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, 157 insertions, 0 deletions

diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
new file mode 100644
index 000000000..d7d45067d
--- /dev/null
+++ b/scripts/Makefile.modpost
@@ -0,0 +1,157 @@
+# SPDX-License-Identifier: GPL-2.0
+# ===========================================================================
+# Module versions
+# ===========================================================================
+#
+# Stage one of module building created the following:
+# a) The individual .o files used for the module
+# b) A <module>.o file which is the .o files above linked together
+# c) A <module>.mod file, listing the name of the preliminary <module>.o file,
+#    plus all .o files
+# d) modules.order, which lists all the modules
+
+# Stage 2 is handled by this file and does the following
+# 1) Find all modules listed in modules.order
+# 2) modpost is then used to
+# 3)  create one <module>.mod.c file per module
+# 4)  create one Module.symvers file with CRC for all exported symbols
+
+# Step 3 is used to place certain information in the module's ELF
+# section, including information such as:
+#   Version magic (see include/linux/vermagic.h for full details)
+#     - Kernel release
+#     - SMP is CONFIG_SMP
+#     - PREEMPT is CONFIG_PREEMPT[_RT]
+#     - GCC Version
+#   Module info
+#     - Module version (MODULE_VERSION)
+#     - Module alias'es (MODULE_ALIAS)
+#     - Module license (MODULE_LICENSE)
+#     - See include/linux/module.h for more details
+
+# Step 4 is solely used to allow module versioning in external modules,
+# where the CRC of each module is retrieved from the Module.symvers file.
+
+PHONY := __modpost
+__modpost:
+
+include $(objtree)/include/config/auto.conf
+include $(srctree)/scripts/Kbuild.include
+
+MODPOST = $(objtree)/scripts/mod/modpost
+
+modpost-args =										\
+	$(if $(CONFIG_MODULES),-M)							\
+	$(if $(CONFIG_MODVERSIONS),-m)							\
+	$(if $(CONFIG_BASIC_MODVERSIONS),-b)						\
+	$(if $(CONFIG_EXTENDED_MODVERSIONS),-x)						\
+	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
+	$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E)					\
+	$(if $(KBUILD_MODPOST_WARN),-w)							\
+	$(if $(KBUILD_NSDEPS),-d modules.nsdeps)					\
+	$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N)	\
+	$(if $(findstring 1, $(KBUILD_EXTRA_WARN)),-W)					\
+	-o $@
+
+modpost-deps := $(MODPOST)
+
+# 'make -i -k' ignores compile errors, and builds as many modules as possible.
+ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),)
+modpost-args += -n
+endif
+
+# Read out modules.order to pass in modpost.
+# Otherwise, allmodconfig would fail with "Argument list too long".
+ifdef KBUILD_MODULES
+modpost-args += -T modules.order
+modpost-deps += modules.order
+endif
+
+ifeq ($(KBUILD_EXTMOD),)
+
+# Generate the list of in-tree objects in vmlinux
+# ---------------------------------------------------------------------------
+
+# This is used to retrieve symbol versions generated by genksyms.
+ifdef CONFIG_MODVERSIONS
+vmlinux.symvers Module.symvers: .vmlinux.objs
+endif
+
+# Ignore libgcc.a
+# Some architectures do '$(CC) --print-libgcc-file-name' to borrow libgcc.a
+# from the toolchain, but there is no EXPORT_SYMBOL in it.
+
+quiet_cmd_vmlinux_objs = GEN     $@
+      cmd_vmlinux_objs =		\
+	for f in $(real-prereqs); do	\
+		case $${f} in		\
+		*libgcc.a) ;;		\
+		*) $(AR) t $${f} ;;	\
+		esac			\
+	done > $@
+
+targets += .vmlinux.objs
+.vmlinux.objs: vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
+	$(call if_changed,vmlinux_objs)
+
+ifdef CONFIG_TRIM_UNUSED_KSYMS
+ksym-wl := $(CONFIG_UNUSED_KSYMS_WHITELIST)
+ksym-wl := $(if $(filter-out /%, $(ksym-wl)),$(if $(wildcard $(ksym-wl)),,$(srctree)/))$(ksym-wl)
+modpost-args += -t $(addprefix -u , $(ksym-wl))
+modpost-deps += $(ksym-wl)
+endif
+
+ifeq ($(wildcard vmlinux.o),)
+missing-input := vmlinux.o
+output-symdump := modules-only.symvers
+else
+modpost-args += vmlinux.o
+modpost-deps += vmlinux.o
+output-symdump := $(if $(KBUILD_MODULES), Module.symvers, vmlinux.symvers)
+endif
+
+else
+
+# set src + obj - they may be used in the modules's Makefile
+obj := .
+src := $(srcroot)
+
+# Include the module's Makefile to find KBUILD_EXTRA_SYMBOLS
+include $(kbuild-file)
+
+output-symdump := Module.symvers
+
+ifeq ($(wildcard $(objtree)/Module.symvers),)
+missing-input := $(objtree)/Module.symvers
+else
+modpost-args += -i $(objtree)/Module.symvers
+modpost-deps += $(objtree)/Module.symvers
+endif
+
+modpost-args += -e $(addprefix -i , $(KBUILD_EXTRA_SYMBOLS))
+
+endif # ($(KBUILD_EXTMOD),)
+
+quiet_cmd_modpost = MODPOST $@
+      cmd_modpost = \
+	$(if $(missing-input), \
+		echo >&2 "WARNING: $(missing-input) is missing."; \
+		echo >&2 "         Modules may not have dependencies or modversions."; \
+		echo >&2 "         You may get many unresolved symbol errors."; \
+		echo >&2 "         You can set KBUILD_MODPOST_WARN=1 to turn errors into warning"; \
+		echo >&2 "         if you want to proceed at your own risk.";) \
+	$(MODPOST) $(modpost-args)
+
+targets += $(output-symdump)
+$(output-symdump): $(modpost-deps) FORCE
+	$(call if_changed,modpost)
+
+__modpost: $(output-symdump)
+PHONY += FORCE
+FORCE:
+
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
+
+.PHONY: $(PHONY)