V4.12 rc3 r5log rebase

fs/btrfs/ctree.h

@@ -244,8 +244,10 @@ struct btrfs_super_block {
 	__le64 cache_generation;
 	__le64 uuid_tree_generation;
 
+	/* r5log journal tail (where recovery starts) */
+	__le64 journal_tail;
 	/* future expansion */
-	__le64 reserved[30];
+	__le64 reserved[29];
 	u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
 	struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
 } __attribute__ ((__packed__));
@@ -697,6 +699,7 @@ 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 +1117,9 @@ 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)
@@ -2287,6 +2293,8 @@ BTRFS_SETGET_STACK_FUNCS(super_log_root_transid, struct btrfs_super_block,
 			 log_root_transid, 64);
 BTRFS_SETGET_STACK_FUNCS(super_log_root_level, struct btrfs_super_block,
 			 log_root_level, 8);
+BTRFS_SETGET_STACK_FUNCS(super_journal_tail, struct btrfs_super_block,
+			 journal_tail, 64);
 BTRFS_SETGET_STACK_FUNCS(super_total_bytes, struct btrfs_super_block,
 			 total_bytes, 64);
 BTRFS_SETGET_STACK_FUNCS(super_bytes_used, struct btrfs_super_block,
@@ -2932,6 +2940,8 @@ 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);
@@ -3278,6 +3288,10 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			unsigned long new_flags);
 int btrfs_sync_fs(struct super_block *sb, int wait);
 
+/* raid56.c */
+void btrfs_r5l_write_journal_tail(struct btrfs_fs_info *fs_info);
+
+
 static inline __printf(2, 3)
 void btrfs_no_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
 {

fs/btrfs/disk-io.c

@@ -2987,6 +2987,22 @@ int open_ctree(struct super_block *sb,
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	if (fs_info->r5log) {
+		u64 cp = btrfs_super_journal_tail(fs_info->super_copy);
+#ifdef BTRFS_DEBUG_R5LOG
+		trace_printk("%s: get journal_tail %llu\n", __func__, cp);
+#endif
+		/* if the data is not replayed, data and parity on
+		 * disk are still consistent.  So we can move on.
+		 *
+		 * About fsync, since fsync can make sure data is
+		 * flushed onto disk and only metadata is kept into
+		 * write-ahead log, the fsync'd data will never ends
+		 * up with being replayed by raid56 log.
+		 */
+		btrfs_r5l_load_log(fs_info, NULL, cp);
+	}
+
 	ret = btrfs_recover_balance(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "failed to recover balance: %d", ret);

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: