[PATCH v4 2/2] perf synthetic events: Remove use of sscanf from /proc reading

From: Ian Rogers
Date: Sat Apr 11 2020 - 02:43:00 EST


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@xxxxxxxxxx>
---
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