libperf: Add arm64 support to perf_mmap__read_self()

Add the arm64 variants for read_perf_counter() and read_timestamp().
Unfortunately the counter number is encoded into the instruction, so the
code is a bit verbose to enumerate all possible counters.

Tested-by: Masayoshi Mizuma <[e-mail]>
Signed-off-by: Rob Herring <[e-mail]>
Acked-by: Jiri Olsa <[e-mail]>
Tested-by: John Garry <[e-mail]>
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Cc: Mark Rutland <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Arnaldo Carvalho de Melo <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]

tools/lib/perf/mmap.c

···
 #include <internal/lib.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
+#include <linux/stringify.h>
 #include "internal.h"
 
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
···
 
 	return low | ((u64)high) << 32;
 }
+#elif defined(__aarch64__)
+#define read_sysreg(r) ({						\
+	u64 __val;							\
+	asm volatile("mrs %0, " __stringify(r) : "=r" (__val));		\
+	__val;								\
+})
+
+static u64 read_pmccntr(void)
+{
+	return read_sysreg(pmccntr_el0);
+}
+
+#define PMEVCNTR_READ(idx)					\
+	static u64 read_pmevcntr_##idx(void) {			\
+		return read_sysreg(pmevcntr##idx##_el0);	\
+	}
+
+PMEVCNTR_READ(0);
+PMEVCNTR_READ(1);
+PMEVCNTR_READ(2);
+PMEVCNTR_READ(3);
+PMEVCNTR_READ(4);
+PMEVCNTR_READ(5);
+PMEVCNTR_READ(6);
+PMEVCNTR_READ(7);
+PMEVCNTR_READ(8);
+PMEVCNTR_READ(9);
+PMEVCNTR_READ(10);
+PMEVCNTR_READ(11);
+PMEVCNTR_READ(12);
+PMEVCNTR_READ(13);
+PMEVCNTR_READ(14);
+PMEVCNTR_READ(15);
+PMEVCNTR_READ(16);
+PMEVCNTR_READ(17);
+PMEVCNTR_READ(18);
+PMEVCNTR_READ(19);
+PMEVCNTR_READ(20);
+PMEVCNTR_READ(21);
+PMEVCNTR_READ(22);
+PMEVCNTR_READ(23);
+PMEVCNTR_READ(24);
+PMEVCNTR_READ(25);
+PMEVCNTR_READ(26);
+PMEVCNTR_READ(27);
+PMEVCNTR_READ(28);
+PMEVCNTR_READ(29);
+PMEVCNTR_READ(30);
+
+/*
+ * Read a value direct from PMEVCNTR<idx>
+ */
+static u64 read_perf_counter(unsigned int counter)
+{
+	static u64 (* const read_f[])(void) = {
+		read_pmevcntr_0,
+		read_pmevcntr_1,
+		read_pmevcntr_2,
+		read_pmevcntr_3,
+		read_pmevcntr_4,
+		read_pmevcntr_5,
+		read_pmevcntr_6,
+		read_pmevcntr_7,
+		read_pmevcntr_8,
+		read_pmevcntr_9,
+		read_pmevcntr_10,
+		read_pmevcntr_11,
+		read_pmevcntr_13,
+		read_pmevcntr_12,
+		read_pmevcntr_14,
+		read_pmevcntr_15,
+		read_pmevcntr_16,
+		read_pmevcntr_17,
+		read_pmevcntr_18,
+		read_pmevcntr_19,
+		read_pmevcntr_20,
+		read_pmevcntr_21,
+		read_pmevcntr_22,
+		read_pmevcntr_23,
+		read_pmevcntr_24,
+		read_pmevcntr_25,
+		read_pmevcntr_26,
+		read_pmevcntr_27,
+		read_pmevcntr_28,
+		read_pmevcntr_29,
+		read_pmevcntr_30,
+		read_pmccntr
+	};
+
+	if (counter < ARRAY_SIZE(read_f))
+		return (read_f[counter])();
+
+	return 0;
+}
+
+static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
+
 #else
 static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
 static u64 read_timestamp(void) { return 0; }

tools/lib/perf/tests/test-evsel.c

···
 	struct perf_event_attr attr = {
 		.type	= PERF_TYPE_HARDWARE,
 		.config	= event,
+#ifdef __aarch64__
+		.config1 = 0x2,		/* Request user access */
+#endif
 	};
 	int err, i;
 
···
 	pc = perf_evsel__mmap_base(evsel, 0, 0);
 	__T("failed to get mmapped address", pc);
 
-#if defined(__i386__) || defined(__x86_64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
 	__T("userspace counter access not supported", pc->cap_user_rdpmc);
 	__T("userspace counter access not enabled", pc->index);
 	__T("userspace counter width not set", pc->pmc_width >= 32);