scoutfs: introduce CodingStyle.txt

Add a coding style document that tries to record the conventions that
the project uses.  It seemed more appropriate to put it up in the -kmod
git repo context rather than in src/ which would end up in fs/scoutfs/
upstream.

Signed-off-by: Zach Brown <zab@versity.com>

CodingStyle.txt

@@ -0,0 +1,82 @@
+
+We try to maintain a consistent coding style across the project.  It's
+admitedly arbitrary and starts with and is based on upstream's
+Documentation/CodingStyle.  Conventions are added here as they come up
+during review.  We'll demonstrate each sylistic preference with a diff
+snippet.
+
+== Try to make one exit point for reasonably long functions
+
+{
+-	void *a;
+-	void *b;
++	void *a = NULL;
++	void *b = NULL;
++	int ret;
+
+	a = kalloc();
+-	if (!a)
+-		return 1;
++	if (!a) {
++		ret = 1;
++		goto out;
++	}
+
+	b = kalloc();
+	if (!b) {
+-		kfree(a);
+-		return 2;
++		ret = 2;
++		goto out;
+	}
+
+-	return 3
++	ret = 3;
++out:
++	kfree(a);
++	kfree(b);
++	return ret;
+}
+
+The idea is to initialize all state at the top of the function,
+modifying it throughout, and clean it all up at the end.  Having one
+exit point also gives us a place to add tracing of function exit.
+
+== Multiple declarations on a line
+
+-	int i, j;
++	int i;
++	int j;
+
+Declare function variables one per line.  The verbose declarations
+create pressure to think about excessive stack use or over-long
+functions, makes initializers clear, and leaves room for comments.
+
+== Balance braces
+
+-	if (IS_ERR(super_block))
++	if (IS_ERR(super_block)) {
+		return PTR_ERR(super_block);
+-	else {
++	} else {
+		*super_res = *super_block;
+		kfree(super_block);
+		return 0;
+	}
+
+*nervous twitch*
+
+== Cute variable defintion waterfalls
+
++	struct block_device *meta_bdev;
+	struct scoutfs_sb_info *sbi;
+	struct mount_options opts;
+-	struct block_device *meta_bdev;
+	struct inode *inode;
+
+This isn't strictly necessary, but it's nice to try and make a pretty
+descending length of variable distributions.  It often has the
+accidental  effect of sorting definitions by decreasing complexity.  I
+tend to group types when the name lengths are pretty close, even if
+they're not strictly sorted, so that all the ints, u64s, keys, etc, are
+all together.

kmod/src/block.c

@@ -286,16 +286,10 @@ static int block_insert(struct super_block *sb, struct block_private *bp)
 
 	WARN_ON_ONCE(atomic_read(&bp->refcount) & BLOCK_REF_INSERTED);
 
-retry:
 	atomic_add(BLOCK_REF_INSERTED, &bp->refcount);
-	ret = rhashtable_lookup_insert_fast(&binf->ht, &bp->ht_head, block_ht_params);
+	ret = rhashtable_insert_fast(&binf->ht, &bp->ht_head, block_ht_params);
 	if (ret < 0) {
 		atomic_sub(BLOCK_REF_INSERTED, &bp->refcount);
-		if (ret == -EBUSY) {
-			/* wait for pending rebalance to finish */
-			synchronize_rcu();
-			goto retry;
-		}
 	} else {
 		atomic_inc(&binf->total_inserted);
 		TRACE_BLOCK(insert, bp);
@@ -402,7 +396,6 @@ static void block_remove_all(struct super_block *sb)
 
 		if (block_get_if_inserted(bp)) {
 			block_remove(sb, bp);
-			WARN_ON_ONCE(atomic_read(&bp->refcount) != 1);
 			block_put(sb, bp);
 		}
 	}
@@ -1080,11 +1073,10 @@ restart:
 		if (bp == NULL)
 			break;
 		if (bp == ERR_PTR(-EAGAIN)) {
-			/* hard exit to wait for rcu rebalance to finish */
+			/* hard reset to not hold rcu grace period across retries */
 			rhashtable_walk_stop(&iter);
 			rhashtable_walk_exit(&iter);
 			scoutfs_inc_counter(sb, block_cache_shrink_restart);
-			synchronize_rcu();
 			goto restart;
 		}
 

kmod/src/client.c

@@ -150,7 +150,7 @@ static int client_lock_response(struct super_block *sb,
 				void *resp, unsigned int resp_len,
 				int error, void *data)
 {
-	if (resp_len != sizeof(struct scoutfs_net_lock))
+	if (resp_len != sizeof(struct scoutfs_net_lock_grant_response))
 		return -EINVAL;
 
 	/* XXX error? */

kmod/src/data.c

@@ -1135,8 +1135,7 @@ static void truncate_inode_pages_extent(struct inode *inode, u64 start, u64 len)
  */
 #define MOVE_DATA_EXTENTS_PER_HOLD 16
 int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
-			     u64 byte_len, struct inode *to, u64 to_off, bool is_stage,
-			     u64 data_version)
+			     u64 byte_len, struct inode *to, u64 to_off)
 {
 	struct scoutfs_inode_info *from_si = SCOUTFS_I(from);
 	struct scoutfs_inode_info *to_si = SCOUTFS_I(to);
@@ -1146,7 +1145,6 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 	struct data_ext_args from_args;
 	struct data_ext_args to_args;
 	struct scoutfs_extent ext;
-	struct timespec cur_time;
 	LIST_HEAD(locks);
 	bool done = false;
 	loff_t from_size;
@@ -1182,11 +1180,6 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 		goto out;
 	}
 
-	if (is_stage && (data_version != SCOUTFS_I(to)->data_version)) {
-		ret = -ESTALE;
-		goto out;
-	}
-
 	from_iblock = from_off >> SCOUTFS_BLOCK_SM_SHIFT;
 	count = (byte_len + SCOUTFS_BLOCK_SM_MASK) >> SCOUTFS_BLOCK_SM_SHIFT;
 	to_iblock = to_off >> SCOUTFS_BLOCK_SM_SHIFT;
@@ -1209,7 +1202,7 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 	/* can't stage once data_version changes */
 	scoutfs_inode_get_onoff(from, &junk, &from_offline);
 	scoutfs_inode_get_onoff(to, &junk, &to_offline);
-	if (from_offline || (to_offline && !is_stage)) {
+	if (from_offline || to_offline) {
 		ret = -ENODATA;
 		goto out;
 	}
@@ -1253,8 +1246,6 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 
 		/* arbitrarily limit the number of extents per trans hold */
 		for (i = 0; i < MOVE_DATA_EXTENTS_PER_HOLD; i++) {
-			struct scoutfs_extent off_ext;
-
 			/* find the next extent to move */
 			ret = scoutfs_ext_next(sb, &data_ext_ops, &from_args,
 					       from_iblock, 1, &ext);
@@ -1283,27 +1274,10 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 
 			to_start = to_iblock + (from_start - from_iblock);
 
-			if (is_stage) {
-				ret = scoutfs_ext_next(sb, &data_ext_ops, &to_args,
-						       to_iblock, 1, &off_ext);
-				if (ret)
-					break;
-
-				if (!scoutfs_ext_inside(to_start, len, &off_ext) ||
-				    !(off_ext.flags & SEF_OFFLINE)) {
-					ret = -EINVAL;
-					break;
-				}
-
-				ret = scoutfs_ext_set(sb, &data_ext_ops, &to_args,
-							 to_start, len,
-							 map, ext.flags);
-			} else {
-				/* insert the new, fails if it overlaps */
-				ret = scoutfs_ext_insert(sb, &data_ext_ops, &to_args,
-							 to_start, len,
-							 map, ext.flags);
-			}
+			/* insert the new, fails if it overlaps */
+			ret = scoutfs_ext_insert(sb, &data_ext_ops, &to_args,
+						 to_start, len,
+						 map, ext.flags);
 			if (ret < 0)
 				break;
 
@@ -1311,18 +1285,10 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 			ret = scoutfs_ext_set(sb, &data_ext_ops, &from_args,
 					      from_start, len, 0, 0);
 			if (ret < 0) {
-				if (is_stage) {
-					/* re-mark dest range as offline */
-					WARN_ON_ONCE(!(off_ext.flags & SEF_OFFLINE));
-					err = scoutfs_ext_set(sb, &data_ext_ops, &to_args,
-							      to_start, len,
-							      0, off_ext.flags);
-				} else {
-					/* remove inserted new on err */
-					err = scoutfs_ext_remove(sb, &data_ext_ops,
-								 &to_args, to_start,
-								 len);
-				}
+				/* remove inserted new on err */
+				err = scoutfs_ext_remove(sb, &data_ext_ops,
+							 &to_args, to_start,
+							 len);
 				BUG_ON(err); /* XXX inconsistent */
 				break;
 			}
@@ -1350,15 +1316,12 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 		up_write(&from_si->extent_sem);
 		up_write(&to_si->extent_sem);
 
-		cur_time = CURRENT_TIME;
-		if (!is_stage) {
-			to->i_ctime = to->i_mtime = cur_time;
-			scoutfs_inode_inc_data_version(to);
-			scoutfs_inode_set_data_seq(to);
-		}
-		from->i_ctime = from->i_mtime = cur_time;
+		from->i_ctime = from->i_mtime =
+			to->i_ctime = to->i_mtime = CURRENT_TIME;
 		scoutfs_inode_inc_data_version(from);
+		scoutfs_inode_inc_data_version(to);
 		scoutfs_inode_set_data_seq(from);
+		scoutfs_inode_set_data_seq(to);
 
 		scoutfs_update_inode_item(from, from_lock, &locks);
 		scoutfs_update_inode_item(to, to_lock, &locks);

kmod/src/data.h

@@ -59,8 +59,7 @@ long scoutfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len);
 int scoutfs_data_init_offline_extent(struct inode *inode, u64 size,
 				     struct scoutfs_lock *lock);
 int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
-			     u64 byte_len, struct inode *to, u64 to_off, bool to_stage,
-			     u64 data_version);
+			     u64 byte_len, struct inode *to, u64 to_off);
 
 int scoutfs_data_wait_check(struct inode *inode, loff_t pos, loff_t len,
 			    u8 sef, u8 op, struct scoutfs_data_wait *ow,

kmod/src/dir.c

@@ -813,7 +813,6 @@ static int scoutfs_link(struct dentry *old_dentry,
 	struct scoutfs_lock *dir_lock;
 	struct scoutfs_lock *inode_lock = NULL;
 	LIST_HEAD(ind_locks);
-	bool del_orphan;
 	u64 dir_size;
 	u64 ind_seq;
 	u64 hash;
@@ -842,8 +841,6 @@ static int scoutfs_link(struct dentry *old_dentry,
 		goto out_unlock;
 
 	dir_size = i_size_read(dir) + dentry->d_name.len;
-	del_orphan = (inode->i_nlink == 0);
-
 retry:
 	ret = scoutfs_inode_index_start(sb, &ind_seq) ?:
 	      scoutfs_inode_index_prepare(sb, &ind_locks, dir, false) ?:
@@ -858,12 +855,6 @@ retry:
 	if (ret)
 		goto out;
 
-	if (del_orphan) {
-		ret = scoutfs_orphan_dirty(sb, scoutfs_ino(inode));
-		if (ret)
-			goto out;
-	}
-
 	pos = SCOUTFS_I(dir)->next_readdir_pos++;
 
 	ret = add_entry_items(sb, scoutfs_ino(dir), hash, pos,
@@ -879,11 +870,6 @@ retry:
 	inode->i_ctime = dir->i_mtime;
 	inc_nlink(inode);
 
-	if (del_orphan) {
-		ret = scoutfs_orphan_delete(sb, scoutfs_ino(inode));
-		WARN_ON_ONCE(ret);
-	}
-
 	scoutfs_update_inode_item(inode, inode_lock, &ind_locks);
 	scoutfs_update_inode_item(dir, dir_lock, &ind_locks);
 
@@ -1774,42 +1760,6 @@ static int scoutfs_dir_open(struct inode *inode, struct file *file)
 }
 #endif
 
-static int scoutfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
-{
-	struct super_block *sb = dir->i_sb;
-	struct inode *inode = NULL;
-	struct scoutfs_lock *dir_lock = NULL;
-	struct scoutfs_lock *inode_lock = NULL;
-	LIST_HEAD(ind_locks);
-	int ret;
-
-	if (dentry->d_name.len > SCOUTFS_NAME_LEN)
-		return -ENAMETOOLONG;
-
-	inode = lock_hold_create(dir, dentry, mode, 0,
-				 &dir_lock, &inode_lock, &ind_locks);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
-	insert_inode_hash(inode);
-	d_tmpfile(dentry, inode);
-
-	scoutfs_update_inode_item(inode, inode_lock, &ind_locks);
-	scoutfs_update_inode_item(dir, dir_lock, &ind_locks);
-	scoutfs_inode_index_unlock(sb, &ind_locks);
-
-	ret = scoutfs_orphan_inode(inode);
-	WARN_ON_ONCE(ret); /* XXX returning error but items deleted */
-
-	scoutfs_release_trans(sb);
-	scoutfs_inode_index_unlock(sb, &ind_locks);
-	scoutfs_unlock(sb, dir_lock, SCOUTFS_LOCK_WRITE);
-	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_WRITE);
-
-	return ret;
-}
-
 const struct file_operations scoutfs_dir_fops = {
 	.KC_FOP_READDIR	= scoutfs_readdir,
 #ifdef KC_FMODE_KABI_ITERATE
@@ -1820,10 +1770,7 @@ const struct file_operations scoutfs_dir_fops = {
 	.llseek		= generic_file_llseek,
 };
 
-
-
-const struct inode_operations_wrapper scoutfs_dir_iops = {
-	.ops = {
+const struct inode_operations scoutfs_dir_iops = {
 	.lookup		= scoutfs_lookup,
 	.mknod		= scoutfs_mknod,
 	.create		= scoutfs_create,
@@ -1840,8 +1787,6 @@ const struct inode_operations_wrapper scoutfs_dir_iops = {
 	.removexattr	= scoutfs_removexattr,
 	.symlink	= scoutfs_symlink,
 	.permission	= scoutfs_permission,
-	},
-	.tmpfile	= scoutfs_tmpfile,
 };
 
 void scoutfs_dir_exit(void)

kmod/src/dir.h

@@ -5,7 +5,7 @@
 #include "lock.h"
 
 extern const struct file_operations scoutfs_dir_fops;
-extern const struct inode_operations_wrapper scoutfs_dir_iops;
+extern const struct inode_operations scoutfs_dir_iops;
 extern const struct inode_operations scoutfs_symlink_iops;
 
 struct scoutfs_link_backref_entry {
@@ -14,7 +14,7 @@ struct scoutfs_link_backref_entry {
 	u64 dir_pos;
 	u16 name_len;
 	struct scoutfs_dirent dent;
-	/* the full name is allocated and stored in dent.name[] */
+	/* the full name is allocated and stored in dent.name[0] */
 };
 
 int scoutfs_dir_get_backref_path(struct super_block *sb, u64 ino, u64 dir_ino,

kmod/src/ext.c

@@ -38,7 +38,7 @@ static bool ext_overlap(struct scoutfs_extent *ext, u64 start, u64 len)
 	return !(e_end < start || ext->start > end);
 }
 
-bool scoutfs_ext_inside(u64 start, u64 len, struct scoutfs_extent *out)
+static bool ext_inside(u64 start, u64 len, struct scoutfs_extent *out)
 {
 	u64 in_end = start + len - 1;
 	u64 out_end = out->start + out->len - 1;
@@ -241,7 +241,7 @@ int scoutfs_ext_remove(struct super_block *sb, struct scoutfs_ext_ops *ops,
 		goto out;
 
 	/* removed extent must be entirely within found */
-	if (!scoutfs_ext_inside(start, len, &found)) {
+	if (!ext_inside(start, len, &found)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -341,7 +341,7 @@ int scoutfs_ext_set(struct super_block *sb, struct scoutfs_ext_ops *ops,
 
 	if (ret == 0 && ext_overlap(&found, start, len)) {
 		/* set extent must be entirely within found */
-		if (!scoutfs_ext_inside(start, len, &found)) {
+		if (!ext_inside(start, len, &found)) {
 			ret = -EINVAL;
 			goto out;
 		}

kmod/src/ext.h

@@ -31,6 +31,5 @@ int scoutfs_ext_alloc(struct super_block *sb, struct scoutfs_ext_ops *ops,
 		      struct scoutfs_extent *ext);
 int scoutfs_ext_set(struct super_block *sb, struct scoutfs_ext_ops *ops,
 		    void *arg, u64 start, u64 len, u64 map, u8 flags);
-bool scoutfs_ext_inside(u64 start, u64 len, struct scoutfs_extent *out);
 
 #endif

kmod/src/forest.c

@@ -276,6 +276,7 @@ int scoutfs_forest_read_items(struct super_block *sb,
 	scoutfs_inc_counter(sb, forest_read_items);
 	calc_bloom_nrs(&bloom, &lock->start);
 
+	roots = lock->roots;
 retry:
 	ret = scoutfs_client_get_roots(sb, &roots);
 	if (ret)
@@ -348,9 +349,15 @@ retry:
 	ret = 0;
 out:
 	if (ret == -ESTALE) {
-		if (memcmp(&prev_refs, &refs, sizeof(refs)) == 0)
-			return -EIO;
+		if (memcmp(&prev_refs, &refs, sizeof(refs)) == 0) {
+			ret = -EIO;
+			goto out;
+		}
 		prev_refs = refs;
+
+		ret = scoutfs_client_get_roots(sb, &roots);
+		if (ret)
+			goto out;
 		goto retry;
 	}
 

kmod/src/format.h

@@ -259,7 +259,7 @@ struct scoutfs_btree_block {
 	__le16 mid_free_len;
 	__u8 level;
 	__u8 __pad[7];
-	struct scoutfs_btree_item items[];
+	struct scoutfs_btree_item items[0];
 	/* leaf blocks have a fixed size item offset hash table at the end */
 };
 
@@ -307,7 +307,7 @@ struct scoutfs_alloc_list_block {
 	struct scoutfs_block_ref next;
 	__le32 start;
 	__le32 nr;
-	__le64 blknos[]; /* naturally aligned for sorting */
+	__le64 blknos[0]; /* naturally aligned for sorting */
 };
 
 #define SCOUTFS_ALLOC_LIST_MAX_BLOCKS					      \
@@ -362,7 +362,7 @@ struct scoutfs_srch_file {
 
 struct scoutfs_srch_parent {
 	struct scoutfs_block_header hdr;
-	struct scoutfs_block_ref refs[];
+	struct scoutfs_block_ref refs[0];
 };
 
 #define SCOUTFS_SRCH_PARENT_REFS				\
@@ -377,7 +377,7 @@ struct scoutfs_srch_block {
 	struct scoutfs_srch_entry tail;
 	__le32 entry_nr;
 	__le32 entry_bytes;
-	__u8 entries[];
+	__u8 entries[0];
 };
 
 /*
@@ -452,7 +452,7 @@ struct scoutfs_log_item_value {
 	__le64 vers;
 	__u8 flags;
 	__u8 __pad[7];
-	__u8 data[];
+	__u8 data[0];
 };
 
 /*
@@ -467,7 +467,7 @@ struct scoutfs_log_item_value {
 struct scoutfs_bloom_block {
 	struct scoutfs_block_header hdr;
 	__le64 total_set;
-	__le64 bits[];
+	__le64 bits[0];
 };
 
 /*
@@ -549,7 +549,7 @@ struct scoutfs_xattr {
 	__le16 val_len;
 	__u8 name_len;
 	__u8 __pad[5];
-	__u8 name[];
+	__u8 name[0];
 };
 
 
@@ -729,7 +729,7 @@ struct scoutfs_dirent {
 	__le64 pos;
 	__u8 type;
 	__u8 __pad[7];
-	__u8 name[];
+	__u8 name[0];
 };
 
 #define SCOUTFS_NAME_LEN 255
@@ -827,7 +827,7 @@ struct scoutfs_net_header {
 	__u8 flags;
 	__u8 error;
 	__u8 __pad[3];
-	__u8 data[];
+	__u8 data[0];
 };
 
 #define SCOUTFS_NET_FLAG_RESPONSE	(1 << 0)
@@ -895,10 +895,15 @@ struct scoutfs_net_lock {
 	__u8 __pad[6];
 };
 
+struct scoutfs_net_lock_grant_response {
+	struct scoutfs_net_lock nl;
+	struct scoutfs_net_roots roots;
+};
+
 struct scoutfs_net_lock_recover {
 	__le16 nr;
 	__u8 __pad[6];
-	struct scoutfs_net_lock locks[];
+	struct scoutfs_net_lock locks[0];
 };
 
 #define SCOUTFS_NET_LOCK_MAX_RECOVER_NR					       \

kmod/src/inode.c

@@ -182,8 +182,7 @@ static void set_inode_ops(struct inode *inode)
 		inode->i_fop = &scoutfs_file_fops;
 		break;
 	case S_IFDIR:
-		inode->i_op = &scoutfs_dir_iops.ops;
-		inode->i_flags |= S_IOPS_WRAPPER;
+		inode->i_op = &scoutfs_dir_iops;
 		inode->i_fop = &scoutfs_dir_fops;
 		break;
 	case S_IFLNK:
@@ -1418,18 +1417,7 @@ static void init_orphan_key(struct scoutfs_key *key, u64 rid, u64 ino)
 	};
 }
 
-int scoutfs_orphan_dirty(struct super_block *sb, u64 ino)
-{
-	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct scoutfs_lock *lock = sbi->rid_lock;
-	struct scoutfs_key key;
-
-	init_orphan_key(&key, sbi->rid, ino);
-
-	return scoutfs_item_dirty(sb, &key, lock);
-}
-
-int scoutfs_orphan_delete(struct super_block *sb, u64 ino)
+static int remove_orphan_item(struct super_block *sb, u64 ino)
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct scoutfs_lock *lock = sbi->rid_lock;
@@ -1528,7 +1516,7 @@ retry:
 	if (ret)
 		goto out;
 
-	ret = scoutfs_orphan_delete(sb, ino);
+	ret = remove_orphan_item(sb, ino);
 out:
 	if (release)
 		scoutfs_release_trans(sb);

kmod/src/inode.h

@@ -114,8 +114,6 @@ int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 int scoutfs_setattr(struct dentry *dentry, struct iattr *attr);
 
 int scoutfs_scan_orphans(struct super_block *sb);
-int scoutfs_orphan_dirty(struct super_block *sb, u64 ino);
-int scoutfs_orphan_delete(struct super_block *sb, u64 ino);
 
 void scoutfs_inode_queue_writeback(struct inode *inode);
 int scoutfs_inode_walk_writeback(struct super_block *sb, bool write);

kmod/src/ioctl.c

@@ -972,18 +972,12 @@ static long scoutfs_ioc_move_blocks(struct file *file, unsigned long arg)
 		goto out;
 	}
 
-	if (mb.flags & SCOUTFS_IOC_MB_UNKNOWN) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	ret = mnt_want_write_file(file);
 	if (ret < 0)
 		goto out;
 
 	ret = scoutfs_data_move_blocks(from, mb.from_off, mb.len,
-				       to, mb.to_off, !!(mb.flags & SCOUTFS_IOC_MB_STAGE),
-				       mb.data_version);
+				       to, mb.to_off);
 	mnt_drop_write_file(file);
 out:
 	fput(from_file);

kmod/src/ioctl.h

@@ -163,7 +163,7 @@ struct scoutfs_ioctl_ino_path_result {
 	__u64 dir_pos;
 	__u16 path_bytes;
 	__u8  _pad[6];
-	__u8  path[];
+	__u8  path[0];
 };
 
 /* Get a single path from the root to the given inode number */
@@ -259,7 +259,7 @@ struct scoutfs_ioctl_data_waiting {
 	__u8 _pad[6];
 };
 
-#define SCOUTFS_IOC_DATA_WAITING_FLAGS_UNKNOWN		(U64_MAX << 0)
+#define SCOUTFS_IOC_DATA_WAITING_FLAGS_UNKNOWN		(U8_MAX << 0)
 
 #define SCOUTFS_IOC_DATA_WAITING _IOR(SCOUTFS_IOCTL_MAGIC, 6, \
 				      struct scoutfs_ioctl_data_waiting)
@@ -279,7 +279,7 @@ struct scoutfs_ioctl_setattr_more {
 };
 
 #define SCOUTFS_IOC_SETATTR_MORE_OFFLINE		(1 << 0)
-#define SCOUTFS_IOC_SETATTR_MORE_UNKNOWN		(U64_MAX << 1)
+#define SCOUTFS_IOC_SETATTR_MORE_UNKNOWN		(U8_MAX << 1)
 
 #define SCOUTFS_IOC_SETATTR_MORE _IOW(SCOUTFS_IOCTL_MAGIC, 7, \
 				      struct scoutfs_ioctl_setattr_more)
@@ -418,13 +418,12 @@ struct scoutfs_ioctl_alloc_detail_entry {
  * on the same file system.
  *
  * from_fd specifies the source file and the ioctl is called on the
- * destination file.  Both files must have write access.  from_off specifies
- * the byte offset in the source, to_off is the byte offset in the
- * destination, and len is the number of bytes in the region to move.  All of
- * the offsets and lengths must be in multiples of 4KB, except in the case
- * where the from_off + len ends at the i_size of the source
- * file. data_version is only used when STAGE flag is set (see below).  flags
- * field is currently only used to optionally specify STAGE behavior.
+ * destination file.  Both files must have write access.  from_off
+ * specifies the byte offset in the source, to_off is the byte offset in
+ * the destination, and len is the number of bytes in the region to
+ * move.   All of the offsets and lengths must be in multiples of 4KB,
+ * except in the case where the from_off + len ends at the i_size of the
+ * source file.
  *
  * This interface only moves extents which are block granular, it does
  * not perform RMW of sub-block byte extents and it does not overwrite
@@ -436,41 +435,30 @@ struct scoutfs_ioctl_alloc_detail_entry {
  * i_size.  The i_size update will maintain final partial blocks in the
  * source.
  *
- * If STAGE flag is not set, it will return an error if either of the files
- * have offline extents.  It will return 0 when all of the extents in the
- * source region have been moved to the destination.  Moving extents updates
- * the ctime, mtime, meta_seq, data_seq, and data_version fields of both the
- * source and destination inodes.  If an error is returned then partial
+ * It will return an error if either of the files have offline extents.
+ * It will return 0 when all of the extents in the source region have
+ * been moved to the destination.  Moving extents updates the ctime,
+ * mtime, meta_seq, data_seq, and data_version fields of both the source
+ * and destination inodes.  If an error is returned then partial
  * progress may have been made and inode fields may have been updated.
  *
- * If STAGE flag is set, as above except destination range must be in an
- * offline extent. Fields are updated only for source inode.
- *
  * Errors specific to this interface include:
  *
  * EINVAL: from_off, len, or to_off aren't a multiple of 4KB; the source
  *	   and destination files are the same inode; either the source or
  *	   destination is not a regular file; the destination file has
- *	   an existing overlapping extent (if STAGE flag not set); the
- *	   destination range is not in an offline extent (if STAGE set).
+ *	   an existing overlapping extent.
  * EOVERFLOW: either from_off + len or to_off + len exceeded 64bits.
  * EBADF: from_fd isn't a valid open file descriptor.
  * EXDEV: the source and destination files are in different filesystems.
  * EISDIR: either the source or destination is a directory.
- * ENODATA: either the source or destination file have offline extents and
- *	    STAGE flag is not set.
- * ESTALE: data_version does not match destination data_version.
+ * ENODATA: either the source or destination file have offline extents.
  */
-#define SCOUTFS_IOC_MB_STAGE		(1 << 0)
-#define SCOUTFS_IOC_MB_UNKNOWN		(U64_MAX << 1)
-
 struct scoutfs_ioctl_move_blocks {
 	__u64 from_fd;
 	__u64 from_off;
 	__u64 len;
 	__u64 to_off;
-	__u64 data_version;
-	__u64 flags;
 };
 
 #define SCOUTFS_IOC_MOVE_BLOCKS _IOR(SCOUTFS_IOCTL_MAGIC, 13, \

kmod/src/lock.c

@@ -638,6 +638,7 @@ static void lock_grant_worker(struct work_struct *work)
 	struct lock_info *linfo = container_of(work, struct lock_info,
 					       grant_work);
 	struct super_block *sb = linfo->sb;
+	struct scoutfs_net_lock_grant_response *gr;
 	struct scoutfs_net_lock *nl;
 	struct scoutfs_lock *lock;
 	struct scoutfs_lock *tmp;
@@ -647,7 +648,8 @@ static void lock_grant_worker(struct work_struct *work)
 	spin_lock(&linfo->lock);
 
 	list_for_each_entry_safe(lock, tmp, &linfo->grant_list, grant_head) {
-		nl = &lock->grant_nl;
+		gr = &lock->grant_resp;
+		nl = &lock->grant_resp.nl;
 
 		/* wait for reordered invalidation to finish */
 		if (lock->mode != nl->old_mode)
@@ -665,6 +667,7 @@ static void lock_grant_worker(struct work_struct *work)
 		lock->request_pending = 0;
 		lock->mode = nl->new_mode;
 		lock->write_version = le64_to_cpu(nl->write_version);
+		lock->roots = gr->roots;
 
 		if (lock_count_match_exists(nl->new_mode, lock->waiters))
 			extend_grace(sb, lock);
@@ -686,8 +689,9 @@ static void lock_grant_worker(struct work_struct *work)
  * work to process.
  */
 int scoutfs_lock_grant_response(struct super_block *sb,
-				struct scoutfs_net_lock *nl)
+				struct scoutfs_net_lock_grant_response *gr)
 {
+	struct scoutfs_net_lock *nl = &gr->nl;
 	DECLARE_LOCK_INFO(sb, linfo);
 	struct scoutfs_lock *lock;
 
@@ -701,7 +705,7 @@ int scoutfs_lock_grant_response(struct super_block *sb,
 	trace_scoutfs_lock_grant_response(sb, lock);
 	BUG_ON(!lock->request_pending);
 
-	lock->grant_nl = *nl;
+	lock->grant_resp = *gr;
 	list_add_tail(&lock->grant_head, &linfo->grant_list);
 	queue_grant_work(linfo);
 

kmod/src/lock.h

@@ -23,6 +23,7 @@ struct scoutfs_lock {
 	u64 refresh_gen;
 	u64 write_version;
 	u64 dirty_trans_seq;
+	struct scoutfs_net_roots roots;
 	struct list_head lru_head;
 	wait_queue_head_t waitq;
 	ktime_t grace_deadline;
@@ -30,7 +31,7 @@ struct scoutfs_lock {
 		      invalidate_pending:1;
 
 	struct list_head grant_head;
-	struct scoutfs_net_lock grant_nl;
+	struct scoutfs_net_lock_grant_response grant_resp;
 	struct list_head inv_head;
 	struct scoutfs_net_lock inv_nl;
 	u64 inv_net_id;
@@ -56,7 +57,7 @@ struct scoutfs_lock_coverage {
 };
 
 int scoutfs_lock_grant_response(struct super_block *sb,
-				struct scoutfs_net_lock *nl);
+				struct scoutfs_net_lock_grant_response *gr);
 int scoutfs_lock_invalidate_request(struct super_block *sb, u64 net_id,
 				    struct scoutfs_net_lock *nl);
 int scoutfs_lock_recover_request(struct super_block *sb, u64 net_id,

kmod/src/lock_server.c

@@ -484,6 +484,7 @@ static int process_waiting_requests(struct super_block *sb,
 				    struct server_lock_node *snode)
 {
 	DECLARE_LOCK_SERVER_INFO(sb, inf);
+	struct scoutfs_net_lock_grant_response gres;
 	struct scoutfs_net_lock nl;
 	struct client_lock_entry *req;
 	struct client_lock_entry *req_tmp;
@@ -546,8 +547,11 @@ static int process_waiting_requests(struct super_block *sb,
 			nl.write_version = cpu_to_le64(wv);
 		}
 
+		gres.nl = nl;
+		scoutfs_server_get_roots(sb, &gres.roots);
+
 		ret = scoutfs_server_lock_response(sb, req->rid,
-						   req->net_id, &nl);
+						   req->net_id, &gres);
 		if (ret)
 			goto out;
 

kmod/src/net.c

@@ -944,6 +944,7 @@ static void scoutfs_net_listen_worker(struct work_struct *work)
 	struct scoutfs_net_connection *acc_conn;
 	DECLARE_WAIT_QUEUE_HEAD(waitq);
 	struct socket *acc_sock;
+	LIST_HEAD(conn_list);
 	int ret;
 
 	trace_scoutfs_net_listen_work_enter(sb, 0, 0);

kmod/src/server.c

@@ -182,7 +182,7 @@ int scoutfs_server_apply_commit(struct super_block *sb, int err)
 	return err;
 }
 
-static void get_roots(struct super_block *sb,
+void scoutfs_server_get_roots(struct super_block *sb,
 			      struct scoutfs_net_roots *roots)
 {
 	DECLARE_SERVER_INFO(sb, server);
@@ -556,7 +556,7 @@ static int server_get_roots(struct super_block *sb,
 		memset(&roots, 0, sizeof(roots));
 		ret = -EINVAL;
 	}  else {
-		get_roots(sb, &roots);
+		scoutfs_server_get_roots(sb, &roots);
 		ret = 0;
 	}
 
@@ -862,13 +862,13 @@ int scoutfs_server_lock_request(struct super_block *sb, u64 rid,
 }
 
 int scoutfs_server_lock_response(struct super_block *sb, u64 rid, u64 id,
-				 struct scoutfs_net_lock *nl)
+				 struct scoutfs_net_lock_grant_response *gr)
 {
 	struct server_info *server = SCOUTFS_SB(sb)->server_info;
 
 	return scoutfs_net_response_node(sb, server->conn, rid,
 					 SCOUTFS_NET_CMD_LOCK, id, 0,
-					 nl, sizeof(*nl));
+					 gr, sizeof(*gr));
 }
 
 static bool invalid_recover(struct scoutfs_net_lock_recover *nlr,
@@ -1551,6 +1551,7 @@ static void scoutfs_server_worker(struct work_struct *work)
 	struct scoutfs_net_connection *conn = NULL;
 	DECLARE_WAIT_QUEUE_HEAD(waitq);
 	struct sockaddr_in sin;
+	LIST_HEAD(conn_list);
 	u64 max_vers;
 	int ret;
 

kmod/src/server.h

@@ -59,9 +59,11 @@ do {								\
 int scoutfs_server_lock_request(struct super_block *sb, u64 rid,
 				struct scoutfs_net_lock *nl);
 int scoutfs_server_lock_response(struct super_block *sb, u64 rid, u64 id,
-				 struct scoutfs_net_lock *nl);
+				 struct scoutfs_net_lock_grant_response *gr);
 int scoutfs_server_lock_recover_request(struct super_block *sb, u64 rid,
 					struct scoutfs_key *key);
+void scoutfs_server_get_roots(struct super_block *sb,
+			      struct scoutfs_net_roots *roots);
 int scoutfs_server_hold_commit(struct super_block *sb);
 int scoutfs_server_apply_commit(struct super_block *sb, int err);
 

kmod/src/srch.c

@@ -2156,8 +2156,7 @@ static void scoutfs_srch_compact_worker(struct work_struct *work)
 	if (ret < 0)
 		goto commit;
 
-	ret = scoutfs_alloc_prepare_commit(sb, &alloc, &wri) ?:
-	      scoutfs_block_writer_write(sb, &wri);
+	ret = scoutfs_block_writer_write(sb, &wri);
 commit:
 	/* the server won't use our partial compact if _ERROR is set */
 	sc->meta_avail = alloc.avail;

tests/Makefile

@@ -1,4 +1,4 @@
-CFLAGS := -Wall -O2 -Werror -D_FILE_OFFSET_BITS=64 -fno-strict-aliasing -I ../kmod/src
+CFLAGS := -Wall -O2 -Werror -D_FILE_OFFSET_BITS=64 -fno-strict-aliasing 
 SHELL := /usr/bin/bash
 
 # each binary command is built from a single .c file
@@ -6,7 +6,6 @@ BIN := src/createmany			\
 	src/dumb_setxattr		\
 	src/handle_cat			\
 	src/bulk_create_paths		\
-	src/stage_tmpfile		\
 	src/find_xattrs
 
 DEPS := $(wildcard src/*.d)

tests/golden/stage-tmpfile

@@ -1,18 +0,0 @@
-total file size 33669120
-00000000  41 41 41 41 41 41 41 41  41 41 41 41 41 41 41 41  |AAAAAAAAAAAAAAAA|
-*
-00400000  42 42 42 42 42 42 42 42  42 42 42 42 42 42 42 42  |BBBBBBBBBBBBBBBB|
-*
-00801000  43 43 43 43 43 43 43 43  43 43 43 43 43 43 43 43  |CCCCCCCCCCCCCCCC|
-*
-00c03000  44 44 44 44 44 44 44 44  44 44 44 44 44 44 44 44  |DDDDDDDDDDDDDDDD|
-*
-01006000  45 45 45 45 45 45 45 45  45 45 45 45 45 45 45 45  |EEEEEEEEEEEEEEEE|
-*
-0140a000  46 46 46 46 46 46 46 46  46 46 46 46 46 46 46 46  |FFFFFFFFFFFFFFFF|
-*
-0180f000  47 47 47 47 47 47 47 47  47 47 47 47 47 47 47 47  |GGGGGGGGGGGGGGGG|
-*
-01c15000  48 48 48 48 48 48 48 48  48 48 48 48 48 48 48 48  |HHHHHHHHHHHHHHHH|
-*
-0201c000

tests/golden/xfstests

@@ -1,7 +1,6 @@
 Ran:
 generic/001
 generic/002
-generic/004
 generic/005
 generic/006
 generic/007
@@ -74,6 +73,7 @@ generic/376
 generic/377
 Not
 run:
+generic/004
 generic/008
 generic/009
 generic/012
@@ -278,4 +278,4 @@ shared/004
 shared/032
 shared/051
 shared/289
-Passed all 73 tests
+Passed all 72 tests

tests/sequence

@@ -18,7 +18,6 @@ createmany-large-names.sh
 createmany-rename-large-dir.sh
 stage-release-race-alloc.sh
 stage-multi-part.sh
-stage-tmpfile.sh
 basic-posix-consistency.sh
 dirent-consistency.sh
 lock-ex-race-processes.sh

tests/src/stage_tmpfile.c

@@ -1,145 +0,0 @@
-/*
- * Exercise O_TMPFILE creation as well as staging from tmpfiles into
- * a released destination file.
- *
- * Copyright (C) 2021 Versity Software, Inc.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
-
-#ifndef _GNU_SOURCE
-#define _GNU_SOURCE
-#endif
-#include <unistd.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <linux/types.h>
-#include <assert.h>
-
-#include "ioctl.h"
-
-#define array_size(arr) (sizeof(arr) / sizeof(arr[0]))
-
-/*
- * Write known data into 8 tmpfiles.
- * Make a new file X and release it
- * Move contents of 8 tmpfiles into X.
- */
-
-struct sub_tmp_info {
-	int fd;
-	unsigned int offset;
-	unsigned int length;
-};
-
-#define SZ	4096
-char buf[SZ];
-
-int main(int argc, char **argv)
-{
-	struct scoutfs_ioctl_release ioctl_args = {0};
-	struct scoutfs_ioctl_move_blocks mb;
-	struct sub_tmp_info sub_tmps[8];
-	int tot_size = 0;
-	char *dest_file;
-	int dest_fd;
-	char *mnt;
-	int ret;
-	int i;
-
-	if (argc < 3) {
-		printf("%s <mountpoint> <dest_file>\n", argv[0]);
-		return 1;
-	}
-
-	mnt = argv[1];
-	dest_file = argv[2];
-
-	for (i = 0; i < array_size(sub_tmps); i++) {
-		struct sub_tmp_info *sub_tmp = &sub_tmps[i];
-		int remaining;
-
-		sub_tmp->fd = open(mnt, O_RDWR | O_TMPFILE, S_IRUSR | S_IWUSR);
-		if (sub_tmp->fd < 0) {
-			perror("error");
-			exit(1);
-		}
-
-		sub_tmp->offset = tot_size;
-
-		/* First tmp file is 4MB */
-		/* Each is 4k bigger than last */
-		sub_tmp->length = (i + 1024) * sizeof(buf);
-
-		remaining = sub_tmp->length;
-
-		/* Each sub tmpfile written with 'A', 'B', etc. */
-		memset(buf, 'A' + i, sizeof(buf));
-		while (remaining) {
-			int written;
-
-			written = write(sub_tmp->fd, buf, sizeof(buf));
-			assert(written == sizeof(buf));
-			tot_size += sizeof(buf);
-			remaining -= written;
-		}
-	}
-
-	printf("total file size %d\n", tot_size);
-
-	dest_fd = open(dest_file, O_RDWR | O_CREAT, S_IRUSR | S_IWUSR);
-	if (dest_fd == -1) {
-		perror("error");
-		exit(1);
-	}
-
-	// make dest file big
-	ret = posix_fallocate(dest_fd, 0, tot_size);
-	if (ret) {
-		perror("error");
-		exit(1);
-	}
-
-	// release everything in dest file
-	ioctl_args.offset = 0;
-	ioctl_args.length = tot_size;
-	ioctl_args.data_version = 0;
-
-	ret = ioctl(dest_fd, SCOUTFS_IOC_RELEASE, &ioctl_args);
-	if (ret < 0) {
-		perror("error");
-		exit(1);
-	}
-
-	// move contents into dest in reverse order
-	for (i = array_size(sub_tmps) - 1; i >= 0 ; i--) {
-		struct sub_tmp_info *sub_tmp = &sub_tmps[i];
-
-		mb.from_fd = sub_tmp->fd;
-		mb.from_off = 0;
-		mb.len = sub_tmp->length;
-		mb.to_off = sub_tmp->offset;
-		mb.data_version = 0;
-		mb.flags = SCOUTFS_IOC_MB_STAGE;
-
-		ret = ioctl(dest_fd, SCOUTFS_IOC_MOVE_BLOCKS, &mb);
-		if (ret < 0) {
-			perror("error");
-			exit(1);
-		}
-
-	}
-
-	return 0;
-}

tests/tests/stage-tmpfile.sh

@@ -1,15 +0,0 @@
-#
-# Run tmpfile_stage and check the output with hexdump.
-#
-
-t_require_commands stage_tmpfile hexdump
-
-DEST_FILE="$T_D0/dest_file"
-
-stage_tmpfile $T_D0 $DEST_FILE
-
-hexdump -C "$DEST_FILE"
-
-rm -fr "$DEST_FILE"
-
-t_pass

utils/src/move_blocks.c

@@ -32,7 +32,7 @@ struct move_blocks_args {
 
 static int do_move_blocks(struct move_blocks_args *args)
 {
-	struct scoutfs_ioctl_move_blocks mb = {0};
+	struct scoutfs_ioctl_move_blocks mb;
 	int from_fd = -1;
 	int to_fd = -1;
 	int ret;