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, 133 insertions, 0 deletions

diff --git a/samples/livepatch/livepatch-shadow-fix2.c b/samples/livepatch/livepatch-shadow-fix2.c
new file mode 100644
index 000000000..b99122cb2
--- /dev/null
+++ b/samples/livepatch/livepatch-shadow-fix2.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2017 Joe Lawrence <joe.lawrence@redhat.com>
+ */
+
+/*
+ * livepatch-shadow-fix2.c - Shadow variables, livepatch demo
+ *
+ * Purpose
+ * -------
+ *
+ * Adds functionality to livepatch-shadow-mod's in-flight data
+ * structures through a shadow variable.  The livepatch patches a
+ * routine that periodically inspects data structures, incrementing a
+ * per-data-structure counter, creating the counter if needed.
+ *
+ *
+ * Usage
+ * -----
+ *
+ * This module is not intended to be standalone.  See the "Usage"
+ * section of livepatch-shadow-mod.c.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/livepatch.h>
+#include <linux/slab.h>
+
+/* Shadow variable enums */
+#define SV_LEAK		1
+#define SV_COUNTER	2
+
+struct dummy {
+	struct list_head list;
+	unsigned long jiffies_expire;
+};
+
+static bool livepatch_fix2_dummy_check(struct dummy *d, unsigned long jiffies)
+{
+	int *shadow_count;
+
+	/*
+	 * Patch: handle in-flight dummy structures, if they do not
+	 * already have a SV_COUNTER shadow variable, then attach a
+	 * new one.
+	 */
+	shadow_count = klp_shadow_get_or_alloc(d, SV_COUNTER,
+				sizeof(*shadow_count), GFP_NOWAIT,
+				NULL, NULL);
+	if (shadow_count)
+		*shadow_count += 1;
+
+	return time_after(jiffies, d->jiffies_expire);
+}
+
+static void livepatch_fix2_dummy_leak_dtor(void *obj, void *shadow_data)
+{
+	void *d = obj;
+	int **shadow_leak = shadow_data;
+
+	pr_info("%s: dummy @ %p, prevented leak @ %p\n",
+			 __func__, d, *shadow_leak);
+	kfree(*shadow_leak);
+}
+
+static void livepatch_fix2_dummy_free(struct dummy *d)
+{
+	int **shadow_leak;
+	int *shadow_count;
+
+	/* Patch: copy the memory leak patch from the fix1 module. */
+	shadow_leak = klp_shadow_get(d, SV_LEAK);
+	if (shadow_leak)
+		klp_shadow_free(d, SV_LEAK, livepatch_fix2_dummy_leak_dtor);
+	else
+		pr_info("%s: dummy @ %p leaked!\n", __func__, d);
+
+	/*
+	 * Patch: fetch the SV_COUNTER shadow variable and display
+	 * the final count.  Detach the shadow variable.
+	 */
+	shadow_count = klp_shadow_get(d, SV_COUNTER);
+	if (shadow_count) {
+		pr_info("%s: dummy @ %p, check counter = %d\n",
+			__func__, d, *shadow_count);
+		klp_shadow_free(d, SV_COUNTER, NULL);
+	}
+
+	kfree(d);
+}
+
+static struct klp_func funcs[] = {
+	{
+		.old_name = "dummy_check",
+		.new_func = livepatch_fix2_dummy_check,
+	},
+	{
+		.old_name = "dummy_free",
+		.new_func = livepatch_fix2_dummy_free,
+	}, { }
+};
+
+static struct klp_object objs[] = {
+	{
+		.name = "livepatch_shadow_mod",
+		.funcs = funcs,
+	}, { }
+};
+
+static struct klp_patch patch = {
+	.mod = THIS_MODULE,
+	.objs = objs,
+};
+
+static int livepatch_shadow_fix2_init(void)
+{
+	return klp_enable_patch(&patch);
+}
+
+static void livepatch_shadow_fix2_exit(void)
+{
+	/* Cleanup any existing SV_COUNTER shadow variables */
+	klp_shadow_free_all(SV_COUNTER, NULL);
+}
+
+module_init(livepatch_shadow_fix2_init);
+module_exit(livepatch_shadow_fix2_exit);
+MODULE_DESCRIPTION("Live patching demo for shadow variables");
+MODULE_LICENSE("GPL");
+MODULE_INFO(livepatch, "Y");