perf jit: Add support for using TSC as a timestamp

Intel PT uses TSC as a timestamp, so add support for using TSC instead
of the monotonic clock. Use of TSC is selected by an environment
variable "JITDUMP_USE_ARCH_TIMESTAMP" and flagged in the jitdump file
with flag JITDUMP_FLAGS_ARCH_TIMESTAMP.

Signed-off-by: Adrian Hunter <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: He Kuang <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Josh Poimboeuf <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Cc: Sukadev Bhattiprolu <[e-mail]>
Cc: Wang Nan <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
[ Added the fixup from He Kuang to make it build on other arches, ]
[ such as aarch64, to avoid inserting this bisectiong breakage upstream ]
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/arch/x86/util/tsc.c

···
 #include <linux/types.h>
 #include "../../util/debug.h"
 #include "../../util/tsc.h"
-#include "tsc.h"
 
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc)

tools/perf/arch/x86/util/tsc.h

···
-#ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
-#define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
-
-#include <linux/types.h>
-
-struct perf_tsc_conversion {
-	u16 time_shift;
-	u32 time_mult;
-	u64 time_zero;
-};
-
-struct perf_event_mmap_page;
-
-int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
-			     struct perf_tsc_conversion *tc);
-
-#endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */

tools/perf/jvmti/jvmti_agent.c

···
 	return ret;
 }
 
+static int use_arch_timestamp;
+
+static inline uint64_t
+get_arch_timestamp(void)
+{
+#if defined(__i386__) || defined(__x86_64__)
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((uint64_t)high) << 32;
+#else
+	return 0;
+#endif
+}
+
 #define NSEC_PER_SEC	1000000000
 static int perf_clk_id = CLOCK_MONOTONIC;
 
···
 {
 	struct timespec ts;
 	int ret;
+
+	if (use_arch_timestamp)
+		return get_arch_timestamp();
 
 	ret = clock_gettime(perf_clk_id, &ts);
 	if (ret)
···
 	munmap(marker_addr, pgsz);
 }
 
+static void
+init_arch_timestamp(void)
+{
+	char *str = getenv("JITDUMP_USE_ARCH_TIMESTAMP");
+
+	if (!str || !*str || !strcmp(str, "0"))
+		return;
+
+	use_arch_timestamp = 1;
+}
+
 void *jvmti_open(void)
 {
 	int pad_cnt;
···
 	int fd;
 	FILE *fp;
 
+	init_arch_timestamp();
+
 	/*
 	 * check if clockid is supported
 	 */
-	if (!perf_get_timestamp())
-		warnx("jvmti: kernel does not support %d clock id", perf_clk_id);
+	if (!perf_get_timestamp()) {
+		if (use_arch_timestamp)
+			warnx("jvmti: arch timestamp not supported");
+		else
+			warnx("jvmti: kernel does not support %d clock id", perf_clk_id);
+	}
 
 	memset(&header, 0, sizeof(header));
 
···
 	header.total_size += pad_cnt;
 
 	header.timestamp = perf_get_timestamp();
+
+	if (use_arch_timestamp)
+		header.flags |= JITDUMP_FLAGS_ARCH_TIMESTAMP;
 
 	if (!fwrite(&header, sizeof(header), 1, fp)) {
 		warn("jvmti: cannot write dumpfile header");

tools/perf/util/Build

···
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
-libperf-$(CONFIG_X86) += tsc.o
-libperf-$(CONFIG_AUXTRACE) += tsc.o
+libperf-y += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o

tools/perf/util/jitdump.c

···
 #include "strlist.h"
 #include <elf.h>
 
+#include "tsc.h"
 #include "session.h"
 #include "jit.h"
 #include "jitdump.h"
···
 	size_t           bufsize;
 	FILE             *in;
 	bool		 needs_bswap; /* handles cross-endianess */
+	bool		 use_arch_timestamp;
 	void		 *debug_data;
 	size_t		 nr_debug_entries;
 	uint32_t         code_load_count;
···
 		header.flags      = bswap_64(header.flags);
 	}
 
+	jd->use_arch_timestamp = header.flags & JITDUMP_FLAGS_ARCH_TIMESTAMP;
+
 	if (verbose > 2)
-		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+		pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\nuse_arch_timestamp=%d\n",
 			header.version,
 			header.total_size,
 			(unsigned long long)header.timestamp,
 			header.pid,
-			header.elf_mach);
+			header.elf_mach,
+			jd->use_arch_timestamp);
 
 	if (header.flags & JITDUMP_FLAGS_RESERVED) {
 		pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
···
 		goto error;
 	}
 
+	if (jd->use_arch_timestamp && !jd->session->time_conv.time_mult) {
+		pr_err("jitdump file uses arch timestamps but there is no timestamp conversion\n");
+		goto error;
+	}
+
 	/*
 	 * validate event is using the correct clockid
 	 */
-	if (jit_validate_events(jd->session)) {
+	if (!jd->use_arch_timestamp && jit_validate_events(jd->session)) {
 		pr_err("error, jitted code must be sampled with perf record -k 1\n");
 		goto error;
 	}
···
 	return 0;
 }
 
+static uint64_t convert_timestamp(struct jit_buf_desc *jd, uint64_t timestamp)
+{
+	struct perf_tsc_conversion tc;
+
+	if (!jd->use_arch_timestamp)
+		return timestamp;
+
+	tc.time_shift = jd->session->time_conv.time_shift;
+	tc.time_mult  = jd->session->time_conv.time_mult;
+	tc.time_zero  = jd->session->time_conv.time_zero;
+
+	if (!tc.time_mult)
+		return 0;
+
+	return tsc_to_perf_time(timestamp, &tc);
+}
+
 static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 {
 	struct perf_sample sample;
···
 		id->tid  = tid;
 	}
 	if (jd->sample_type & PERF_SAMPLE_TIME)
-		id->time = jr->load.p.timestamp;
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
 
 	/*
 	 * create pseudo sample to induce dso hit increment
···
 		id->tid  = tid;
 	}
 	if (jd->sample_type & PERF_SAMPLE_TIME)
-		id->time = jr->load.p.timestamp;
+		id->time = convert_timestamp(jd, jr->load.p.timestamp);
 
 	/*
 	 * create pseudo sample to induce dso hit increment

tools/perf/util/jitdump.h

···
 #define JITHEADER_VERSION 1
 
 enum jitdump_flags_bits {
+	JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT,
 	JITDUMP_FLAGS_MAX_BIT,
 };
+
+#define JITDUMP_FLAGS_ARCH_TIMESTAMP	(1ULL << JITDUMP_FLAGS_ARCH_TIMESTAMP_BIT)
 
 #define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
 				(~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)

tools/perf/util/tsc.h

···
 #include <linux/types.h>
 
 #include "event.h"
-#include "../arch/x86/util/tsc.h"
+
+struct perf_tsc_conversion {
+	u16 time_shift;
+	u32 time_mult;
+	u64 time_zero;
+};
+struct perf_event_mmap_page;
+
+int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
+			     struct perf_tsc_conversion *tc);
 
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);