Btrfs: add basic restriper infrastructure

Add basic restriper infrastructure: extended balancing ioctl and all
related ioctl data structures, add data structure for tracking
restriper's state to fs_info, etc.  The semantics of the old balancing
ioctl are fully preserved.

Explicitly disallow any volume operations when balance is in progress.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

6 files changed, 281 insertions, 41 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 3f8f11e18b53..c4d98c8df5c5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -934,6 +934,7 @@ struct btrfs_block_group_cache {
 struct reloc_control;
 struct btrfs_device;
 struct btrfs_fs_devices;
+struct btrfs_balance_control;
 struct btrfs_delayed_root;
 struct btrfs_fs_info {
         u8 fsid[BTRFS_FSID_SIZE];
@@ -1159,6 +1160,11 @@ struct btrfs_fs_info {
         u64 avail_metadata_alloc_bits;
         u64 avail_system_alloc_bits;
 
+        /* restriper state */
+        spinlock_t balance_lock;
+        struct mutex balance_mutex;
+        struct btrfs_balance_control *balance_ctl;
+
         unsigned data_chunk_allocations;
         unsigned metadata_ratio;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index ce9d0fb3627d..190a1b24c902 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2002,6 +2002,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         init_rwsem(&fs_info->scrub_super_lock);
         fs_info->scrub_workers_refcnt = 0;
 
+        spin_lock_init(&fs_info->balance_lock);
+        mutex_init(&fs_info->balance_mutex);
+        fs_info->balance_ctl = NULL;
+
         sb->s_blocksize = 4096;
         sb->s_blocksize_bits = blksize_bits(4096);
         sb->s_bdi = &fs_info->bdi;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c04f02c7d5bb..d838d2cfb947 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1203,13 +1203,21 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
         if (!capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
+        mutex_lock(&root->fs_info->volume_mutex);
+        if (root->fs_info->balance_ctl) {
+                printk(KERN_INFO "btrfs: balance in progress\n");
+                ret = -EINVAL;
+                goto out;
+        }
+
         vol_args = memdup_user(arg, sizeof(*vol_args));
-        if (IS_ERR(vol_args))
-                return PTR_ERR(vol_args);
+        if (IS_ERR(vol_args)) {
+                ret = PTR_ERR(vol_args);
+                goto out;
+        }
 
         vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
 
-        mutex_lock(&root->fs_info->volume_mutex);
         sizestr = vol_args->name;
         devstr = strchr(sizestr, ':');
         if (devstr) {
@@ -1226,7 +1234,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
                        (unsigned long long)devid);
                 ret = -EINVAL;
-                goto out_unlock;
+                goto out_free;
         }
         if (!strcmp(sizestr, "max"))
                 new_size = device->bdev->bd_inode->i_size;
@@ -1241,7 +1249,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 new_size = memparse(sizestr, NULL);
                 if (new_size == 0) {
                         ret = -EINVAL;
-                        goto out_unlock;
+                        goto out_free;
                 }
         }
 
@@ -1250,7 +1258,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
         if (mod < 0) {
                 if (new_size > old_size) {
                         ret = -EINVAL;
-                        goto out_unlock;
+                        goto out_free;
                 }
                 new_size = old_size - new_size;
         } else if (mod > 0) {
@@ -1259,11 +1267,11 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 
         if (new_size < 256 * 1024 * 1024) {
                 ret = -EINVAL;
-                goto out_unlock;
+                goto out_free;
         }
         if (new_size > device->bdev->bd_inode->i_size) {
                 ret = -EFBIG;
-                goto out_unlock;
+                goto out_free;
         }
 
         do_div(new_size, root->sectorsize);
@@ -1276,7 +1284,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 trans = btrfs_start_transaction(root, 0);
                 if (IS_ERR(trans)) {
                         ret = PTR_ERR(trans);
-                        goto out_unlock;
+                        goto out_free;
                 }
                 ret = btrfs_grow_device(trans, device, new_size);
                 btrfs_commit_transaction(trans, root);
@@ -1284,9 +1292,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
                 ret = btrfs_shrink_device(device, new_size);
         }
 
-out_unlock:
-        mutex_unlock(&root->fs_info->volume_mutex);
+out_free:
         kfree(vol_args);
+out:
+        mutex_unlock(&root->fs_info->volume_mutex);
         return ret;
 }
 
@@ -2052,14 +2061,25 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
         if (!capable(CAP_SYS_ADMIN))
                 return -EPERM;
 
+        mutex_lock(&root->fs_info->volume_mutex);
+        if (root->fs_info->balance_ctl) {
+                printk(KERN_INFO "btrfs: balance in progress\n");
+                ret = -EINVAL;
+                goto out;
+        }
+
         vol_args = memdup_user(arg, sizeof(*vol_args));
-        if (IS_ERR(vol_args))
-                return PTR_ERR(vol_args);
+        if (IS_ERR(vol_args)) {
+                ret = PTR_ERR(vol_args);
+                goto out;
+        }
 
         vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
         ret = btrfs_init_new_device(root, vol_args->name);
 
         kfree(vol_args);
+out:
+        mutex_unlock(&root->fs_info->volume_mutex);
         return ret;
 }
 
@@ -2074,14 +2094,25 @@ static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg)
         if (root->fs_info->sb->s_flags & MS_RDONLY)
                 return -EROFS;
 
+        mutex_lock(&root->fs_info->volume_mutex);
+        if (root->fs_info->balance_ctl) {
+                printk(KERN_INFO "btrfs: balance in progress\n");
+                ret = -EINVAL;
+                goto out;
+        }
+
         vol_args = memdup_user(arg, sizeof(*vol_args));
-        if (IS_ERR(vol_args))
-                return PTR_ERR(vol_args);
+        if (IS_ERR(vol_args)) {
+                ret = PTR_ERR(vol_args);
+                goto out;
+        }
 
         vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
         ret = btrfs_rm_device(root, vol_args->name);
 
         kfree(vol_args);
+out:
+        mutex_unlock(&root->fs_info->volume_mutex);
         return ret;
 }
 
@@ -3034,6 +3065,76 @@ out:
         return ret;
 }
 
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
+                               struct btrfs_ioctl_balance_args *bargs)
+{
+        struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+        bargs->flags = bctl->flags;
+
+        memcpy(&bargs->data, &bctl->data, sizeof(bargs->data));
+        memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
+        memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
+}
+
+static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg)
+{
+        struct btrfs_fs_info *fs_info = root->fs_info;
+        struct btrfs_ioctl_balance_args *bargs;
+        struct btrfs_balance_control *bctl;
+        int ret;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EPERM;
+
+        if (fs_info->sb->s_flags & MS_RDONLY)
+                return -EROFS;
+
+        mutex_lock(&fs_info->volume_mutex);
+        mutex_lock(&fs_info->balance_mutex);
+
+        if (arg) {
+                bargs = memdup_user(arg, sizeof(*bargs));
+                if (IS_ERR(bargs)) {
+                        ret = PTR_ERR(bargs);
+                        goto out;
+                }
+        } else {
+                bargs = NULL;
+        }
+
+        bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+        if (!bctl) {
+                ret = -ENOMEM;
+                goto out_bargs;
+        }
+
+        bctl->fs_info = fs_info;
+        if (arg) {
+                memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
+                memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
+                memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
+
+                bctl->flags = bargs->flags;
+        }
+
+        ret = btrfs_balance(bctl, bargs);
+        /*
+         * bctl is freed in __cancel_balance
+         */
+        if (arg) {
+                if (copy_to_user(arg, bargs, sizeof(*bargs)))
+                        ret = -EFAULT;
+        }
+
+out_bargs:
+        kfree(bargs);
+out:
+        mutex_unlock(&fs_info->balance_mutex);
+        mutex_unlock(&fs_info->volume_mutex);
+        return ret;
+}
+
 long btrfs_ioctl(struct file *file, unsigned int
                 cmd, unsigned long arg)
 {
@@ -3078,7 +3179,7 @@ long btrfs_ioctl(struct file *file, unsigned int
         case BTRFS_IOC_DEV_INFO:
                 return btrfs_ioctl_dev_info(root, argp);
         case BTRFS_IOC_BALANCE:
-                return btrfs_balance(root->fs_info->dev_root);
+                return btrfs_ioctl_balance(root, NULL);
         case BTRFS_IOC_CLONE:
                 return btrfs_ioctl_clone(file, arg, 0, 0, 0);
         case BTRFS_IOC_CLONE_RANGE:
@@ -3110,6 +3211,8 @@ long btrfs_ioctl(struct file *file, unsigned int
                 return btrfs_ioctl_scrub_cancel(root, argp);
         case BTRFS_IOC_SCRUB_PROGRESS:
                 return btrfs_ioctl_scrub_progress(root, argp);
+        case BTRFS_IOC_BALANCE_V2:
+                return btrfs_ioctl_balance(root, argp);
         }
 
         return -ENOTTY;
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index 252ae9915de8..c8b37d2c0d77 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -109,6 +109,47 @@ struct btrfs_ioctl_fs_info_args {
         __u64 reserved[124];                    /* pad to 1k */
 };
 
+/*
+ * this is packed, because it should be exactly the same as its disk
+ * byte order counterpart (struct btrfs_disk_balance_args)
+ */
+struct btrfs_balance_args {
+        __u64 profiles;
+        __u64 usage;
+        __u64 devid;
+        __u64 pstart;
+        __u64 pend;
+        __u64 vstart;
+        __u64 vend;
+
+        __u64 target;
+
+        __u64 flags;
+
+        __u64 unused[8];
+} __attribute__ ((__packed__));
+
+/* report balance progress to userspace */
+struct btrfs_balance_progress {
+        __u64 expected;         /* estimated # of chunks that will be
+                                 * relocated to fulfill the request */
+        __u64 considered;       /* # of chunks we have considered so far */
+        __u64 completed;        /* # of chunks relocated so far */
+};
+
+struct btrfs_ioctl_balance_args {
+        __u64 flags;                            /* in/out */
+        __u64 state;                            /* out */
+
+        struct btrfs_balance_args data;         /* in/out */
+        struct btrfs_balance_args meta;         /* in/out */
+        struct btrfs_balance_args sys;          /* in/out */
+
+        struct btrfs_balance_progress stat;     /* out */
+
+        __u64 unused[72];                       /* pad to 1k */
+};
+
 #define BTRFS_INO_LOOKUP_PATH_MAX 4080
 struct btrfs_ioctl_ino_lookup_args {
         __u64 treeid;
@@ -272,6 +313,8 @@ struct btrfs_ioctl_logical_ino_args {
                                  struct btrfs_ioctl_dev_info_args)
 #define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \
                                struct btrfs_ioctl_fs_info_args)
+#define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \
+                                   struct btrfs_ioctl_balance_args)
 #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \
                                         struct btrfs_ioctl_ino_path_args)
 #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d5fdee56777f..9fc06e6bc51a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1282,7 +1282,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
         bool clear_super = false;
 
         mutex_lock(&uuid_mutex);
-        mutex_lock(&root->fs_info->volume_mutex);
 
         all_avail = root->fs_info->avail_data_alloc_bits |
                 root->fs_info->avail_system_alloc_bits |
@@ -1452,7 +1451,6 @@ error_close:
         if (bdev)
                 blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 out:
-        mutex_unlock(&root->fs_info->volume_mutex);
         mutex_unlock(&uuid_mutex);
         return ret;
 error_undo:
@@ -1629,7 +1627,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
         }
 
         filemap_write_and_wait(bdev->bd_inode->i_mapping);
-        mutex_lock(&root->fs_info->volume_mutex);
 
         devices = &root->fs_info->fs_devices->devices;
         /*
@@ -1757,8 +1754,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
                 ret = btrfs_relocate_sys_chunks(root);
                 BUG_ON(ret);
         }
-out:
-        mutex_unlock(&root->fs_info->volume_mutex);
+
         return ret;
 error:
         blkdev_put(bdev, FMODE_EXCL);
@@ -1766,7 +1762,7 @@ error:
                 mutex_unlock(&uuid_mutex);
                 up_write(&sb->s_umount);
         }
-        goto out;
+        return ret;
 }
 
 static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
@@ -2077,6 +2073,35 @@ error:
         return ret;
 }
 
+/*
+ * Should be called with both balance and volume mutexes held to
+ * serialize other volume operations (add_dev/rm_dev/resize) with
+ * restriper.  Same goes for unset_balance_control.
+ */
+static void set_balance_control(struct btrfs_balance_control *bctl)
+{
+        struct btrfs_fs_info *fs_info = bctl->fs_info;
+
+        BUG_ON(fs_info->balance_ctl);
+
+        spin_lock(&fs_info->balance_lock);
+        fs_info->balance_ctl = bctl;
+        spin_unlock(&fs_info->balance_lock);
+}
+
+static void unset_balance_control(struct btrfs_fs_info *fs_info)
+{
+        struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+        BUG_ON(!fs_info->balance_ctl);
+
+        spin_lock(&fs_info->balance_lock);
+        fs_info->balance_ctl = NULL;
+        spin_unlock(&fs_info->balance_lock);
+
+        kfree(bctl);
+}
+
 static u64 div_factor(u64 num, int factor)
 {
         if (factor == 10)
@@ -2086,29 +2111,23 @@ static u64 div_factor(u64 num, int factor)
         return num;
 }
 
-int btrfs_balance(struct btrfs_root *dev_root)
+static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 {
-        int ret;
-        struct list_head *devices = &dev_root->fs_info->fs_devices->devices;
+        struct btrfs_root *chunk_root = fs_info->chunk_root;
+        struct btrfs_root *dev_root = fs_info->dev_root;
+        struct list_head *devices;
         struct btrfs_device *device;
         u64 old_size;
         u64 size_to_free;
         struct btrfs_path *path;
         struct btrfs_key key;
-        struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root;
-        struct btrfs_trans_handle *trans;
         struct btrfs_key found_key;
-
-        if (dev_root->fs_info->sb->s_flags & MS_RDONLY)
-                return -EROFS;
-
-        if (!capable(CAP_SYS_ADMIN))
-                return -EPERM;
-
-        mutex_lock(&dev_root->fs_info->volume_mutex);
-        dev_root = dev_root->fs_info->dev_root;
+        struct btrfs_trans_handle *trans;
+        int ret;
+        int enospc_errors = 0;
 
         /* step one make some room on all the devices */
+        devices = &fs_info->fs_devices->devices;
         list_for_each_entry(device, devices, dev_list) {
                 old_size = device->total_bytes;
                 size_to_free = div_factor(old_size, 1);
@@ -2151,12 +2170,14 @@ int btrfs_balance(struct btrfs_root *dev_root)
                  * failed
                  */
                 if (ret == 0)
-                        break;
+                        BUG(); /* FIXME break ? */
 
                 ret = btrfs_previous_item(chunk_root, path, 0,
                                           BTRFS_CHUNK_ITEM_KEY);
-                if (ret)
+                if (ret) {
+                        ret = 0;
                         break;
+                }
 
                 btrfs_item_key_to_cpu(path->nodes[0], &found_key,
                                       path->slots[0]);
@@ -2174,12 +2195,63 @@ int btrfs_balance(struct btrfs_root *dev_root)
                                            found_key.offset);
                 if (ret && ret != -ENOSPC)
                         goto error;
+                if (ret == -ENOSPC)
+                        enospc_errors++;
                 key.offset = found_key.offset - 1;
         }
-        ret = 0;
+
 error:
         btrfs_free_path(path);
-        mutex_unlock(&dev_root->fs_info->volume_mutex);
+        if (enospc_errors) {
+                printk(KERN_INFO "btrfs: %d enospc errors during balance\n",
+                       enospc_errors);
+                if (!ret)
+                        ret = -ENOSPC;
+        }
+
+        return ret;
+}
+
+static void __cancel_balance(struct btrfs_fs_info *fs_info)
+{
+        unset_balance_control(fs_info);
+}
+
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
+                               struct btrfs_ioctl_balance_args *bargs);
+
+/*
+ * Should be called with both balance and volume mutexes held
+ */
+int btrfs_balance(struct btrfs_balance_control *bctl,
+                  struct btrfs_ioctl_balance_args *bargs)
+{
+        struct btrfs_fs_info *fs_info = bctl->fs_info;
+        int ret;
+
+        if (btrfs_fs_closing(fs_info)) {
+                ret = -EINVAL;
+                goto out;
+        }
+
+        set_balance_control(bctl);
+
+        mutex_unlock(&fs_info->balance_mutex);
+
+        ret = __btrfs_balance(fs_info);
+
+        mutex_lock(&fs_info->balance_mutex);
+
+        if (bargs) {
+                memset(bargs, 0, sizeof(*bargs));
+                update_ioctl_balance_args(fs_info, bargs);
+        }
+
+        __cancel_balance(fs_info);
+
+        return ret;
+out:
+        kfree(bctl);
         return ret;
 }
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 78f2d4d4f37f..882582385283 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -186,6 +186,17 @@ struct map_lookup {
 #define map_lookup_size(n) (sizeof(struct map_lookup) + \
                             (sizeof(struct btrfs_bio_stripe) * (n)))
 
+struct btrfs_balance_args;
+struct btrfs_balance_control {
+        struct btrfs_fs_info *fs_info;
+
+        struct btrfs_balance_args data;
+        struct btrfs_balance_args meta;
+        struct btrfs_balance_args sys;
+
+        u64 flags;
+};
+
 int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
                                    u64 end, u64 *length);
 
@@ -228,7 +239,8 @@ struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
                                        u8 *uuid, u8 *fsid);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_root *root, char *path);
-int btrfs_balance(struct btrfs_root *dev_root);
+int btrfs_balance(struct btrfs_balance_control *bctl,
+                  struct btrfs_ioctl_balance_args *bargs);
 int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
 int find_free_dev_extent(struct btrfs_trans_handle *trans,
                          struct btrfs_device *device, u64 num_bytes,