[PATCH v3 1/2] tools api: add a lightweight buffered reading api

[PATCH v3 1/2] tools api: add a lightweight buffered reading api

[Ian Rogers]

The synthesize benchmark shows the majority of execution time going to
fgets and sscanf, necessary to parse /proc/pid/maps. Add a new buffered
reading library that will be used to replace these calls in a follow-up
CL. Add tests for the library to perf test.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/lib/api/io.h              | 112 ++++++++++++++++++++++++++++++++
 tools/perf/tests/Build          |   1 +
 tools/perf/tests/builtin-test.c |   4 ++
 tools/perf/tests/tests.h        |   1 +
 4 files changed, 118 insertions(+)
 create mode 100644 tools/lib/api/io.h

diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h
new file mode 100644
index 000000000000..b7e55b5f8a4a
--- /dev/null
+++ b/tools/lib/api/io.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Lightweight buffered reading library.
+ *
+ * Copyright 2019 Google LLC.
+ */
+#ifndef __API_IO__
+#define __API_IO__
+
+struct io {
+	/* File descriptor being read/ */
+	int fd;
+	/* Size of the read buffer. */
+	unsigned int buf_len;
+	/* Pointer to storage for buffering read. */
+	char *buf;
+	/* End of the storage. */
+	char *end;
+	/* Currently accessed data pointer. */
+	char *data;
+	/* Set true on when the end of file on read error. */
+	bool eof;
+};
+
+static inline void io__init(struct io *io, int fd,
+			    char *buf, unsigned int buf_len)
+{
+	io->fd = fd;
+	io->buf_len = buf_len;
+	io->buf = buf;
+	io->end = buf;
+	io->data = buf;
+	io->eof = false;
+}
+
+/* Reads one character from the "io" file with similar semantics to fgetc. */
+static inline int io__get_char(struct io *io)
+{
+	char *ptr = io->data;
+
+	if (io->eof)
+		return -1;
+
+	if (ptr == io->end) {
+		ssize_t n = read(io->fd, io->buf, io->buf_len);
+
+		if (n <= 0) {
+			io->eof = true;
+			return -1;
+		}
+		ptr = &io->buf[0];
+		io->end = &io->buf[n];
+	}
+	io->data = ptr + 1;
+	return *ptr;
+}
+
+/* Read a hexadecimal value with no 0x prefix into the out argument hex. If the
+ * first character isn't hexadecimal returns -2, io->eof returns -1, otherwise
+ * returns the character after the hexadecimal value which may be -1 for eof.
+ * If the read value is larger than a u64 the high-order bits will be dropped.
+ */
+static inline int io__get_hex(struct io *io, __u64 *hex)
+{
+	bool first_read = true;
+
+	*hex = 0;
+	while (true) {
+		int ch = io__get_char(io);
+
+		if (ch < 0)
+			return ch;
+		if (ch >= '0' && ch <= '9')
+			*hex = (*hex << 4) | (ch - '0');
+		else if (ch >= 'a' && ch <= 'f')
+			*hex = (*hex << 4) | (ch - 'a' + 10);
+		else if (ch >= 'A' && ch <= 'F')
+			*hex = (*hex << 4) | (ch - 'A' + 10);
+		else if (first_read)
+			return -2;
+		else
+			return ch;
+		first_read = false;
+	}
+}
+
+/* Read a positive decimal value with out argument dec. If the first character
+ * isn't a decimal returns -2, io->eof returns -1, otherwise returns the
+ * character after the decimal value which may be -1 for eof. If the read value
+ * is larger than a u64 the high-order bits will be dropped.
+ */
+static inline int io__get_dec(struct io *io, __u64 *dec)
+{
+	bool first_read = true;
+
+	*dec = 0;
+	while (true) {
+		int ch = io__get_char(io);
+
+		if (ch < 0)
+			return ch;
+		if (ch >= '0' && ch <= '9')
+			*dec = (*dec * 10) + ch - '0';
+		else if (first_read)
+			return -2;
+		else
+			return ch;
+		first_read = false;
+	}
+}
+
+#endif /* __API_IO__ */
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index b3d1bf13ca07..c75557aeef0e 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -56,6 +56,7 @@ perf-y += mem2node.o
 perf-y += maps.o
 perf-y += time-utils-test.o
 perf-y += genelf.o
+perf-y += api-io.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index b6322eb0f423..3471ec52ea11 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -309,6 +309,10 @@ static struct test generic_tests[] = {
 		.desc = "Test jit_write_elf",
 		.func = test__jit_write_elf,
 	},
+	{
+		.desc = "Test api io",
+		.func = test__api_io,
+	},
 	{
 		.desc = "maps__merge_in",
 		.func = test__maps__merge_in,
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 61a1ab032080..d6d4ac34eeb7 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -112,6 +112,7 @@ int test__mem2node(struct test *t, int subtest);
 int test__maps__merge_in(struct test *t, int subtest);
 int test__time_utils(struct test *t, int subtest);
 int test__jit_write_elf(struct test *test, int subtest);
+int test__api_io(struct test *test, int subtest);
 
 bool test__bp_signal_is_supported(void);
 bool test__bp_account_is_supported(void);
-- 
2.26.0.110.g2183baf09c-goog

[PATCH v3 2/2] perf synthetic events: Remove use of sscanf from /proc reading

[Ian Rogers]

The synthesize benchmark, run on a single process and thread, shows
perf_event__synthesize_mmap_events as the hottest function with fgets
and sscanf taking the majority of execution time. fscanf performs
similarly well. Replace the scanf call with manual reading of each field
of the /proc/pid/maps line, and remove some unnecessary buffering.
This change also addresses potential, but unlikely, buffer overruns for
the string values read by scanf.

Performance before is:
Average synthesis took: 120.195100 usec
Average data synthesis took: 156.582300 usec

And after is:
Average synthesis took: 67.189100 usec
Average data synthesis took: 102.451600 usec

On a Intel Xeon 6154 compiling with Debian gcc 9.2.1.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/synthetic-events.c | 157 +++++++++++++++++++----------
 1 file changed, 105 insertions(+), 52 deletions(-)

diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 9d4aa951eaa6..1ea9adaef9c7 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -37,6 +37,7 @@
 #include <string.h>
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include <api/fs/fs.h>
+#include <api/io.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -273,6 +274,79 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 	return 0;
 }
 
+static bool read_proc_maps_line(struct io *io, __u64 *start, __u64 *end,
+				u32 *prot, u32 *flags, __u64 *offset,
+				u32 *maj, u32 *min,
+				__u64 *inode,
+				ssize_t pathname_size, char *pathname)
+{
+	__u64 temp;
+	int ch;
+	char *start_pathname = pathname;
+
+	if (io__get_hex(io, start) != '-')
+		return false;
+	if (io__get_hex(io, end) != ' ')
+		return false;
+
+	/* map protection and flags bits */
+	*prot = 0;
+	ch = io__get_char(io);
+	if (ch == 'r')
+		*prot |= PROT_READ;
+	else if (ch != '-')
+		return false;
+	ch = io__get_char(io);
+	if (ch == 'w')
+		*prot |= PROT_WRITE;
+	else if (ch != '-')
+		return false;
+	ch = io__get_char(io);
+	if (ch == 'x')
+		*prot |= PROT_EXEC;
+	else if (ch != '-')
+		return false;
+	ch = io__get_char(io);
+	if (ch == 's')
+		*flags = MAP_SHARED;
+	else if (ch == 'p')
+		*flags = MAP_PRIVATE;
+	else
+		return false;
+	if (io__get_char(io) != ' ')
+		return false;
+
+	if (io__get_hex(io, offset) != ' ')
+		return false;
+
+	if (io__get_hex(io, &temp) != ':')
+		return false;
+	*maj = temp;
+	if (io__get_hex(io, &temp) != ' ')
+		return false;
+	*min = temp;
+
+	ch = io__get_dec(io, inode);
+	if (ch != ' ') {
+		*pathname = '\0';
+		return ch == '\n';
+	}
+	do {
+		ch = io__get_char(io);
+	} while (ch == ' ');
+	while (true) {
+		if (ch < 0)
+			return false;
+		if (ch == '\0' || ch == '\n' ||
+		    (pathname + 1 - start_pathname) >= pathname_size) {
+			*pathname = '\0';
+			return true;
+		}
+		*pathname++ = ch;
+		ch = io__get_char(io);
+	}
+}
+
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       union perf_event *event,
 				       pid_t pid, pid_t tgid,
@@ -280,9 +354,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       struct machine *machine,
 				       bool mmap_data)
 {
-	FILE *fp;
 	unsigned long long t;
 	char bf[BUFSIZ];
+	struct io io;
 	bool truncation = false;
 	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
@@ -295,28 +369,39 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	snprintf(bf, sizeof(bf), "%s/proc/%d/task/%d/maps",
 		machine->root_dir, pid, pid);
 
-	fp = fopen(bf, "r");
-	if (fp == NULL) {
+	io.fd = open(bf, O_RDONLY, 0);
+	if (io.fd < 0) {
 		/*
 		 * We raced with a task exiting - just return:
 		 */
 		pr_debug("couldn't open %s\n", bf);
 		return -1;
 	}
+	io__init(&io, io.fd, bf, sizeof(bf));
 
 	event->header.type = PERF_RECORD_MMAP2;
 	t = rdclock();
 
-	while (1) {
-		char prot[5];
-		char execname[PATH_MAX];
-		char anonstr[] = "//anon";
-		unsigned int ino;
+	while (!io.eof) {
+		static const char anonstr[] = "//anon";
 		size_t size;
-		ssize_t n;
 
-		if (fgets(bf, sizeof(bf), fp) == NULL)
-			break;
+		/* ensure null termination since stack will be reused. */
+		event->mmap2.filename[0] = '\0';
+
+		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
+		if (!read_proc_maps_line(&io,
+					&event->mmap2.start,
+					&event->mmap2.len,
+					&event->mmap2.prot,
+					&event->mmap2.flags,
+					&event->mmap2.pgoff,
+					&event->mmap2.maj,
+					&event->mmap2.min,
+					&event->mmap2.ino,
+					sizeof(event->mmap2.filename),
+					event->mmap2.filename))
+			continue;
 
 		if ((rdclock() - t) > timeout) {
 			pr_warning("Reading %s/proc/%d/task/%d/maps time out. "
@@ -327,23 +412,6 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			goto out;
 		}
 
-		/* ensure null termination since stack will be reused. */
-		strcpy(execname, "");
-
-		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRI_lx64"-%"PRI_lx64" %s %"PRI_lx64" %x:%x %u %[^\n]\n",
-		       &event->mmap2.start, &event->mmap2.len, prot,
-		       &event->mmap2.pgoff, &event->mmap2.maj,
-		       &event->mmap2.min,
-		       &ino, execname);
-
-		/*
- 		 * Anon maps don't have the execname.
- 		 */
-		if (n < 7)
-			continue;
-
-		event->mmap2.ino = (u64)ino;
 		event->mmap2.ino_generation = 0;
 
 		/*
@@ -354,23 +422,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		else
 			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
-		/* map protection and flags bits */
-		event->mmap2.prot = 0;
-		event->mmap2.flags = 0;
-		if (prot[0] == 'r')
-			event->mmap2.prot |= PROT_READ;
-		if (prot[1] == 'w')
-			event->mmap2.prot |= PROT_WRITE;
-		if (prot[2] == 'x')
-			event->mmap2.prot |= PROT_EXEC;
-
-		if (prot[3] == 's')
-			event->mmap2.flags |= MAP_SHARED;
-		else
-			event->mmap2.flags |= MAP_PRIVATE;
-
-		if (prot[2] != 'x') {
-			if (!mmap_data || prot[0] != 'r')
+		if ((event->mmap2.prot & PROT_EXEC) == 0) {
+			if (!mmap_data || (event->mmap2.prot & PROT_READ) == 0)
 				continue;
 
 			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -380,17 +433,17 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		if (truncation)
 			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
 
-		if (!strcmp(execname, ""))
-			strcpy(execname, anonstr);
+		if (!strcmp(event->mmap2.filename, ""))
+			strcpy(event->mmap2.filename, anonstr);
 
 		if (hugetlbfs_mnt_len &&
-		    !strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
-			strcpy(execname, anonstr);
+		    !strncmp(event->mmap2.filename, hugetlbfs_mnt,
+			     hugetlbfs_mnt_len)) {
+			strcpy(event->mmap2.filename, anonstr);
 			event->mmap2.flags |= MAP_HUGETLB;
 		}
 
-		size = strlen(execname) + 1;
-		memcpy(event->mmap2.filename, execname, size);
+		size = strlen(event->mmap2.filename) + 1;
 		size = PERF_ALIGN(size, sizeof(u64));
 		event->mmap2.len -= event->mmap.start;
 		event->mmap2.header.size = (sizeof(event->mmap2) -
@@ -409,7 +462,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			break;
 	}
 
-	fclose(fp);
+	close(io.fd);
 	return rc;
 }
 
-- 
2.26.0.110.g2183baf09c-goog