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, 159 insertions, 0 deletions

diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
new file mode 100644
index 000000000..637daf6e4
--- /dev/null
+++ b/fs/binfmt_script.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/fs/binfmt_script.c
+ *
+ *  Copyright (C) 1996  Martin von Löwis
+ *  original #!-checking implemented by tytso.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/binfmts.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+
+static inline bool spacetab(char c) { return c == ' ' || c == '\t'; }
+static inline const char *next_non_spacetab(const char *first, const char *last)
+{
+	for (; first <= last; first++)
+		if (!spacetab(*first))
+			return first;
+	return NULL;
+}
+static inline const char *next_terminator(const char *first, const char *last)
+{
+	for (; first <= last; first++)
+		if (spacetab(*first) || !*first)
+			return first;
+	return NULL;
+}
+
+static int load_script(struct linux_binprm *bprm)
+{
+	const char *i_name, *i_sep, *i_arg, *i_end, *buf_end;
+	struct file *file;
+	int retval;
+
+	/* Not ours to exec if we don't start with "#!". */
+	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
+		return -ENOEXEC;
+
+	/*
+	 * This section handles parsing the #! line into separate
+	 * interpreter path and argument strings. We must be careful
+	 * because bprm->buf is not yet guaranteed to be NUL-terminated
+	 * (though the buffer will have trailing NUL padding when the
+	 * file size was smaller than the buffer size).
+	 *
+	 * We do not want to exec a truncated interpreter path, so either
+	 * we find a newline (which indicates nothing is truncated), or
+	 * we find a space/tab/NUL after the interpreter path (which
+	 * itself may be preceded by spaces/tabs). Truncating the
+	 * arguments is fine: the interpreter can re-read the script to
+	 * parse them on its own.
+	 */
+	buf_end = bprm->buf + sizeof(bprm->buf) - 1;
+	i_end = strnchr(bprm->buf, sizeof(bprm->buf), '\n');
+	if (!i_end) {
+		i_end = next_non_spacetab(bprm->buf + 2, buf_end);
+		if (!i_end)
+			return -ENOEXEC; /* Entire buf is spaces/tabs */
+		/*
+		 * If there is no later space/tab/NUL we must assume the
+		 * interpreter path is truncated.
+		 */
+		if (!next_terminator(i_end, buf_end))
+			return -ENOEXEC;
+		i_end = buf_end;
+	}
+	/* Trim any trailing spaces/tabs from i_end */
+	while (spacetab(i_end[-1]))
+		i_end--;
+
+	/* Skip over leading spaces/tabs */
+	i_name = next_non_spacetab(bprm->buf+2, i_end);
+	if (!i_name || (i_name == i_end))
+		return -ENOEXEC; /* No interpreter name found */
+
+	/* Is there an optional argument? */
+	i_arg = NULL;
+	i_sep = next_terminator(i_name, i_end);
+	if (i_sep && (*i_sep != '\0'))
+		i_arg = next_non_spacetab(i_sep, i_end);
+
+	/*
+	 * If the script filename will be inaccessible after exec, typically
+	 * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
+	 * up now (on the assumption that the interpreter will want to load
+	 * this file).
+	 */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
+	/*
+	 * OK, we've parsed out the interpreter name and
+	 * (optional) argument.
+	 * Splice in (1) the interpreter's name for argv[0]
+	 *           (2) (optional) argument to interpreter
+	 *           (3) filename of shell script (replace argv[0])
+	 *
+	 * This is done in reverse order, because of how the
+	 * user environment and arguments are stored.
+	 */
+	retval = remove_arg_zero(bprm);
+	if (retval)
+		return retval;
+	retval = copy_string_kernel(bprm->interp, bprm);
+	if (retval < 0)
+		return retval;
+	bprm->argc++;
+	*((char *)i_end) = '\0';
+	if (i_arg) {
+		*((char *)i_sep) = '\0';
+		retval = copy_string_kernel(i_arg, bprm);
+		if (retval < 0)
+			return retval;
+		bprm->argc++;
+	}
+	retval = copy_string_kernel(i_name, bprm);
+	if (retval)
+		return retval;
+	bprm->argc++;
+	retval = bprm_change_interp(i_name, bprm);
+	if (retval < 0)
+		return retval;
+
+	/*
+	 * OK, now restart the process with the interpreter's dentry.
+	 */
+	file = open_exec(i_name);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	bprm->interpreter = file;
+	return 0;
+}
+
+static struct linux_binfmt script_format = {
+	.module		= THIS_MODULE,
+	.load_binary	= load_script,
+};
+
+static int __init init_script_binfmt(void)
+{
+	register_binfmt(&script_format);
+	return 0;
+}
+
+static void __exit exit_script_binfmt(void)
+{
+	unregister_binfmt(&script_format);
+}
+
+core_initcall(init_script_binfmt);
+module_exit(exit_script_binfmt);
+MODULE_DESCRIPTION("Kernel support for scripts starting with #!");
+MODULE_LICENSE("GPL");