This patch introduce several zone related functions: btrfs_get_zone_info()
to get zone information from the specified device and put the information
in zinfo, and zone_is_sequential() to check if a zone is a sequential
required zone.
btrfs_get_zone_info() is intentionaly works with "struct btrfs_zone_info"
instead of "struct btrfs_device". We need to load zone information at
btrfs_prepare_device(), but there are no "struct btrfs_device" at that
time.
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
Makefile | 2 +-
common/hmzoned.c | 218 +++++++++++++++++++++++++++++++++++++++++++++++
common/hmzoned.h | 67 +++++++++++++++
3 files changed, 286 insertions(+), 1 deletion(-)
create mode 100644 common/hmzoned.c
create mode 100644 common/hmzoned.h
diff --git a/Makefile b/Makefile
index 82417d19a9f8..60a9e8992864 100644
--- a/Makefile
+++ b/Makefile
@@ -140,7 +140,7 @@ objects = ctree.o disk-io.o kernel-lib/radix-tree.o extent-tree.o print-tree.o \
inode.o file.o find-root.o free-space-tree.o common/help.o send-dump.o \
common/fsfeatures.o kernel-lib/tables.o kernel-lib/raid56.o transaction.o \
delayed-ref.o common/format-output.o common/path-utils.o \
- common/device-utils.o common/device-scan.o
+ common/device-utils.o common/device-scan.o common/hmzoned.o
cmds_objects = cmds/subvolume.o cmds/filesystem.o cmds/device.o cmds/scrub.o \
cmds/inspect.o cmds/balance.o cmds/send.o cmds/receive.o \
cmds/quota.o cmds/qgroup.o cmds/replace.o check/main.o \
diff --git a/common/hmzoned.c b/common/hmzoned.c
new file mode 100644
index 000000000000..7114943458ef
--- /dev/null
+++ b/common/hmzoned.c
@@ -0,0 +1,218 @@
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Authors:
+ * Naohiro Aota <naohiro.aota@xxxxxxx>
+ * Damien Le Moal <damien.lemoal@xxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <sys/ioctl.h>
+
+#include "common/utils.h"
+#include "common/device-utils.h"
+#include "common/messages.h"
+#include "mkfs/common.h"
+#include "common/hmzoned.h"
+
+#define BTRFS_REPORT_NR_ZONES 8192
+
+enum btrfs_zoned_model zoned_model(const char *file)
+{
+ char model[32];
+ int ret;
+
+ ret = queue_param(file, "zoned", model, sizeof(model));
+ if (ret <= 0)
+ return ZONED_NONE;
+
+ if (strncmp(model, "host-aware", 10) == 0)
+ return ZONED_HOST_AWARE;
+ if (strncmp(model, "host-managed", 12) == 0)
+ return ZONED_HOST_MANAGED;
+
+ return ZONED_NONE;
+}
+
+size_t 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 strtoul((const char *)chunk, NULL, 10) << 9;
+}
+
+#ifdef BTRFS_ZONED
+bool zone_is_sequential(struct btrfs_zone_info *zinfo, u64 bytenr)
+{
+ unsigned int zno;
+
+ if (zinfo->model == ZONED_NONE)
+ return false;
+
+ zno = bytenr / zinfo->zone_size;
+
+ /*
+ * Only sequential write required zones on host-managed
+ * devices cannot be written randomly.
+ */
+ return zinfo->zones[zno].type == BLK_ZONE_TYPE_SEQWRITE_REQ;
+}
+
+static int report_zones(int fd, const char *file, u64 block_count,
+ struct btrfs_zone_info *zinfo)
+{
+ size_t 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 the 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("Illegal zone size %zu (not a power of 2)", zone_bytes);
+ exit(1);
+ }
+ if (zone_bytes < BTRFS_MKFS_SYSTEM_GROUP_SIZE) {
+ error("Illegal zone size %zu (smaller than %d)", zone_bytes,
+ BTRFS_MKFS_SYSTEM_GROUP_SIZE);
+ exit(1);
+ }
+
+ /* Allocate the zone information array */
+ zinfo->zone_size = zone_bytes;
+ zinfo->nr_zones = block_count / zone_bytes;
+ if (block_count & (zone_bytes - 1))
+ zinfo->nr_zones++;
+ zinfo->zones = calloc(zinfo->nr_zones, sizeof(struct blk_zone));
+ if (!zinfo->zones) {
+ error("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("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("ioctl BLKREPORTZONE failed (%s)",
+ strerror(errno));
+ 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;
+ }
+
+ /*
+ * We need at least one random write zone (a conventional zone or
+ * a sequential write preferred zone on a host-aware device).
+ */
+ if (zone_is_sequential(zinfo, 0)) {
+ error("No conventional zone at block 0");
+ exit(1);
+ }
+
+ free(rep);
+
+ return 0;
+}
+
+#endif
+
+int btrfs_get_zone_info(int fd, const char *file, bool hmzoned,
+ struct btrfs_zone_info *zinfo)
+{
+ struct stat st;
+ int ret;
+
+ memset(zinfo, 0, sizeof(struct btrfs_zone_info));
+
+ ret = fstat(fd, &st);
+ if (ret < 0) {
+ error("unable to stat %s", file);
+ return 1;
+ }
+
+ if (!S_ISBLK(st.st_mode))
+ return 0;
+
+ /* Check zone model */
+ zinfo->model = zoned_model(file);
+ if (zinfo->model == ZONED_NONE)
+ return 0;
+
+ if (zinfo->model == ZONED_HOST_MANAGED && !hmzoned) {
+ error(
+"%s: host-managed zoned block device (enable zone block device support with -O hmzoned)",
+ file);
+ return 1;
+ }
+
+ if (!hmzoned) {
+ /* Treat host-aware devices as regular devices */
+ zinfo->model = ZONED_NONE;
+ return 0;
+ }
+
+#ifdef BTRFS_ZONED
+ /* Get zone information */
+ ret = report_zones(fd, file, btrfs_device_size(fd, &st), zinfo);
+ if (ret != 0)
+ return ret;
+#else
+ error("%s: Unsupported host-%s zoned block device", file,
+ zinfo->model == ZONED_HOST_MANAGED ? "managed" : "aware");
+ if (zinfo->model == ZONED_HOST_MANAGED)
+ return 1;
+
+ error("%s: handling host-aware block device as a regular disk", file);
+#endif
+ return 0;
+}
diff --git a/common/hmzoned.h b/common/hmzoned.h
new file mode 100644
index 000000000000..fbcaaf2da20e
--- /dev/null
+++ b/common/hmzoned.h
@@ -0,0 +1,67 @@
+/*
+ * Copyright (C) 2019 Western Digital Corporation or its affiliates.
+ * Authors:
+ * Naohiro Aota <naohiro.aota@xxxxxxx>
+ * Damien Le Moal <damien.lemoal@xxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_HMZONED_H__
+#define __BTRFS_HMZONED_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 = 0,
+ ZONED_HOST_AWARE,
+ ZONED_HOST_MANAGED,
+};
+
+/*
+ * Zone information for a zoned block device.
+ */
+struct btrfs_zone_info {
+ enum btrfs_zoned_model model;
+ size_t zone_size;
+ struct blk_zone *zones;
+ unsigned int nr_zones;
+};
+
+enum btrfs_zoned_model zoned_model(const char *file);
+size_t zone_size(const char *file);
+int btrfs_get_zone_info(int fd, const char *file, bool hmzoned,
+ struct btrfs_zone_info *zinfo);
+
+#ifdef BTRFS_ZONED
+bool zone_is_sequential(struct btrfs_zone_info *zinfo, u64 bytenr);
+#else
+static inline bool zone_is_sequential(struct btrfs_zone_info *zinfo,
+ u64 bytenr)
+{
+ return true;
+}
+#endif /* BTRFS_ZONED */
+
+#endif /* __BTRFS_HMZONED_H__ */
--
2.23.0
