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, 132 insertions, 0 deletions

diff --git a/fs/tests/exec_kunit.c b/fs/tests/exec_kunit.c
new file mode 100644
index 000000000..1c32cac09
--- /dev/null
+++ b/fs/tests/exec_kunit.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <kunit/test.h>
+
+struct bprm_stack_limits_result {
+	struct linux_binprm bprm;
+	int expected_rc;
+	unsigned long expected_argmin;
+};
+
+static const struct bprm_stack_limits_result bprm_stack_limits_results[] = {
+	/* Negative argc/envc counts produce -E2BIG */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = INT_MIN, .envc = INT_MIN }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = 5, .envc = -1 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = -1, .envc = 10 }, .expected_rc = -E2BIG },
+	/* The max value of argc or envc is MAX_ARG_STRINGS. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = INT_MAX, .envc = INT_MAX }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = MAX_ARG_STRINGS, .envc = MAX_ARG_STRINGS }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = 0, .envc = MAX_ARG_STRINGS }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = MAX_ARG_STRINGS, .envc = 0 }, .expected_rc = -E2BIG },
+	/*
+	 * On 32-bit system these argc and envc counts, while likely impossible
+	 * to represent within the associated TASK_SIZE, could overflow the
+	 * limit calculation, and bypass the ptr_size <= limit check.
+	 */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = 0x20000001, .envc = 0x20000001 }, .expected_rc = -E2BIG },
+#ifdef CONFIG_MMU
+	/* Make sure a pathological bprm->p doesn't cause an overflow. */
+	{ { .p = sizeof(void *), .rlim_stack.rlim_cur = ULONG_MAX,
+	    .argc = 10, .envc = 10 }, .expected_rc = -E2BIG },
+#endif
+	/*
+	 * 0 rlim_stack will get raised to ARG_MAX. With 1 string pointer,
+	 * we should see p - ARG_MAX + sizeof(void *).
+	 */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = 1, .envc = 0 }, .expected_argmin = ULONG_MAX - ARG_MAX + sizeof(void *)},
+	/* Validate that argc is always raised to a minimum of 1. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = 0, .envc = 0 }, .expected_argmin = ULONG_MAX - ARG_MAX + sizeof(void *)},
+	/*
+	 * 0 rlim_stack will get raised to ARG_MAX. With pointers filling ARG_MAX,
+	 * we should see -E2BIG. (Note argc is always raised to at least 1.)
+	 */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = ARG_MAX / sizeof(void *), .envc = 0 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = 0, .envc = ARG_MAX / sizeof(void *) - 1 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = ARG_MAX / sizeof(void *) + 1, .envc = 0 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = 0, .envc = ARG_MAX / sizeof(void *) }, .expected_rc = -E2BIG },
+	/* And with one less, we see space for exactly 1 pointer. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = (ARG_MAX / sizeof(void *)) - 1, .envc = 0 },
+	  .expected_argmin = ULONG_MAX - sizeof(void *) },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 0,
+	    .argc = 0, .envc = (ARG_MAX / sizeof(void *)) - 2, },
+	  .expected_argmin = ULONG_MAX - sizeof(void *) },
+	/* If we raise rlim_stack / 4 to exactly ARG_MAX, nothing changes. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ARG_MAX * 4,
+	    .argc = ARG_MAX / sizeof(void *), .envc = 0 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ARG_MAX * 4,
+	    .argc = 0, .envc = ARG_MAX / sizeof(void *) - 1 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ARG_MAX * 4,
+	    .argc = ARG_MAX / sizeof(void *) + 1, .envc = 0 }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ARG_MAX * 4,
+	    .argc = 0, .envc = ARG_MAX / sizeof(void *) }, .expected_rc = -E2BIG },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ARG_MAX * 4,
+	    .argc = (ARG_MAX / sizeof(void *)) - 1, .envc = 0 },
+	  .expected_argmin = ULONG_MAX - sizeof(void *) },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = ARG_MAX * 4,
+	    .argc = 0, .envc = (ARG_MAX / sizeof(void *)) - 2, },
+	  .expected_argmin = ULONG_MAX - sizeof(void *) },
+	/* But raising it another pointer * 4 will provide space for 1 more pointer. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = (ARG_MAX + sizeof(void *)) * 4,
+	    .argc = ARG_MAX / sizeof(void *), .envc = 0 },
+	  .expected_argmin = ULONG_MAX - sizeof(void *) },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = (ARG_MAX + sizeof(void *)) * 4,
+	    .argc = 0, .envc = ARG_MAX / sizeof(void *) - 1 },
+	  .expected_argmin = ULONG_MAX - sizeof(void *) },
+	/* Raising rlim_stack / 4 to _STK_LIM / 4 * 3 will see more space. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * (_STK_LIM / 4 * 3),
+	    .argc = 0, .envc = 0 },
+	  .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) },
+	/* But raising it any further will see no increase. */
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * (_STK_LIM / 4 * 3 + sizeof(void *)),
+	    .argc = 0, .envc = 0 },
+	  .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) },
+	{ { .p = ULONG_MAX, .rlim_stack.rlim_cur = 4 * _STK_LIM,
+	    .argc = 0, .envc = 0 },
+	  .expected_argmin = ULONG_MAX - (_STK_LIM / 4 * 3) + sizeof(void *) },
+};
+
+static void exec_test_bprm_stack_limits(struct kunit *test)
+{
+	/* Double-check the constants. */
+	KUNIT_EXPECT_EQ(test, _STK_LIM, SZ_8M);
+	KUNIT_EXPECT_EQ(test, ARG_MAX, 32 * SZ_4K);
+	KUNIT_EXPECT_EQ(test, MAX_ARG_STRINGS, 0x7FFFFFFF);
+
+	for (int i = 0; i < ARRAY_SIZE(bprm_stack_limits_results); i++) {
+		const struct bprm_stack_limits_result *result = &bprm_stack_limits_results[i];
+		struct linux_binprm bprm = result->bprm;
+		int rc;
+
+		rc = bprm_stack_limits(&bprm);
+		KUNIT_EXPECT_EQ_MSG(test, rc, result->expected_rc, "on loop %d", i);
+#ifdef CONFIG_MMU
+		KUNIT_EXPECT_EQ_MSG(test, bprm.argmin, result->expected_argmin, "on loop %d", i);
+#endif
+	}
+}
+
+static struct kunit_case exec_test_cases[] = {
+	KUNIT_CASE(exec_test_bprm_stack_limits),
+	{},
+};
+
+static struct kunit_suite exec_test_suite = {
+	.name = "exec",
+	.test_cases = exec_test_cases,
+};
+
+kunit_test_suite(exec_test_suite);