1 files changed, 168 insertions, 74 deletions

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 8fd195cfe81b..1f5748c7d1c7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -26,10 +26,11 @@
 #include <linux/radix-tree.h>
 #include <linux/vmalloc.h>
 #include <linux/string.h>
+#include <linux/compat.h>
+#include <linux/crc32c.h>
 
 #include "send.h"
 #include "backref.h"
-#include "hash.h"
 #include "locking.h"
 #include "disk-io.h"
 #include "btrfs_inode.h"
@@ -111,6 +112,7 @@ struct send_ctx {
 	u64 cur_inode_mode;
 	u64 cur_inode_rdev;
 	u64 cur_inode_last_extent;
+	u64 cur_inode_next_write_offset;
 
 	u64 send_progress;
 
@@ -269,6 +271,7 @@ struct name_cache_entry {
 	char name[];
 };
 
+__cold
 static void inconsistent_snapshot_error(struct send_ctx *sctx,
 					enum btrfs_compare_tree_result result,
 					const char *what)
@@ -610,9 +613,9 @@ static int tlv_put_btrfs_timespec(struct send_ctx *sctx, u16 attr,
 }
 
 
-#define TLV_PUT(sctx, attrtype, attrlen, data) \
+#define TLV_PUT(sctx, attrtype, data, attrlen) \
 	do { \
-		ret = tlv_put(sctx, attrtype, attrlen, data); \
+		ret = tlv_put(sctx, attrtype, data, attrlen); \
 		if (ret < 0) \
 			goto tlv_put_failure; \
 	} while (0)
@@ -694,7 +697,7 @@ static int send_cmd(struct send_ctx *sctx)
 	hdr->len = cpu_to_le32(sctx->send_size - sizeof(*hdr));
 	hdr->crc = 0;
 
-	crc = btrfs_crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
+	crc = crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
 	hdr->crc = cpu_to_le32(crc);
 
 	ret = write_buf(sctx->send_filp, sctx->send_buf, sctx->send_size,
@@ -992,7 +995,6 @@ typedef int (*iterate_dir_item_t)(int num, struct btrfs_key *di_key,
  * path must point to the dir item when called.
  */
 static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
-			    struct btrfs_key *found_key,
 			    iterate_dir_item_t iterate, void *ctx)
 {
 	int ret = 0;
@@ -1059,12 +1061,6 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 			}
 		}
 
-		ret = btrfs_is_name_len_valid(eb, path->slots[0],
-			  (unsigned long)(di + 1), name_len + data_len);
-		if (!ret) {
-			ret = -EIO;
-			goto out;
-		}
 		if (name_len + data_len > buf_len) {
 			buf_len = name_len + data_len;
 			if (is_vmalloc_addr(buf)) {
@@ -1271,12 +1267,6 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
 		 */
 		if (ino >= bctx->cur_objectid)
 			return 0;
-#if 0
-		if (ino > bctx->cur_objectid)
-			return 0;
-		if (offset + bctx->extent_len > bctx->cur_offset)
-			return 0;
-#endif
 	}
 
 	bctx->found++;
@@ -1429,7 +1419,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 		extent_item_pos = 0;
 	ret = iterate_extent_inodes(fs_info, found_key.objectid,
 				    extent_item_pos, 1, __iterate_backrefs,
-				    backref_ctx);
+				    backref_ctx, false);
 
 	if (ret < 0)
 		goto out;
@@ -3527,7 +3517,40 @@ out:
 }
 
 /*
- * Check if ino ino1 is an ancestor of inode ino2 in the given root.
+ * Check if inode ino2, or any of its ancestors, is inode ino1.
+ * Return 1 if true, 0 if false and < 0 on error.
+ */
+static int check_ino_in_path(struct btrfs_root *root,
+			     const u64 ino1,
+			     const u64 ino1_gen,
+			     const u64 ino2,
+			     const u64 ino2_gen,
+			     struct fs_path *fs_path)
+{
+	u64 ino = ino2;
+
+	if (ino1 == ino2)
+		return ino1_gen == ino2_gen;
+
+	while (ino > BTRFS_FIRST_FREE_OBJECTID) {
+		u64 parent;
+		u64 parent_gen;
+		int ret;
+
+		fs_path_reset(fs_path);
+		ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
+		if (ret < 0)
+			return ret;
+		if (parent == ino1)
+			return parent_gen == ino1_gen;
+		ino = parent;
+	}
+	return 0;
+}
+
+/*
+ * Check if ino ino1 is an ancestor of inode ino2 in the given root for any
+ * possible path (in case ino2 is not a directory and has multiple hard links).
  * Return 1 if true, 0 if false and < 0 on error.
  */
 static int is_ancestor(struct btrfs_root *root,
@@ -3536,36 +3559,91 @@ static int is_ancestor(struct btrfs_root *root,
 		       const u64 ino2,
 		       struct fs_path *fs_path)
 {
-	u64 ino = ino2;
-	bool free_path = false;
+	bool free_fs_path = false;
 	int ret = 0;
+	struct btrfs_path *path = NULL;
+	struct btrfs_key key;
 
 	if (!fs_path) {
 		fs_path = fs_path_alloc();
 		if (!fs_path)
 			return -ENOMEM;
-		free_path = true;
+		free_fs_path = true;
 	}
 
-	while (ino > BTRFS_FIRST_FREE_OBJECTID) {
-		u64 parent;
-		u64 parent_gen;
+	path = alloc_path_for_send();
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
-		fs_path_reset(fs_path);
-		ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
-		if (ret < 0) {
-			if (ret == -ENOENT && ino == ino2)
-				ret = 0;
-			goto out;
+	key.objectid = ino2;
+	key.type = BTRFS_INODE_REF_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	while (true) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+		u32 cur_offset = 0;
+		u32 item_size;
+
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			if (ret > 0)
+				break;
+			continue;
 		}
-		if (parent == ino1) {
-			ret = parent_gen == ino1_gen ? 1 : 0;
-			goto out;
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid != ino2)
+			break;
+		if (key.type != BTRFS_INODE_REF_KEY &&
+		    key.type != BTRFS_INODE_EXTREF_KEY)
+			break;
+
+		item_size = btrfs_item_size_nr(leaf, slot);
+		while (cur_offset < item_size) {
+			u64 parent;
+			u64 parent_gen;
+
+			if (key.type == BTRFS_INODE_EXTREF_KEY) {
+				unsigned long ptr;
+				struct btrfs_inode_extref *extref;
+
+				ptr = btrfs_item_ptr_offset(leaf, slot);
+				extref = (struct btrfs_inode_extref *)
+					(ptr + cur_offset);
+				parent = btrfs_inode_extref_parent(leaf,
+								   extref);
+				cur_offset += sizeof(*extref);
+				cur_offset += btrfs_inode_extref_name_len(leaf,
+								  extref);
+			} else {
+				parent = key.offset;
+				cur_offset = item_size;
+			}
+
+			ret = get_inode_info(root, parent, NULL, &parent_gen,
+					     NULL, NULL, NULL, NULL);
+			if (ret < 0)
+				goto out;
+			ret = check_ino_in_path(root, ino1, ino1_gen,
+						parent, parent_gen, fs_path);
+			if (ret)
+				goto out;
 		}
-		ino = parent;
+		path->slots[0]++;
 	}
+	ret = 0;
  out:
-	if (free_path)
+	btrfs_free_path(path);
+	if (free_fs_path)
 		fs_path_free(fs_path);
 	return ret;
 }
@@ -4106,8 +4184,8 @@ out:
 	return ret;
 }
 
-static int record_ref(struct btrfs_root *root, int num, u64 dir, int index,
-		      struct fs_path *name, void *ctx, struct list_head *refs)
+static int record_ref(struct btrfs_root *root, u64 dir, struct fs_path *name,
+		      void *ctx, struct list_head *refs)
 {
 	int ret = 0;
 	struct send_ctx *sctx = ctx;
@@ -4143,8 +4221,7 @@ static int __record_new_ref(int num, u64 dir, int index,
 			    void *ctx)
 {
 	struct send_ctx *sctx = ctx;
-	return record_ref(sctx->send_root, num, dir, index, name,
-			  ctx, &sctx->new_refs);
+	return record_ref(sctx->send_root, dir, name, ctx, &sctx->new_refs);
 }
 
 
@@ -4153,8 +4230,8 @@ static int __record_deleted_ref(int num, u64 dir, int index,
 				void *ctx)
 {
 	struct send_ctx *sctx = ctx;
-	return record_ref(sctx->parent_root, num, dir, index, name,
-			  ctx, &sctx->deleted_refs);
+	return record_ref(sctx->parent_root, dir, name, ctx,
+			  &sctx->deleted_refs);
 }
 
 static int record_new_ref(struct send_ctx *sctx)
@@ -4498,7 +4575,7 @@ static int process_new_xattr(struct send_ctx *sctx)
 	int ret = 0;
 
 	ret = iterate_dir_item(sctx->send_root, sctx->left_path,
-			       sctx->cmp_key, __process_new_xattr, sctx);
+			       __process_new_xattr, sctx);
 
 	return ret;
 }
@@ -4506,7 +4583,7 @@ static int process_new_xattr(struct send_ctx *sctx)
 static int process_deleted_xattr(struct send_ctx *sctx)
 {
 	return iterate_dir_item(sctx->parent_root, sctx->right_path,
-				sctx->cmp_key, __process_deleted_xattr, sctx);
+				__process_deleted_xattr, sctx);
 }
 
 struct find_xattr_ctx {
@@ -4551,7 +4628,7 @@ static int find_xattr(struct btrfs_root *root,
 	ctx.found_data = NULL;
 	ctx.found_data_len = 0;
 
-	ret = iterate_dir_item(root, path, key, __find_xattr, &ctx);
+	ret = iterate_dir_item(root, path, __find_xattr, &ctx);
 	if (ret < 0)
 		return ret;
 
@@ -4621,11 +4698,11 @@ static int process_changed_xattr(struct send_ctx *sctx)
 	int ret = 0;
 
 	ret = iterate_dir_item(sctx->send_root, sctx->left_path,
-			sctx->cmp_key, __process_changed_new_xattr, sctx);
+			__process_changed_new_xattr, sctx);
 	if (ret < 0)
 		goto out;
 	ret = iterate_dir_item(sctx->parent_root, sctx->right_path,
-			sctx->cmp_key, __process_changed_deleted_xattr, sctx);
+			__process_changed_deleted_xattr, sctx);
 
 out:
 	return ret;
@@ -4675,8 +4752,7 @@ static int process_all_new_xattrs(struct send_ctx *sctx)
 			goto out;
 		}
 
-		ret = iterate_dir_item(root, path, &found_key,
-				       __process_new_xattr, sctx);
+		ret = iterate_dir_item(root, path, __process_new_xattr, sctx);
 		if (ret < 0)
 			goto out;
 
@@ -4723,16 +4799,27 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	/* initial readahead */
 	memset(&sctx->ra, 0, sizeof(struct file_ra_state));
 	file_ra_state_init(&sctx->ra, inode->i_mapping);
-	page_cache_sync_readahead(inode->i_mapping, &sctx->ra, NULL, index,
-		       last_index - index + 1);
 
 	while (index <= last_index) {
 		unsigned cur_len = min_t(unsigned, len,
 					 PAGE_SIZE - pg_offset);
-		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
+
+		page = find_lock_page(inode->i_mapping, index);
 		if (!page) {
-			ret = -ENOMEM;
-			break;
+			page_cache_sync_readahead(inode->i_mapping, &sctx->ra,
+				NULL, index, last_index + 1 - index);
+
+			page = find_or_create_page(inode->i_mapping, index,
+					GFP_KERNEL);
+			if (!page) {
+				ret = -ENOMEM;
+				break;
+			}
+		}
+
+		if (PageReadahead(page)) {
+			page_cache_async_readahead(inode->i_mapping, &sctx->ra,
+				NULL, page, index, last_index + 1 - index);
 		}
 
 		if (!PageUptodate(page)) {
@@ -4920,6 +5007,9 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	u64 len;
 	int ret = 0;
 
+	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
+		return send_update_extent(sctx, offset, end - offset);
+
 	p = fs_path_alloc();
 	if (!p)
 		return -ENOMEM;
@@ -4941,6 +5031,7 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 			break;
 		offset += len;
 	}
+	sctx->cur_inode_next_write_offset = offset;
 tlv_put_failure:
 	fs_path_free(p);
 	return ret;
@@ -5176,6 +5267,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 	} else {
 		ret = send_extent_data(sctx, offset, len);
 	}
+	sctx->cur_inode_next_write_offset = offset + len;
 out:
 	return ret;
 }
@@ -5700,6 +5792,7 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	u64 right_gid;
 	int need_chmod = 0;
 	int need_chown = 0;
+	int need_truncate = 1;
 	int pending_move = 0;
 	int refs_processed = 0;
 
@@ -5737,9 +5830,13 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 		need_chown = 1;
 		if (!S_ISLNK(sctx->cur_inode_mode))
 			need_chmod = 1;
+		if (sctx->cur_inode_next_write_offset == sctx->cur_inode_size)
+			need_truncate = 0;
 	} else {
+		u64 old_size;
+
 		ret = get_inode_info(sctx->parent_root, sctx->cur_ino,
-				NULL, NULL, &right_mode, &right_uid,
+				&old_size, NULL, &right_mode, &right_uid,
 				&right_gid, NULL);
 		if (ret < 0)
 			goto out;
@@ -5748,6 +5845,10 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 			need_chown = 1;
 		if (!S_ISLNK(sctx->cur_inode_mode) && left_mode != right_mode)
 			need_chmod = 1;
+		if ((old_size == sctx->cur_inode_size) ||
+		    (sctx->cur_inode_size > old_size &&
+		     sctx->cur_inode_next_write_offset == sctx->cur_inode_size))
+			need_truncate = 0;
 	}
 
 	if (S_ISREG(sctx->cur_inode_mode)) {
@@ -5766,10 +5867,13 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 					goto out;
 			}
 		}
-		ret = send_truncate(sctx, sctx->cur_ino, sctx->cur_inode_gen,
-				sctx->cur_inode_size);
-		if (ret < 0)
-			goto out;
+		if (need_truncate) {
+			ret = send_truncate(sctx, sctx->cur_ino,
+					    sctx->cur_inode_gen,
+					    sctx->cur_inode_size);
+			if (ret < 0)
+				goto out;
+		}
 	}
 
 	if (need_chown) {
@@ -5823,6 +5927,7 @@ static int changed_inode(struct send_ctx *sctx,
 	sctx->cur_ino = key->objectid;
 	sctx->cur_inode_new_gen = 0;
 	sctx->cur_inode_last_extent = (u64)-1;
+	sctx->cur_inode_next_write_offset = 0;
 
 	/*
 	 * Set send_progress to current inode. This will tell all get_cur_xxx
@@ -6162,9 +6267,7 @@ out:
  * Updates compare related fields in sctx and simply forwards to the actual
  * changed_xxx functions.
  */
-static int changed_cb(struct btrfs_root *left_root,
-		      struct btrfs_root *right_root,
-		      struct btrfs_path *left_path,
+static int changed_cb(struct btrfs_path *left_path,
 		      struct btrfs_path *right_path,
 		      struct btrfs_key *key,
 		      enum btrfs_compare_tree_result result,
@@ -6246,8 +6349,8 @@ static int full_send_tree(struct send_ctx *sctx)
 		slot = path->slots[0];
 		btrfs_item_key_to_cpu(eb, &found_key, slot);
 
-		ret = changed_cb(send_root, NULL, path, NULL,
-				&found_key, BTRFS_COMPARE_TREE_NEW, sctx);
+		ret = changed_cb(path, NULL, &found_key,
+				 BTRFS_COMPARE_TREE_NEW, sctx);
 		if (ret < 0)
 			goto out;
 
@@ -6365,13 +6468,12 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
 	spin_unlock(&root->root_item_lock);
 }
 
-long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
+long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 {
 	int ret = 0;
 	struct btrfs_root *send_root = BTRFS_I(file_inode(mnt_file))->root;
 	struct btrfs_fs_info *fs_info = send_root->fs_info;
 	struct btrfs_root *clone_root;
-	struct btrfs_ioctl_send_args *arg = NULL;
 	struct btrfs_key key;
 	struct send_ctx *sctx = NULL;
 	u32 i;
@@ -6407,13 +6509,6 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
-	arg = memdup_user(arg_, sizeof(*arg));
-	if (IS_ERR(arg)) {
-		ret = PTR_ERR(arg);
-		arg = NULL;
-		goto out;
-	}
-
 	/*
 	 * Check that we don't overflow at later allocations, we request
 	 * clone_sources_count + 1 items, and compare to unsigned long inside
@@ -6654,7 +6749,6 @@ out:
 	if (sctx && !IS_ERR_OR_NULL(sctx->parent_root))
 		btrfs_root_dec_send_in_progress(sctx->parent_root);
 
-	kfree(arg);
 	kvfree(clone_sources_tmp);
 
 	if (sctx) {