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, 315 insertions, 0 deletions

diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
new file mode 100644
index 000000000..051aa1331
--- /dev/null
+++ b/include/asm-generic/pgalloc.h
@@ -0,0 +1,315 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_PGALLOC_H
+#define __ASM_GENERIC_PGALLOC_H
+
+#ifdef CONFIG_MMU
+
+#define GFP_PGTABLE_KERNEL	(GFP_KERNEL | __GFP_ZERO | __GFP_SKIP_KASAN)
+#define GFP_PGTABLE_USER	(GFP_PGTABLE_KERNEL | __GFP_ACCOUNT)
+
+/**
+ * __pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table
+ * @mm: the mm_struct of the current context
+ *
+ * This function is intended for architectures that need
+ * anything beyond simple page allocation.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm)
+{
+	struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL, 0);
+
+	if (!ptdesc)
+		return NULL;
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
+	}
+
+	ptdesc_set_kernel(ptdesc);
+
+	return ptdesc_address(ptdesc);
+}
+#define __pte_alloc_one_kernel(...)	alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
+/**
+ * pte_alloc_one_kernel - allocate memory for a PTE-level kernel page table
+ * @mm: the mm_struct of the current context
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm)
+{
+	return __pte_alloc_one_kernel_noprof(mm);
+}
+#define pte_alloc_one_kernel(...)	alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__))
+#endif
+
+/**
+ * pte_free_kernel - free PTE-level kernel page table memory
+ * @mm: the mm_struct of the current context
+ * @pte: pointer to the memory containing the page table
+ */
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	pagetable_dtor_free(virt_to_ptdesc(pte));
+}
+
+/**
+ * __pte_alloc_one - allocate memory for a PTE-level user page table
+ * @mm: the mm_struct of the current context
+ * @gfp: GFP flags to use for the allocation
+ *
+ * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor().
+ *
+ * This function is intended for architectures that need
+ * anything beyond simple page allocation or must have custom GFP flags.
+ *
+ * Return: `struct page` referencing the ptdesc or %NULL on error
+ */
+static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp)
+{
+	struct ptdesc *ptdesc;
+
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
+	}
+
+	return ptdesc_page(ptdesc);
+}
+#define __pte_alloc_one(...)	alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_PTE_ALLOC_ONE
+/**
+ * pte_alloc_one - allocate a page for PTE-level user page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocate memory for a page table and ptdesc and runs pagetable_pte_ctor().
+ *
+ * Return: `struct page` referencing the ptdesc or %NULL on error
+ */
+static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm)
+{
+	return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER);
+}
+#define pte_alloc_one(...)	alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+/*
+ * Should really implement gc for free page table pages. This could be
+ * done with a reference count in struct page.
+ */
+
+/**
+ * pte_free - free PTE-level user page table memory
+ * @mm: the mm_struct of the current context
+ * @pte_page: the `struct page` referencing the ptdesc
+ */
+static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
+{
+	struct ptdesc *ptdesc = page_ptdesc(pte_page);
+
+	pagetable_dtor_free(ptdesc);
+}
+
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+#ifndef __HAVE_ARCH_PMD_ALLOC_ONE
+/**
+ * pmd_alloc_one - allocate memory for a PMD-level page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocate memory for a page table and ptdesc and runs pagetable_pmd_ctor().
+ *
+ * Allocations use %GFP_PGTABLE_USER in user context and
+ * %GFP_PGTABLE_KERNEL in kernel context.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	struct ptdesc *ptdesc;
+	gfp_t gfp = GFP_PGTABLE_USER;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+	if (!pagetable_pmd_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
+		return NULL;
+	}
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
+	return ptdesc_address(ptdesc);
+}
+#define pmd_alloc_one(...)	alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+#ifndef __HAVE_ARCH_PMD_FREE
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
+
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	pagetable_dtor_free(ptdesc);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+	struct ptdesc *ptdesc;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+
+	pagetable_pud_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
+	return ptdesc_address(ptdesc);
+}
+#define __pud_alloc_one(...)	alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_PUD_ALLOC_ONE
+/**
+ * pud_alloc_one - allocate memory for a PUD-level page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocate memory for a page table using %GFP_PGTABLE_USER for user context
+ * and %GFP_PGTABLE_KERNEL for kernel context.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	return __pud_alloc_one_noprof(mm, addr);
+}
+#define pud_alloc_one(...)	alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+static inline void __pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
+	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+	pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_PUD_FREE
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	__pud_free(mm, pud);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 3 */
+
+#if CONFIG_PGTABLE_LEVELS > 4
+
+static inline p4d_t *__p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+	struct ptdesc *ptdesc;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+
+	ptdesc = pagetable_alloc_noprof(gfp, 0);
+	if (!ptdesc)
+		return NULL;
+
+	pagetable_p4d_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
+	return ptdesc_address(ptdesc);
+}
+#define __p4d_alloc_one(...)	alloc_hooks(__p4d_alloc_one_noprof(__VA_ARGS__))
+
+#ifndef __HAVE_ARCH_P4D_ALLOC_ONE
+static inline p4d_t *p4d_alloc_one_noprof(struct mm_struct *mm, unsigned long addr)
+{
+	return __p4d_alloc_one_noprof(mm, addr);
+}
+#define p4d_alloc_one(...)	alloc_hooks(p4d_alloc_one_noprof(__VA_ARGS__))
+#endif
+
+static inline void __p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(p4d);
+
+	BUG_ON((unsigned long)p4d & (PAGE_SIZE-1));
+	pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_P4D_FREE
+static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
+{
+	if (!mm_p4d_folded(mm))
+		__p4d_free(mm, p4d);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 4 */
+
+static inline pgd_t *__pgd_alloc_noprof(struct mm_struct *mm, unsigned int order)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+	struct ptdesc *ptdesc;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+
+	ptdesc = pagetable_alloc_noprof(gfp, order);
+	if (!ptdesc)
+		return NULL;
+
+	pagetable_pgd_ctor(ptdesc);
+
+	if (mm == &init_mm)
+		ptdesc_set_kernel(ptdesc);
+
+	return ptdesc_address(ptdesc);
+}
+#define __pgd_alloc(...)	alloc_hooks(__pgd_alloc_noprof(__VA_ARGS__))
+
+static inline void __pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
+
+	BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+	pagetable_dtor_free(ptdesc);
+}
+
+#ifndef __HAVE_ARCH_PGD_FREE
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	__pgd_free(mm, pgd);
+}
+#endif
+
+#endif /* CONFIG_MMU */
+
+#endif /* __ASM_GENERIC_PGALLOC_H */