This introduces add_dev_v2 ioctl to add a device as raid56 journal
device. With the help of a journal device, raid56 is able to to get
rid of potential write holes.
Signed-off-by: Liu Bo <bo.li....@oracle.com>
---
fs/btrfs/ctree.h | 6 ++++++
fs/btrfs/ioctl.c | 48 ++++++++++++++++++++++++++++++++++++++++-
fs/btrfs/raid56.c | 42 ++++++++++++++++++++++++++++++++++++
fs/btrfs/raid56.h | 1 +
fs/btrfs/volumes.c | 26 ++++++++++++++++------
fs/btrfs/volumes.h | 3 ++-
include/uapi/linux/btrfs.h | 3 +++
include/uapi/linux/btrfs_tree.h | 4 ++++
8 files changed, 125 insertions(+), 8 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 643c70d..d967627 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -697,6 +697,7 @@ struct btrfs_stripe_hash_table {
void btrfs_init_async_reclaim_work(struct work_struct *work);
/* fs_info */
+struct btrfs_r5l_log;
struct reloc_control;
struct btrfs_device;
struct btrfs_fs_devices;
@@ -1114,6 +1115,9 @@ struct btrfs_fs_info {
u32 nodesize;
u32 sectorsize;
u32 stripesize;
+
+ /* raid56 log */
+ struct btrfs_r5l_log *r5log;
};
static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
@@ -2932,6 +2936,8 @@ static inline int btrfs_need_cleaner_sleep(struct
btrfs_fs_info *fs_info)
static inline void free_fs_info(struct btrfs_fs_info *fs_info)
{
+ if (fs_info->r5log)
+ kfree(fs_info->r5log);
kfree(fs_info->balance_ctl);
kfree(fs_info->delayed_root);
kfree(fs_info->extent_root);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e176375..3d1ef4d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2653,6 +2653,50 @@ static int btrfs_ioctl_defrag(struct file *file, void
__user *argp)
return ret;
}
+/* identical to btrfs_ioctl_add_dev, but this is with flags */
+static long btrfs_ioctl_add_dev_v2(struct btrfs_fs_info *fs_info, void __user
*arg)
+{
+ struct btrfs_ioctl_vol_args_v2 *vol_args;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
+ return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
+
+ mutex_lock(&fs_info->volume_mutex);
+ vol_args = memdup_user(arg, sizeof(*vol_args));
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
+
+ if (vol_args->flags & BTRFS_DEVICE_RAID56_LOG &&
+ fs_info->r5log) {
+ ret = -EEXIST;
+ btrfs_info(fs_info, "r5log: attempting to add another log
device!");
+ goto out_free;
+ }
+
+ vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+ ret = btrfs_init_new_device(fs_info, vol_args->name, vol_args->flags);
+ if (!ret) {
+ if (vol_args->flags & BTRFS_DEVICE_RAID56_LOG) {
+ ASSERT(fs_info->r5log);
+ btrfs_info(fs_info, "disk added %s as raid56 log",
vol_args->name);
+ } else {
+ btrfs_info(fs_info, "disk added %s", vol_args->name);
+ }
+ }
+out_free:
+ kfree(vol_args);
+out:
+ mutex_unlock(&fs_info->volume_mutex);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+ return ret;
+}
+
static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user
*arg)
{
struct btrfs_ioctl_vol_args *vol_args;
@@ -2672,7 +2716,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info
*fs_info, void __user *arg)
}
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
- ret = btrfs_init_new_device(fs_info, vol_args->name);
+ ret = btrfs_init_new_device(fs_info, vol_args->name, 0);
if (!ret)
btrfs_info(fs_info, "disk added %s", vol_args->name);
@@ -5539,6 +5583,8 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_resize(file, argp);
case BTRFS_IOC_ADD_DEV:
return btrfs_ioctl_add_dev(fs_info, argp);
+ case BTRFS_IOC_ADD_DEV_V2:
+ return btrfs_ioctl_add_dev_v2(fs_info, argp);
case BTRFS_IOC_RM_DEV:
return btrfs_ioctl_rm_dev(file, argp);
case BTRFS_IOC_RM_DEV_V2:
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index d8ea0eb..2b91b95 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -177,6 +177,25 @@ struct btrfs_raid_bio {
unsigned long *dbitmap;
};
+/* raid56 log */
+struct btrfs_r5l_log {
+ /* protect this struct and log io */
+ struct mutex io_mutex;
+
+ /* r5log device */
+ struct btrfs_device *dev;
+
+ /* allocation range for log entries */
+ u64 data_offset;
+ u64 device_size;
+
+ u64 last_checkpoint;
+ u64 last_cp_seq;
+ u64 seq;
+ u64 log_start;
+ struct btrfs_r5l_io_unit *current_io;
+};
+
static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
static void rmw_work(struct btrfs_work *work);
@@ -2715,3 +2734,26 @@ void raid56_submit_missing_rbio(struct btrfs_raid_bio
*rbio)
if (!lock_stripe_add(rbio))
async_missing_raid56(rbio);
}
+
+int btrfs_set_r5log(struct btrfs_fs_info *fs_info, struct btrfs_device *device)
+{
+ struct btrfs_r5l_log *log;
+
+ log = kzalloc(sizeof(*log), GFP_NOFS);
+ if (!log)
+ return -ENOMEM;
+
+ /* see find_free_dev_extent for 1M start offset */
+ log->data_offset = 1024ull * 1024;
+ log->device_size = btrfs_device_get_total_bytes(device) -
log->data_offset;
+ log->device_size = round_down(log->device_size, PAGE_SIZE);
+ log->dev = device;
+ mutex_init(&log->io_mutex);
+
+ cmpxchg(&fs_info->r5log, NULL, log);
+ ASSERT(fs_info->r5log == log);
+
+ trace_printk("r5log: set a r5log in fs_info, alloc_range 0x%llx
0x%llx",
+ log->data_offset, log->data_offset + log->device_size);
+ return 0;
+}
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 4ee4fe3..0c8bf6a 100644
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -65,4 +65,5 @@ void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio);
int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info);
void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info);
+int btrfs_set_r5log(struct btrfs_fs_info *fs_info, struct btrfs_device
*device);
#endif
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 017b67d..dafc541 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2313,7 +2313,7 @@ static int btrfs_finish_sprout(struct btrfs_trans_handle
*trans,
return ret;
}
-int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char
*device_path)
+int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char
*device_path, const u64 flags)
{
struct btrfs_root *root = fs_info->dev_root;
struct request_queue *q;
@@ -2326,6 +2326,10 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info,
const char *device_path
u64 tmp;
int seeding_dev = 0;
int ret = 0;
+ bool is_r5log = (flags & BTRFS_DEVICE_RAID56_LOG);
+
+ if (is_r5log)
+ ASSERT(!fs_info->fs_devices->seeding);
if ((sb->s_flags & MS_RDONLY) && !fs_info->fs_devices->seeding)
return -EROFS;
@@ -2382,6 +2386,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info,
const char *device_path
q = bdev_get_queue(bdev);
if (blk_queue_discard(q))
device->can_discard = 1;
+ if (is_r5log)
+ device->type |= BTRFS_DEV_RAID56_LOG;
device->writeable = 1;
device->generation = trans->transid;
device->io_width = fs_info->sectorsize;
@@ -2434,11 +2440,13 @@ int btrfs_init_new_device(struct btrfs_fs_info
*fs_info, const char *device_path
/* add sysfs device entry */
btrfs_sysfs_add_device_link(fs_info->fs_devices, device);
- /*
- * we've got more storage, clear any full flags on the space
- * infos
- */
- btrfs_clear_space_info_full(fs_info);
+ if (!is_r5log) {
+ /*
+ * we've got more storage, clear any full flags on the space
+ * infos
+ */
+ btrfs_clear_space_info_full(fs_info);
+ }
mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -2459,6 +2467,12 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info,
const char *device_path
goto error_trans;
}
+ if (is_r5log) {
+ ret = btrfs_set_r5log(fs_info, device);
+ if (ret)
+ goto error_trans;
+ }
+
if (seeding_dev) {
char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index c7d0fbc..60e347a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -437,7 +437,8 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64
devid,
u8 *uuid, u8 *fsid);
int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
-int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
+int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path,
+ const u64 flags);
int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
const char *device_path,
struct btrfs_device *srcdev,
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index a456e53..be5991f 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -35,6 +35,7 @@ struct btrfs_ioctl_vol_args {
#define BTRFS_DEVICE_PATH_NAME_MAX 1024
#define BTRFS_DEVICE_SPEC_BY_ID (1ULL << 3)
+#define BTRFS_DEVICE_RAID56_LOG (1ULL << 4)
#define BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED \
(BTRFS_SUBVOL_CREATE_ASYNC | \
@@ -818,5 +819,7 @@ enum btrfs_err_code {
struct btrfs_ioctl_feature_flags[3])
#define BTRFS_IOC_RM_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 58, \
struct btrfs_ioctl_vol_args_v2)
+#define BTRFS_IOC_ADD_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 59, \
+ struct btrfs_ioctl_vol_args_v2)
#endif /* _UAPI_LINUX_BTRFS_H */
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index 10689e1..52fed59 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -347,6 +347,10 @@ struct btrfs_key {
__u64 offset;
} __attribute__ ((__packed__));
+/* dev_item.type */
+/* #define BTRFS_DEV_REGULAR 0 */
+#define BTRFS_DEV_RAID56_LOG (1ULL << 0)
+
struct btrfs_dev_item {
/* the internal btrfs device id */
__le64 devid;
--
2.9.4
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
