boot-utils: Add '--gh-json-file'

In moving the rootfs images to GitHub releases, we risk hitting GitHub's
API rate limit with GITHUB_TOKEN, which is 1,000 requests per hour per
repository, because each boot test within a workflow will be a separate
call. It is totally possible for us to run 1,000 boots an hour during a
busy workflow period, so this needs special consideration.

To make it easier for CI to cache the results of a GitHub release API
query, add '--gh-json-file' to both boot-qemu.py and boot-uml.py to
allow the tuxsuite parent job to generate boot-utils.json and pass that
along to each child job, so that at worst, each workflow will query the
API three times (once for defconfigs, allconfigs, and distro configs).

Signed-off-by: Nathan Chancellor <nathan@kernel.org>

Author: nathanchance

boot-qemu.py

@@ -44,6 +44,7 @@ def __init__(self):
         self.efi = False
         self.gdb = False
         self.gdb_bin = ''
+        self.gh_json_file = None
         self.interactive = False
         self.kernel = None
         self.kernel_dir = None
@@ -162,7 +163,8 @@ def _have_dev_kvm_access(self):
     def _prepare_initrd(self):
         if not self._initrd_arch:
             raise RuntimeError('No initrd architecture specified?')
-        return utils.prepare_initrd(self._initrd_arch)
+        return utils.prepare_initrd(self._initrd_arch,
+                                    gh_json_file=self.gh_json_file)
 
     def _run_fg(self):
         # Pretty print and run QEMU command
@@ -740,6 +742,11 @@ def parse_arguments():
         '--gdb-bin',
         default='gdb-multiarch',
         help='gdb binary to use for debugging (default: gdb-multiarch)')
+    parser.add_argument(
+        '--gh-json-file',
+        help=
+        'Use file for downloading rootfs images, instead of querying GitHub API directly'
+    )
     parser.add_argument(
         '-k',
         '--kernel-location',
@@ -827,6 +834,9 @@ def parse_arguments():
         runner.gdb = True
         runner.gdb_bin = args.gdb_bin
 
+    if args.gh_json_file:
+        runner.gh_json_file = Path(args.gh_json_file).resolve()
+
     if args.no_kvm:
         runner.use_kvm = False
 

boot-uml.py

@@ -2,6 +2,7 @@
 # pylint: disable=invalid-name
 
 import argparse
+from pathlib import Path
 import subprocess
 
 import utils
@@ -16,6 +17,12 @@ def parse_arguments():
     """
     parser = argparse.ArgumentParser()
 
+    parser.add_argument(
+        '-g',
+        '--gh-json-file',
+        help=
+        'Use file for downloading rootfs images, instead of querying GitHub API directly'
+    )
     parser.add_argument(
         "-i",
         "--interactive",
@@ -54,7 +61,12 @@ def run_kernel(kernel_image, rootfs, interactive):
 
 if __name__ == '__main__':
     args = parse_arguments()
+
     kernel = utils.get_full_kernel_path(args.kernel_location, "linux")
-    initrd = utils.prepare_initrd('x86_64', rootfs_format='ext4')
+
+    initrd_args = {'rootfs_format': 'ext4'}
+    if args.gh_json_file:
+        initrd_args['gh_json_file'] = Path(args.gh_json_file).resolve()
+    initrd = utils.prepare_initrd('x86_64', **initrd_args)
 
     run_kernel(kernel, initrd, args.interactive)

utils.py

@@ -172,7 +172,7 @@ def green(string):
     print(f"\n\033[01;32m{string}\033[0m", flush=True)
 
 
-def prepare_initrd(architecture, rootfs_format='cpio'):
+def prepare_initrd(architecture, rootfs_format='cpio', gh_json_file=None):
     """
     Returns a decompressed initial ramdisk.
 
@@ -189,11 +189,19 @@ def prepare_initrd(architecture, rootfs_format='cpio'):
     gh_json_rl = get_gh_json('https://api.github.com/rate_limit')
     remaining = gh_json_rl['resources']['core']['remaining']
 
-    # If we have API calls remaining, we can query for the latest release to
-    # make sure that we are up to date.
-    if remaining > 0:
-        gh_json_rel = get_gh_json(
-            f"https://api.github.com/repos/{REPO}/releases/latest")
+    # If we have API calls remaining or have already queried the API previously
+    # and cached the result, we can query for the latest release to make sure
+    # that we are up to date.
+    if remaining > 0 or gh_json_file:
+        if gh_json_file:
+            if not gh_json_file.exists():
+                raise FileNotFoundError(
+                    f"Provided GitHub JSON file ('{gh_json_file}') does not exist!"
+                )
+            gh_json_rel = json.loads(gh_json_file.read_text(encoding='utf-8'))
+        else:
+            gh_json_rel = get_gh_json(
+                f"https://api.github.com/repos/{REPO}/releases/latest")
         # Download the ramdisk if it is not already downloaded
         if not src.exists():
             download_initrd(gh_json_rel, src)