btrfs-progs: zoned: get zone information of zoned block devices

Get the zone information (number of zones and zone size) from all the
devices, if the volume contains a zoned block device. To avoid costly
run-time zone report commands to test the device zones type during block
allocation, it also records all the zone status (zone type, write
pointer position, etc.).

Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

Makefile

@@ -169,7 +169,7 @@ libbtrfs_objects = common/send-stream.o common/send-utils.o kernel-lib/rbtree.o
 		   kernel-shared/free-space-cache.o kernel-shared/root-tree.o \
 		   kernel-shared/volumes.o kernel-shared/transaction.o \
 		   kernel-shared/free-space-tree.o repair.o kernel-shared/inode-item.o \
-		   kernel-shared/file-item.o \
+		   kernel-shared/file-item.o kernel-shared/zoned.o \
 		   kernel-lib/raid56.o kernel-lib/tables.o \
 		   common/device-scan.o common/path-utils.o \
 		   common/utils.o libbtrfsutil/subvolume.o libbtrfsutil/stubs.o \

common/device-scan.c

@@ -35,6 +35,7 @@
 #include "kernel-shared/ctree.h"
 #include "kernel-shared/volumes.h"
 #include "kernel-shared/disk-io.h"
+#include "kernel-shared/zoned.h"
 #include "ioctl.h"
 
 static int btrfs_scan_done = 0;
@@ -198,6 +199,7 @@ int btrfs_add_to_fsid(struct btrfs_trans_handle *trans,
 	return 0;
 
 out:
+	free(device->zone_info);
 	free(device);
 	free(buf);
 	return ret;

kerncompat.h

@@ -76,6 +76,10 @@
 #define ULONG_MAX       (~0UL)
 #endif
 
+#ifndef SECTOR_SHIFT
+#define SECTOR_SHIFT	(9)
+#endif
+
 #define __token_glue(a,b,c)	___token_glue(a,b,c)
 #define ___token_glue(a,b,c)	a ## b ## c
 #ifdef DEBUG_BUILD_CHECKS

kernel-shared/disk-io.c

@@ -29,6 +29,7 @@
 #include "kernel-shared/disk-io.h"
 #include "kernel-shared/volumes.h"
 #include "kernel-shared/transaction.h"
+#include "zoned.h"
 #include "crypto/crc32c.h"
 #include "common/utils.h"
 #include "kernel-shared/print-tree.h"
@@ -1313,6 +1314,17 @@ static struct btrfs_fs_info *__open_ctree_fd(int fp, struct open_ctree_flags *oc
 	if (!fs_info->chunk_root)
 		return fs_info;
 
+	/*
+	 * Get zone type information of zoned block devices. This will also
+	 * handle emulation of a zoned filesystem if a regular device has the
+	 * zoned incompat feature flag set.
+	 */
+	ret = btrfs_get_dev_zone_info_all_devices(fs_info);
+	if (ret) {
+		error("zoned: failed to read device zone info: %d", ret);
+		goto out_chunk;
+	}
+
 	eb = fs_info->chunk_root->node;
 	read_extent_buffer(eb, fs_info->chunk_tree_uuid,
 			   btrfs_header_chunk_tree_uuid(eb),

kernel-shared/volumes.c

@@ -27,6 +27,7 @@
 #include "kernel-shared/transaction.h"
 #include "kernel-shared/print-tree.h"
 #include "kernel-shared/volumes.h"
+#include "zoned.h"
 #include "common/utils.h"
 #include "kernel-lib/raid56.h"
 
@@ -357,6 +358,7 @@ again:
 		/* free the memory */
 		free(device->name);
 		free(device->label);
+		free(device->zone_info);
 		free(device);
 	}
 

kernel-shared/volumes.h

@@ -45,6 +45,8 @@ struct btrfs_device {
 
 	u64 generation;
 
+	struct btrfs_zoned_device_info *zone_info;
+
 	/* the internal btrfs device id */
 	u64 devid;
 

kernel-shared/zoned.c

@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/ioctl.h>
+#include <linux/fs.h>
+
+#include "kernel-lib/list.h"
+#include "kernel-shared/volumes.h"
+#include "kernel-shared/zoned.h"
+#include "common/utils.h"
+#include "common/device-utils.h"
+#include "common/messages.h"
+#include "mkfs/common.h"
+
+/* Maximum number of zones to report per ioctl(BLKREPORTZONE) call */
+#define BTRFS_REPORT_NR_ZONES  		4096
+
+static int btrfs_get_dev_zone_info(struct btrfs_device *device);
+
+enum btrfs_zoned_model zoned_model(const char *file)
+{
+	const char host_aware[] = "host-aware";
+	const char host_managed[] = "host-managed";
+	struct stat st;
+	char model[32];
+	int ret;
+
+	ret = stat(file, &st);
+	if (ret < 0) {
+		error("zoned: unable to stat %s", file);
+		return -ENOENT;
+	}
+
+	/* Consider a regular file as non-zoned device */
+	if (!S_ISBLK(st.st_mode))
+		return ZONED_NONE;
+
+	ret = queue_param(file, "zoned", model, sizeof(model));
+	if (ret <= 0)
+		return ZONED_NONE;
+
+	if (strncmp(model, host_aware, strlen(host_aware)) == 0)
+		return ZONED_HOST_AWARE;
+	if (strncmp(model, host_managed, strlen(host_managed)) == 0)
+		return ZONED_HOST_MANAGED;
+
+	return ZONED_NONE;
+}
+
+u64 zone_size(const char *file)
+{
+	char chunk[32];
+	int ret;
+
+	ret = queue_param(file, "chunk_sectors", chunk, sizeof(chunk));
+	if (ret <= 0)
+		return 0;
+
+	return strtoull((const char *)chunk, NULL, 10) << SECTOR_SHIFT;
+}
+
+#ifdef BTRFS_ZONED
+static int report_zones(int fd, const char *file,
+			struct btrfs_zoned_device_info *zinfo)
+{
+	u64 device_size;
+	u64 zone_bytes = zone_size(file);
+	size_t rep_size;
+	u64 sector = 0;
+	struct blk_zone_report *rep;
+	struct blk_zone *zone;
+	unsigned int i, n = 0;
+	int ret;
+
+	/*
+	 * Zones are guaranteed (by kernel) to be a power of 2 number of
+	 * sectors. Check this here and make sure that zones are not too small.
+	 */
+	if (!zone_bytes || !is_power_of_2(zone_bytes)) {
+		error("zoned: illegal zone size %llu (not a power of 2)",
+		      zone_bytes);
+		exit(1);
+	}
+	/*
+	 * The zone size must be large enough to hold the initial system
+	 * block group for mkfs time.
+	 */
+	if (zone_bytes < BTRFS_MKFS_SYSTEM_GROUP_SIZE) {
+		error("zoned: illegal zone size %llu (smaller than %d)",
+		      zone_bytes, BTRFS_MKFS_SYSTEM_GROUP_SIZE);
+		exit(1);
+	}
+
+	/*
+	 * No need to use btrfs_device_size() here, since it is ensured
+	 * that the file is block device.
+	 */
+	if (ioctl(fd, BLKGETSIZE64, &device_size) < 0) {
+		error("zoned: ioctl(BLKGETSIZE64) failed on %s (%m)", file);
+		exit(1);
+	}
+
+	/* Allocate the zone information array */
+	zinfo->zone_size = zone_bytes;
+	zinfo->nr_zones = device_size / zone_bytes;
+	if (device_size & (zone_bytes - 1))
+		zinfo->nr_zones++;
+	zinfo->zones = calloc(zinfo->nr_zones, sizeof(struct blk_zone));
+	if (!zinfo->zones) {
+		error("zoned: no memory for zone information");
+		exit(1);
+	}
+
+	/* Allocate a zone report */
+	rep_size = sizeof(struct blk_zone_report) +
+		   sizeof(struct blk_zone) * BTRFS_REPORT_NR_ZONES;
+	rep = malloc(rep_size);
+	if (!rep) {
+		error("zoned: no memory for zones report");
+		exit(1);
+	}
+
+	/* Get zone information */
+	zone = (struct blk_zone *)(rep + 1);
+	while (n < zinfo->nr_zones) {
+		memset(rep, 0, rep_size);
+		rep->sector = sector;
+		rep->nr_zones = BTRFS_REPORT_NR_ZONES;
+
+		ret = ioctl(fd, BLKREPORTZONE, rep);
+		if (ret != 0) {
+			error("zoned: ioctl BLKREPORTZONE failed (%m)");
+			exit(1);
+		}
+
+		if (!rep->nr_zones)
+			break;
+
+		for (i = 0; i < rep->nr_zones; i++) {
+			if (n >= zinfo->nr_zones)
+				break;
+			memcpy(&zinfo->zones[n], &zone[i],
+			       sizeof(struct blk_zone));
+			n++;
+		}
+
+		sector = zone[rep->nr_zones - 1].start +
+			 zone[rep->nr_zones - 1].len;
+	}
+
+	free(rep);
+
+	return 0;
+}
+
+#endif
+
+int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_device *device;
+	int ret = 0;
+
+	/* fs_info->zone_size might not set yet. Use the incomapt flag here. */
+	if (!btrfs_fs_incompat(fs_info, ZONED))
+		return 0;
+
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		/* We can skip reading of zone info for missing devices */
+		if (device->fd == -1)
+			continue;
+
+		ret = btrfs_get_dev_zone_info(device);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int btrfs_get_dev_zone_info(struct btrfs_device *device)
+{
+	struct btrfs_fs_info *fs_info = device->fs_info;
+
+	/*
+	 * Cannot use btrfs_is_zoned here, since fs_info::zone_size might not
+	 * yet be set.
+	 */
+	if (!btrfs_fs_incompat(fs_info, ZONED))
+		return 0;
+
+	if (device->zone_info)
+		return 0;
+
+	return btrfs_get_zone_info(device->fd, device->name, &device->zone_info);
+}
+
+int btrfs_get_zone_info(int fd, const char *file,
+			struct btrfs_zoned_device_info **zinfo_ret)
+{
+#ifdef BTRFS_ZONED
+	struct btrfs_zoned_device_info *zinfo;
+	int ret;
+#endif
+	enum btrfs_zoned_model model;
+
+	*zinfo_ret = NULL;
+
+	/* Check zone model */
+	model = zoned_model(file);
+	if (model == ZONED_NONE)
+		return 0;
+
+#ifdef BTRFS_ZONED
+	zinfo = calloc(1, sizeof(*zinfo));
+	if (!zinfo) {
+		error("zoned: no memory for zone information");
+		exit(1);
+	}
+
+	zinfo->model = model;
+
+	/* Get zone information */
+	ret = report_zones(fd, file, zinfo);
+	if (ret != 0) {
+		kfree(zinfo);
+		return ret;
+	}
+	*zinfo_ret = zinfo;
+#else
+	error("zoned: %s: unsupported host-%s zoned block device", file,
+	      model == ZONED_HOST_MANAGED ? "managed" : "aware");
+	if (model == ZONED_HOST_MANAGED)
+		return -EOPNOTSUPP;
+
+	error("zoned: %s: handling host-aware block device as a regular disk",
+	      file);
+#endif
+
+	return 0;
+}

kernel-shared/zoned.h

@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __BTRFS_ZONED_H__
+#define __BTRFS_ZONED_H__
+
+#include "kerncompat.h"
+#include <stdbool.h>
+
+#ifdef BTRFS_ZONED
+#include <linux/blkzoned.h>
+#else
+
+struct blk_zone {
+	int dummy;
+};
+
+#endif /* BTRFS_ZONED */
+
+/*
+ * Zoned block device models
+ */
+enum btrfs_zoned_model {
+	ZONED_NONE,
+	ZONED_HOST_AWARE,
+	ZONED_HOST_MANAGED,
+};
+
+/*
+ * Zone information for a zoned block device.
+ */
+struct btrfs_zoned_device_info {
+	enum btrfs_zoned_model	model;
+	u64			zone_size;
+	u32			nr_zones;
+	struct blk_zone		*zones;
+};
+
+enum btrfs_zoned_model zoned_model(const char *file);
+u64 zone_size(const char *file);
+int btrfs_get_zone_info(int fd, const char *file,
+			struct btrfs_zoned_device_info **zinfo);
+int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info);
+
+#endif /* __BTRFS_ZONED_H__ */