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, 225 insertions, 0 deletions

diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
new file mode 100644
index 000000000..8833582c1
--- /dev/null
+++ b/drivers/firmware/sysfb.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Generic System Framebuffers
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ */
+
+/*
+ * Simple-Framebuffer support
+ * Create a platform-device for any available boot framebuffer. The
+ * simple-framebuffer platform device is already available on DT systems, so
+ * this module parses the global "screen_info" object and creates a suitable
+ * platform device compatible with the "simple-framebuffer" DT object. If
+ * the framebuffer is incompatible, we instead create a legacy
+ * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and
+ * pass the screen_info as platform_data. This allows legacy drivers
+ * to pick these devices up without messing with simple-framebuffer drivers.
+ * The global "screen_info" is still valid at all times.
+ *
+ * If CONFIG_SYSFB_SIMPLEFB is not selected, never register "simple-framebuffer"
+ * platform devices, but only use legacy framebuffer devices for
+ * backwards compatibility.
+ *
+ * TODO: We set the dev_id field of all platform-devices to 0. This allows
+ * other OF/DT parsers to create such devices, too. However, they must
+ * start at offset 1 for this to work.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <linux/sysfb.h>
+
+static struct platform_device *pd;
+static DEFINE_MUTEX(disable_lock);
+static bool disabled;
+
+static struct device *sysfb_parent_dev(const struct screen_info *si);
+
+static bool sysfb_unregister(void)
+{
+	if (IS_ERR_OR_NULL(pd))
+		return false;
+
+	platform_device_unregister(pd);
+	pd = NULL;
+
+	return true;
+}
+
+/**
+ * sysfb_disable() - disable the Generic System Framebuffers support
+ * @dev:	the device to check if non-NULL
+ *
+ * This disables the registration of system framebuffer devices that match the
+ * generic drivers that make use of the system framebuffer set up by firmware.
+ *
+ * It also unregisters a device if this was already registered by sysfb_init().
+ *
+ * Context: The function can sleep. A @disable_lock mutex is acquired to serialize
+ *          against sysfb_init(), that registers a system framebuffer device.
+ */
+void sysfb_disable(struct device *dev)
+{
+	struct screen_info *si = &sysfb_primary_display.screen;
+	struct device *parent;
+
+	mutex_lock(&disable_lock);
+	parent = sysfb_parent_dev(si);
+	if (!dev || !parent || dev == parent) {
+		sysfb_unregister();
+		disabled = true;
+	}
+	mutex_unlock(&disable_lock);
+}
+EXPORT_SYMBOL_GPL(sysfb_disable);
+
+/**
+ * sysfb_handles_screen_info() - reports if sysfb handles the global screen_info
+ *
+ * Callers can use sysfb_handles_screen_info() to determine whether the Generic
+ * System Framebuffers (sysfb) can handle the global screen_info data structure
+ * or not. Drivers might need this information to know if they have to setup the
+ * system framebuffer, or if they have to delegate this action to sysfb instead.
+ *
+ * Returns:
+ * True if sysfb handles the global screen_info data structure.
+ */
+bool sysfb_handles_screen_info(void)
+{
+	const struct screen_info *si = &sysfb_primary_display.screen;
+
+	return !!screen_info_video_type(si);
+}
+EXPORT_SYMBOL_GPL(sysfb_handles_screen_info);
+
+#if defined(CONFIG_PCI)
+static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+{
+	/*
+	 * TODO: Try to integrate this code into the PCI subsystem
+	 */
+	int ret;
+	u16 command;
+
+	ret = pci_read_config_word(pdev, PCI_COMMAND, &command);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return false;
+	if (!(command & PCI_COMMAND_MEMORY))
+		return false;
+	return true;
+}
+#else
+static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+{
+	return false;
+}
+#endif
+
+static struct device *sysfb_parent_dev(const struct screen_info *si)
+{
+	struct pci_dev *pdev;
+
+	pdev = screen_info_pci_dev(si);
+	if (IS_ERR(pdev)) {
+		return ERR_CAST(pdev);
+	} else if (pdev) {
+		if (!sysfb_pci_dev_is_enabled(pdev)) {
+			pci_dev_put(pdev);
+			return ERR_PTR(-ENODEV);
+		}
+		return &pdev->dev;
+	}
+
+	return NULL;
+}
+
+static __init int sysfb_init(void)
+{
+	struct sysfb_display_info *dpy = &sysfb_primary_display;
+	struct screen_info *si = &dpy->screen;
+	struct device *parent;
+	unsigned int type;
+	struct simplefb_platform_data mode;
+	const char *name;
+	bool compatible;
+	int ret = 0;
+
+	screen_info_apply_fixups();
+
+	mutex_lock(&disable_lock);
+	if (disabled)
+		goto unlock_mutex;
+
+	sysfb_apply_efi_quirks(si);
+
+	parent = sysfb_parent_dev(si);
+	if (IS_ERR(parent)) {
+		ret = PTR_ERR(parent);
+		goto unlock_mutex;
+	}
+
+	/* try to create a simple-framebuffer device */
+	compatible = sysfb_parse_mode(si, &mode);
+	if (compatible) {
+		pd = sysfb_create_simplefb(si, &mode, parent);
+		if (!IS_ERR(pd))
+			goto put_device;
+	}
+
+	type = screen_info_video_type(si);
+
+	/* if the FB is incompatible, create a legacy framebuffer device */
+	switch (type) {
+	case VIDEO_TYPE_EGAC:
+		name = "ega-framebuffer";
+		break;
+	case VIDEO_TYPE_VGAC:
+		name = "vga-framebuffer";
+		break;
+	case VIDEO_TYPE_VLFB:
+		name = "vesa-framebuffer";
+		break;
+	case VIDEO_TYPE_EFI:
+		name = "efi-framebuffer";
+		break;
+	default:
+		name = "platform-framebuffer";
+		break;
+	}
+
+	pd = platform_device_alloc(name, 0);
+	if (!pd) {
+		ret = -ENOMEM;
+		goto put_device;
+	}
+
+	pd->dev.parent = parent;
+
+	sysfb_set_efifb_fwnode(si, pd);
+
+	ret = platform_device_add_data(pd, dpy, sizeof(*dpy));
+	if (ret)
+		goto err;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		goto err;
+
+	goto put_device;
+err:
+	platform_device_put(pd);
+put_device:
+	put_device(parent);
+unlock_mutex:
+	mutex_unlock(&disable_lock);
+	return ret;
+}
+
+/* must execute after PCI subsystem for EFI quirks */
+device_initcall(sysfb_init);