From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/btrfs/tree-log.c | 1765 ++++++++++++++++++++++++++++++++++++----------------------
1 files changed, 1,083 insertions(+), 682 deletions(-)
diff --git a/kernel/fs/btrfs/tree-log.c b/kernel/fs/btrfs/tree-log.c
index 1f5facd..372ebbc 100644
--- a/kernel/fs/btrfs/tree-log.c
+++ b/kernel/fs/btrfs/tree-log.c
@@ -8,6 +8,7 @@
#include <linux/blkdev.h>
#include <linux/list_sort.h>
#include <linux/iversion.h>
+#include "misc.h"
#include "ctree.h"
#include "tree-log.h"
#include "disk-io.h"
@@ -17,6 +18,8 @@
#include "compression.h"
#include "qgroup.h"
#include "inode-map.h"
+#include "block-group.h"
+#include "space-info.h"
/* magic values for the inode_only field in btrfs_log_inode:
*
@@ -24,9 +27,12 @@
* LOG_INODE_EXISTS means to log just enough to recreate the inode
* during log replay
*/
-#define LOG_INODE_ALL 0
-#define LOG_INODE_EXISTS 1
-#define LOG_OTHER_INODE 2
+enum {
+ LOG_INODE_ALL,
+ LOG_INODE_EXISTS,
+ LOG_OTHER_INODE,
+ LOG_OTHER_INODE_ALL,
+};
/*
* directory trouble cases
@@ -80,16 +86,16 @@
* The last stage is to deal with directories and links and extents
* and all the other fun semantics
*/
-#define LOG_WALK_PIN_ONLY 0
-#define LOG_WALK_REPLAY_INODES 1
-#define LOG_WALK_REPLAY_DIR_INDEX 2
-#define LOG_WALK_REPLAY_ALL 3
+enum {
+ LOG_WALK_PIN_ONLY,
+ LOG_WALK_REPLAY_INODES,
+ LOG_WALK_REPLAY_DIR_INDEX,
+ LOG_WALK_REPLAY_ALL,
+};
static int btrfs_log_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_inode *inode,
int inode_only,
- const loff_t start,
- const loff_t end,
struct btrfs_log_ctx *ctx);
static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -138,7 +144,7 @@
mutex_lock(&root->log_mutex);
if (root->log_root) {
- if (btrfs_need_log_full_commit(fs_info, trans)) {
+ if (btrfs_need_log_full_commit(trans)) {
ret = -EAGAIN;
goto out;
}
@@ -161,13 +167,14 @@
if (ret)
goto out;
+ set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
root->log_start_pid = current->pid;
}
atomic_inc(&root->log_batch);
atomic_inc(&root->log_writers);
- if (ctx) {
+ if (ctx && !ctx->logging_new_name) {
int index = root->log_transid % 2;
list_add_tail(&ctx->list, &root->log_ctxs[index]);
ctx->log_transid = root->log_transid;
@@ -187,9 +194,8 @@
{
int ret = -ENOENT;
- smp_mb();
- if (!root->log_root)
- return -ENOENT;
+ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state))
+ return ret;
mutex_lock(&root->log_mutex);
if (root->log_root) {
@@ -205,14 +211,9 @@
* until you call btrfs_end_log_trans() or it makes any future
* log transactions wait until you call btrfs_end_log_trans()
*/
-int btrfs_pin_log_trans(struct btrfs_root *root)
+void btrfs_pin_log_trans(struct btrfs_root *root)
{
- int ret = -ENOENT;
-
- mutex_lock(&root->log_mutex);
atomic_inc(&root->log_writers);
- mutex_unlock(&root->log_mutex);
- return ret;
}
/*
@@ -227,6 +228,17 @@
}
}
+static int btrfs_write_tree_block(struct extent_buffer *buf)
+{
+ return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
+ buf->start + buf->len - 1);
+}
+
+static void btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
+{
+ filemap_fdatawait_range(buf->pages[0]->mapping,
+ buf->start, buf->start + buf->len - 1);
+}
/*
* the walk control struct is used to pass state down the chain when
@@ -301,12 +313,12 @@
}
if (wc->pin)
- ret = btrfs_pin_extent_for_log_replay(fs_info, eb->start,
+ ret = btrfs_pin_extent_for_log_replay(wc->trans, eb->start,
eb->len);
if (!ret && btrfs_buffer_uptodate(eb, gen, 0)) {
if (wc->pin && btrfs_header_level(eb) == 0)
- ret = btrfs_exclude_logged_extents(fs_info, eb);
+ ret = btrfs_exclude_logged_extents(eb);
if (wc->write)
btrfs_write_tree_block(eb);
if (wc->wait)
@@ -335,7 +347,6 @@
struct extent_buffer *eb, int slot,
struct btrfs_key *key)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
u32 item_size;
u64 saved_i_size = 0;
@@ -456,10 +467,9 @@
found_size = btrfs_item_size_nr(path->nodes[0],
path->slots[0]);
if (found_size > item_size)
- btrfs_truncate_item(fs_info, path, item_size, 1);
+ btrfs_truncate_item(path, item_size, 1);
else if (found_size < item_size)
- btrfs_extend_item(fs_info, path,
- item_size - found_size);
+ btrfs_extend_item(path, item_size - found_size);
} else if (ret) {
return ret;
}
@@ -495,13 +505,8 @@
*/
if (S_ISREG(btrfs_inode_mode(eb, src_item)) &&
S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) &&
- ino_size != 0) {
- struct btrfs_map_token token;
-
- btrfs_init_map_token(&token);
- btrfs_set_token_inode_size(dst_eb, dst_item,
- ino_size, &token);
- }
+ ino_size != 0)
+ btrfs_set_inode_size(dst_eb, dst_item, ino_size);
goto no_copy;
}
@@ -545,13 +550,9 @@
static noinline struct inode *read_one_inode(struct btrfs_root *root,
u64 objectid)
{
- struct btrfs_key key;
struct inode *inode;
- key.objectid = objectid;
- key.type = BTRFS_INODE_ITEM_KEY;
- key.offset = 0;
- inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
+ inode = btrfs_iget(root->fs_info->sb, objectid, root);
if (IS_ERR(inode))
inode = NULL;
return inode;
@@ -696,20 +697,27 @@
goto out;
if (ins.objectid > 0) {
+ struct btrfs_ref ref = { 0 };
u64 csum_start;
u64 csum_end;
LIST_HEAD(ordered_sums);
+
/*
* is this extent already allocated in the extent
* allocation tree? If so, just add a reference
*/
ret = btrfs_lookup_data_extent(fs_info, ins.objectid,
ins.offset);
- if (ret == 0) {
- ret = btrfs_inc_extent_ref(trans, root,
- ins.objectid, ins.offset,
- 0, root->root_key.objectid,
+ if (ret < 0) {
+ goto out;
+ } else if (ret == 0) {
+ btrfs_init_generic_ref(&ref,
+ BTRFS_ADD_DELAYED_REF,
+ ins.objectid, ins.offset, 0);
+ btrfs_init_data_ref(&ref,
+ root->root_key.objectid,
key->objectid, offset);
+ ret = btrfs_inc_extent_ref(trans, &ref);
if (ret)
goto out;
} else {
@@ -816,6 +824,11 @@
if (ret)
goto out;
}
+
+ ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), start,
+ extent_end - start);
+ if (ret)
+ goto out;
inode_add_bytes(inode, nbytes);
update_inode:
@@ -941,54 +954,32 @@
const char *name, int namelen)
{
struct btrfs_path *path;
- struct btrfs_inode_ref *ref;
- unsigned long ptr;
- unsigned long ptr_end;
- unsigned long name_ptr;
- int found_name_len;
- int item_size;
int ret;
- int match = 0;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
- if (ret != 0)
+ if (ret < 0) {
goto out;
+ } else if (ret == 1) {
+ ret = 0;
+ goto out;
+ }
- ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
-
- if (key->type == BTRFS_INODE_EXTREF_KEY) {
- if (btrfs_find_name_in_ext_backref(path->nodes[0],
+ if (key->type == BTRFS_INODE_EXTREF_KEY)
+ ret = !!btrfs_find_name_in_ext_backref(path->nodes[0],
+ path->slots[0],
+ ref_objectid,
+ name, namelen);
+ else
+ ret = !!btrfs_find_name_in_backref(path->nodes[0],
path->slots[0],
- ref_objectid,
- name, namelen, NULL))
- match = 1;
-
- goto out;
- }
-
- item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
- ptr_end = ptr + item_size;
- while (ptr < ptr_end) {
- ref = (struct btrfs_inode_ref *)ptr;
- found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
- if (found_name_len == namelen) {
- name_ptr = (unsigned long)(ref + 1);
- ret = memcmp_extent_buffer(path->nodes[0], name,
- name_ptr, namelen);
- if (ret == 0) {
- match = 1;
- goto out;
- }
- }
- ptr = (unsigned long)(ref + 1) + found_name_len;
- }
+ name, namelen);
out:
btrfs_free_path(path);
- return match;
+ return ret;
}
static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
@@ -1046,10 +1037,13 @@
(unsigned long)(victim_ref + 1),
victim_name_len);
- if (!backref_in_log(log_root, &search_key,
- parent_objectid,
- victim_name,
- victim_name_len)) {
+ ret = backref_in_log(log_root, &search_key,
+ parent_objectid, victim_name,
+ victim_name_len);
+ if (ret < 0) {
+ kfree(victim_name);
+ return ret;
+ } else if (!ret) {
inc_nlink(&inode->vfs_inode);
btrfs_release_path(path);
@@ -1081,7 +1075,9 @@
extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
inode_objectid, parent_objectid, 0,
0);
- if (!IS_ERR_OR_NULL(extref)) {
+ if (IS_ERR(extref)) {
+ return PTR_ERR(extref);
+ } else if (extref) {
u32 item_size;
u32 cur_offset = 0;
unsigned long base;
@@ -1111,10 +1107,13 @@
search_key.offset = btrfs_extref_hash(parent_objectid,
victim_name,
victim_name_len);
- ret = 0;
- if (!backref_in_log(log_root, &search_key,
- parent_objectid, victim_name,
- victim_name_len)) {
+ ret = backref_in_log(log_root, &search_key,
+ parent_objectid, victim_name,
+ victim_name_len);
+ if (ret < 0) {
+ kfree(victim_name);
+ return ret;
+ } else if (!ret) {
ret = -ENOENT;
victim_parent = read_one_inode(root,
parent_objectid);
@@ -1159,7 +1158,7 @@
}
btrfs_release_path(path);
- /* look for a conflicing name */
+ /* look for a conflicting name */
di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir),
name, namelen, 0);
if (IS_ERR(di)) {
@@ -1268,12 +1267,12 @@
goto out;
if (key->type == BTRFS_INODE_EXTREF_KEY)
- ret = btrfs_find_name_in_ext_backref(log_eb, log_slot,
- parent_id, name,
- namelen, NULL);
+ ret = !!btrfs_find_name_in_ext_backref(log_eb, log_slot,
+ parent_id, name,
+ namelen);
else
- ret = btrfs_find_name_in_backref(log_eb, log_slot, name,
- namelen, NULL);
+ ret = !!btrfs_find_name_in_backref(log_eb, log_slot,
+ name, namelen);
if (!ret) {
struct inode *dir;
@@ -1289,6 +1288,15 @@
inode, name, namelen);
kfree(name);
iput(dir);
+ /*
+ * Whenever we need to check if a name exists or not, we
+ * check the subvolume tree. So after an unlink we must
+ * run delayed items, so that future checks for a name
+ * during log replay see that the name does not exists
+ * anymore.
+ */
+ if (!ret)
+ ret = btrfs_run_delayed_items(trans);
if (ret)
goto out;
goto again;
@@ -1335,15 +1343,75 @@
goto out;
}
if (key.type == BTRFS_INODE_EXTREF_KEY)
- ret = btrfs_find_name_in_ext_backref(path->nodes[0],
- path->slots[0], parent_id,
- name, namelen, NULL);
+ ret = !!btrfs_find_name_in_ext_backref(path->nodes[0],
+ path->slots[0], parent_id, name, namelen);
else
- ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
- name, namelen, NULL);
+ ret = !!btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
+ name, namelen);
out:
btrfs_free_path(path);
+ return ret;
+}
+
+static int add_link(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+ struct inode *dir, struct inode *inode, const char *name,
+ int namelen, u64 ref_index)
+{
+ struct btrfs_dir_item *dir_item;
+ struct btrfs_key key;
+ struct btrfs_path *path;
+ struct inode *other_inode = NULL;
+ int ret;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ dir_item = btrfs_lookup_dir_item(NULL, root, path,
+ btrfs_ino(BTRFS_I(dir)),
+ name, namelen, 0);
+ if (!dir_item) {
+ btrfs_release_path(path);
+ goto add_link;
+ } else if (IS_ERR(dir_item)) {
+ ret = PTR_ERR(dir_item);
+ goto out;
+ }
+
+ /*
+ * Our inode's dentry collides with the dentry of another inode which is
+ * in the log but not yet processed since it has a higher inode number.
+ * So delete that other dentry.
+ */
+ btrfs_dir_item_key_to_cpu(path->nodes[0], dir_item, &key);
+ btrfs_release_path(path);
+ other_inode = read_one_inode(root, key.objectid);
+ if (!other_inode) {
+ ret = -ENOENT;
+ goto out;
+ }
+ ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), BTRFS_I(other_inode),
+ name, namelen);
+ if (ret)
+ goto out;
+ /*
+ * If we dropped the link count to 0, bump it so that later the iput()
+ * on the inode will not free it. We will fixup the link count later.
+ */
+ if (other_inode->i_nlink == 0)
+ inc_nlink(other_inode);
+
+ ret = btrfs_run_delayed_items(trans);
+ if (ret)
+ goto out;
+add_link:
+ ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
+ name, namelen, 0, ref_index);
+out:
+ iput(other_inode);
+ btrfs_free_path(path);
+
return ret;
}
@@ -1480,14 +1548,22 @@
*/
if (!ret && inode->i_nlink == 0)
inc_nlink(inode);
+ /*
+ * Whenever we need to check if a name exists or
+ * not, we check the subvolume tree. So after an
+ * unlink we must run delayed items, so that future
+ * checks for a name during log replay see that the
+ * name does not exists anymore.
+ */
+ if (!ret)
+ ret = btrfs_run_delayed_items(trans);
}
if (ret < 0)
goto out;
/* insert our name */
- ret = btrfs_add_link(trans, BTRFS_I(dir),
- BTRFS_I(inode),
- name, namelen, 0, ref_index);
+ ret = add_link(trans, root, dir, inode, name, namelen,
+ ref_index);
if (ret)
goto out;
@@ -1829,30 +1905,6 @@
}
/*
- * Return true if an inode reference exists in the log for the given name,
- * inode and parent inode.
- */
-static bool name_in_log_ref(struct btrfs_root *log_root,
- const char *name, const int name_len,
- const u64 dirid, const u64 ino)
-{
- struct btrfs_key search_key;
-
- search_key.objectid = ino;
- search_key.type = BTRFS_INODE_REF_KEY;
- search_key.offset = dirid;
- if (backref_in_log(log_root, &search_key, dirid, name, name_len))
- return true;
-
- search_key.type = BTRFS_INODE_EXTREF_KEY;
- search_key.offset = btrfs_extref_hash(dirid, name, name_len);
- if (backref_in_log(log_root, &search_key, dirid, name, name_len))
- return true;
-
- return false;
-}
-
-/*
* take a single entry in a log directory item and replay it into
* the subvolume.
*
@@ -1975,8 +2027,31 @@
return ret;
insert:
- if (name_in_log_ref(root->log_root, name, name_len,
- key->objectid, log_key.objectid)) {
+ /*
+ * Check if the inode reference exists in the log for the given name,
+ * inode and parent inode
+ */
+ found_key.objectid = log_key.objectid;
+ found_key.type = BTRFS_INODE_REF_KEY;
+ found_key.offset = key->objectid;
+ ret = backref_in_log(root->log_root, &found_key, 0, name, name_len);
+ if (ret < 0) {
+ goto out;
+ } else if (ret) {
+ /* The dentry will be added later. */
+ ret = 0;
+ update_size = false;
+ goto out;
+ }
+
+ found_key.objectid = log_key.objectid;
+ found_key.type = BTRFS_INODE_EXTREF_KEY;
+ found_key.offset = key->objectid;
+ ret = backref_in_log(root->log_root, &found_key, key->objectid, name,
+ name_len);
+ if (ret < 0) {
+ goto out;
+ } else if (ret) {
/* The dentry will be added later. */
ret = 0;
update_size = false;
@@ -2629,29 +2704,45 @@
return ret;
}
+/*
+ * Correctly adjust the reserved bytes occupied by a log tree extent buffer
+ */
+static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start)
+{
+ struct btrfs_block_group *cache;
+
+ cache = btrfs_lookup_block_group(fs_info, start);
+ if (!cache) {
+ btrfs_err(fs_info, "unable to find block group for %llu", start);
+ return;
+ }
+
+ spin_lock(&cache->space_info->lock);
+ spin_lock(&cache->lock);
+ cache->reserved -= fs_info->nodesize;
+ cache->space_info->bytes_reserved -= fs_info->nodesize;
+ spin_unlock(&cache->lock);
+ spin_unlock(&cache->space_info->lock);
+
+ btrfs_put_block_group(cache);
+}
+
static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, int *level,
struct walk_control *wc)
{
struct btrfs_fs_info *fs_info = root->fs_info;
- u64 root_owner;
u64 bytenr;
u64 ptr_gen;
struct extent_buffer *next;
struct extent_buffer *cur;
- struct extent_buffer *parent;
u32 blocksize;
int ret = 0;
-
- WARN_ON(*level < 0);
- WARN_ON(*level >= BTRFS_MAX_LEVEL);
while (*level > 0) {
struct btrfs_key first_key;
- WARN_ON(*level < 0);
- WARN_ON(*level >= BTRFS_MAX_LEVEL);
cur = path->nodes[*level];
WARN_ON(btrfs_header_level(cur) != *level);
@@ -2664,9 +2755,6 @@
ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
blocksize = fs_info->nodesize;
-
- parent = path->nodes[*level];
- root_owner = btrfs_header_owner(parent);
next = btrfs_find_create_tree_block(fs_info, bytenr);
if (IS_ERR(next))
@@ -2691,23 +2779,20 @@
if (trans) {
btrfs_tree_lock(next);
- btrfs_set_lock_blocking(next);
- clean_tree_block(fs_info, next);
+ btrfs_set_lock_blocking_write(next);
+ btrfs_clean_tree_block(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
+ ret = btrfs_pin_reserved_extent(trans,
+ bytenr, blocksize);
+ if (ret) {
+ free_extent_buffer(next);
+ return ret;
+ }
} else {
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
clear_extent_buffer_dirty(next);
- }
-
- WARN_ON(root_owner !=
- BTRFS_TREE_LOG_OBJECTID);
- ret = btrfs_free_and_pin_reserved_extent(
- fs_info, bytenr,
- blocksize);
- if (ret) {
- free_extent_buffer(next);
- return ret;
+ unaccount_log_buffer(fs_info, bytenr);
}
}
free_extent_buffer(next);
@@ -2719,7 +2804,6 @@
return ret;
}
- WARN_ON(*level <= 0);
if (path->nodes[*level-1])
free_extent_buffer(path->nodes[*level-1]);
path->nodes[*level-1] = next;
@@ -2727,9 +2811,6 @@
path->slots[*level] = 0;
cond_resched();
}
- WARN_ON(*level < 0);
- WARN_ON(*level >= BTRFS_MAX_LEVEL);
-
path->slots[*level] = btrfs_header_nritems(path->nodes[*level]);
cond_resched();
@@ -2742,7 +2823,6 @@
struct walk_control *wc)
{
struct btrfs_fs_info *fs_info = root->fs_info;
- u64 root_owner;
int i;
int slot;
int ret;
@@ -2755,13 +2835,6 @@
WARN_ON(*level == 0);
return 0;
} else {
- struct extent_buffer *parent;
- if (path->nodes[*level] == root->node)
- parent = path->nodes[*level];
- else
- parent = path->nodes[*level + 1];
-
- root_owner = btrfs_header_owner(parent);
ret = wc->process_func(root, path->nodes[*level], wc,
btrfs_header_generation(path->nodes[*level]),
*level);
@@ -2775,22 +2848,22 @@
if (trans) {
btrfs_tree_lock(next);
- btrfs_set_lock_blocking(next);
- clean_tree_block(fs_info, next);
+ btrfs_set_lock_blocking_write(next);
+ btrfs_clean_tree_block(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
+ ret = btrfs_pin_reserved_extent(trans,
+ path->nodes[*level]->start,
+ path->nodes[*level]->len);
+ if (ret)
+ return ret;
} else {
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
clear_extent_buffer_dirty(next);
- }
- WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
- ret = btrfs_free_and_pin_reserved_extent(
- fs_info,
- path->nodes[*level]->start,
- path->nodes[*level]->len);
- if (ret)
- return ret;
+ unaccount_log_buffer(fs_info,
+ path->nodes[*level]->start);
+ }
}
free_extent_buffer(path->nodes[*level]);
path->nodes[*level] = NULL;
@@ -2822,7 +2895,7 @@
level = btrfs_header_level(log->node);
orig_level = level;
path->nodes[level] = log->node;
- extent_buffer_get(log->node);
+ atomic_inc(&log->node->refs);
path->slots[level] = 0;
while (1) {
@@ -2857,21 +2930,19 @@
if (trans) {
btrfs_tree_lock(next);
- btrfs_set_lock_blocking(next);
- clean_tree_block(fs_info, next);
+ btrfs_set_lock_blocking_write(next);
+ btrfs_clean_tree_block(next);
btrfs_wait_tree_block_writeback(next);
btrfs_tree_unlock(next);
+ ret = btrfs_pin_reserved_extent(trans,
+ next->start, next->len);
+ if (ret)
+ goto out;
} else {
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
clear_extent_buffer_dirty(next);
+ unaccount_log_buffer(fs_info, next->start);
}
-
- WARN_ON(log->root_key.objectid !=
- BTRFS_TREE_LOG_OBJECTID);
- ret = btrfs_free_and_pin_reserved_extent(fs_info,
- next->start, next->len);
- if (ret)
- goto out;
}
}
@@ -3035,7 +3106,7 @@
}
/* bail out if we need to do a full commit */
- if (btrfs_need_log_full_commit(fs_info, trans)) {
+ if (btrfs_need_log_full_commit(trans)) {
ret = -EAGAIN;
mutex_unlock(&root->log_mutex);
goto out;
@@ -3054,7 +3125,7 @@
if (ret) {
blk_finish_plug(&plug);
btrfs_abort_transaction(trans, ret);
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
mutex_unlock(&root->log_mutex);
goto out;
}
@@ -3088,16 +3159,10 @@
btrfs_init_log_ctx(&root_log_ctx, NULL);
mutex_lock(&log_root_tree->log_mutex);
- atomic_inc(&log_root_tree->log_batch);
- atomic_inc(&log_root_tree->log_writers);
index2 = log_root_tree->log_transid % 2;
list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
root_log_ctx.log_transid = log_root_tree->log_transid;
-
- mutex_unlock(&log_root_tree->log_mutex);
-
- mutex_lock(&log_root_tree->log_mutex);
/*
* Now we are safe to update the log_root_tree because we're under the
@@ -3105,18 +3170,12 @@
* open until we drop the log_mutex.
*/
ret = update_log_root(trans, log, &new_root_item);
-
- if (atomic_dec_and_test(&log_root_tree->log_writers)) {
- /* atomic_dec_and_test implies a barrier */
- cond_wake_up_nomb(&log_root_tree->log_writer_wait);
- }
-
if (ret) {
if (!list_empty(&root_log_ctx.list))
list_del_init(&root_log_ctx.list);
blk_finish_plug(&plug);
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
if (ret != -ENOSPC) {
btrfs_abort_transaction(trans, ret);
@@ -3156,13 +3215,11 @@
root_log_ctx.log_transid - 1);
}
- wait_for_writer(log_root_tree);
-
/*
* now that we've moved on to the tree of log tree roots,
* check the full commit flag again
*/
- if (btrfs_need_log_full_commit(fs_info, trans)) {
+ if (btrfs_need_log_full_commit(trans)) {
blk_finish_plug(&plug);
btrfs_wait_tree_log_extents(log, mark);
mutex_unlock(&log_root_tree->log_mutex);
@@ -3175,7 +3232,7 @@
EXTENT_DIRTY | EXTENT_NEW);
blk_finish_plug(&plug);
if (ret) {
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
btrfs_abort_transaction(trans, ret);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
@@ -3185,7 +3242,7 @@
ret = btrfs_wait_tree_log_extents(log_root_tree,
EXTENT_NEW | EXTENT_DIRTY);
if (ret) {
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
@@ -3199,7 +3256,7 @@
mutex_unlock(&log_root_tree->log_mutex);
/*
- * nobody else is going to jump in and write the the ctree
+ * Nobody else is going to jump in and write the ctree
* super here because the log_commit atomic below is protecting
* us. We must be called with a transaction handle pinning
* the running transaction open, so a full commit can't hop
@@ -3207,7 +3264,7 @@
*/
ret = write_all_supers(fs_info, 1);
if (ret) {
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
btrfs_abort_transaction(trans, ret);
goto out_wake_log_root;
}
@@ -3251,8 +3308,6 @@
struct btrfs_root *log)
{
int ret;
- u64 start;
- u64 end;
struct walk_control wc = {
.free = 1,
.process_func = process_one_buffer
@@ -3266,20 +3321,10 @@
btrfs_handle_fs_error(log->fs_info, ret, NULL);
}
- while (1) {
- ret = find_first_extent_bit(&log->dirty_log_pages,
- 0, &start, &end,
- EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT,
- NULL);
- if (ret)
- break;
-
- clear_extent_bits(&log->dirty_log_pages, start, end,
- EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
- }
-
- free_extent_buffer(log->node);
- kfree(log);
+ clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,
+ EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
+ extent_io_tree_release(&log->log_csum_range);
+ btrfs_put_root(log);
}
/*
@@ -3291,6 +3336,7 @@
if (root->log_root) {
free_log_tree(trans, root->log_root);
root->log_root = NULL;
+ clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
}
return 0;
}
@@ -3447,7 +3493,7 @@
out_unlock:
mutex_unlock(&dir->log_mutex);
if (err == -ENOSPC) {
- btrfs_set_log_full_commit(root->fs_info, trans);
+ btrfs_set_log_full_commit(trans);
err = 0;
} else if (err < 0 && err != -ENOENT) {
/* ENOENT can be returned if the entry hasn't been fsynced yet */
@@ -3465,7 +3511,6 @@
const char *name, int name_len,
struct btrfs_inode *inode, u64 dirid)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_root *log;
u64 index;
int ret;
@@ -3483,7 +3528,7 @@
dirid, &index);
mutex_unlock(&inode->log_mutex);
if (ret == -ENOSPC) {
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
ret = 0;
} else if (ret < 0 && ret != -ENOENT)
btrfs_abort_transaction(trans, ret);
@@ -3807,8 +3852,9 @@
found_key.offset = 0;
found_key.type = 0;
- ret = btrfs_bin_search(path->nodes[0], &found_key, 0,
- &start_slot);
+ ret = btrfs_bin_search(path->nodes[0], &found_key, &start_slot);
+ if (ret < 0)
+ break;
ret = btrfs_del_items(trans, log, path, start_slot,
path->slots[0] - start_slot + 1);
@@ -3834,7 +3880,7 @@
{
struct btrfs_map_token token;
- btrfs_init_map_token(&token);
+ btrfs_init_map_token(&token, leaf);
if (log_inode_only) {
/* set the generation to zero so the recover code
@@ -3842,44 +3888,41 @@
* just to say 'this inode exists' and a logging
* to say 'update this inode with these values'
*/
- btrfs_set_token_inode_generation(leaf, item, 0, &token);
- btrfs_set_token_inode_size(leaf, item, logged_isize, &token);
+ btrfs_set_token_inode_generation(&token, item, 0);
+ btrfs_set_token_inode_size(&token, item, logged_isize);
} else {
- btrfs_set_token_inode_generation(leaf, item,
- BTRFS_I(inode)->generation,
- &token);
- btrfs_set_token_inode_size(leaf, item, inode->i_size, &token);
+ btrfs_set_token_inode_generation(&token, item,
+ BTRFS_I(inode)->generation);
+ btrfs_set_token_inode_size(&token, item, inode->i_size);
}
- btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
- btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
- btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
- btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
+ btrfs_set_token_inode_uid(&token, item, i_uid_read(inode));
+ btrfs_set_token_inode_gid(&token, item, i_gid_read(inode));
+ btrfs_set_token_inode_mode(&token, item, inode->i_mode);
+ btrfs_set_token_inode_nlink(&token, item, inode->i_nlink);
- btrfs_set_token_timespec_sec(leaf, &item->atime,
- inode->i_atime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->atime,
- inode->i_atime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->atime,
+ inode->i_atime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->atime,
+ inode->i_atime.tv_nsec);
- btrfs_set_token_timespec_sec(leaf, &item->mtime,
- inode->i_mtime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->mtime,
- inode->i_mtime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->mtime,
+ inode->i_mtime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->mtime,
+ inode->i_mtime.tv_nsec);
- btrfs_set_token_timespec_sec(leaf, &item->ctime,
- inode->i_ctime.tv_sec, &token);
- btrfs_set_token_timespec_nsec(leaf, &item->ctime,
- inode->i_ctime.tv_nsec, &token);
+ btrfs_set_token_timespec_sec(&token, &item->ctime,
+ inode->i_ctime.tv_sec);
+ btrfs_set_token_timespec_nsec(&token, &item->ctime,
+ inode->i_ctime.tv_nsec);
- btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
- &token);
+ btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode));
- btrfs_set_token_inode_sequence(leaf, item,
- inode_peek_iversion(inode), &token);
- btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
- btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
- btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
- btrfs_set_token_inode_block_group(leaf, item, 0, &token);
+ btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode));
+ btrfs_set_token_inode_transid(&token, item, trans->transid);
+ btrfs_set_token_inode_rdev(&token, item, inode->i_rdev);
+ btrfs_set_token_inode_flags(&token, item, BTRFS_I(inode)->flags);
+ btrfs_set_token_inode_block_group(&token, item, 0);
}
static int log_inode_item(struct btrfs_trans_handle *trans,
@@ -3902,11 +3945,32 @@
}
static int log_csums(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
struct btrfs_root *log_root,
struct btrfs_ordered_sum *sums)
{
+ const u64 lock_end = sums->bytenr + sums->len - 1;
+ struct extent_state *cached_state = NULL;
int ret;
+ /*
+ * If this inode was not used for reflink operations in the current
+ * transaction with new extents, then do the fast path, no need to
+ * worry about logging checksum items with overlapping ranges.
+ */
+ if (inode->last_reflink_trans < trans->transid)
+ return btrfs_csum_file_blocks(trans, log_root, sums);
+
+ /*
+ * Serialize logging for checksums. This is to avoid racing with the
+ * same checksum being logged by another task that is logging another
+ * file which happens to refer to the same extent as well. Such races
+ * can leave checksum items in the log with overlapping ranges.
+ */
+ ret = lock_extent_bits(&log_root->log_csum_range, sums->bytenr,
+ lock_end, &cached_state);
+ if (ret)
+ return ret;
/*
* Due to extent cloning, we might have logged a csum item that covers a
* subrange of a cloned extent, and later we can end up logging a csum
@@ -3917,10 +3981,13 @@
* trim and adjust) any existing csum items in the log for this range.
*/
ret = btrfs_del_csums(trans, log_root, sums->bytenr, sums->len);
- if (ret)
- return ret;
+ if (!ret)
+ ret = btrfs_csum_file_blocks(trans, log_root, sums);
- return btrfs_csum_file_blocks(trans, log_root, sums);
+ unlock_extent_cached(&log_root->log_csum_range, sums->bytenr, lock_end,
+ &cached_state);
+
+ return ret;
}
static noinline int copy_items(struct btrfs_trans_handle *trans,
@@ -4041,7 +4108,7 @@
struct btrfs_ordered_sum,
list);
if (!ret)
- ret = log_csums(trans, log, sums);
+ ret = log_csums(trans, inode, log, sums);
list_del(&sums->list);
kfree(sums);
}
@@ -4066,10 +4133,14 @@
static int log_extent_csums(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode,
struct btrfs_root *log_root,
- const struct extent_map *em)
+ const struct extent_map *em,
+ struct btrfs_log_ctx *ctx)
{
+ struct btrfs_ordered_extent *ordered;
u64 csum_offset;
u64 csum_len;
+ u64 mod_start = em->mod_start;
+ u64 mod_len = em->mod_len;
LIST_HEAD(ordered_sums);
int ret = 0;
@@ -4078,13 +4149,71 @@
em->block_start == EXTENT_MAP_HOLE)
return 0;
+ list_for_each_entry(ordered, &ctx->ordered_extents, log_list) {
+ const u64 ordered_end = ordered->file_offset + ordered->num_bytes;
+ const u64 mod_end = mod_start + mod_len;
+ struct btrfs_ordered_sum *sums;
+
+ if (mod_len == 0)
+ break;
+
+ if (ordered_end <= mod_start)
+ continue;
+ if (mod_end <= ordered->file_offset)
+ break;
+
+ /*
+ * We are going to copy all the csums on this ordered extent, so
+ * go ahead and adjust mod_start and mod_len in case this ordered
+ * extent has already been logged.
+ */
+ if (ordered->file_offset > mod_start) {
+ if (ordered_end >= mod_end)
+ mod_len = ordered->file_offset - mod_start;
+ /*
+ * If we have this case
+ *
+ * |--------- logged extent ---------|
+ * |----- ordered extent ----|
+ *
+ * Just don't mess with mod_start and mod_len, we'll
+ * just end up logging more csums than we need and it
+ * will be ok.
+ */
+ } else {
+ if (ordered_end < mod_end) {
+ mod_len = mod_end - ordered_end;
+ mod_start = ordered_end;
+ } else {
+ mod_len = 0;
+ }
+ }
+
+ /*
+ * To keep us from looping for the above case of an ordered
+ * extent that falls inside of the logged extent.
+ */
+ if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM, &ordered->flags))
+ continue;
+
+ list_for_each_entry(sums, &ordered->list, list) {
+ ret = log_csums(trans, inode, log_root, sums);
+ if (ret)
+ return ret;
+ }
+ }
+
+ /* We're done, found all csums in the ordered extents. */
+ if (mod_len == 0)
+ return 0;
+
/* If we're compressed we have to save the entire range of csums. */
if (em->compress_type) {
csum_offset = 0;
csum_len = max(em->block_len, em->orig_block_len);
} else {
- csum_offset = em->mod_start - em->start;
- csum_len = em->mod_len;
+ csum_offset = mod_start - em->start;
+ csum_len = mod_len;
}
/* block start is already adjusted for the file extent offset. */
@@ -4100,7 +4229,7 @@
struct btrfs_ordered_sum,
list);
if (!ret)
- ret = log_csums(trans, log_root, sums);
+ ret = log_csums(trans, inode, log_root, sums);
list_del(&sums->list);
kfree(sums);
}
@@ -4124,13 +4253,11 @@
int ret;
int extent_inserted = 0;
- ret = log_extent_csums(trans, inode, log, em);
+ ret = log_extent_csums(trans, inode, log, em, ctx);
if (ret)
return ret;
- btrfs_init_map_token(&token);
-
- ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start,
+ ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
em->start + em->len, NULL, 0, 1,
sizeof(*fi), &extent_inserted);
if (ret)
@@ -4147,46 +4274,39 @@
return ret;
}
leaf = path->nodes[0];
+ btrfs_init_map_token(&token, leaf);
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
- btrfs_set_token_file_extent_generation(leaf, fi, trans->transid,
- &token);
+ btrfs_set_token_file_extent_generation(&token, fi, trans->transid);
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- btrfs_set_token_file_extent_type(leaf, fi,
- BTRFS_FILE_EXTENT_PREALLOC,
- &token);
+ btrfs_set_token_file_extent_type(&token, fi,
+ BTRFS_FILE_EXTENT_PREALLOC);
else
- btrfs_set_token_file_extent_type(leaf, fi,
- BTRFS_FILE_EXTENT_REG,
- &token);
+ btrfs_set_token_file_extent_type(&token, fi,
+ BTRFS_FILE_EXTENT_REG);
block_len = max(em->block_len, em->orig_block_len);
if (em->compress_type != BTRFS_COMPRESS_NONE) {
- btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
- em->block_start,
- &token);
- btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
- &token);
+ btrfs_set_token_file_extent_disk_bytenr(&token, fi,
+ em->block_start);
+ btrfs_set_token_file_extent_disk_num_bytes(&token, fi, block_len);
} else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
- btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
+ btrfs_set_token_file_extent_disk_bytenr(&token, fi,
em->block_start -
- extent_offset, &token);
- btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
- &token);
+ extent_offset);
+ btrfs_set_token_file_extent_disk_num_bytes(&token, fi, block_len);
} else {
- btrfs_set_token_file_extent_disk_bytenr(leaf, fi, 0, &token);
- btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, 0,
- &token);
+ btrfs_set_token_file_extent_disk_bytenr(&token, fi, 0);
+ btrfs_set_token_file_extent_disk_num_bytes(&token, fi, 0);
}
- btrfs_set_token_file_extent_offset(leaf, fi, extent_offset, &token);
- btrfs_set_token_file_extent_num_bytes(leaf, fi, em->len, &token);
- btrfs_set_token_file_extent_ram_bytes(leaf, fi, em->ram_bytes, &token);
- btrfs_set_token_file_extent_compression(leaf, fi, em->compress_type,
- &token);
- btrfs_set_token_file_extent_encryption(leaf, fi, 0, &token);
- btrfs_set_token_file_extent_other_encoding(leaf, fi, 0, &token);
+ btrfs_set_token_file_extent_offset(&token, fi, extent_offset);
+ btrfs_set_token_file_extent_num_bytes(&token, fi, em->len);
+ btrfs_set_token_file_extent_ram_bytes(&token, fi, em->ram_bytes);
+ btrfs_set_token_file_extent_compression(&token, fi, em->compress_type);
+ btrfs_set_token_file_extent_encryption(&token, fi, 0);
+ btrfs_set_token_file_extent_other_encoding(&token, fi, 0);
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
@@ -4196,7 +4316,7 @@
/*
* Log all prealloc extents beyond the inode's i_size to make sure we do not
- * lose them after doing a fast fsync and replaying the log. We scan the
+ * lose them after doing a full/fast fsync and replaying the log. We scan the
* subvolume's root instead of iterating the inode's extent map tree because
* otherwise we can log incorrect extent items based on extent map conversion.
* That can happen due to the fact that extent maps are merged when they
@@ -4322,12 +4442,9 @@
}
}
}
- if (ins_nr > 0) {
+ if (ins_nr > 0)
ret = copy_items(trans, inode, dst_path, path,
start_slot, ins_nr, 1, 0);
- if (ret > 0)
- ret = 0;
- }
out:
btrfs_release_path(path);
btrfs_free_path(dst_path);
@@ -4338,14 +4455,13 @@
struct btrfs_root *root,
struct btrfs_inode *inode,
struct btrfs_path *path,
- struct btrfs_log_ctx *ctx,
- const u64 start,
- const u64 end)
+ struct btrfs_log_ctx *ctx)
{
+ struct btrfs_ordered_extent *ordered;
+ struct btrfs_ordered_extent *tmp;
struct extent_map *em, *n;
struct list_head extents;
struct extent_map_tree *tree = &inode->extent_tree;
- u64 logged_start, logged_end;
u64 test_gen;
int ret = 0;
int num = 0;
@@ -4354,27 +4470,8 @@
write_lock(&tree->lock);
test_gen = root->fs_info->last_trans_committed;
- logged_start = start;
- logged_end = end;
list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
- /*
- * Skip extents outside our logging range. It's important to do
- * it for correctness because if we don't ignore them, we may
- * log them before their ordered extent completes, and therefore
- * we could log them without logging their respective checksums
- * (the checksum items are added to the csum tree at the very
- * end of btrfs_finish_ordered_io()). Also leave such extents
- * outside of our range in the list, since we may have another
- * ranged fsync in the near future that needs them. If an extent
- * outside our range corresponds to a hole, log it to avoid
- * leaving gaps between extents (fsck will complain when we are
- * not using the NO_HOLES feature).
- */
- if ((em->start > end || em->start + em->len <= start) &&
- em->block_start != EXTENT_MAP_HOLE)
- continue;
-
list_del_init(&em->list);
/*
* Just an arbitrary number, this can be really CPU intensive
@@ -4395,11 +4492,6 @@
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
em->start >= i_size_read(&inode->vfs_inode))
continue;
-
- if (em->start < logged_start)
- logged_start = em->start;
- if ((em->start + em->len - 1) > logged_end)
- logged_end = em->start + em->len - 1;
/* Need a ref to keep it from getting evicted from cache */
refcount_inc(&em->refs);
@@ -4438,8 +4530,32 @@
btrfs_release_path(path);
if (!ret)
ret = btrfs_log_prealloc_extents(trans, inode, path);
+ if (ret)
+ return ret;
- return ret;
+ /*
+ * We have logged all extents successfully, now make sure the commit of
+ * the current transaction waits for the ordered extents to complete
+ * before it commits and wipes out the log trees, otherwise we would
+ * lose data if an ordered extents completes after the transaction
+ * commits and a power failure happens after the transaction commit.
+ */
+ list_for_each_entry_safe(ordered, tmp, &ctx->ordered_extents, log_list) {
+ list_del_init(&ordered->log_list);
+ set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags);
+
+ if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
+ spin_lock_irq(&inode->ordered_tree.lock);
+ if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
+ set_bit(BTRFS_ORDERED_PENDING, &ordered->flags);
+ atomic_inc(&trans->transaction->pending_ordered);
+ }
+ spin_unlock_irq(&inode->ordered_tree.lock);
+ }
+ btrfs_put_ordered_extent(ordered);
+ }
+
+ return 0;
}
static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
@@ -4502,6 +4618,10 @@
const u64 ino = btrfs_ino(inode);
int ins_nr = 0;
int start_slot = 0;
+ bool found_xattrs = false;
+
+ if (test_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags))
+ return 0;
key.objectid = ino;
key.type = BTRFS_XATTR_ITEM_KEY;
@@ -4540,6 +4660,7 @@
start_slot = slot;
ins_nr++;
path->slots[0]++;
+ found_xattrs = true;
cond_resched();
}
if (ins_nr > 0) {
@@ -4548,6 +4669,9 @@
if (ret < 0)
return ret;
}
+
+ if (!found_xattrs)
+ set_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags);
return 0;
}
@@ -4585,9 +4709,7 @@
return ret;
while (true) {
- struct btrfs_file_extent_item *extent;
struct extent_buffer *leaf = path->nodes[0];
- u64 len;
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
ret = btrfs_next_leaf(root, path);
@@ -4636,18 +4758,7 @@
leaf = path->nodes[0];
}
- extent = btrfs_item_ptr(leaf, path->slots[0],
- struct btrfs_file_extent_item);
- if (btrfs_file_extent_type(leaf, extent) ==
- BTRFS_FILE_EXTENT_INLINE) {
- len = btrfs_file_extent_ram_bytes(leaf, extent);
- prev_extent_end = ALIGN(key.offset + len,
- fs_info->sectorsize);
- } else {
- len = btrfs_file_extent_num_bytes(leaf, extent);
- prev_extent_end = key.offset + len;
- }
-
+ prev_extent_end = btrfs_file_extent_end(path);
path->slots[0]++;
cond_resched();
}
@@ -4714,7 +4825,7 @@
const int slot,
const struct btrfs_key *key,
struct btrfs_inode *inode,
- u64 *other_ino)
+ u64 *other_ino, u64 *other_parent)
{
int ret;
struct btrfs_path *search_path;
@@ -4777,8 +4888,13 @@
btrfs_dir_item_key_to_cpu(search_path->nodes[0],
di, &di_key);
if (di_key.type == BTRFS_INODE_ITEM_KEY) {
- ret = 1;
- *other_ino = di_key.objectid;
+ if (di_key.objectid != key->objectid) {
+ ret = 1;
+ *other_ino = di_key.objectid;
+ *other_parent = parent;
+ } else {
+ ret = 0;
+ }
} else {
ret = -EAGAIN;
}
@@ -4795,6 +4911,334 @@
out:
btrfs_free_path(search_path);
kfree(name);
+ return ret;
+}
+
+struct btrfs_ino_list {
+ u64 ino;
+ u64 parent;
+ struct list_head list;
+};
+
+static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_log_ctx *ctx,
+ u64 ino, u64 parent)
+{
+ struct btrfs_ino_list *ino_elem;
+ LIST_HEAD(inode_list);
+ int ret = 0;
+
+ ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS);
+ if (!ino_elem)
+ return -ENOMEM;
+ ino_elem->ino = ino;
+ ino_elem->parent = parent;
+ list_add_tail(&ino_elem->list, &inode_list);
+
+ while (!list_empty(&inode_list)) {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_key key;
+ struct inode *inode;
+
+ ino_elem = list_first_entry(&inode_list, struct btrfs_ino_list,
+ list);
+ ino = ino_elem->ino;
+ parent = ino_elem->parent;
+ list_del(&ino_elem->list);
+ kfree(ino_elem);
+ if (ret)
+ continue;
+
+ btrfs_release_path(path);
+
+ inode = btrfs_iget(fs_info->sb, ino, root);
+ /*
+ * If the other inode that had a conflicting dir entry was
+ * deleted in the current transaction, we need to log its parent
+ * directory.
+ */
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ if (ret == -ENOENT) {
+ inode = btrfs_iget(fs_info->sb, parent, root);
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ } else {
+ ret = btrfs_log_inode(trans, root,
+ BTRFS_I(inode),
+ LOG_OTHER_INODE_ALL,
+ ctx);
+ btrfs_add_delayed_iput(inode);
+ }
+ }
+ continue;
+ }
+ /*
+ * If the inode was already logged skip it - otherwise we can
+ * hit an infinite loop. Example:
+ *
+ * From the commit root (previous transaction) we have the
+ * following inodes:
+ *
+ * inode 257 a directory
+ * inode 258 with references "zz" and "zz_link" on inode 257
+ * inode 259 with reference "a" on inode 257
+ *
+ * And in the current (uncommitted) transaction we have:
+ *
+ * inode 257 a directory, unchanged
+ * inode 258 with references "a" and "a2" on inode 257
+ * inode 259 with reference "zz_link" on inode 257
+ * inode 261 with reference "zz" on inode 257
+ *
+ * When logging inode 261 the following infinite loop could
+ * happen if we don't skip already logged inodes:
+ *
+ * - we detect inode 258 as a conflicting inode, with inode 261
+ * on reference "zz", and log it;
+ *
+ * - we detect inode 259 as a conflicting inode, with inode 258
+ * on reference "a", and log it;
+ *
+ * - we detect inode 258 as a conflicting inode, with inode 259
+ * on reference "zz_link", and log it - again! After this we
+ * repeat the above steps forever.
+ */
+ spin_lock(&BTRFS_I(inode)->lock);
+ /*
+ * Check the inode's logged_trans only instead of
+ * btrfs_inode_in_log(). This is because the last_log_commit of
+ * the inode is not updated when we only log that it exists and
+ * it has the full sync bit set (see btrfs_log_inode()).
+ */
+ if (BTRFS_I(inode)->logged_trans == trans->transid) {
+ spin_unlock(&BTRFS_I(inode)->lock);
+ btrfs_add_delayed_iput(inode);
+ continue;
+ }
+ spin_unlock(&BTRFS_I(inode)->lock);
+ /*
+ * We are safe logging the other inode without acquiring its
+ * lock as long as we log with the LOG_INODE_EXISTS mode. We
+ * are safe against concurrent renames of the other inode as
+ * well because during a rename we pin the log and update the
+ * log with the new name before we unpin it.
+ */
+ ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
+ LOG_OTHER_INODE, ctx);
+ if (ret) {
+ btrfs_add_delayed_iput(inode);
+ continue;
+ }
+
+ key.objectid = ino;
+ key.type = BTRFS_INODE_REF_KEY;
+ key.offset = 0;
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ btrfs_add_delayed_iput(inode);
+ continue;
+ }
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ u64 other_ino = 0;
+ u64 other_parent = 0;
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0) {
+ break;
+ } else if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid != ino ||
+ (key.type != BTRFS_INODE_REF_KEY &&
+ key.type != BTRFS_INODE_EXTREF_KEY)) {
+ ret = 0;
+ break;
+ }
+
+ ret = btrfs_check_ref_name_override(leaf, slot, &key,
+ BTRFS_I(inode), &other_ino,
+ &other_parent);
+ if (ret < 0)
+ break;
+ if (ret > 0) {
+ ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS);
+ if (!ino_elem) {
+ ret = -ENOMEM;
+ break;
+ }
+ ino_elem->ino = other_ino;
+ ino_elem->parent = other_parent;
+ list_add_tail(&ino_elem->list, &inode_list);
+ ret = 0;
+ }
+ path->slots[0]++;
+ }
+ btrfs_add_delayed_iput(inode);
+ }
+
+ return ret;
+}
+
+static int copy_inode_items_to_log(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct btrfs_key *min_key,
+ const struct btrfs_key *max_key,
+ struct btrfs_path *path,
+ struct btrfs_path *dst_path,
+ const u64 logged_isize,
+ const bool recursive_logging,
+ const int inode_only,
+ struct btrfs_log_ctx *ctx,
+ bool *need_log_inode_item)
+{
+ const u64 i_size = i_size_read(&inode->vfs_inode);
+ struct btrfs_root *root = inode->root;
+ int ins_start_slot = 0;
+ int ins_nr = 0;
+ int ret;
+
+ while (1) {
+ ret = btrfs_search_forward(root, min_key, path, trans->transid);
+ if (ret < 0)
+ return ret;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+again:
+ /* Note, ins_nr might be > 0 here, cleanup outside the loop */
+ if (min_key->objectid != max_key->objectid)
+ break;
+ if (min_key->type > max_key->type)
+ break;
+
+ if (min_key->type == BTRFS_INODE_ITEM_KEY) {
+ *need_log_inode_item = false;
+ } else if (min_key->type == BTRFS_EXTENT_DATA_KEY &&
+ min_key->offset >= i_size) {
+ /*
+ * Extents at and beyond eof are logged with
+ * btrfs_log_prealloc_extents().
+ * Only regular files have BTRFS_EXTENT_DATA_KEY keys,
+ * and no keys greater than that, so bail out.
+ */
+ break;
+ } else if ((min_key->type == BTRFS_INODE_REF_KEY ||
+ min_key->type == BTRFS_INODE_EXTREF_KEY) &&
+ inode->generation == trans->transid &&
+ !recursive_logging) {
+ u64 other_ino = 0;
+ u64 other_parent = 0;
+
+ ret = btrfs_check_ref_name_override(path->nodes[0],
+ path->slots[0], min_key, inode,
+ &other_ino, &other_parent);
+ if (ret < 0) {
+ return ret;
+ } else if (ret > 0 && ctx &&
+ other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
+ if (ins_nr > 0) {
+ ins_nr++;
+ } else {
+ ins_nr = 1;
+ ins_start_slot = path->slots[0];
+ }
+ ret = copy_items(trans, inode, dst_path, path,
+ ins_start_slot, ins_nr,
+ inode_only, logged_isize);
+ if (ret < 0)
+ return ret;
+ ins_nr = 0;
+
+ ret = log_conflicting_inodes(trans, root, path,
+ ctx, other_ino, other_parent);
+ if (ret)
+ return ret;
+ btrfs_release_path(path);
+ goto next_key;
+ }
+ } else if (min_key->type == BTRFS_XATTR_ITEM_KEY) {
+ /* Skip xattrs, logged later with btrfs_log_all_xattrs() */
+ if (ins_nr == 0)
+ goto next_slot;
+ ret = copy_items(trans, inode, dst_path, path,
+ ins_start_slot,
+ ins_nr, inode_only, logged_isize);
+ if (ret < 0)
+ return ret;
+ ins_nr = 0;
+ goto next_slot;
+ }
+
+ if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
+ ins_nr++;
+ goto next_slot;
+ } else if (!ins_nr) {
+ ins_start_slot = path->slots[0];
+ ins_nr = 1;
+ goto next_slot;
+ }
+
+ ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
+ ins_nr, inode_only, logged_isize);
+ if (ret < 0)
+ return ret;
+ ins_nr = 1;
+ ins_start_slot = path->slots[0];
+next_slot:
+ path->slots[0]++;
+ if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
+ btrfs_item_key_to_cpu(path->nodes[0], min_key,
+ path->slots[0]);
+ goto again;
+ }
+ if (ins_nr) {
+ ret = copy_items(trans, inode, dst_path, path,
+ ins_start_slot, ins_nr, inode_only,
+ logged_isize);
+ if (ret < 0)
+ return ret;
+ ins_nr = 0;
+ }
+ btrfs_release_path(path);
+next_key:
+ if (min_key->offset < (u64)-1) {
+ min_key->offset++;
+ } else if (min_key->type < max_key->type) {
+ min_key->type++;
+ min_key->offset = 0;
+ } else {
+ break;
+ }
+ }
+ if (ins_nr) {
+ ret = copy_items(trans, inode, dst_path, path, ins_start_slot,
+ ins_nr, inode_only, logged_isize);
+ if (ret)
+ return ret;
+ }
+
+ if (inode_only == LOG_INODE_ALL && S_ISREG(inode->vfs_inode.i_mode)) {
+ /*
+ * Release the path because otherwise we might attempt to double
+ * lock the same leaf with btrfs_log_prealloc_extents() below.
+ */
+ btrfs_release_path(path);
+ ret = btrfs_log_prealloc_extents(trans, inode, dst_path);
+ }
+
return ret;
}
@@ -4815,27 +5259,22 @@
static int btrfs_log_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_inode *inode,
int inode_only,
- const loff_t start,
- const loff_t end,
struct btrfs_log_ctx *ctx)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_path *path;
struct btrfs_path *dst_path;
struct btrfs_key min_key;
struct btrfs_key max_key;
struct btrfs_root *log = root->log_root;
int err = 0;
- int ret;
- int nritems;
- int ins_start_slot = 0;
- int ins_nr;
+ int ret = 0;
bool fast_search = false;
u64 ino = btrfs_ino(inode);
struct extent_map_tree *em_tree = &inode->extent_tree;
u64 logged_isize = 0;
bool need_log_inode_item = true;
bool xattrs_logged = false;
+ bool recursive_logging = false;
path = btrfs_alloc_path();
if (!path)
@@ -4864,15 +5303,19 @@
max_key.offset = (u64)-1;
/*
- * Only run delayed items if we are a dir or a new file.
- * Otherwise commit the delayed inode only, which is needed in
- * order for the log replay code to mark inodes for link count
- * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items).
+ * Only run delayed items if we are a directory. We want to make sure
+ * all directory indexes hit the fs/subvolume tree so we can find them
+ * and figure out which index ranges have to be logged.
+ *
+ * Otherwise commit the delayed inode only if the full sync flag is set,
+ * as we want to make sure an up to date version is in the subvolume
+ * tree so copy_inode_items_to_log() / copy_items() can find it and copy
+ * it to the log tree. For a non full sync, we always log the inode item
+ * based on the in-memory struct btrfs_inode which is always up to date.
*/
- if (S_ISDIR(inode->vfs_inode.i_mode) ||
- inode->generation > fs_info->last_trans_committed)
+ if (S_ISDIR(inode->vfs_inode.i_mode))
ret = btrfs_commit_inode_delayed_items(trans, inode);
- else
+ else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
ret = btrfs_commit_inode_delayed_inode(inode);
if (ret) {
@@ -4881,12 +5324,28 @@
return ret;
}
- if (inode_only == LOG_OTHER_INODE) {
- inode_only = LOG_INODE_EXISTS;
+ if (inode_only == LOG_OTHER_INODE || inode_only == LOG_OTHER_INODE_ALL) {
+ recursive_logging = true;
+ if (inode_only == LOG_OTHER_INODE)
+ inode_only = LOG_INODE_EXISTS;
+ else
+ inode_only = LOG_INODE_ALL;
mutex_lock_nested(&inode->log_mutex, SINGLE_DEPTH_NESTING);
} else {
mutex_lock(&inode->log_mutex);
}
+
+ /*
+ * For symlinks, we must always log their content, which is stored in an
+ * inline extent, otherwise we could end up with an empty symlink after
+ * log replay, which is invalid on linux (symlink(2) returns -ENOENT if
+ * one attempts to create an empty symlink).
+ * We don't need to worry about flushing delalloc, because when we create
+ * the inline extent when the symlink is created (we never have delalloc
+ * for symlinks).
+ */
+ if (S_ISLNK(inode->vfs_inode.i_mode))
+ inode_only = LOG_INODE_ALL;
/*
* a brute force approach to making sure we get the most uptodate
@@ -4955,170 +5414,12 @@
goto out_unlock;
}
- while (1) {
- ins_nr = 0;
- ret = btrfs_search_forward(root, &min_key,
- path, trans->transid);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- }
- if (ret != 0)
- break;
-again:
- /* note, ins_nr might be > 0 here, cleanup outside the loop */
- if (min_key.objectid != ino)
- break;
- if (min_key.type > max_key.type)
- break;
-
- if (min_key.type == BTRFS_INODE_ITEM_KEY)
- need_log_inode_item = false;
-
- if ((min_key.type == BTRFS_INODE_REF_KEY ||
- min_key.type == BTRFS_INODE_EXTREF_KEY) &&
- inode->generation == trans->transid) {
- u64 other_ino = 0;
-
- ret = btrfs_check_ref_name_override(path->nodes[0],
- path->slots[0], &min_key, inode,
- &other_ino);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- } else if (ret > 0 && ctx &&
- other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
- struct btrfs_key inode_key;
- struct inode *other_inode;
-
- if (ins_nr > 0) {
- ins_nr++;
- } else {
- ins_nr = 1;
- ins_start_slot = path->slots[0];
- }
- ret = copy_items(trans, inode, dst_path, path,
- ins_start_slot,
- ins_nr, inode_only,
- logged_isize);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- }
- ins_nr = 0;
- btrfs_release_path(path);
- inode_key.objectid = other_ino;
- inode_key.type = BTRFS_INODE_ITEM_KEY;
- inode_key.offset = 0;
- other_inode = btrfs_iget(fs_info->sb,
- &inode_key, root,
- NULL);
- /*
- * If the other inode that had a conflicting dir
- * entry was deleted in the current transaction,
- * we don't need to do more work nor fallback to
- * a transaction commit.
- */
- if (other_inode == ERR_PTR(-ENOENT)) {
- goto next_key;
- } else if (IS_ERR(other_inode)) {
- err = PTR_ERR(other_inode);
- goto out_unlock;
- }
- /*
- * We are safe logging the other inode without
- * acquiring its i_mutex as long as we log with
- * the LOG_INODE_EXISTS mode. We're safe against
- * concurrent renames of the other inode as well
- * because during a rename we pin the log and
- * update the log with the new name before we
- * unpin it.
- */
- err = btrfs_log_inode(trans, root,
- BTRFS_I(other_inode),
- LOG_OTHER_INODE, 0, LLONG_MAX,
- ctx);
- btrfs_add_delayed_iput(other_inode);
- if (err)
- goto out_unlock;
- else
- goto next_key;
- }
- }
-
- /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
- if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
- if (ins_nr == 0)
- goto next_slot;
- ret = copy_items(trans, inode, dst_path, path,
- ins_start_slot,
- ins_nr, inode_only, logged_isize);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- }
- ins_nr = 0;
- goto next_slot;
- }
-
- if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
- ins_nr++;
- goto next_slot;
- } else if (!ins_nr) {
- ins_start_slot = path->slots[0];
- ins_nr = 1;
- goto next_slot;
- }
-
- ret = copy_items(trans, inode, dst_path, path,
- ins_start_slot, ins_nr, inode_only,
- logged_isize);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- }
- ins_nr = 1;
- ins_start_slot = path->slots[0];
-next_slot:
-
- nritems = btrfs_header_nritems(path->nodes[0]);
- path->slots[0]++;
- if (path->slots[0] < nritems) {
- btrfs_item_key_to_cpu(path->nodes[0], &min_key,
- path->slots[0]);
- goto again;
- }
- if (ins_nr) {
- ret = copy_items(trans, inode, dst_path, path,
- ins_start_slot,
- ins_nr, inode_only, logged_isize);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- }
- ins_nr = 0;
- }
- btrfs_release_path(path);
-next_key:
- if (min_key.offset < (u64)-1) {
- min_key.offset++;
- } else if (min_key.type < max_key.type) {
- min_key.type++;
- min_key.offset = 0;
- } else {
- break;
- }
- }
- if (ins_nr) {
- ret = copy_items(trans, inode, dst_path, path,
- ins_start_slot, ins_nr, inode_only,
- logged_isize);
- if (ret < 0) {
- err = ret;
- goto out_unlock;
- }
- ins_nr = 0;
- }
+ err = copy_inode_items_to_log(trans, inode, &min_key, &max_key,
+ path, dst_path, logged_isize,
+ recursive_logging, inode_only, ctx,
+ &need_log_inode_item);
+ if (err)
+ goto out_unlock;
btrfs_release_path(path);
btrfs_release_path(dst_path);
@@ -5148,7 +5449,7 @@
}
if (fast_search) {
ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
- ctx, start, end);
+ ctx);
if (ret) {
err = ret;
goto out_unlock;
@@ -5157,31 +5458,8 @@
struct extent_map *em, *n;
write_lock(&em_tree->lock);
- /*
- * We can't just remove every em if we're called for a ranged
- * fsync - that is, one that doesn't cover the whole possible
- * file range (0 to LLONG_MAX). This is because we can have
- * em's that fall outside the range we're logging and therefore
- * their ordered operations haven't completed yet
- * (btrfs_finish_ordered_io() not invoked yet). This means we
- * didn't get their respective file extent item in the fs/subvol
- * tree yet, and need to let the next fast fsync (one which
- * consults the list of modified extent maps) find the em so
- * that it logs a matching file extent item and waits for the
- * respective ordered operation to complete (if it's still
- * running).
- *
- * Removing every em outside the range we're logging would make
- * the next fast fsync not log their matching file extent items,
- * therefore making us lose data after a log replay.
- */
- list_for_each_entry_safe(em, n, &em_tree->modified_extents,
- list) {
- const u64 mod_end = em->mod_start + em->mod_len - 1;
-
- if (em->mod_start >= start && mod_end <= end)
- list_del_init(&em->list);
- }
+ list_for_each_entry_safe(em, n, &em_tree->modified_extents, list)
+ list_del_init(&em->list);
write_unlock(&em_tree->lock);
}
@@ -5195,19 +5473,34 @@
}
/*
- * Don't update last_log_commit if we logged that an inode exists after
- * it was loaded to memory (full_sync bit set).
- * This is to prevent data loss when we do a write to the inode, then
- * the inode gets evicted after all delalloc was flushed, then we log
- * it exists (due to a rename for example) and then fsync it. This last
- * fsync would do nothing (not logging the extents previously written).
+ * If we are logging that an ancestor inode exists as part of logging a
+ * new name from a link or rename operation, don't mark the inode as
+ * logged - otherwise if an explicit fsync is made against an ancestor,
+ * the fsync considers the inode in the log and doesn't sync the log,
+ * resulting in the ancestor missing after a power failure unless the
+ * log was synced as part of an fsync against any other unrelated inode.
+ * So keep it simple for this case and just don't flag the ancestors as
+ * logged.
*/
- spin_lock(&inode->lock);
- inode->logged_trans = trans->transid;
- if (inode_only != LOG_INODE_EXISTS ||
- !test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
- inode->last_log_commit = inode->last_sub_trans;
- spin_unlock(&inode->lock);
+ if (!ctx ||
+ !(S_ISDIR(inode->vfs_inode.i_mode) && ctx->logging_new_name &&
+ &inode->vfs_inode != ctx->inode)) {
+ spin_lock(&inode->lock);
+ inode->logged_trans = trans->transid;
+ /*
+ * Don't update last_log_commit if we logged that an inode exists
+ * after it was loaded to memory (full_sync bit set).
+ * This is to prevent data loss when we do a write to the inode,
+ * then the inode gets evicted after all delalloc was flushed,
+ * then we log it exists (due to a rename for example) and then
+ * fsync it. This last fsync would do nothing (not logging the
+ * extents previously written).
+ */
+ if (inode_only != LOG_INODE_EXISTS ||
+ !test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
+ inode->last_log_commit = inode->last_sub_trans;
+ spin_unlock(&inode->lock);
+ }
out_unlock:
mutex_unlock(&inode->log_mutex);
@@ -5244,7 +5537,7 @@
* Make sure any commits to the log are forced to be full
* commits.
*/
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
ret = true;
}
mutex_unlock(&inode->log_mutex);
@@ -5432,7 +5725,7 @@
continue;
btrfs_release_path(path);
- di_inode = btrfs_iget(fs_info->sb, &di_key, root, NULL);
+ di_inode = btrfs_iget(fs_info->sb, di_key.objectid, root);
if (IS_ERR(di_inode)) {
ret = PTR_ERR(di_inode);
goto next_dir_inode;
@@ -5444,10 +5737,10 @@
}
ctx->log_new_dentries = false;
- if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
+ if (type == BTRFS_FT_DIR)
log_mode = LOG_INODE_ALL;
ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode),
- log_mode, 0, LLONG_MAX, ctx);
+ log_mode, ctx);
if (!ret &&
btrfs_must_commit_transaction(trans, BTRFS_I(di_inode)))
ret = 1;
@@ -5558,8 +5851,8 @@
cur_offset = item_size;
}
- dir_inode = btrfs_iget(fs_info->sb, &inode_key,
- root, NULL);
+ dir_inode = btrfs_iget(fs_info->sb, inode_key.objectid,
+ root);
/*
* If the parent inode was deleted, return an error to
* fallback to a transaction commit. This is to prevent
@@ -5591,7 +5884,7 @@
if (ctx)
ctx->log_new_dentries = false;
ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode),
- LOG_INODE_ALL, 0, LLONG_MAX, ctx);
+ LOG_INODE_ALL, ctx);
if (!ret &&
btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode)))
ret = 1;
@@ -5610,6 +5903,192 @@
return ret;
}
+static int log_new_ancestors(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_key found_key;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
+
+ while (true) {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ const u64 last_committed = fs_info->last_trans_committed;
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ struct btrfs_key search_key;
+ struct inode *inode;
+ u64 ino;
+ int ret = 0;
+
+ btrfs_release_path(path);
+
+ ino = found_key.offset;
+
+ search_key.objectid = found_key.offset;
+ search_key.type = BTRFS_INODE_ITEM_KEY;
+ search_key.offset = 0;
+ inode = btrfs_iget(fs_info->sb, ino, root);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ if (BTRFS_I(inode)->generation > last_committed)
+ ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
+ LOG_INODE_EXISTS, ctx);
+ btrfs_add_delayed_iput(inode);
+ if (ret)
+ return ret;
+
+ if (search_key.objectid == BTRFS_FIRST_FREE_OBJECTID)
+ break;
+
+ search_key.type = BTRFS_INODE_REF_KEY;
+ ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ return ret;
+ else if (ret > 0)
+ return -ENOENT;
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ }
+
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+ if (found_key.objectid != search_key.objectid ||
+ found_key.type != BTRFS_INODE_REF_KEY)
+ return -ENOENT;
+ }
+ return 0;
+}
+
+static int log_new_ancestors_fast(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct dentry *parent,
+ struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_root *root = inode->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct dentry *old_parent = NULL;
+ struct super_block *sb = inode->vfs_inode.i_sb;
+ int ret = 0;
+
+ while (true) {
+ if (!parent || d_really_is_negative(parent) ||
+ sb != parent->d_sb)
+ break;
+
+ inode = BTRFS_I(d_inode(parent));
+ if (root != inode->root)
+ break;
+
+ if (inode->generation > fs_info->last_trans_committed) {
+ ret = btrfs_log_inode(trans, root, inode,
+ LOG_INODE_EXISTS, ctx);
+ if (ret)
+ break;
+ }
+ if (IS_ROOT(parent))
+ break;
+
+ parent = dget_parent(parent);
+ dput(old_parent);
+ old_parent = parent;
+ }
+ dput(old_parent);
+
+ return ret;
+}
+
+static int log_all_new_ancestors(struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode,
+ struct dentry *parent,
+ struct btrfs_log_ctx *ctx)
+{
+ struct btrfs_root *root = inode->root;
+ const u64 ino = btrfs_ino(inode);
+ struct btrfs_path *path;
+ struct btrfs_key search_key;
+ int ret;
+
+ /*
+ * For a single hard link case, go through a fast path that does not
+ * need to iterate the fs/subvolume tree.
+ */
+ if (inode->vfs_inode.i_nlink < 2)
+ return log_new_ancestors_fast(trans, inode, parent, ctx);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ search_key.objectid = ino;
+ search_key.type = BTRFS_INODE_REF_KEY;
+ search_key.offset = 0;
+again:
+ ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ if (ret == 0)
+ path->slots[0]++;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ struct btrfs_key found_key;
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ else if (ret > 0)
+ break;
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
+ if (found_key.objectid != ino ||
+ found_key.type > BTRFS_INODE_EXTREF_KEY)
+ break;
+
+ /*
+ * Don't deal with extended references because they are rare
+ * cases and too complex to deal with (we would need to keep
+ * track of which subitem we are processing for each item in
+ * this loop, etc). So just return some error to fallback to
+ * a transaction commit.
+ */
+ if (found_key.type == BTRFS_INODE_EXTREF_KEY) {
+ ret = -EMLINK;
+ goto out;
+ }
+
+ /*
+ * Logging ancestors needs to do more searches on the fs/subvol
+ * tree, so it releases the path as needed to avoid deadlocks.
+ * Keep track of the last inode ref key and resume from that key
+ * after logging all new ancestors for the current hard link.
+ */
+ memcpy(&search_key, &found_key, sizeof(search_key));
+
+ ret = log_new_ancestors(trans, root, path, ctx);
+ if (ret)
+ goto out;
+ btrfs_release_path(path);
+ goto again;
+ }
+ ret = 0;
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
/*
* helper function around btrfs_log_inode to make sure newly created
* parent directories also end up in the log. A minimal inode and backref
@@ -5619,19 +6098,15 @@
static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode,
struct dentry *parent,
- const loff_t start,
- const loff_t end,
int inode_only,
struct btrfs_log_ctx *ctx)
{
struct btrfs_root *root = inode->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct super_block *sb;
- struct dentry *old_parent = NULL;
int ret = 0;
u64 last_committed = fs_info->last_trans_committed;
bool log_dentries = false;
- struct btrfs_inode *orig_inode = inode;
sb = inode->vfs_inode.i_sb;
@@ -5665,7 +6140,8 @@
* (since logging them is pointless, a link count of 0 means they
* will never be accessible).
*/
- if (btrfs_inode_in_log(inode, trans->transid) ||
+ if ((btrfs_inode_in_log(inode, trans->transid) &&
+ list_empty(&ctx->ordered_extents)) ||
inode->vfs_inode.i_nlink == 0) {
ret = BTRFS_NO_LOG_SYNC;
goto end_no_trans;
@@ -5675,7 +6151,7 @@
if (ret)
goto end_no_trans;
- ret = btrfs_log_inode(trans, root, inode, inode_only, start, end, ctx);
+ ret = btrfs_log_inode(trans, root, inode, inode_only, ctx);
if (ret)
goto end_trans;
@@ -5737,56 +6213,22 @@
* and has a link count of 2.
*/
if (inode->last_unlink_trans > last_committed) {
- ret = btrfs_log_all_parents(trans, orig_inode, ctx);
+ ret = btrfs_log_all_parents(trans, inode, ctx);
if (ret)
goto end_trans;
}
- /*
- * If a new hard link was added to the inode in the current transaction
- * and its link count is now greater than 1, we need to fallback to a
- * transaction commit, otherwise we can end up not logging all its new
- * parents for all the hard links. Here just from the dentry used to
- * fsync, we can not visit the ancestor inodes for all the other hard
- * links to figure out if any is new, so we fallback to a transaction
- * commit (instead of adding a lot of complexity of scanning a btree,
- * since this scenario is not a common use case).
- */
- if (inode->vfs_inode.i_nlink > 1 &&
- inode->last_link_trans > last_committed) {
- ret = -EMLINK;
+ ret = log_all_new_ancestors(trans, inode, parent, ctx);
+ if (ret)
goto end_trans;
- }
- while (1) {
- if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
- break;
-
- inode = BTRFS_I(d_inode(parent));
- if (root != inode->root)
- break;
-
- if (inode->generation > last_committed) {
- ret = btrfs_log_inode(trans, root, inode,
- LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
- if (ret)
- goto end_trans;
- }
- if (IS_ROOT(parent))
- break;
-
- parent = dget_parent(parent);
- dput(old_parent);
- old_parent = parent;
- }
if (log_dentries)
- ret = log_new_dir_dentries(trans, root, orig_inode, ctx);
+ ret = log_new_dir_dentries(trans, root, inode, ctx);
else
ret = 0;
end_trans:
- dput(old_parent);
if (ret < 0) {
- btrfs_set_log_full_commit(fs_info, trans);
+ btrfs_set_log_full_commit(trans);
ret = 1;
}
@@ -5805,15 +6247,13 @@
*/
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
struct dentry *dentry,
- const loff_t start,
- const loff_t end,
struct btrfs_log_ctx *ctx)
{
struct dentry *parent = dget_parent(dentry);
int ret;
ret = btrfs_log_inode_parent(trans, BTRFS_I(d_inode(dentry)), parent,
- start, end, LOG_INODE_ALL, ctx);
+ LOG_INODE_ALL, ctx);
dput(parent);
return ret;
@@ -5830,12 +6270,11 @@
struct btrfs_trans_handle *trans;
struct btrfs_key key;
struct btrfs_key found_key;
- struct btrfs_key tmp_key;
struct btrfs_root *log;
struct btrfs_fs_info *fs_info = log_root_tree->fs_info;
struct walk_control wc = {
.process_func = process_one_buffer,
- .stage = 0,
+ .stage = LOG_WALK_PIN_ONLY,
};
path = btrfs_alloc_path();
@@ -5884,7 +6323,7 @@
if (found_key.objectid != BTRFS_TREE_LOG_OBJECTID)
break;
- log = btrfs_read_fs_root(log_root_tree, &found_key);
+ log = btrfs_read_tree_root(log_root_tree, &found_key);
if (IS_ERR(log)) {
ret = PTR_ERR(log);
btrfs_handle_fs_error(fs_info, ret,
@@ -5892,11 +6331,8 @@
goto error;
}
- tmp_key.objectid = found_key.offset;
- tmp_key.type = BTRFS_ROOT_ITEM_KEY;
- tmp_key.offset = (u64)-1;
-
- wc.replay_dest = btrfs_read_fs_root_no_name(fs_info, &tmp_key);
+ wc.replay_dest = btrfs_get_fs_root(fs_info, found_key.offset,
+ true);
if (IS_ERR(wc.replay_dest)) {
ret = PTR_ERR(wc.replay_dest);
@@ -5912,12 +6348,10 @@
* each subsequent pass.
*/
if (ret == -ENOENT)
- ret = btrfs_pin_extent_for_log_replay(fs_info,
+ ret = btrfs_pin_extent_for_log_replay(trans,
log->node->start,
log->node->len);
- free_extent_buffer(log->node);
- free_extent_buffer(log->commit_root);
- kfree(log);
+ btrfs_put_root(log);
if (!ret)
goto next;
@@ -5953,9 +6387,8 @@
}
wc.replay_dest->log_root = NULL;
- free_extent_buffer(log->node);
- free_extent_buffer(log->commit_root);
- kfree(log);
+ btrfs_put_root(wc.replay_dest);
+ btrfs_put_root(log);
if (ret)
goto error;
@@ -5986,10 +6419,9 @@
if (ret)
return ret;
- free_extent_buffer(log_root_tree->node);
log_root_tree->log_root = NULL;
clear_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags);
- kfree(log_root_tree);
+ btrfs_put_root(log_root_tree);
return 0;
error:
@@ -6085,26 +6517,12 @@
/*
* Call this after adding a new name for a file and it will properly
* update the log to reflect the new name.
- *
- * @ctx can not be NULL when @sync_log is false, and should be NULL when it's
- * true (because it's not used).
- *
- * Return value depends on whether @sync_log is true or false.
- * When true: returns BTRFS_NEED_TRANS_COMMIT if the transaction needs to be
- * committed by the caller, and BTRFS_DONT_NEED_TRANS_COMMIT
- * otherwise.
- * When false: returns BTRFS_DONT_NEED_LOG_SYNC if the caller does not need to
- * to sync the log, BTRFS_NEED_LOG_SYNC if it needs to sync the log,
- * or BTRFS_NEED_TRANS_COMMIT if the transaction needs to be
- * committed (without attempting to sync the log).
*/
-int btrfs_log_new_name(struct btrfs_trans_handle *trans,
+void btrfs_log_new_name(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode, struct btrfs_inode *old_dir,
- struct dentry *parent,
- bool sync_log, struct btrfs_log_ctx *ctx)
+ struct dentry *parent)
{
- struct btrfs_fs_info *fs_info = trans->fs_info;
- int ret;
+ struct btrfs_log_ctx ctx;
/*
* this will force the logging code to walk the dentry chain
@@ -6117,36 +6535,19 @@
* if this inode hasn't been logged and directory we're renaming it
* from hasn't been logged, we don't need to log it
*/
- if (inode->logged_trans <= fs_info->last_trans_committed &&
- (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed))
- return sync_log ? BTRFS_DONT_NEED_TRANS_COMMIT :
- BTRFS_DONT_NEED_LOG_SYNC;
+ if (!inode_logged(trans, inode) &&
+ (!old_dir || !inode_logged(trans, old_dir)))
+ return;
- if (sync_log) {
- struct btrfs_log_ctx ctx2;
-
- btrfs_init_log_ctx(&ctx2, &inode->vfs_inode);
- ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX,
- LOG_INODE_EXISTS, &ctx2);
- if (ret == BTRFS_NO_LOG_SYNC)
- return BTRFS_DONT_NEED_TRANS_COMMIT;
- else if (ret)
- return BTRFS_NEED_TRANS_COMMIT;
-
- ret = btrfs_sync_log(trans, inode->root, &ctx2);
- if (ret)
- return BTRFS_NEED_TRANS_COMMIT;
- return BTRFS_DONT_NEED_TRANS_COMMIT;
- }
-
- ASSERT(ctx);
- ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX,
- LOG_INODE_EXISTS, ctx);
- if (ret == BTRFS_NO_LOG_SYNC)
- return BTRFS_DONT_NEED_LOG_SYNC;
- else if (ret)
- return BTRFS_NEED_TRANS_COMMIT;
-
- return BTRFS_NEED_LOG_SYNC;
+ btrfs_init_log_ctx(&ctx, &inode->vfs_inode);
+ ctx.logging_new_name = true;
+ /*
+ * We don't care about the return value. If we fail to log the new name
+ * then we know the next attempt to sync the log will fallback to a full
+ * transaction commit (due to a call to btrfs_set_log_full_commit()), so
+ * we don't need to worry about getting a log committed that has an
+ * inconsistent state after a rename operation.
+ */
+ btrfs_log_inode_parent(trans, inode, parent, LOG_INODE_EXISTS, &ctx);
}
--
Gitblit v1.6.2