is known, the events of the PMU can be
scanned for the 'read' style problem. A new term type is added for
these raw terms, used to enable deferring the evaluation.

While this change is large, it has stats of:
170 insertions(+), 436 deletions(-)
the bulk of the change is deleting the old approach. It isn't possible
to break apart the code added due to the dependencies on how the parts
of the parsing work.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Edward Baker <edward.baker@intel.com>
Cc: Florian Fischer <florian.fischer@muhq.space>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kang Minchul <tegongkang@gmail.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Samantha Alt <samantha.alt@intel.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Cc: Weilin Wang <weilin.wang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yang Jihong <yangjihong1@huawei.com>
Link: https://lore.kernel.org/r/20230502223851.2234828-19-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 10 insertions, 75 deletions

diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 51fe0a9fb3de..4b35c099189a 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -63,17 +63,6 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
-static int raw(yyscan_t scanner)
-{
-	YYSTYPE *yylval = parse_events_get_lval(scanner);
-	char *text = parse_events_get_text(scanner);
-
-	if (perf_pmu__parse_check(text) == PMU_EVENT_SYMBOL)
-		return str(scanner, PE_NAME);
-
-	return __value(yylval, text + 1, 16, PE_RAW);
-}
-
 static bool isbpf_suffix(char *text)
 {
 	int len = strlen(text);
@@ -131,35 +120,6 @@ do {								\
 	yyless(0);						\
 } while (0)
 
-static int pmu_str_check(yyscan_t scanner, struct parse_events_state *parse_state)
-{
-	YYSTYPE *yylval = parse_events_get_lval(scanner);
-	char *text = parse_events_get_text(scanner);
-
-	yylval->str = strdup(text);
-
-	/*
-	 * If we're not testing then parse check determines the PMU event type
-	 * which if it isn't a PMU returns PE_NAME. When testing the result of
-	 * parse check can't be trusted so we return PE_PMU_EVENT_FAKE unless
-	 * an '!' is present in which case the text can't be a PMU name.
-	 */
-	switch (perf_pmu__parse_check(text)) {
-		case PMU_EVENT_SYMBOL_PREFIX:
-			return PE_PMU_EVENT_PRE;
-		case PMU_EVENT_SYMBOL_SUFFIX:
-			return PE_PMU_EVENT_SUF;
-		case PMU_EVENT_SYMBOL_SUFFIX2:
-			return PE_PMU_EVENT_SUF2;
-		case PMU_EVENT_SYMBOL:
-			return parse_state->fake_pmu
-				? PE_PMU_EVENT_FAKE : PE_KERNEL_PMU_EVENT;
-		default:
-			return parse_state->fake_pmu && !strchr(text,'!')
-				? PE_PMU_EVENT_FAKE : PE_NAME;
-	}
-}
-
 static int sym(yyscan_t scanner, int type, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -211,13 +171,15 @@ bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!]*
+name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]*
 name_tag	[\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\']
 name_minus	[a-zA-Z_*?][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() */
 modifier_event	[ukhpPGHSDIWeb]+
 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)
 
 %%
 
@@ -303,8 +265,8 @@ percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
 aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
 metric-id		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
-r{num_raw_hex}		{ return raw(yyscanner); }
-r0x{num_raw_hex}	{ return raw(yyscanner); }
+r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
+r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
@@ -359,47 +321,20 @@ system_time						{ return tool(yyscanner, PERF_TOOL_SYSTEM_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
-	/*
-	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
-	 * Because the prefix cycles is mixed up with cpu-cycles.
-	 * loads and stores are mixed up with cache event
-	 */
-cycles-ct				|
-cycles-t				|
-mem-loads				|
-mem-loads-aux				|
-mem-stores				|
-topdown-[a-z-]+				|
-tx-capacity-[a-z-]+			|
-el-capacity-[a-z-]+			{ return str(yyscanner, PE_KERNEL_PMU_EVENT); }
-
-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					{ return str(yyscanner, PE_NAME_CACHE_TYPE); }
-
-load|loads|read				|
-store|stores|write			|
-prefetch|prefetches			|
-speculative-read|speculative-load	|
-refs|Reference|ops|access		|
-misses|miss				{ return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
-
+{lc_type}			{ return str(yyscanner, PE_LEGACY_CACHE); }
+{lc_type}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
+{lc_type}-{lc_op_result}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
 mem:			{ BEGIN(mem); return PE_PREFIX_MEM; }
-r{num_raw_hex}		{ return raw(yyscanner); }
+r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
 {num_dec}		{ return value(yyscanner, 10); }
 {num_hex}		{ return value(yyscanner, 16); }
 
 {modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
 {bpf_object}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_OBJECT); }
 {bpf_source}		{ if (!isbpf(yyscanner)) { USER_REJECT }; return str(yyscanner, PE_BPF_SOURCE); }
-{name}			{ return pmu_str_check(yyscanner, _parse_state); }
+{name}			{ return str(yyscanner, PE_NAME); }
 {name_tag}		{ return str(yyscanner, PE_NAME); }
 "/"			{ BEGIN(config); return '/'; }
--			{ return '-'; }
 ,			{ BEGIN(event); return ','; }
 :			{ return ':'; }
 "{"			{ BEGIN(event); return '{'; }