virtio_blk: set the zone write granularitygrafted

virtblk_read_zoned_limits() reads the write granularity that the device
reports in virtio_blk_zoned_characteristics and assigns it to the
physical block size and to io_min, but never to the limit that is named
after it. queue_limits.zone_write_granularity is left at zero, so
blk_validate_zoned_limits() raises it to the logical block size:

	if (lim->zone_write_granularity < lim->logical_block_size)
		lim->zone_write_granularity = lim->logical_block_size;

A device that reports a granularity coarser than its logical block size,
which is what the field exists to express, therefore has it silently
reduced. A 512e host managed disk passed through to a guest reports a
logical block size of 512 and a write granularity of 4096, and the guest
ends up with a zone write granularity of 512.

bio_split_alignment() returns lim->zone_write_granularity if it is non-zero
and bio_split_io_at() may split a bio with as per bio_split_alignment().
This can real to the write getting rejected by the host drive, as the write
is not aligned to the physical block size.

zonefs also takes its block size from bdev_zone_write_granularity(), so it
would incorrectly use 512 on a disk that requires 4096.

sd_zbc_read_zones() sets the limit from the physical block size for the
same reason. NVMe ZNS and null_blk leave it unset, but the fallback
gives the right answer for them, as their write granularity is the
logical block size. virtio carries a separate value that may exceed it.

Set the zone write granularity from the value that the device reports.

Fixes: 95bfec41bd3d ("virtio-blk: add support for zoned block devices")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20260918140641.2031075-2-cassel@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 199 insertions, 0 deletions

diff --git a/scripts/container b/scripts/container
new file mode 100755
index 000000000..b05333d85
--- /dev/null
+++ b/scripts/container
@@ -0,0 +1,199 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2025 Guillaume Tucker
+
+"""Containerized builds"""
+
+import abc
+import argparse
+import logging
+import os
+import pathlib
+import shutil
+import subprocess
+import sys
+import uuid
+
+
+class ContainerRuntime(abc.ABC):
+    """Base class for a container runtime implementation"""
+
+    name = None  # Property defined in each implementation class
+
+    def __init__(self, args, logger):
+        self._uid = args.uid or os.getuid()
+        self._gid = args.gid or args.uid or os.getgid()
+        self._env_file = args.env_file
+        self._shell = args.shell
+        self._logger = logger
+
+    @classmethod
+    def is_present(cls):
+        """Determine whether the runtime is present on the system"""
+        return shutil.which(cls.name) is not None
+
+    @abc.abstractmethod
+    def _do_run(self, image, cmd, container_name):
+        """Runtime-specific handler to run a command in a container"""
+
+    @abc.abstractmethod
+    def _do_abort(self, container_name):
+        """Runtime-specific handler to abort a running container"""
+
+    def run(self, image, cmd):
+        """Run a command in a runtime container"""
+        container_name = str(uuid.uuid4())
+        self._logger.debug("container: %s", container_name)
+        try:
+            return self._do_run(image, cmd, container_name)
+        except KeyboardInterrupt:
+            self._logger.error("user aborted")
+            self._do_abort(container_name)
+            return 1
+
+
+class CommonRuntime(ContainerRuntime):
+    """Common logic for Docker and Podman"""
+
+    def _do_run(self, image, cmd, container_name):
+        cmdline = [self.name, 'run']
+        cmdline += self._get_opts(container_name)
+        cmdline.append(image)
+        cmdline += cmd
+        self._logger.debug('command: %s', ' '.join(cmdline))
+        return subprocess.call(cmdline)
+
+    def _get_opts(self, container_name):
+        opts = [
+            '--name', container_name,
+            '--rm',
+            '--volume', f'{pathlib.Path.cwd()}:/src',
+            '--workdir', '/src',
+        ]
+        if self._env_file:
+            opts += ['--env-file', self._env_file]
+        if self._shell:
+            opts += ['--interactive', '--tty']
+        return opts
+
+    def _do_abort(self, container_name):
+        subprocess.call([self.name, 'kill', container_name])
+
+
+class DockerRuntime(CommonRuntime):
+    """Run a command in a Docker container"""
+
+    name = 'docker'
+
+    def _get_opts(self, container_name):
+        return super()._get_opts(container_name) + [
+            '--user', f'{self._uid}:{self._gid}'
+        ]
+
+
+class PodmanRuntime(CommonRuntime):
+    """Run a command in a Podman container"""
+
+    name = 'podman'
+
+    def _get_opts(self, container_name):
+        return super()._get_opts(container_name) + [
+            '--userns', f'keep-id:uid={self._uid},gid={self._gid}',
+        ]
+
+
+class Runtimes:
+    """List of all supported runtimes"""
+
+    runtimes = [PodmanRuntime, DockerRuntime]
+
+    @classmethod
+    def get_names(cls):
+        """Get a list of all the runtime names"""
+        return list(runtime.name for runtime in cls.runtimes)
+
+    @classmethod
+    def get(cls, name):
+        """Get a single runtime class matching the given name"""
+        for runtime in cls.runtimes:
+            if runtime.name == name:
+                if not runtime.is_present():
+                    raise ValueError(f"runtime not found: {name}")
+                return runtime
+        raise ValueError(f"unknown runtime: {name}")
+
+    @classmethod
+    def find(cls):
+        """Find the first runtime present on the system"""
+        for runtime in cls.runtimes:
+            if runtime.is_present():
+                return runtime
+        raise ValueError("no runtime found")
+
+
+def _get_logger(verbose):
+    """Set up a logger with the appropriate level"""
+    logger = logging.getLogger('container')
+    handler = logging.StreamHandler()
+    handler.setFormatter(logging.Formatter(
+        fmt='[container {levelname}] {message}', style='{'
+    ))
+    logger.addHandler(handler)
+    logger.setLevel(logging.DEBUG if verbose is True else logging.INFO)
+    return logger
+
+
+def main(args):
+    """Main entry point for the container tool"""
+    logger = _get_logger(args.verbose)
+    try:
+        cls = Runtimes.get(args.runtime) if args.runtime else Runtimes.find()
+    except ValueError as ex:
+        logger.error(ex)
+        return 1
+    logger.debug("runtime: %s", cls.name)
+    logger.debug("image: %s", args.image)
+    return cls(args, logger).run(args.image, args.cmd)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(
+        'container',
+        description="See the documentation for more details: "
+        "https://docs.kernel.org/dev-tools/container.html"
+    )
+    parser.add_argument(
+        '-e', '--env-file',
+        help="Path to an environment file to load in the container."
+    )
+    parser.add_argument(
+        '-g', '--gid',
+        help="Group ID to use inside the container."
+    )
+    parser.add_argument(
+        '-i', '--image', required=True,
+        help="Container image name."
+    )
+    parser.add_argument(
+        '-r', '--runtime', choices=Runtimes.get_names(),
+        help="Container runtime name.  If not specified, the first one found "
+        "on the system will be used i.e. Podman if present, otherwise Docker."
+    )
+    parser.add_argument(
+        '-s', '--shell', action='store_true',
+        help="Run the container in an interactive shell."
+    )
+    parser.add_argument(
+        '-u', '--uid',
+        help="User ID to use inside the container.  If the -g option is not "
+        "specified, the user ID will also be set as the group ID."
+    )
+    parser.add_argument(
+        '-v', '--verbose', action='store_true',
+        help="Enable verbose output."
+    )
+    parser.add_argument(
+        'cmd', nargs='+',
+        help="Command to run in the container"
+    )
+    sys.exit(main(parser.parse_args(sys.argv[1:])))