Merge tag 'perf-core-for-mingo-4.15-20171023' of git://git.kernel.org…

…/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 - Update vendor events JSON metrics for Intel's Broadwell, Broadwell
   Server, Haswell, Haswell Server, IvyBridge, IvyTown, JakeTown, Sandy
   Bridge, Skylake and SkyLake Server (Andi Kleen)

 - Add vendor event file for Intel's Goldmont Plus V1 (Kan Liang)

 - Move perf_mmap methods from 'perf record' and evlist.c to a separate
   mmap.[ch] pair, to better separate things and pave the way for further
   work on multithreading tools (Arnaldo Carvalho de Melo)

 - Do not check ABI headers in a detached tarball build, as it the kernel
   headers from where we copied tools/include/ are by definition not
   available (Arnaldo Carvalho de Melo)

 - Make 'perf script' use fprintf() like printing, i.e. receiving a FILE
   pointer so that it gets consistent with other tools/ code and allows
   for printing to per-event files (Arnaldo Carvalho de Melo)

 - Error handling fixes (resource release on exit) for 'perf script'
   and 'perf kmem' (Christophe JAILLET)

 - Make some 'perf event attr' tests optional on virtual machines, where
   tested counters are not available (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/perf/Documentation/perf-list.txt

@@ -204,7 +204,7 @@ For example Intel Core CPUs typically have four generic performance counters
 for the core, plus three fixed counters for instructions, cycles and
 ref-cycles. Some special events have restrictions on which counter they
 can schedule, and may not support multiple instances in a single group.
-When too many events are specified in the group none of them will not
+When too many events are specified in the group some of them will not
 be measured.
 
 Globally pinned events can limit the number of counters available for

tools/perf/arch/arm/annotate/instructions.c

@@ -1,3 +1,4 @@
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -23,7 +24,7 @@ static struct ins_ops *arm__associate_instruction_ops(struct arch *arch, const c
 	return ops;
 }
 
-static int arm__annotate_init(struct arch *arch)
+static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
 	struct arm_annotate *arm;
 	int err;

tools/perf/arch/arm64/annotate/instructions.c

@@ -1,3 +1,4 @@
+#include <linux/compiler.h>
 #include <sys/types.h>
 #include <regex.h>
 
@@ -25,7 +26,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
 	return ops;
 }
 
-static int arm64__annotate_init(struct arch *arch)
+static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
 	struct arm64_annotate *arm;
 	int err;

tools/perf/arch/powerpc/annotate/instructions.c

@@ -1,3 +1,5 @@
+#include <linux/compiler.h>
+
 static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, const char *name)
 {
 	int i;
@@ -46,7 +48,7 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con
 	return ops;
 }
 
-static int powerpc__annotate_init(struct arch *arch)
+static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
 	if (!arch->initialized) {
 		arch->initialized = true;

tools/perf/arch/s390/annotate/instructions.c

@@ -1,3 +1,5 @@
+#include <linux/compiler.h>
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
 	struct ins_ops *ops = NULL;
@@ -19,7 +21,7 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 	return ops;
 }
 
-static int s390__annotate_init(struct arch *arch)
+static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
 	if (!arch->initialized) {
 		arch->initialized = true;

tools/perf/arch/x86/annotate/instructions.c

@@ -122,3 +122,17 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid)
 
 	return -1;
 }
+
+static int x86__annotate_init(struct arch *arch, char *cpuid)
+{
+	int err = 0;
+
+	if (arch->initialized)
+		return 0;
+
+	if (cpuid)
+		err = x86__cpuid_parse(arch, cpuid);
+
+	arch->initialized = true;
+	return err;
+}

tools/perf/builtin-kmem.c

@@ -1983,7 +1983,8 @@ int cmd_kmem(int argc, const char **argv)
 
 	if (perf_time__parse_str(&ptime, time_str) != 0) {
 		pr_err("Invalid time string\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_delete;
 	}
 
 	if (!strcmp(argv[0], "stat")) {

tools/perf/builtin-record.c

@@ -129,107 +129,12 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, event, event->header.size);
 }
 
-static int
-backward_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
-{
-	struct perf_event_header *pheader;
-	u64 evt_head = head;
-	int size = mask + 1;
-
-	pr_debug2("backward_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
-	pheader = (struct perf_event_header *)(buf + (head & mask));
-	*start = head;
-	while (true) {
-		if (evt_head - head >= (unsigned int)size) {
-			pr_debug("Finished reading backward ring buffer: rewind\n");
-			if (evt_head - head > (unsigned int)size)
-				evt_head -= pheader->size;
-			*end = evt_head;
-			return 0;
-		}
-
-		pheader = (struct perf_event_header *)(buf + (evt_head & mask));
-
-		if (pheader->size == 0) {
-			pr_debug("Finished reading backward ring buffer: get start\n");
-			*end = evt_head;
-			return 0;
-		}
-
-		evt_head += pheader->size;
-		pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
-	}
-	WARN_ONCE(1, "Shouldn't get here\n");
-	return -1;
-}
-
-static int
-rb_find_range(void *data, int mask, u64 head, u64 old,
-	      u64 *start, u64 *end, bool backward)
+static int record__pushfn(void *to, void *bf, size_t size)
 {
-	if (!backward) {
-		*start = old;
-		*end = head;
-		return 0;
-	}
-
-	return backward_rb_find_range(data, mask, head, start, end);
-}
-
-static int
-record__mmap_read(struct record *rec, struct perf_mmap *md,
-		  bool overwrite, bool backward)
-{
-	u64 head = perf_mmap__read_head(md);
-	u64 old = md->prev;
-	u64 end = head, start = old;
-	unsigned char *data = md->base + page_size;
-	unsigned long size;
-	void *buf;
-	int rc = 0;
-
-	if (rb_find_range(data, md->mask, head,
-			  old, &start, &end, backward))
-		return -1;
-
-	if (start == end)
-		return 0;
+	struct record *rec = to;
 
 	rec->samples++;
-
-	size = end - start;
-	if (size > (unsigned long)(md->mask) + 1) {
-		WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
-
-		md->prev = head;
-		perf_mmap__consume(md, overwrite || backward);
-		return 0;
-	}
-
-	if ((start & md->mask) + size != (end & md->mask)) {
-		buf = &data[start & md->mask];
-		size = md->mask + 1 - (start & md->mask);
-		start += size;
-
-		if (record__write(rec, buf, size) < 0) {
-			rc = -1;
-			goto out;
-		}
-	}
-
-	buf = &data[start & md->mask];
-	size = end - start;
-	start += size;
-
-	if (record__write(rec, buf, size) < 0) {
-		rc = -1;
-		goto out;
-	}
-
-	md->prev = head;
-	perf_mmap__consume(md, overwrite || backward);
-out:
-	return rc;
+	return record__write(rec, bf, size);
 }
 
 static volatile int done;
@@ -576,8 +481,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
 		if (maps[i].base) {
-			if (record__mmap_read(rec, &maps[i],
-					      evlist->overwrite, backward) != 0) {
+			if (perf_mmap__push(&maps[i], evlist->overwrite, backward, rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}