Signed-off-by: Filipe David Borba Manana <fdmanana@xxxxxxxxx>
---
fs/btrfs/ctree.c | 266 +++++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 204 insertions(+), 62 deletions(-)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 59664f6..e99e5f6 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -474,6 +474,8 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
* the index is the shifted logical of the *new* root node for root replace
* operations, or the shifted logical of the affected block for all other
* operations.
+ *
+ * Note: must be called with write lock (tree_mod_log_write_lock).
*/
static noinline int
__tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
@@ -486,20 +488,6 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
BUG_ON(!tm);
- tree_mod_log_write_lock(fs_info);
- if (list_empty(&fs_info->tree_mod_seq_list)) {
- tree_mod_log_write_unlock(fs_info);
- /*
- * Ok we no longer care about logging modifications, free up tm
- * and return 0. Any callers shouldn't be using tm after
- * calling tree_mod_log_insert, but if they do we can just
- * change this to return a special error code to let the callers
- * do their own thing.
- */
- kfree(tm);
- return 0;
- }
-
spin_lock(&fs_info->tree_mod_seq_lock);
tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info);
spin_unlock(&fs_info->tree_mod_seq_lock);
@@ -527,7 +515,6 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
rb_link_node(&tm->node, parent, new);
rb_insert_color(&tm->node, tm_root);
out:
- tree_mod_log_write_unlock(fs_info);
return ret;
}
@@ -544,19 +531,38 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info,
return 1;
if (eb && btrfs_header_level(eb) == 0)
return 1;
+
+ tree_mod_log_write_lock(fs_info);
+ if (list_empty(&(fs_info)->tree_mod_seq_list)) {
+ tree_mod_log_write_unlock(fs_info);
+ return 1;
+ }
+
return 0;
}
-static inline int
-__tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int slot,
- enum mod_log_op op, gfp_t flags)
+/* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
+static inline int tree_mod_need_log(const struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb)
+{
+ smp_mb();
+ if (list_empty(&(fs_info)->tree_mod_seq_list))
+ return 0;
+ if (eb && btrfs_header_level(eb) == 0)
+ return 0;
+
+ return 1;
+}
+
+static struct tree_mod_elem *
+alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
+ enum mod_log_op op, gfp_t flags)
{
struct tree_mod_elem *tm;
tm = kzalloc(sizeof(*tm), flags);
if (!tm)
- return -ENOMEM;
+ return NULL;
tm->index = eb->start >> PAGE_CACHE_SHIFT;
if (op != MOD_LOG_KEY_ADD) {
@@ -567,7 +573,7 @@ __tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
tm->slot = slot;
tm->generation = btrfs_node_ptr_generation(eb, slot);
- return __tree_mod_log_insert(fs_info, tm);
+ return tm;
}
static noinline int
@@ -575,10 +581,25 @@ tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int slot,
enum mod_log_op op, gfp_t flags)
{
- if (tree_mod_dont_log(fs_info, eb))
+ struct tree_mod_elem *tm;
+ int ret;
+
+ if (!tree_mod_need_log(fs_info, eb))
return 0;
- return __tree_mod_log_insert_key(fs_info, eb, slot, op, flags);
+ tm = alloc_tree_mod_elem(eb, slot, op, flags);
+ if (!tm)
+ return -ENOMEM;
+
+ if (tree_mod_dont_log(fs_info, eb)) {
+ kfree(tm);
+ return 0;
+ }
+
+ ret = __tree_mod_log_insert(fs_info, tm);
+ tree_mod_log_write_unlock(fs_info);
+
+ return ret;
}
static noinline int
@@ -586,51 +607,76 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int dst_slot, int src_slot,
int nr_items, gfp_t flags)
{
- struct tree_mod_elem *tm;
- int ret;
+ struct tree_mod_elem *tm = NULL;
+ struct tree_mod_elem **tm_list = NULL;
+ int ret = 0;
int i;
- if (tree_mod_dont_log(fs_info, eb))
+ if (!tree_mod_need_log(fs_info, eb))
return 0;
+ tm = kzalloc(sizeof(*tm), flags);
+ if (!tm)
+ return -ENOMEM;
+
+ tm->index = eb->start >> PAGE_CACHE_SHIFT;
+ tm->slot = src_slot;
+ tm->move.dst_slot = dst_slot;
+ tm->move.nr_items = nr_items;
+ tm->op = MOD_LOG_MOVE_KEYS;
+
+ tm_list = kzalloc(nr_items * sizeof(struct tree_mod_elem *), flags);
+ if (!tm_list) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+
+ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
+ tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
+ MOD_LOG_KEY_REMOVE_WHILE_MOVING, flags);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+
+ if (tree_mod_dont_log(fs_info, eb))
+ goto free_tms;
+
/*
* When we override something during the move, we log these removals.
* This can only happen when we move towards the beginning of the
* buffer, i.e. dst_slot < src_slot.
*/
for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
- ret = __tree_mod_log_insert_key(fs_info, eb, i + dst_slot,
- MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
+ ret = __tree_mod_log_insert(fs_info, tm_list[i]);
BUG_ON(ret < 0);
}
- tm = kzalloc(sizeof(*tm), flags);
- if (!tm)
- return -ENOMEM;
+ ret = __tree_mod_log_insert(fs_info, tm);
+ tree_mod_log_write_unlock(fs_info);
+ kfree(tm_list);
- tm->index = eb->start >> PAGE_CACHE_SHIFT;
- tm->slot = src_slot;
- tm->move.dst_slot = dst_slot;
- tm->move.nr_items = nr_items;
- tm->op = MOD_LOG_MOVE_KEYS;
+ return ret;
+free_tms:
+ for (i = 0; i < nr_items; i++)
+ kfree(tm_list[i]);
+ kfree(tm_list);
+ kfree(tm);
- return __tree_mod_log_insert(fs_info, tm);
+ return ret;
}
static inline void
-__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
+__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
+ struct tree_mod_elem **tm_list,
+ int nritems)
{
int i;
- u32 nritems;
int ret;
- if (btrfs_header_level(eb) == 0)
- return;
-
- nritems = btrfs_header_nritems(eb);
for (i = nritems - 1; i >= 0; i--) {
- ret = __tree_mod_log_insert_key(fs_info, eb, i,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
+ ret = __tree_mod_log_insert(fs_info, tm_list[i]);
BUG_ON(ret < 0);
}
}
@@ -641,17 +687,38 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
struct extent_buffer *new_root, gfp_t flags,
int log_removal)
{
- struct tree_mod_elem *tm;
+ struct tree_mod_elem *tm = NULL;
+ struct tree_mod_elem **tm_list = NULL;
+ int nritems = 0;
+ int ret = 0;
+ int i;
- if (tree_mod_dont_log(fs_info, NULL))
+ if (!tree_mod_need_log(fs_info, NULL))
return 0;
- if (log_removal)
- __tree_mod_log_free_eb(fs_info, old_root);
+ if (log_removal && btrfs_header_level(old_root) > 0) {
+ nritems = btrfs_header_nritems(old_root);
+ tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
+ flags);
+ if (!tm_list) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ for (i = 0; i < nritems; i++) {
+ tm_list[i] = alloc_tree_mod_elem(old_root, i,
+ MOD_LOG_KEY_REMOVE_WHILE_FREEING, flags);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+ }
tm = kzalloc(sizeof(*tm), flags);
- if (!tm)
- return -ENOMEM;
+ if (!tm) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
tm->index = new_root->start >> PAGE_CACHE_SHIFT;
tm->old_root.logical = old_root->start;
@@ -659,7 +726,27 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
tm->generation = btrfs_header_generation(old_root);
tm->op = MOD_LOG_ROOT_REPLACE;
- return __tree_mod_log_insert(fs_info, tm);
+ if (tree_mod_dont_log(fs_info, NULL))
+ goto free_tms;
+
+ if (tm_list)
+ __tree_mod_log_free_eb(fs_info, tm_list, nritems);
+
+ ret = __tree_mod_log_insert(fs_info, tm);
+ tree_mod_log_write_unlock(fs_info);
+ kfree(tm_list);
+
+ return ret;
+
+free_tms:
+ if (tm_list) {
+ for (i = 0; i < nritems; i++)
+ kfree(tm_list[i]);
+ kfree(tm_list);
+ }
+ kfree(tm);
+
+ return ret;
}
static struct tree_mod_elem *
@@ -733,26 +820,51 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
struct extent_buffer *src, unsigned long dst_offset,
unsigned long src_offset, int nr_items)
{
+ struct tree_mod_elem **tm_list = NULL;
+ struct tree_mod_elem **tm_list_add, **tm_list_rem;
int ret;
int i;
- if (tree_mod_dont_log(fs_info, NULL))
+ if (!tree_mod_need_log(fs_info, NULL))
return;
if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
return;
+ tm_list = kzalloc(nr_items * 2 * sizeof(struct tree_mod_elem *),
+ GFP_NOFS);
+ BUG_ON(!tm_list);
