[RFC PATCH 1/4] scripts: convert bootgraph.pl to Python

[Breno Rodrigues Alves]

Faithful re-implementation of bootgraph.pl in Python 3 (stdlib only).
Same CLI (-h, -header), same SVG output, same error handling.

One intentional change: the Perl version has an unreachable
'exit 1' after 'help(1); exit 1;' (help() already calls exit 0),
so it always returned 0 even on error. The Python version
returns exit 1 when no data is found in dmesg.

Tested with a synthetic dmesg containing three initcalls;
generated SVG is byte-for-byte identical to the Perl output.

Signed-off-by: Breno Rodrigues Alves <breno3011alves@xxxxxxxxx>
---
 scripts/bootgraph.py | 194 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 194 insertions(+)
 create mode 100755 scripts/bootgraph.py

diff --git a/scripts/bootgraph.py b/scripts/bootgraph.py
new file mode 100755
index 000000000..6839d2824
--- /dev/null
+++ b/scripts/bootgraph.py
@@ -0,0 +1,194 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright 2008, Intel Corporation
+# Authors: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
+#
+# Turn dmesg output into an SVG graphic showing which initcalls take
+# how much time. The kernel must be compiled with CONFIG_PRINTK_TIME
+# and booted with "initcall_debug" on the command line.
+#
+# usage:
+#     dmesg | python3 scripts/bootgraph.py > output.svg
+
+import argparse
+import re
+import subprocess
+import sys
+
+RE_CALLING     = re.compile(r'([0-9.]+)\] calling  ([a-zA-Z0-9_.]+)\+')
+RE_PID         = re.compile(r'@ ([0-9]+)')
+RE_ASYNC_WAIT  = re.compile(r'([0-9.]+)\] async_waiting @ ([0-9]+)')
+RE_RETURNED    = re.compile(r'([0-9.]+)\] initcall ([a-zA-Z0-9_.]+)\+.*returned')
+RE_ASYNC_CONT  = re.compile(r'([0-9.]+)\] async_continuing @ ([0-9]+)')
+RE_STOP        = re.compile(r'(Write protecting the|Freeing unused kernel memory)')
+
+STYLES = [
+    'fill:rgb(0,0,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(0,255,0);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(255,0,20);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(255,255,20);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(255,0,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(0,255,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(0,128,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(0,255,128);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(255,0,128);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(255,255,128);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(255,128,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+    'fill:rgb(128,255,255);fill-opacity:0.5;stroke-width:1;stroke:rgb(0,0,0)',
+]
+STYLE_WAIT = 'fill:rgb(128,128,128);fill-opacity:0.5;stroke-width:0;stroke:rgb(0,0,0)'
+
+HEADERSTEP = 20
+XHEADER    = 15
+YHEADER    = 25
+
+
+def usage(exit_code=1):
+    stream = sys.stdout if exit_code == 0 else sys.stderr
+    print('Usage:', file=stream)
+    print('1) dmesg | python3 scripts/bootgraph.py [OPTION] > output.svg',
+          file=stream)
+    print('2) python3 scripts/bootgraph.py -h', file=stream)
+    print('', file=stream)
+    print('Options:', file=stream)
+    print('\t-header\tInsert kernel version and date', file=stream)
+    sys.exit(exit_code)
+
+
+def parse_dmesg(stream):
+    """Return (start, end, types, pids, count, first, last)."""
+    start, end, types, pids, pidctr = {}, {}, {}, {}, {}
+    done = False
+    first, last, count = 99999.0, 0.0, 0
+
+    for line in stream:
+        m = RE_CALLING.search(line)
+        if m:
+            func = m.group(2)
+            if not done:
+                start[func] = float(m.group(1))
+                types[func] = 0
+                first = min(first, start[func])
+            mp = RE_PID.search(line)
+            if mp:
+                pids[func] = int(mp.group(1))
+            count += 1
+
+        m = RE_ASYNC_WAIT.search(line)
+        if m:
+            pid = int(m.group(2))
+            pidctr[pid] = pidctr.get(pid, 0) + 1
+            func = f'wait_{pid}_{pidctr[pid]}'
+            if not done:
+                start[func] = float(m.group(1))
+                types[func] = 1
+                first = min(first, start[func])
+            pids[func] = pid
+            count += 1
+
+        m = RE_RETURNED.search(line)
+        if m and not done:
+            end[m.group(2)] = float(m.group(1))
+            last = end[m.group(2)]
+
+        m = RE_ASYNC_CONT.search(line)
+        if m:
+            pid = int(m.group(2))
+            func = f'wait_{pid}_{pidctr.get(pid, "")}'
+            end[func] = float(m.group(1))
+            last = end[func]
+
+        if RE_STOP.search(line):
+            done = True
+
+    return start, end, types, pids, count, first, last
+
+
+def emit_svg(out, start, end, types, pids, first, last, header):
+    out.write('<?xml version="1.0" standalone="no"?> \n')
+    out.write('<svg width="2000" height="100%" version="1.1" '
+              'xmlns="http://www.w3.org/2000/svg";>\n')
+
+    if header:
+        version = subprocess.check_output(['uname', '-a'], text=True).rstrip()
+        date = subprocess.check_output(['date'], text=True).rstrip()
+        out.write(f'<text transform="translate({XHEADER},{YHEADER})">'
+                  f'Kernel version: {version}</text>\n')
+        cyheader = YHEADER + HEADERSTEP
+        out.write(f'<text transform="translate({XHEADER},{cyheader})">'
+                  f'Date: {date}</text>\n')
+
+    mult = 1950.0 / (last - first)
+    threshold2 = (last - first) / 120.0
+    threshold = threshold2 / 10
+
+    stylecounter = 0
+    rows, rowscount = {}, 1
+
+    for key in sorted(start.keys(), key=lambda k: start[k]):
+        duration = end[key] - start[key]
+        if duration < threshold:
+            continue
+        pid = pids.get(key)
+        if pid not in rows:
+            rows[pid] = rowscount
+            rowscount += 1
+        s = (start[key] - first) * mult
+        s2, s3 = s + 6, s + 1
+        e = (end[key] - first) * mult
+        w = e - s
+        y = rows[pid] * 150
+        y2 = y + 4
+        style = STYLES[stylecounter]
+        stylecounter = (stylecounter + 1) % 12
+        if types[key] == 1:
+            y += 15
+            out.write(f'<rect x="{s:.15g}" width="{w:.15g}" y="{y}" '
+                      f'height="115" style="{STYLE_WAIT}"/>\n')
+        else:
+            out.write(f'<rect x="{s:.15g}" width="{w:.15g}" y="{y}" '
+                      f'height="145" style="{style}"/>\n')
+            if duration >= threshold2:
+                out.write(f'<text transform="translate({s2:.15g},{y2}) '
+                          f'rotate(90)">{key}</text>\n')
+            else:
+                out.write(f'<text transform="translate({s3:.15g},{y2}) '
+                          f'rotate(90)" font-size="3pt">{key}</text>\n')
+
+    # top timeline
+    time = first
+    step = (last - first) / 15.0
+    while time < last:
+        s3 = (time - first) * mult
+        tm = int(time * 100) / 100.0
+        out.write(f'<text transform="translate({s3:.15g},89) rotate(90)">{tm:.15g}</text>\n')
+        time += step
+
+    out.write('</svg>\n')
+
+
+def main(argv):
+    parser = argparse.ArgumentParser(add_help=False)
+    parser.add_argument('-h', '--help', action='store_true')
+    parser.add_argument('-header', '--header', action='store_true')
+    args = parser.parse_args(argv)
+
+    if args.help:
+        usage(0)
+
+    start, end, types, pids, count, first, last = parse_dmesg(sys.stdin)
+
+    if count == 0:
+        print("No data found in the dmesg. Make sure that 'printk.time=1' and",
+              file=sys.stderr)
+        print("'initcall_debug' are passed on the kernel command line.",
+              file=sys.stderr)
+        usage(1)
+
+    emit_svg(sys.stdout, start, end, types, pids, first, last, args.header)
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main(sys.argv[1:]))
\ No newline at end of file
-- 
2.43.0