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>

1 files changed, 119 insertions, 16 deletions

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;