perf tests: objdump output can contain multi byte chunks

objdump's raw insn output can vary across architectures on the number of
bytes per chunk (bpc) displayed and their endianness.

The code-reading test relied on reading objdump output as 1 bpc. Kaixu
Xia reported test failure on ARM64, where objdump displays 4 bpc:

  70c48:        f90027bf         str        xzr, [x29,#72]
  70c4c:        91224000         add        x0, x0, #0x890
  70c50:        f90023a0         str        x0, [x29,#64]

This patch adds support to read raw insn output for any bpc length.
In case of 2+ bpc it also guesses objdump's display endian.

Reported-and-Tested-by: Kaixu Xia <xiakaixu@huawei.com>
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/07f0f7bcbda78deb423298708ef9b6a54d6b92bd.1452592712.git.jstancek@redhat.com
[ Fix up pr_fmt() call to use %zd for size_t variables, fixing the build on Ubuntu cross-compiling to armhf and ppc64 ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 71 insertions, 29 deletions

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 68a69a195545..2af156a8d4e5 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -33,44 +33,86 @@ static unsigned int hex(char c)
         return c - 'A' + 10;
 }
 
-static size_t read_objdump_line(const char *line, size_t line_len, void *buf,
-                              size_t len)
+static size_t read_objdump_chunk(const char **line, unsigned char **buf,
+                                 size_t *buf_len)
 {
-        const char *p;
-        size_t i, j = 0;
-
-        /* Skip to a colon */
-        p = strchr(line, ':');
-        if (!p)
-                return 0;
-        i = p + 1 - line;
+        size_t bytes_read = 0;
+        unsigned char *chunk_start = *buf;
 
         /* Read bytes */
-        while (j < len) {
+        while (*buf_len > 0) {
                 char c1, c2;
 
-                /* Skip spaces */
-                for (; i < line_len; i++) {
-                        if (!isspace(line[i]))
-                                break;
-                }
                 /* Get 2 hex digits */
-                if (i >= line_len || !isxdigit(line[i]))
+                c1 = *(*line)++;
+                if (!isxdigit(c1))
                         break;
-                c1 = line[i++];
-                if (i >= line_len || !isxdigit(line[i]))
+                c2 = *(*line)++;
+                if (!isxdigit(c2))
                         break;
-                c2 = line[i++];
-                /* Followed by a space */
-                if (i < line_len && line[i] && !isspace(line[i]))
+
+                /* Store byte and advance buf */
+                **buf = (hex(c1) << 4) | hex(c2);
+                (*buf)++;
+                (*buf_len)--;
+                bytes_read++;
+
+                /* End of chunk? */
+                if (isspace(**line))
                         break;
-                /* Store byte */
-                *(unsigned char *)buf = (hex(c1) << 4) | hex(c2);
-                buf += 1;
-                j++;
         }
+
+        /*
+         * objdump will display raw insn as LE if code endian
+         * is LE and bytes_per_chunk > 1. In that case reverse
+         * the chunk we just read.
+         *
+         * see disassemble_bytes() at binutils/objdump.c for details
+         * how objdump chooses display endian)
+         */
+        if (bytes_read > 1 && !bigendian()) {
+                unsigned char *chunk_end = chunk_start + bytes_read - 1;
+                unsigned char tmp;
+
+                while (chunk_start < chunk_end) {
+                        tmp = *chunk_start;
+                        *chunk_start = *chunk_end;
+                        *chunk_end = tmp;
+                        chunk_start++;
+                        chunk_end--;
+                }
+        }
+
+        return bytes_read;
+}
+
+static size_t read_objdump_line(const char *line, unsigned char *buf,
+                                size_t buf_len)
+{
+        const char *p;
+        size_t ret, bytes_read = 0;
+
+        /* Skip to a colon */
+        p = strchr(line, ':');
+        if (!p)
+                return 0;
+        p++;
+
+        /* Skip initial spaces */
+        while (*p) {
+                if (!isspace(*p))
+                        break;
+                p++;
+        }
+
+        do {
+                ret = read_objdump_chunk(&p, &buf, &buf_len);
+                bytes_read += ret;
+                p++;
+        } while (ret > 0);
+
         /* return number of successfully read bytes */
-        return j;
+        return bytes_read;
 }
 
 static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
@@ -95,7 +137,7 @@ static int read_objdump_output(FILE *f, void *buf, size_t *len, u64 start_addr)
                 }
 
                 /* read objdump data into temporary buffer */
-                read_bytes = read_objdump_line(line, ret, tmp, sizeof(tmp));
+                read_bytes = read_objdump_line(line, tmp, sizeof(tmp));
                 if (!read_bytes)
                         continue;
 
@@ -152,7 +194,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 
         ret = read_objdump_output(f, buf, &len, addr);
         if (len) {
-                pr_debug("objdump read too few bytes\n");
+                pr_debug("objdump read too few bytes: %zd\n", len);
                 if (!ret)
                         ret = len;
         }