perf jevents: Add a new expression builtin strcmp_cpuid_str()

This will allow writing formulas that are conditional on a specific
CPU type or CPU version. It calls through to the existing
strcmp_cpuid_str() function in Perf which has a default weak version,
and an arch specific version for x86 and arm64.

The function takes an 'ID' type value, which is a string. But in this
case Arm CPU IDs are hex numbers prefixed with '0x'. metric.py
assumes strings are only used by event names, and that they can't start
with a number ('0'), so an additional change has to be made to the
regex to convert hex numbers back to 'ID' types.

Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Forrington <nick.forrington@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Sohom Datta <sohomdatta1@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230816114841.1679234-5-james.clark@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/arm64/util/pmu.c

@@ -2,28 +2,12 @@
 
 #include <internal/cpumap.h>
 #include "../../../util/cpumap.h"
+#include "../../../util/header.h"
 #include "../../../util/pmu.h"
 #include "../../../util/pmus.h"
 #include <api/fs/fs.h>
 #include <math.h>
 
-static struct perf_pmu *pmu__find_core_pmu(void)
-{
-	struct perf_pmu *pmu = NULL;
-
-	while ((pmu = perf_pmus__scan_core(pmu))) {
-		/*
-		 * The cpumap should cover all CPUs. Otherwise, some CPUs may
-		 * not support some events or have different event IDs.
-		 */
-		if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu)
-			return NULL;
-
-		return pmu;
-	}
-	return NULL;
-}
-
 const struct pmu_metrics_table *pmu_metrics_table__find(void)
 {
 	struct perf_pmu *pmu = pmu__find_core_pmu();

tools/perf/pmu-events/metric.py

@@ -413,6 +413,10 @@ def has_event(event: Event) -> Function:
   # pylint: disable=invalid-name
   return Function('has_event', event)
 
+def strcmp_cpuid_str(event: str) -> Function:
+  # pylint: disable=redefined-builtin
+  # pylint: disable=invalid-name
+  return Function('strcmp_cpuid_str', event)
 
 class Metric:
   """An individual metric that will specifiable on the perf command line."""
@@ -541,14 +545,23 @@ def ParsePerfJson(orig: str) -> Expression:
   """
   # pylint: disable=eval-used
   py = orig.strip()
+  # First try to convert everything that looks like a string (event name) into Event(r"EVENT_NAME").
+  # This isn't very selective so is followed up by converting some unwanted conversions back again
   py = re.sub(r'([a-zA-Z][^-+/\* \\\(\),]*(?:\\.[^-+/\* \\\(\),]*)*)',
               r'Event(r"\1")', py)
+  # If it started with a # it should have been a literal, rather than an event name
   py = re.sub(r'#Event\(r"([^"]*)"\)', r'Literal("#\1")', py)
+  # Convert accidentally converted hex constants ("0Event(r"xDEADBEEF)"") back to a constant,
+  # but keep it wrapped in Event(), otherwise Python drops the 0x prefix and it gets interpreted as
+  # a double by the Bison parser
+  py = re.sub(r'0Event\(r"[xX]([0-9a-fA-F]*)"\)', r'Event("0x\1")', py)
+  # Convert accidentally converted scientific notation constants back
   py = re.sub(r'([0-9]+)Event\(r"(e[0-9]+)"\)', r'\1\2', py)
-  keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event']
+  # Convert all the known keywords back from events to just the keyword
+  keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event', 'strcmp_cpuid_str',
+              'cpuid_not_more_than']
   for kw in keywords:
     py = re.sub(rf'Event\(r"{kw}"\)', kw, py)
-
   try:
     parsed = ast.parse(py, mode='eval')
   except SyntaxError as e:

tools/perf/util/expr.c

@@ -13,6 +13,8 @@
 #include <util/expr-bison.h>
 #include <util/expr-flex.h>
 #include "util/hashmap.h"
+#include "util/header.h"
+#include "util/pmu.h"
 #include "smt.h"
 #include "tsc.h"
 #include <api/fs/fs.h>
@@ -495,3 +497,19 @@ double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const
 	evlist__delete(tmp);
 	return ret;
 }
+
+double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused,
+		       bool compute_ids __maybe_unused, const char *test_id)
+{
+	double ret;
+	struct perf_pmu *pmu = pmu__find_core_pmu();
+	char *cpuid = perf_pmu__getcpuid(pmu);
+
+	if (!cpuid)
+		return NAN;
+
+	ret = !strcmp_cpuid_str(test_id, cpuid);
+
+	free(cpuid);
+	return ret;
+}

tools/perf/util/expr.h

@@ -55,5 +55,6 @@ double expr_id_data__value(const struct expr_id_data *data);
 double expr_id_data__source_count(const struct expr_id_data *data);
 double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx);
 double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
+double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
 
 #endif

tools/perf/util/expr.l

@@ -114,6 +114,7 @@ if		{ return IF; }
 else		{ return ELSE; }
 source_count	{ return SOURCE_COUNT; }
 has_event	{ return HAS_EVENT; }
+strcmp_cpuid_str	{ return STRCMP_CPUID_STR; }
 {literal}	{ return literal(yyscanner, sctx); }
 {number}	{ return value(yyscanner); }
 {symbol}	{ return str(yyscanner, ID, sctx->runtime); }

tools/perf/util/expr.y

@@ -39,7 +39,7 @@ int expr_lex(YYSTYPE * yylval_param , void *yyscanner);
 	} ids;
 }
 
-%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT EXPR_ERROR
+%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT STRCMP_CPUID_STR EXPR_ERROR
 %left MIN MAX IF
 %left '|'
 %left '^'
@@ -207,6 +207,12 @@ expr: NUMBER
 	$$.ids = NULL;
 	free($3);
 }
+| STRCMP_CPUID_STR '(' ID ')'
+{
+	$$.val = expr__strcmp_cpuid_str(ctx, compute_ids, $3);
+	$$.ids = NULL;
+	free($3);
+}
 | expr '|' expr
 {
 	if (is_const($1.val) && is_const($3.val)) {

tools/perf/util/pmu.c

@@ -1790,3 +1790,20 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->alias_name);
 	free(pmu);
 }
+
+struct perf_pmu *pmu__find_core_pmu(void)
+{
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmus__scan_core(pmu))) {
+		/*
+		 * The cpumap should cover all CPUs. Otherwise, some CPUs may
+		 * not support some events or have different event IDs.
+		 */
+		if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu)
+			return NULL;
+
+		return pmu;
+	}
+	return NULL;
+}

tools/perf/util/pmu.h

@@ -289,5 +289,6 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename,
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
+struct perf_pmu *pmu__find_core_pmu(void);
 
 #endif /* __PMU_H */