[PATCH v3 7/7] perf pmus: Treat both numbers of NVIDIA PCIe PMU names as suffix

[Besar Wicaksono]

The NVIDIA PCIe and PCIe target PMUs are named <name>_<socket>_rc_<rc>,
like nvidia_pcie_pmu_1_rc_3. pmu_name_len_no_suffix() only strips the
last number, so perf treats the PMUs of each socket as a different PMU.
An event or metric on all PCIe PMUs then gives one result per socket,
each labelled with the first RC of its socket.

Make pmu_name_len_no_suffix() strip both numbers of these names, so the
instances on all sockets are merged as one PMU, nvidia_pcie_pmu or
nvidia_pcie_tgt_pmu. Also accept that name on the command line, as perf
list shows it, and sort these PMUs by socket and then by RC.

Suggested-by: Ian Rogers <irogers at google.com>
Signed-off-by: Besar Wicaksono <bwicaksono at nvidia.com>
---
 tools/perf/util/pmu.c  |  9 +++++++++
 tools/perf/util/pmus.c | 23 +++++++++++++++++++++++
 2 files changed, 32 insertions(+)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 01753d5c69d1..1ae8bcf71c68 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -926,6 +926,15 @@ static bool perf_pmu__match_wildcard(const char *pmu_name, const char *tok)
 	bool has_underscore = false;
 	size_t tok_len = strlen(tok);
 
+	if (strstarts(pmu_name, "nvidia_")) {
+		/* NVIDIA PMU with a non-ABI suffix of nvidia_..._[0-9]+_rc_[0-9]+. */
+		const char *rc = strstr(pmu_name, "_rc_");
+
+		if (rc && isdigit(rc[-1]) && tok_len == pmu_name_len_no_suffix(pmu_name) &&
+		    !strncmp(pmu_name, tok, tok_len))
+			return true;
+	}
+
 	/* Check start of pmu_name for equality. */
 	if (strncmp(pmu_name, tok, tok_len))
 		return false;
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 1355b317f3ed..8d3238fd23f1 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -67,6 +67,15 @@ size_t pmu_name_len_no_suffix(const char *str)
 {
 	int orig_len, len;
 	bool has_hex_digits = false;
+	const char *rc = strstr(str, "_rc_");
+
+	if (strstarts(str, "nvidia_") && rc && isdigit(rc[-1])) {
+		/* NVIDIA PMU with a non-ABI suffix of nvidia_..._[0-9]+_rc_[0-9]+. */
+		while (isdigit(rc[-1]))
+			rc--;
+		if (rc[-1] == '_')
+			return rc - str - 1;
+	}
 
 	orig_len = len = strlen(str);
 
@@ -106,6 +115,20 @@ int pmu_name_cmp(const char *lhs_pmu_name, const char *rhs_pmu_name)
 	if (rhs_pmu_name_len + 1 < strlen(rhs_pmu_name))
 		rhs_num = strtoull(&rhs_pmu_name[rhs_pmu_name_len + 1], NULL, 16);
 
+	if (lhs_num == rhs_num && strstarts(lhs_pmu_name, "nvidia_")) {
+		/*
+		 * NVIDIA PMU with a non-ABI suffix of nvidia_..._[0-9]+_rc_[0-9]+:
+		 * compare the RC too.
+		 */
+		const char *lhs_rc = strstr(lhs_pmu_name, "_rc_");
+		const char *rhs_rc = strstr(rhs_pmu_name, "_rc_");
+
+		if (lhs_rc && rhs_rc && isdigit(lhs_rc[-1]) && isdigit(rhs_rc[-1])) {
+			lhs_num = strtoull(lhs_rc + 4, NULL, 10);
+			rhs_num = strtoull(rhs_rc + 4, NULL, 10);
+		}
+	}
+
 	return lhs_num < rhs_num ? -1 : (lhs_num > rhs_num ? 1 : 0);
 }
 
-- 
2.43.0