| Message ID | 20191204081735.852438-4-naohiro.aota@wdc.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | btrfs: zoned block device support | expand |
On Wed, Dec 04, 2019 at 05:17:10PM +0900, Naohiro Aota wrote: > HMZONED mode cannot be used together with the RAID5/6 profile for now. > Introduce the function btrfs_check_hmzoned_mode() to check this. This > function will also check if HMZONED flag is enabled on the file system and > if the file system consists of zoned devices with equal zone size. I have a question, you wrote you check for a file system consisting of zoned devices with equal zone size. What happens if you create a multi device file system combining zoned and regular devices? Is this even supported and if no where are the checks for it? [...] > +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info) > +{ > + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; > + struct btrfs_device *device; > + u64 hmzoned_devices = 0; > + u64 nr_devices = 0; > + u64 zone_size = 0; > + int incompat_hmzoned = btrfs_fs_incompat(fs_info, HMZONED); > + int ret = 0; > + > + /* Count zoned devices */ > + list_for_each_entry(device, &fs_devices->devices, dev_list) { > + if (!device->bdev) > + continue; Nit: enum blk_zoned_model zone_model = blk_zoned_model(device->bdev); if (zone_model == BLK_ZONED_HM || zone_model == BLK_ZONED_HA && incompat_hmzoned) { > + if (bdev_zoned_model(device->bdev) == BLK_ZONED_HM || > + (bdev_zoned_model(device->bdev) == BLK_ZONED_HA && > + incompat_hmzoned)) { > + hmzoned_devices++; > + if (!zone_size) { > + zone_size = device->zone_info->zone_size; > + } else if (device->zone_info->zone_size != zone_size) { > + btrfs_err(fs_info, > + "Zoned block devices must have equal zone sizes"); > + ret = -EINVAL; > + goto out; > + } > + } > + nr_devices++; > + }
On Wed, Dec 04, 2019 at 05:07:34PM +0100, Johannes Thumshirn wrote: >On Wed, Dec 04, 2019 at 05:17:10PM +0900, Naohiro Aota wrote: >> HMZONED mode cannot be used together with the RAID5/6 profile for now. >> Introduce the function btrfs_check_hmzoned_mode() to check this. This >> function will also check if HMZONED flag is enabled on the file system and >> if the file system consists of zoned devices with equal zone size. > >I have a question, you wrote you check for a file system consisting of zoned >devices with equal zone size. What happens if you create a multi device file >system combining zoned and regular devices? Is this even supported and if no >where are the checks for it? We don't allow creaing a file system mixed with zoned and regular device. This is checked by btrfs_check_hmzoned_mode() (called from open_ctree()) at the mount time. "if (hmzoned_devices != nr_devices) { ... }" is doing the actual check. # I noticed putting "fs_info->zone_size = zone_size;" after this check is # better. Also, btrfs_check_device_zone_type() (called from btrfs_init_new_device() and btrfs_init_dev_replace_tgtdev()) does the similar check against new device for "btrfs device add" and "btrfs replace". > >[...] > >> +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info) >> +{ >> + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; >> + struct btrfs_device *device; >> + u64 hmzoned_devices = 0; >> + u64 nr_devices = 0; >> + u64 zone_size = 0; >> + int incompat_hmzoned = btrfs_fs_incompat(fs_info, HMZONED); >> + int ret = 0; >> + >> + /* Count zoned devices */ >> + list_for_each_entry(device, &fs_devices->devices, dev_list) { >> + if (!device->bdev) >> + continue; > >Nit: > enum blk_zoned_model zone_model = blk_zoned_model(device->bdev); > > if (zone_model == BLK_ZONED_HM || > zone_model == BLK_ZONED_HA && > incompat_hmzoned) { > Thanks, it's clearer. >> + if (bdev_zoned_model(device->bdev) == BLK_ZONED_HM || >> + (bdev_zoned_model(device->bdev) == BLK_ZONED_HA && >> + incompat_hmzoned)) { >> + hmzoned_devices++; >> + if (!zone_size) { >> + zone_size = device->zone_info->zone_size; >> + } else if (device->zone_info->zone_size != zone_size) { >> + btrfs_err(fs_info, >> + "Zoned block devices must have equal zone sizes"); >> + ret = -EINVAL; >> + goto out; >> + } >> + } >> + nr_devices++; >> + }
On Thu, Dec 05, 2019 at 02:17:04PM +0900, Naohiro Aota wrote: > >I have a question, you wrote you check for a file system consisting of zoned > >devices with equal zone size. What happens if you create a multi device file > >system combining zoned and regular devices? Is this even supported and if no > >where are the checks for it? > > We don't allow creaing a file system mixed with zoned and regular device. > This is checked by btrfs_check_hmzoned_mode() (called from open_ctree()) at > the mount time. "if (hmzoned_devices != nr_devices) { ... }" is doing the > actual check. It's ok for first implementation to have more restrictions, like not allowing mixing hmzoned and regular devices or hmzoned devices with different zone sizes. Adding that later should be possible and not complicating the review for now.
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b2e8fd8a8e59..44517802b9e5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -541,6 +541,9 @@ struct btrfs_fs_info { struct btrfs_root *uuid_root; struct btrfs_root *free_space_root; + /* Zone size when in HMZONED mode */ + u64 zone_size; + /* the log root tree is a directory of all the other log roots */ struct btrfs_root *log_root_tree; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index f639dde2a679..9286c6e0b636 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -21,6 +21,7 @@ #include "rcu-string.h" #include "dev-replace.h" #include "sysfs.h" +#include "hmzoned.h" static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret); @@ -202,6 +203,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return PTR_ERR(bdev); } + if (!btrfs_check_device_zone_type(fs_info, bdev)) { + btrfs_err(fs_info, + "zone type of target device mismatch with the filesystem!"); + ret = -EINVAL; + goto error; + } + sync_blockdev(bdev); devices = &fs_info->fs_devices->devices; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e0edfdc9c82b..ff418e393f82 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -41,6 +41,7 @@ #include "tree-checker.h" #include "ref-verify.h" #include "block-group.h" +#include "hmzoned.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ @@ -3082,6 +3083,13 @@ int __cold open_ctree(struct super_block *sb, btrfs_free_extra_devids(fs_devices, 1); + ret = btrfs_check_hmzoned_mode(fs_info); + if (ret) { + btrfs_err(fs_info, "failed to init hmzoned mode: %d", + ret); + goto fail_block_groups; + } + ret = btrfs_sysfs_add_fsid(fs_devices, NULL); if (ret) { btrfs_err(fs_info, "failed to init sysfs fsid interface: %d", diff --git a/fs/btrfs/hmzoned.c b/fs/btrfs/hmzoned.c index e37335625f76..9a04240910f6 100644 --- a/fs/btrfs/hmzoned.c +++ b/fs/btrfs/hmzoned.c @@ -172,3 +172,77 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, return 0; } + +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + u64 hmzoned_devices = 0; + u64 nr_devices = 0; + u64 zone_size = 0; + int incompat_hmzoned = btrfs_fs_incompat(fs_info, HMZONED); + int ret = 0; + + /* Count zoned devices */ + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (!device->bdev) + continue; + if (bdev_zoned_model(device->bdev) == BLK_ZONED_HM || + (bdev_zoned_model(device->bdev) == BLK_ZONED_HA && + incompat_hmzoned)) { + hmzoned_devices++; + if (!zone_size) { + zone_size = device->zone_info->zone_size; + } else if (device->zone_info->zone_size != zone_size) { + btrfs_err(fs_info, + "Zoned block devices must have equal zone sizes"); + ret = -EINVAL; + goto out; + } + } + nr_devices++; + } + + if (!hmzoned_devices && !incompat_hmzoned) + goto out; + + if (!hmzoned_devices && incompat_hmzoned) { + /* No zoned block device found on HMZONED FS */ + btrfs_err(fs_info, "HMZONED enabled file system should have zoned devices"); + ret = -EINVAL; + goto out; + } + + if (hmzoned_devices && !incompat_hmzoned) { + btrfs_err(fs_info, + "Enable HMZONED mode to mount HMZONED device"); + ret = -EINVAL; + goto out; + } + + fs_info->zone_size = zone_size; + + if (hmzoned_devices != nr_devices) { + btrfs_err(fs_info, + "zoned devices cannot be mixed with regular devices"); + ret = -EINVAL; + goto out; + } + + /* + * stripe_size is always aligned to BTRFS_STRIPE_LEN in + * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size, + * check the alignment here. + */ + if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) { + btrfs_err(fs_info, + "zone size is not aligned to BTRFS_STRIPE_LEN"); + ret = -EINVAL; + goto out; + } + + btrfs_info(fs_info, "HMZONED mode enabled, zone size %llu B", + fs_info->zone_size); +out: + return ret; +} diff --git a/fs/btrfs/hmzoned.h b/fs/btrfs/hmzoned.h index 0f8006f39aaf..8e17f64ff986 100644 --- a/fs/btrfs/hmzoned.h +++ b/fs/btrfs/hmzoned.h @@ -9,6 +9,8 @@ #ifndef BTRFS_HMZONED_H #define BTRFS_HMZONED_H +#include <linux/blkdev.h> + struct btrfs_zoned_device_info { /* * Number of zones, zone size and types of zones if bdev is a @@ -26,6 +28,7 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone); int btrfs_get_dev_zone_info(struct btrfs_device *device); void btrfs_destroy_dev_zone_info(struct btrfs_device *device); +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -37,6 +40,14 @@ static inline int btrfs_get_dev_zone_info(struct btrfs_device *device) return 0; } static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { } +static inline int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_fs_incompat(fs_info, HMZONED)) + return 0; + + btrfs_err(fs_info, "Zoned block devices support is not enabled"); + return -EOPNOTSUPP; +} #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) @@ -89,4 +100,19 @@ static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, btrfs_dev_set_empty_zone_bit(device, pos, false); } +static inline bool btrfs_check_device_zone_type(struct btrfs_fs_info *fs_info, + struct block_device *bdev) +{ + u64 zone_size; + + if (btrfs_fs_incompat(fs_info, HMZONED)) { + zone_size = (u64)bdev_zone_sectors(bdev) << SECTOR_SHIFT; + /* Do not allow non-zoned device */ + return bdev_is_zoned(bdev) && fs_info->zone_size == zone_size; + } + + /* Do not allow Host Manged zoned device */ + return bdev_zoned_model(bdev) != BLK_ZONED_HM; +} + #endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a98c3c71fc54..616f5abec267 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -44,6 +44,7 @@ #include "backref.h" #include "space-info.h" #include "sysfs.h" +#include "hmzoned.h" #include "tests/btrfs-tests.h" #include "block-group.h" diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 18ea8dfce244..ab3590b310af 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2395,6 +2395,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (IS_ERR(bdev)) return PTR_ERR(bdev); + if (!btrfs_check_device_zone_type(fs_info, bdev)) { + ret = -EINVAL; + goto error; + } + if (fs_devices->seeding) { seeding_dev = 1; down_write(&sb->s_umount);