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, 415 insertions, 0 deletions

diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
new file mode 100644
index 000000000..0aa322e9a
--- /dev/null
+++ b/drivers/firmware/raspberrypi.c
@@ -0,0 +1,415 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Defines interfaces for interacting with the Raspberry Pi firmware's
+ * property channel.
+ *
+ * Copyright © 2015 Broadcom
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kref.h>
+#include <linux/mailbox_client.h>
+#include <linux/mailbox_controller.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <soc/bcm2835/raspberrypi-firmware.h>
+
+#define MBOX_MSG(chan, data28)		(((data28) & ~0xf) | ((chan) & 0xf))
+#define MBOX_CHAN(msg)			((msg) & 0xf)
+#define MBOX_DATA28(msg)		((msg) & ~0xf)
+#define MBOX_CHAN_PROPERTY		8
+
+static struct platform_device *rpi_hwmon;
+static struct platform_device *rpi_clk;
+
+struct rpi_firmware {
+	struct mbox_client cl;
+	struct mbox_chan *chan; /* The property channel. */
+	struct completion c;
+	u32 enabled;
+
+	struct kref consumers;
+};
+
+static DEFINE_MUTEX(transaction_lock);
+
+static void response_callback(struct mbox_client *cl, void *msg)
+{
+	struct rpi_firmware *fw = container_of(cl, struct rpi_firmware, cl);
+	complete(&fw->c);
+}
+
+/*
+ * Sends a request to the firmware through the BCM2835 mailbox driver,
+ * and synchronously waits for the reply.
+ */
+static int
+rpi_firmware_transaction(struct rpi_firmware *fw, u32 chan, u32 data)
+{
+	u32 message = MBOX_MSG(chan, data);
+	int ret;
+
+	WARN_ON(data & 0xf);
+
+	mutex_lock(&transaction_lock);
+	reinit_completion(&fw->c);
+	ret = mbox_send_message(fw->chan, &message);
+	if (ret >= 0) {
+		if (wait_for_completion_timeout(&fw->c, HZ)) {
+			ret = 0;
+		} else {
+			ret = -ETIMEDOUT;
+		}
+	} else {
+		dev_err(fw->cl.dev, "mbox_send_message returned %d\n", ret);
+	}
+	mutex_unlock(&transaction_lock);
+
+	return ret;
+}
+
+/**
+ * rpi_firmware_property_list - Submit firmware property list
+ * @fw:		Pointer to firmware structure from rpi_firmware_get().
+ * @data:	Buffer holding tags.
+ * @tag_size:	Size of tags buffer.
+ *
+ * Submits a set of concatenated tags to the VPU firmware through the
+ * mailbox property interface.
+ *
+ * The buffer header and the ending tag are added by this function and
+ * don't need to be supplied, just the actual tags for your operation.
+ * See struct rpi_firmware_property_tag_header for the per-tag
+ * structure.
+ */
+int rpi_firmware_property_list(struct rpi_firmware *fw,
+			       void *data, size_t tag_size)
+{
+	size_t size = tag_size + 12;
+	u32 *buf;
+	dma_addr_t bus_addr;
+	int ret;
+
+	/* Packets are processed a dword at a time. */
+	if (size & 3)
+		return -EINVAL;
+
+	buf = dma_alloc_coherent(fw->chan->mbox->dev, PAGE_ALIGN(size),
+				 &bus_addr, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	/* The firmware will error out without parsing in this case. */
+	WARN_ON(size >= 1024 * 1024);
+
+	buf[0] = size;
+	buf[1] = RPI_FIRMWARE_STATUS_REQUEST;
+	memcpy(&buf[2], data, tag_size);
+	buf[size / 4 - 1] = RPI_FIRMWARE_PROPERTY_END;
+	wmb();
+
+	ret = rpi_firmware_transaction(fw, MBOX_CHAN_PROPERTY, bus_addr);
+
+	rmb();
+	memcpy(data, &buf[2], tag_size);
+	if (ret == 0 && buf[1] != RPI_FIRMWARE_STATUS_SUCCESS) {
+		/*
+		 * The tag name here might not be the one causing the
+		 * error, if there were multiple tags in the request.
+		 * But single-tag is the most common, so go with it.
+		 */
+		dev_err(fw->cl.dev, "Request 0x%08x returned status 0x%08x\n",
+			buf[2], buf[1]);
+		ret = -EINVAL;
+	} else if (ret == -ETIMEDOUT) {
+		WARN_ONCE(1, "Firmware transaction 0x%08x timeout", buf[2]);
+	}
+
+	dma_free_coherent(fw->chan->mbox->dev, PAGE_ALIGN(size), buf, bus_addr);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpi_firmware_property_list);
+
+/**
+ * rpi_firmware_property - Submit single firmware property
+ * @fw:		Pointer to firmware structure from rpi_firmware_get().
+ * @tag:	One of enum_mbox_property_tag.
+ * @tag_data:	Tag data buffer.
+ * @buf_size:	Buffer size.
+ *
+ * Submits a single tag to the VPU firmware through the mailbox
+ * property interface.
+ *
+ * This is a convenience wrapper around
+ * rpi_firmware_property_list() to avoid some of the
+ * boilerplate in property calls.
+ */
+int rpi_firmware_property(struct rpi_firmware *fw,
+			  u32 tag, void *tag_data, size_t buf_size)
+{
+	struct rpi_firmware_property_tag_header *header;
+	int ret;
+
+	/* Some mailboxes can use over 1k bytes. Rather than checking
+	 * size and using stack or kmalloc depending on requirements,
+	 * just use kmalloc. Mailboxes don't get called enough to worry
+	 * too much about the time taken in the allocation.
+	 */
+	void *data = kmalloc(sizeof(*header) + buf_size, GFP_KERNEL);
+
+	if (!data)
+		return -ENOMEM;
+
+	header = data;
+	header->tag = tag;
+	header->buf_size = buf_size;
+	header->req_resp_size = 0;
+	memcpy(data + sizeof(*header), tag_data, buf_size);
+
+	ret = rpi_firmware_property_list(fw, data, buf_size + sizeof(*header));
+
+	memcpy(tag_data, data + sizeof(*header), buf_size);
+
+	kfree(data);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpi_firmware_property);
+
+static void
+rpi_firmware_print_firmware_revision(struct rpi_firmware *fw)
+{
+	time64_t date_and_time;
+	u32 packet;
+	int ret = rpi_firmware_property(fw,
+					RPI_FIRMWARE_GET_FIRMWARE_REVISION,
+					&packet, sizeof(packet));
+
+	if (ret)
+		return;
+
+	/* This is not compatible with y2038 */
+	date_and_time = packet;
+	dev_info(fw->cl.dev, "Attached to firmware from %ptT\n", &date_and_time);
+}
+
+static void
+rpi_register_hwmon_driver(struct device *dev, struct rpi_firmware *fw)
+{
+	u32 packet;
+	int ret = rpi_firmware_property(fw, RPI_FIRMWARE_GET_THROTTLED,
+					&packet, sizeof(packet));
+
+	if (ret)
+		return;
+
+	rpi_hwmon = platform_device_register_data(dev, "raspberrypi-hwmon",
+						  -1, NULL, 0);
+}
+
+static void rpi_register_clk_driver(struct device *dev)
+{
+	struct device_node *firmware;
+
+	/*
+	 * Earlier DTs don't have a node for the firmware clocks but
+	 * rely on us creating a platform device by hand. If we do
+	 * have a node for the firmware clocks, just bail out here.
+	 */
+	firmware = of_get_compatible_child(dev->of_node,
+					   "raspberrypi,firmware-clocks");
+	if (firmware) {
+		of_node_put(firmware);
+		return;
+	}
+
+	rpi_clk = platform_device_register_data(dev, "raspberrypi-clk",
+						-1, NULL, 0);
+}
+
+unsigned int rpi_firmware_clk_get_max_rate(struct rpi_firmware *fw, unsigned int id)
+{
+	struct rpi_firmware_clk_rate_request msg =
+		RPI_FIRMWARE_CLK_RATE_REQUEST(id);
+	int ret;
+
+	ret = rpi_firmware_property(fw, RPI_FIRMWARE_GET_MAX_CLOCK_RATE,
+				    &msg, sizeof(msg));
+	if (ret)
+		/*
+		 * If our firmware doesn't support that operation, or fails, we
+		 * assume the maximum clock rate is absolute maximum we can
+		 * store over our type.
+		 */
+		 return UINT_MAX;
+
+	return le32_to_cpu(msg.rate);
+}
+EXPORT_SYMBOL_GPL(rpi_firmware_clk_get_max_rate);
+
+static void rpi_firmware_delete(struct kref *kref)
+{
+	struct rpi_firmware *fw = container_of(kref, struct rpi_firmware,
+					       consumers);
+
+	mbox_free_channel(fw->chan);
+	kfree(fw);
+}
+
+void rpi_firmware_put(struct rpi_firmware *fw)
+{
+	kref_put(&fw->consumers, rpi_firmware_delete);
+}
+EXPORT_SYMBOL_GPL(rpi_firmware_put);
+
+static void devm_rpi_firmware_put(void *data)
+{
+	struct rpi_firmware *fw = data;
+
+	rpi_firmware_put(fw);
+}
+
+static int rpi_firmware_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct rpi_firmware *fw;
+
+	/*
+	 * Memory will be freed by rpi_firmware_delete() once all users have
+	 * released their firmware handles. Don't use devm_kzalloc() here.
+	 */
+	fw = kzalloc_obj(*fw);
+	if (!fw)
+		return -ENOMEM;
+
+	fw->cl.dev = dev;
+	fw->cl.rx_callback = response_callback;
+	fw->cl.tx_block = true;
+
+	fw->chan = mbox_request_channel(&fw->cl, 0);
+	if (IS_ERR(fw->chan)) {
+		int ret = PTR_ERR(fw->chan);
+		kfree(fw);
+		return dev_err_probe(dev, ret, "Failed to get mbox channel\n");
+	}
+
+	init_completion(&fw->c);
+	kref_init(&fw->consumers);
+
+	platform_set_drvdata(pdev, fw);
+
+	rpi_firmware_print_firmware_revision(fw);
+	rpi_register_hwmon_driver(dev, fw);
+	rpi_register_clk_driver(dev);
+
+	return 0;
+}
+
+static void rpi_firmware_shutdown(struct platform_device *pdev)
+{
+	struct rpi_firmware *fw = platform_get_drvdata(pdev);
+
+	if (!fw)
+		return;
+
+	rpi_firmware_property(fw, RPI_FIRMWARE_NOTIFY_REBOOT, NULL, 0);
+}
+
+static void rpi_firmware_remove(struct platform_device *pdev)
+{
+	struct rpi_firmware *fw = platform_get_drvdata(pdev);
+
+	platform_device_unregister(rpi_hwmon);
+	rpi_hwmon = NULL;
+	platform_device_unregister(rpi_clk);
+	rpi_clk = NULL;
+
+	rpi_firmware_put(fw);
+}
+
+static const struct of_device_id rpi_firmware_of_match[] = {
+	{ .compatible = "raspberrypi,bcm2835-firmware", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, rpi_firmware_of_match);
+
+struct device_node *rpi_firmware_find_node(void)
+{
+	return of_find_matching_node(NULL, rpi_firmware_of_match);
+}
+EXPORT_SYMBOL_GPL(rpi_firmware_find_node);
+
+/**
+ * rpi_firmware_get - Get pointer to rpi_firmware structure.
+ * @firmware_node:    Pointer to the firmware Device Tree node.
+ *
+ * The reference to rpi_firmware has to be released with rpi_firmware_put().
+ *
+ * Returns NULL is the firmware device is not ready.
+ */
+struct rpi_firmware *rpi_firmware_get(struct device_node *firmware_node)
+{
+	struct platform_device *pdev = of_find_device_by_node(firmware_node);
+	struct rpi_firmware *fw;
+
+	if (!pdev)
+		return NULL;
+
+	fw = platform_get_drvdata(pdev);
+	if (!fw)
+		goto err_put_device;
+
+	if (!kref_get_unless_zero(&fw->consumers))
+		goto err_put_device;
+
+	put_device(&pdev->dev);
+
+	return fw;
+
+err_put_device:
+	put_device(&pdev->dev);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(rpi_firmware_get);
+
+/**
+ * devm_rpi_firmware_get - Get pointer to rpi_firmware structure.
+ * @dev:              The firmware device structure
+ * @firmware_node:    Pointer to the firmware Device Tree node.
+ *
+ * Returns NULL is the firmware device is not ready.
+ */
+struct rpi_firmware *devm_rpi_firmware_get(struct device *dev,
+					   struct device_node *firmware_node)
+{
+	struct rpi_firmware *fw;
+
+	fw = rpi_firmware_get(firmware_node);
+	if (!fw)
+		return NULL;
+
+	if (devm_add_action_or_reset(dev, devm_rpi_firmware_put, fw))
+		return NULL;
+
+	return fw;
+}
+EXPORT_SYMBOL_GPL(devm_rpi_firmware_get);
+
+static struct platform_driver rpi_firmware_driver = {
+	.driver = {
+		.name = "raspberrypi-firmware",
+		.of_match_table = rpi_firmware_of_match,
+	},
+	.probe		= rpi_firmware_probe,
+	.shutdown	= rpi_firmware_shutdown,
+	.remove		= rpi_firmware_remove,
+};
+module_platform_driver(rpi_firmware_driver);
+
+MODULE_AUTHOR("Eric Anholt <eric@anholt.net>");
+MODULE_DESCRIPTION("Raspberry Pi firmware driver");
+MODULE_LICENSE("GPL v2");