Merge branch 'allocator-fixes' into for-linus-4.4
Signed-off-by: Chris Mason <clm@fb.com>
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ced08c9..bc3c711 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1950,6 +1950,9 @@
int send_in_progress;
struct btrfs_subvolume_writers *subv_writers;
atomic_t will_be_snapshoted;
+
+ /* For qgroup metadata space reserve */
+ atomic_t qgroup_meta_rsv;
};
struct btrfs_ioctl_defrag_range_args {
@@ -3470,8 +3473,11 @@
BTRFS_RESERVE_FLUSH_ALL,
};
-int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes);
-void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
+int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
+int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes);
+void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
+void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+ u64 len);
void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
@@ -3487,8 +3493,8 @@
u64 qgroup_reserved);
int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
+void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root,
unsigned short type);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index ac3e81d..bd9b63b 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -476,6 +476,8 @@
INIT_LIST_HEAD(&head_ref->ref_list);
head_ref->processing = 0;
head_ref->total_ref_mod = count_mod;
+ head_ref->qgroup_reserved = 0;
+ head_ref->qgroup_ref_root = 0;
/* Record qgroup extent info if provided */
if (qrecord) {
@@ -746,6 +748,33 @@
return 0;
}
+int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
+ struct btrfs_trans_handle *trans,
+ u64 ref_root, u64 bytenr, u64 num_bytes)
+{
+ struct btrfs_delayed_ref_root *delayed_refs;
+ struct btrfs_delayed_ref_head *ref_head;
+ int ret = 0;
+
+ if (!fs_info->quota_enabled || !is_fstree(ref_root))
+ return 0;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+
+ spin_lock(&delayed_refs->lock);
+ ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0);
+ if (!ref_head) {
+ ret = -ENOENT;
+ goto out;
+ }
+ WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root);
+ ref_head->qgroup_ref_root = ref_root;
+ ref_head->qgroup_reserved = num_bytes;
+out:
+ spin_unlock(&delayed_refs->lock);
+ return ret;
+}
+
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 13fb5e6..d4c41e2 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -113,6 +113,17 @@
int total_ref_mod;
/*
+ * For qgroup reserved space freeing.
+ *
+ * ref_root and reserved will be recorded after
+ * BTRFS_ADD_DELAYED_EXTENT is called.
+ * And will be used to free reserved qgroup space at
+ * run_delayed_refs() time.
+ */
+ u64 qgroup_ref_root;
+ u64 qgroup_reserved;
+
+ /*
* when a new extent is allocated, it is just reserved in memory
* The actual extent isn't inserted into the extent allocation tree
* until the delayed ref is processed. must_insert_reserved is
@@ -242,6 +253,9 @@
u64 owner, u64 offset, int action,
struct btrfs_delayed_extent_op *extent_op,
int no_quota);
+int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
+ struct btrfs_trans_handle *trans,
+ u64 ref_root, u64 bytenr, u64 num_bytes);
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index dceabb1..86a11a9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1267,6 +1267,7 @@
atomic_set(&root->orphan_inodes, 0);
atomic_set(&root->refs, 1);
atomic_set(&root->will_be_snapshoted, 0);
+ atomic_set(&root->qgroup_meta_rsv, 0);
root->log_transid = 0;
root->log_transid_committed = -1;
root->last_log_commit = 0;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4757645..92fdbc6 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2409,6 +2409,11 @@
node->num_bytes);
}
}
+
+ /* Also free its reserved qgroup space */
+ btrfs_qgroup_free_delayed_ref(root->fs_info,
+ head->qgroup_ref_root,
+ head->qgroup_reserved);
return ret;
}
@@ -3424,7 +3429,7 @@
num_pages *= 16;
num_pages *= PAGE_CACHE_SIZE;
- ret = btrfs_check_data_free_space(inode, num_pages, num_pages);
+ ret = btrfs_check_data_free_space(inode, 0, num_pages);
if (ret)
goto out_put;
@@ -3443,7 +3448,7 @@
dcs = BTRFS_DC_SETUP;
else if (ret == -ENOSPC)
set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags);
- btrfs_free_reserved_data_space(inode, num_pages);
+ btrfs_free_reserved_data_space(inode, 0, num_pages);
out_put:
iput(inode);
@@ -3983,11 +3988,7 @@
return ret;
}
-/*
- * This will check the space that the inode allocates from to make sure we have
- * enough space for bytes.
- */
-int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes)
+int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
{
struct btrfs_space_info *data_sinfo;
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -4109,38 +4110,86 @@
data_sinfo->flags, bytes, 1);
return -ENOSPC;
}
- ret = btrfs_qgroup_reserve(root, write_bytes);
- if (ret)
- goto out;
data_sinfo->bytes_may_use += bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
data_sinfo->flags, bytes, 1);
-out:
spin_unlock(&data_sinfo->lock);
return ret;
}
/*
- * Called if we need to clear a data reservation for this inode.
+ * New check_data_free_space() with ability for precious data reservation
+ * Will replace old btrfs_check_data_free_space(), but for patch split,
+ * add a new function first and then replace it.
*/
-void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
+int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ int ret;
+
+ /* align the range */
+ len = round_up(start + len, root->sectorsize) -
+ round_down(start, root->sectorsize);
+ start = round_down(start, root->sectorsize);
+
+ ret = btrfs_alloc_data_chunk_ondemand(inode, len);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * Use new btrfs_qgroup_reserve_data to reserve precious data space
+ *
+ * TODO: Find a good method to avoid reserve data space for NOCOW
+ * range, but don't impact performance on quota disable case.
+ */
+ ret = btrfs_qgroup_reserve_data(inode, start, len);
+ return ret;
+}
+
+/*
+ * Called if we need to clear a data reservation for this inode
+ * Normally in a error case.
+ *
+ * This one will *NOT* use accurate qgroup reserved space API, just for case
+ * which we can't sleep and is sure it won't affect qgroup reserved space.
+ * Like clear_bit_hook().
+ */
+void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+ u64 len)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_space_info *data_sinfo;
- /* make sure bytes are sectorsize aligned */
- bytes = ALIGN(bytes, root->sectorsize);
+ /* Make sure the range is aligned to sectorsize */
+ len = round_up(start + len, root->sectorsize) -
+ round_down(start, root->sectorsize);
+ start = round_down(start, root->sectorsize);
data_sinfo = root->fs_info->data_sinfo;
spin_lock(&data_sinfo->lock);
- WARN_ON(data_sinfo->bytes_may_use < bytes);
- data_sinfo->bytes_may_use -= bytes;
+ if (WARN_ON(data_sinfo->bytes_may_use < len))
+ data_sinfo->bytes_may_use = 0;
+ else
+ data_sinfo->bytes_may_use -= len;
trace_btrfs_space_reservation(root->fs_info, "space_info",
- data_sinfo->flags, bytes, 0);
+ data_sinfo->flags, len, 0);
spin_unlock(&data_sinfo->lock);
}
+/*
+ * Called if we need to clear a data reservation for this inode
+ * Normally in a error case.
+ *
+ * This one will handle the per-indoe data rsv map for accurate reserved
+ * space framework.
+ */
+void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
+{
+ btrfs_free_reserved_data_space_noquota(inode, start, len);
+ btrfs_qgroup_free_data(inode, start, len);
+}
+
static void force_metadata_allocation(struct btrfs_fs_info *info)
{
struct list_head *head = &info->space_info;
@@ -5417,7 +5466,7 @@
if (root->fs_info->quota_enabled) {
/* One for parent inode, two for dir entries */
num_bytes = 3 * root->nodesize;
- ret = btrfs_qgroup_reserve(root, num_bytes);
+ ret = btrfs_qgroup_reserve_meta(root, num_bytes);
if (ret)
return ret;
} else {
@@ -5435,10 +5484,8 @@
if (ret == -ENOSPC && use_global_rsv)
ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes);
- if (ret) {
- if (*qgroup_reserved)
- btrfs_qgroup_free(root, *qgroup_reserved);
- }
+ if (ret && *qgroup_reserved)
+ btrfs_qgroup_free_meta(root, *qgroup_reserved);
return ret;
}
@@ -5599,15 +5646,15 @@
spin_unlock(&BTRFS_I(inode)->lock);
if (root->fs_info->quota_enabled) {
- ret = btrfs_qgroup_reserve(root, nr_extents * root->nodesize);
+ ret = btrfs_qgroup_reserve_meta(root,
+ nr_extents * root->nodesize);
if (ret)
goto out_fail;
}
ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
if (unlikely(ret)) {
- if (root->fs_info->quota_enabled)
- btrfs_qgroup_free(root, nr_extents * root->nodesize);
+ btrfs_qgroup_free_meta(root, nr_extents * root->nodesize);
goto out_fail;
}
@@ -5730,41 +5777,48 @@
}
/**
- * btrfs_delalloc_reserve_space - reserve data and metadata space for delalloc
+ * btrfs_delalloc_reserve_space - reserve data and metadata space for
+ * delalloc
* @inode: inode we're writing to
- * @num_bytes: the number of bytes we want to allocate
+ * @start: start range we are writing to
+ * @len: how long the range we are writing to
+ *
+ * TODO: This function will finally replace old btrfs_delalloc_reserve_space()
*
* This will do the following things
*
- * o reserve space in the data space info for num_bytes
- * o reserve space in the metadata space info based on number of outstanding
- * extents and how much csums will be needed
- * o add to the inodes ->delalloc_bytes
- * o add it to the fs_info's delalloc inodes list.
+ * o reserve space in data space info for num bytes
+ * and reserve precious corresponding qgroup space
+ * (Done in check_data_free_space)
*
- * This will return 0 for success and -ENOSPC if there is no space left.
+ * o reserve space for metadata space, based on the number of outstanding
+ * extents and how much csums will be needed
+ * also reserve metadata space in a per root over-reserve method.
+ * o add to the inodes->delalloc_bytes
+ * o add it to the fs_info's delalloc inodes list.
+ * (Above 3 all done in delalloc_reserve_metadata)
+ *
+ * Return 0 for success
+ * Return <0 for error(-ENOSPC or -EQUOT)
*/
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes)
+int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
{
int ret;
- ret = btrfs_check_data_free_space(inode, num_bytes, num_bytes);
- if (ret)
+ ret = btrfs_check_data_free_space(inode, start, len);
+ if (ret < 0)
return ret;
-
- ret = btrfs_delalloc_reserve_metadata(inode, num_bytes);
- if (ret) {
- btrfs_free_reserved_data_space(inode, num_bytes);
- return ret;
- }
-
- return 0;
+ ret = btrfs_delalloc_reserve_metadata(inode, len);
+ if (ret < 0)
+ btrfs_free_reserved_data_space(inode, start, len);
+ return ret;
}
/**
* btrfs_delalloc_release_space - release data and metadata space for delalloc
* @inode: inode we're releasing space for
- * @num_bytes: the number of bytes we want to free up
+ * @start: start position of the space already reserved
+ * @len: the len of the space already reserved
*
* This must be matched with a call to btrfs_delalloc_reserve_space. This is
* called in the case that we don't need the metadata AND data reservations
@@ -5773,11 +5827,12 @@
* This function will release the metadata space that was not used and will
* decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes
* list if there are no delalloc bytes left.
+ * Also it will handle the qgroup reserved space.
*/
-void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes)
+void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len)
{
- btrfs_delalloc_release_metadata(inode, num_bytes);
- btrfs_free_reserved_data_space(inode, num_bytes);
+ btrfs_delalloc_release_metadata(inode, len);
+ btrfs_free_reserved_data_space(inode, start, len);
}
static int update_block_group(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6e6df34..33a01ea 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -131,6 +131,25 @@
unsigned int sync_io:1;
};
+static void add_extent_changeset(struct extent_state *state, unsigned bits,
+ struct extent_changeset *changeset,
+ int set)
+{
+ int ret;
+
+ if (!changeset)
+ return;
+ if (set && (state->state & bits) == bits)
+ return;
+ if (!set && (state->state & bits) == 0)
+ return;
+ changeset->bytes_changed += state->end - state->start + 1;
+ ret = ulist_add(changeset->range_changed, state->start, state->end,
+ GFP_ATOMIC);
+ /* ENOMEM */
+ BUG_ON(ret < 0);
+}
+
static noinline void flush_write_bio(void *data);
static inline struct btrfs_fs_info *
tree_fs_info(struct extent_io_tree *tree)
@@ -410,7 +429,8 @@
}
static void set_state_bits(struct extent_io_tree *tree,
- struct extent_state *state, unsigned *bits);
+ struct extent_state *state, unsigned *bits,
+ struct extent_changeset *changeset);
/*
* insert an extent_state struct into the tree. 'bits' are set on the
@@ -426,7 +446,7 @@
struct extent_state *state, u64 start, u64 end,
struct rb_node ***p,
struct rb_node **parent,
- unsigned *bits)
+ unsigned *bits, struct extent_changeset *changeset)
{
struct rb_node *node;
@@ -436,7 +456,7 @@
state->start = start;
state->end = end;
- set_state_bits(tree, state, bits);
+ set_state_bits(tree, state, bits, changeset);
node = tree_insert(&tree->state, NULL, end, &state->rb_node, p, parent);
if (node) {
@@ -511,7 +531,8 @@
*/
static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
struct extent_state *state,
- unsigned *bits, int wake)
+ unsigned *bits, int wake,
+ struct extent_changeset *changeset)
{
struct extent_state *next;
unsigned bits_to_clear = *bits & ~EXTENT_CTLBITS;
@@ -522,6 +543,7 @@
tree->dirty_bytes -= range;
}
clear_state_cb(tree, state, bits);
+ add_extent_changeset(state, bits_to_clear, changeset, 0);
state->state &= ~bits_to_clear;
if (wake)
wake_up(&state->wq);
@@ -569,10 +591,10 @@
*
* This takes the tree lock, and returns 0 on success and < 0 on error.
*/
-int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, int wake, int delete,
- struct extent_state **cached_state,
- gfp_t mask)
+static int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int wake, int delete,
+ struct extent_state **cached_state,
+ gfp_t mask, struct extent_changeset *changeset)
{
struct extent_state *state;
struct extent_state *cached;
@@ -671,7 +693,8 @@
if (err)
goto out;
if (state->end <= end) {
- state = clear_state_bit(tree, state, &bits, wake);
+ state = clear_state_bit(tree, state, &bits, wake,
+ changeset);
goto next;
}
goto search_again;
@@ -692,13 +715,13 @@
if (wake)
wake_up(&state->wq);
- clear_state_bit(tree, prealloc, &bits, wake);
+ clear_state_bit(tree, prealloc, &bits, wake, changeset);
prealloc = NULL;
goto out;
}
- state = clear_state_bit(tree, state, &bits, wake);
+ state = clear_state_bit(tree, state, &bits, wake, changeset);
next:
if (last_end == (u64)-1)
goto out;
@@ -789,7 +812,7 @@
static void set_state_bits(struct extent_io_tree *tree,
struct extent_state *state,
- unsigned *bits)
+ unsigned *bits, struct extent_changeset *changeset)
{
unsigned bits_to_set = *bits & ~EXTENT_CTLBITS;
@@ -798,6 +821,7 @@
u64 range = state->end - state->start + 1;
tree->dirty_bytes += range;
}
+ add_extent_changeset(state, bits_to_set, changeset, 1);
state->state |= bits_to_set;
}
@@ -835,7 +859,7 @@
__set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned exclusive_bits,
u64 *failed_start, struct extent_state **cached_state,
- gfp_t mask)
+ gfp_t mask, struct extent_changeset *changeset)
{
struct extent_state *state;
struct extent_state *prealloc = NULL;
@@ -873,7 +897,7 @@
prealloc = alloc_extent_state_atomic(prealloc);
BUG_ON(!prealloc);
err = insert_state(tree, prealloc, start, end,
- &p, &parent, &bits);
+ &p, &parent, &bits, changeset);
if (err)
extent_io_tree_panic(tree, err);
@@ -899,7 +923,7 @@
goto out;
}
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, changeset);
cache_state(state, cached_state);
merge_state(tree, state);
if (last_end == (u64)-1)
@@ -945,7 +969,7 @@
if (err)
goto out;
if (state->end <= end) {
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, changeset);
cache_state(state, cached_state);
merge_state(tree, state);
if (last_end == (u64)-1)
@@ -980,7 +1004,7 @@
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- NULL, NULL, &bits);
+ NULL, NULL, &bits, changeset);
if (err)
extent_io_tree_panic(tree, err);
@@ -1008,7 +1032,7 @@
if (err)
extent_io_tree_panic(tree, err);
- set_state_bits(tree, prealloc, &bits);
+ set_state_bits(tree, prealloc, &bits, changeset);
cache_state(prealloc, cached_state);
merge_state(tree, prealloc);
prealloc = NULL;
@@ -1038,7 +1062,7 @@
struct extent_state **cached_state, gfp_t mask)
{
return __set_extent_bit(tree, start, end, bits, 0, failed_start,
- cached_state, mask);
+ cached_state, mask, NULL);
}
@@ -1111,7 +1135,7 @@
goto out;
}
err = insert_state(tree, prealloc, start, end,
- &p, &parent, &bits);
+ &p, &parent, &bits, NULL);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
@@ -1130,9 +1154,9 @@
* Just lock what we found and keep going
*/
if (state->start == start && state->end <= end) {
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, NULL);
cache_state(state, cached_state);
- state = clear_state_bit(tree, state, &clear_bits, 0);
+ state = clear_state_bit(tree, state, &clear_bits, 0, NULL);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
@@ -1171,9 +1195,10 @@
if (err)
goto out;
if (state->end <= end) {
- set_state_bits(tree, state, &bits);
+ set_state_bits(tree, state, &bits, NULL);
cache_state(state, cached_state);
- state = clear_state_bit(tree, state, &clear_bits, 0);
+ state = clear_state_bit(tree, state, &clear_bits, 0,
+ NULL);
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
@@ -1208,7 +1233,7 @@
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- NULL, NULL, &bits);
+ NULL, NULL, &bits, NULL);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
@@ -1233,9 +1258,9 @@
if (err)
extent_io_tree_panic(tree, err);
- set_state_bits(tree, prealloc, &bits);
+ set_state_bits(tree, prealloc, &bits, NULL);
cache_state(prealloc, cached_state);
- clear_state_bit(tree, prealloc, &clear_bits, 0);
+ clear_state_bit(tree, prealloc, &clear_bits, 0, NULL);
prealloc = NULL;
goto out;
}
@@ -1274,6 +1299,30 @@
NULL, mask);
}
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, gfp_t mask,
+ struct extent_changeset *changeset)
+{
+ /*
+ * We don't support EXTENT_LOCKED yet, as current changeset will
+ * record any bits changed, so for EXTENT_LOCKED case, it will
+ * either fail with -EEXIST or changeset will record the whole
+ * range.
+ */
+ BUG_ON(bits & EXTENT_LOCKED);
+
+ return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask,
+ changeset);
+}
+
+int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, int wake, int delete,
+ struct extent_state **cached, gfp_t mask)
+{
+ return __clear_extent_bit(tree, start, end, bits, wake, delete,
+ cached, mask, NULL);
+}
+
int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, gfp_t mask)
{
@@ -1285,6 +1334,20 @@
return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
}
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, gfp_t mask,
+ struct extent_changeset *changeset)
+{
+ /*
+ * Don't support EXTENT_LOCKED case, same reason as
+ * set_record_extent_bits().
+ */
+ BUG_ON(bits & EXTENT_LOCKED);
+
+ return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask,
+ changeset);
+}
+
int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached_state, gfp_t mask)
{
@@ -1343,7 +1406,7 @@
while (1) {
err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
EXTENT_LOCKED, &failed_start,
- cached_state, GFP_NOFS);
+ cached_state, GFP_NOFS, NULL);
if (err == -EEXIST) {
wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
start = failed_start;
@@ -1365,7 +1428,7 @@
u64 failed_start;
err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, EXTENT_LOCKED,
- &failed_start, NULL, GFP_NOFS);
+ &failed_start, NULL, GFP_NOFS, NULL);
if (err == -EEXIST) {
if (failed_start > start)
clear_extent_bit(tree, start, failed_start - 1,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index c668f36..f4c1ae1 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -2,6 +2,7 @@
#define __EXTENTIO__
#include <linux/rbtree.h>
+#include "ulist.h"
/* bits for the extent state */
#define EXTENT_DIRTY (1U << 0)
@@ -18,6 +19,7 @@
#define EXTENT_NEED_WAIT (1U << 13)
#define EXTENT_DAMAGED (1U << 14)
#define EXTENT_NORESERVE (1U << 15)
+#define EXTENT_QGROUP_RESERVED (1U << 16)
#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
@@ -161,6 +163,17 @@
#endif
};
+/*
+ * Structure to record how many bytes and which ranges are set/cleared
+ */
+struct extent_changeset {
+ /* How many bytes are set/cleared in this operation */
+ u64 bytes_changed;
+
+ /* Changed ranges */
+ struct ulist *range_changed;
+};
+
static inline void extent_set_compress_type(unsigned long *bio_flags,
int compress_type)
{
@@ -210,11 +223,17 @@
struct extent_state *cached_state);
int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, gfp_t mask);
+int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, gfp_t mask,
+ struct extent_changeset *changeset);
int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, int wake, int delete,
struct extent_state **cached, gfp_t mask);
int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, gfp_t mask);
+int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
+ unsigned bits, gfp_t mask,
+ struct extent_changeset *changeset);
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, u64 *failed_start,
struct extent_state **cached_state, gfp_t mask);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7031e96..1243205 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1507,12 +1507,17 @@
}
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
- ret = btrfs_check_data_free_space(inode, reserve_bytes, write_bytes);
- if (ret == -ENOSPC &&
- (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
- BTRFS_INODE_PREALLOC))) {
+
+ if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) {
ret = check_can_nocow(inode, pos, &write_bytes);
+ if (ret < 0)
+ break;
if (ret > 0) {
+ /*
+ * For nodata cow case, no need to reserve
+ * data space.
+ */
only_release_metadata = true;
/*
* our prealloc extent may be smaller than
@@ -1521,20 +1526,19 @@
num_pages = DIV_ROUND_UP(write_bytes + offset,
PAGE_CACHE_SIZE);
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
- ret = 0;
- } else {
- ret = -ENOSPC;
+ goto reserve_metadata;
}
}
-
- if (ret)
+ ret = btrfs_check_data_free_space(inode, pos, write_bytes);
+ if (ret < 0)
break;
+reserve_metadata:
ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
if (ret) {
if (!only_release_metadata)
- btrfs_free_reserved_data_space(inode,
- reserve_bytes);
+ btrfs_free_reserved_data_space(inode, pos,
+ write_bytes);
else
btrfs_end_write_no_snapshoting(root);
break;
@@ -1604,7 +1608,7 @@
btrfs_delalloc_release_metadata(inode,
release_bytes);
else
- btrfs_delalloc_release_space(inode,
+ btrfs_delalloc_release_space(inode, pos,
release_bytes);
}
@@ -1657,7 +1661,7 @@
btrfs_end_write_no_snapshoting(root);
btrfs_delalloc_release_metadata(inode, release_bytes);
} else {
- btrfs_delalloc_release_space(inode, release_bytes);
+ btrfs_delalloc_release_space(inode, pos, release_bytes);
}
}
@@ -2538,17 +2542,61 @@
return err;
}
+/* Helper structure to record which range is already reserved */
+struct falloc_range {
+ struct list_head list;
+ u64 start;
+ u64 len;
+};
+
+/*
+ * Helper function to add falloc range
+ *
+ * Caller should have locked the larger range of extent containing
+ * [start, len)
+ */
+static int add_falloc_range(struct list_head *head, u64 start, u64 len)
+{
+ struct falloc_range *prev = NULL;
+ struct falloc_range *range = NULL;
+
+ if (list_empty(head))
+ goto insert;
+
+ /*
+ * As fallocate iterate by bytenr order, we only need to check
+ * the last range.
+ */
+ prev = list_entry(head->prev, struct falloc_range, list);
+ if (prev->start + prev->len == start) {
+ prev->len += len;
+ return 0;
+ }
+insert:
+ range = kmalloc(sizeof(*range), GFP_NOFS);
+ if (!range)
+ return -ENOMEM;
+ range->start = start;
+ range->len = len;
+ list_add_tail(&range->list, head);
+ return 0;
+}
+
static long btrfs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
struct extent_state *cached_state = NULL;
+ struct falloc_range *range;
+ struct falloc_range *tmp;
+ struct list_head reserve_list;
u64 cur_offset;
u64 last_byte;
u64 alloc_start;
u64 alloc_end;
u64 alloc_hint = 0;
u64 locked_end;
+ u64 actual_end = 0;
struct extent_map *em;
int blocksize = BTRFS_I(inode)->root->sectorsize;
int ret;
@@ -2564,11 +2612,12 @@
return btrfs_punch_hole(inode, offset, len);
/*
- * Make sure we have enough space before we do the
- * allocation.
+ * Only trigger disk allocation, don't trigger qgroup reserve
+ *
+ * For qgroup space, it will be checked later.
*/
- ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start, alloc_end - alloc_start);
- if (ret)
+ ret = btrfs_alloc_data_chunk_ondemand(inode, alloc_end - alloc_start);
+ if (ret < 0)
return ret;
mutex_lock(&inode->i_mutex);
@@ -2576,6 +2625,13 @@
if (ret)
goto out;
+ /*
+ * TODO: Move these two operations after we have checked
+ * accurate reserved space, or fallocate can still fail but
+ * with page truncated or size expanded.
+ *
+ * But that's a minor problem and won't do much harm BTW.
+ */
if (alloc_start > inode->i_size) {
ret = btrfs_cont_expand(inode, i_size_read(inode),
alloc_start);
@@ -2634,10 +2690,10 @@
}
}
+ /* First, check if we exceed the qgroup limit */
+ INIT_LIST_HEAD(&reserve_list);
cur_offset = alloc_start;
while (1) {
- u64 actual_end;
-
em = btrfs_get_extent(inode, NULL, 0, cur_offset,
alloc_end - cur_offset, 0);
if (IS_ERR_OR_NULL(em)) {
@@ -2650,57 +2706,82 @@
last_byte = min(extent_map_end(em), alloc_end);
actual_end = min_t(u64, extent_map_end(em), offset + len);
last_byte = ALIGN(last_byte, blocksize);
-
if (em->block_start == EXTENT_MAP_HOLE ||
(cur_offset >= inode->i_size &&
!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
- ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
- last_byte - cur_offset,
- 1 << inode->i_blkbits,
- offset + len,
- &alloc_hint);
- } else if (actual_end > inode->i_size &&
- !(mode & FALLOC_FL_KEEP_SIZE)) {
- struct btrfs_trans_handle *trans;
- struct btrfs_root *root = BTRFS_I(inode)->root;
-
- /*
- * We didn't need to allocate any more space, but we
- * still extended the size of the file so we need to
- * update i_size and the inode item.
- */
- trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- } else {
- inode->i_ctime = CURRENT_TIME;
- i_size_write(inode, actual_end);
- btrfs_ordered_update_i_size(inode, actual_end,
- NULL);
- ret = btrfs_update_inode(trans, root, inode);
- if (ret)
- btrfs_end_transaction(trans, root);
- else
- ret = btrfs_end_transaction(trans,
- root);
+ ret = add_falloc_range(&reserve_list, cur_offset,
+ last_byte - cur_offset);
+ if (ret < 0) {
+ free_extent_map(em);
+ break;
}
+ ret = btrfs_qgroup_reserve_data(inode, cur_offset,
+ last_byte - cur_offset);
+ if (ret < 0)
+ break;
}
free_extent_map(em);
- if (ret < 0)
- break;
-
cur_offset = last_byte;
- if (cur_offset >= alloc_end) {
- ret = 0;
+ if (cur_offset >= alloc_end)
break;
+ }
+
+ /*
+ * If ret is still 0, means we're OK to fallocate.
+ * Or just cleanup the list and exit.
+ */
+ list_for_each_entry_safe(range, tmp, &reserve_list, list) {
+ if (!ret)
+ ret = btrfs_prealloc_file_range(inode, mode,
+ range->start,
+ range->len, 1 << inode->i_blkbits,
+ offset + len, &alloc_hint);
+ list_del(&range->list);
+ kfree(range);
+ }
+ if (ret < 0)
+ goto out_unlock;
+
+ if (actual_end > inode->i_size &&
+ !(mode & FALLOC_FL_KEEP_SIZE)) {
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+
+ /*
+ * We didn't need to allocate any more space, but we
+ * still extended the size of the file so we need to
+ * update i_size and the inode item.
+ */
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ } else {
+ inode->i_ctime = CURRENT_TIME;
+ i_size_write(inode, actual_end);
+ btrfs_ordered_update_i_size(inode, actual_end, NULL);
+ ret = btrfs_update_inode(trans, root, inode);
+ if (ret)
+ btrfs_end_transaction(trans, root);
+ else
+ ret = btrfs_end_transaction(trans, root);
}
}
+out_unlock:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
&cached_state, GFP_NOFS);
out:
+ /*
+ * As we waited the extent range, the data_rsv_map must be empty
+ * in the range, as written data range will be released from it.
+ * And for prealloacted extent, it will also be released when
+ * its metadata is written.
+ * So this is completely used as cleanup.
+ */
+ btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start);
mutex_unlock(&inode->i_mutex);
/* Let go of our reservation. */
- btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
+ btrfs_free_reserved_data_space(inode, alloc_start,
+ alloc_end - alloc_start);
return ret;
}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index d4a582a..767a605 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -488,17 +488,17 @@
/* Just to make sure we have enough space */
prealloc += 8 * PAGE_CACHE_SIZE;
- ret = btrfs_delalloc_reserve_space(inode, prealloc);
+ ret = btrfs_delalloc_reserve_space(inode, 0, prealloc);
if (ret)
goto out_put;
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_space(inode, prealloc);
+ btrfs_delalloc_release_space(inode, 0, prealloc);
goto out_put;
}
- btrfs_free_reserved_data_space(inode, prealloc);
+ btrfs_free_reserved_data_space(inode, 0, prealloc);
ret = btrfs_write_out_ino_cache(root, trans, path, inode);
out_put:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a3e0783..a018e47 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -310,6 +310,13 @@
btrfs_delalloc_release_metadata(inode, end + 1 - start);
btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
out:
+ /*
+ * Don't forget to free the reserved space, as for inlined extent
+ * it won't count as data extent, free them directly here.
+ * And at reserve time, it's always aligned to page size, so
+ * just free one page here.
+ */
+ btrfs_qgroup_free_data(inode, 0, PAGE_CACHE_SIZE);
btrfs_free_path(path);
btrfs_end_transaction(trans, root);
return ret;
@@ -1769,7 +1776,8 @@
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
&& do_list && !(state->state & EXTENT_NORESERVE))
- btrfs_free_reserved_data_space(inode, len);
+ btrfs_free_reserved_data_space_noquota(inode,
+ state->start, len);
__percpu_counter_add(&root->fs_info->delalloc_bytes, -len,
root->fs_info->delalloc_batch);
@@ -1992,7 +2000,8 @@
goto again;
}
- ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ ret = btrfs_delalloc_reserve_space(inode, page_start,
+ PAGE_CACHE_SIZE);
if (ret) {
mapping_set_error(page->mapping, ret);
end_extent_writepage(page, ret, page_start, page_end);
@@ -2119,6 +2128,16 @@
ret = btrfs_alloc_reserved_file_extent(trans, root,
root->root_key.objectid,
btrfs_ino(inode), file_pos, &ins);
+ if (ret < 0)
+ goto out;
+ /*
+ * Release the reserved range from inode dirty range map, and
+ * move it to delayed ref codes, as now accounting only happens at
+ * commit_transaction() time.
+ */
+ btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+ ret = btrfs_add_delayed_qgroup_reserve(root->fs_info, trans,
+ root->objectid, disk_bytenr, ram_bytes);
out:
btrfs_free_path(path);
@@ -2826,6 +2845,14 @@
if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */
+
+ /*
+ * For mwrite(mmap + memset to write) case, we still reserve
+ * space for NOCOW range.
+ * As NOCOW won't cause a new delayed ref, just free the space
+ */
+ btrfs_qgroup_free_data(inode, ordered_extent->file_offset,
+ ordered_extent->len);
btrfs_ordered_update_i_size(inode, 0, ordered_extent);
if (nolock)
trans = btrfs_join_transaction_nolock(root);
@@ -4628,14 +4655,17 @@
if ((offset & (blocksize - 1)) == 0 &&
(!len || ((len & (blocksize - 1)) == 0)))
goto out;
- ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ ret = btrfs_delalloc_reserve_space(inode,
+ round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE);
if (ret)
goto out;
again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode,
+ round_down(from, PAGE_CACHE_SIZE),
+ PAGE_CACHE_SIZE);
ret = -ENOMEM;
goto out;
}
@@ -4703,7 +4733,8 @@
out_unlock:
if (ret)
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode, page_start,
+ PAGE_CACHE_SIZE);
unlock_page(page);
page_cache_release(page);
out:
@@ -5101,6 +5132,18 @@
spin_unlock(&io_tree->lock);
lock_extent_bits(io_tree, start, end, 0, &cached_state);
+
+ /*
+ * If still has DELALLOC flag, the extent didn't reach disk,
+ * and its reserved space won't be freed by delayed_ref.
+ * So we need to free its reserved space here.
+ * (Refer to comment in btrfs_invalidatepage, case 2)
+ *
+ * Note, end is the bytenr of last byte, so we need + 1 here.
+ */
+ if (state->state & EXTENT_DELALLOC)
+ btrfs_qgroup_free_data(inode, start, end - start + 1);
+
clear_extent_bit(io_tree, start, end,
EXTENT_LOCKED | EXTENT_DIRTY |
EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
@@ -7634,7 +7677,7 @@
spin_unlock(&BTRFS_I(inode)->lock);
}
- btrfs_free_reserved_data_space(inode, len);
+ btrfs_free_reserved_data_space(inode, start, len);
WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
current->journal_info = dio_data;
@@ -8424,7 +8467,7 @@
mutex_unlock(&inode->i_mutex);
relock = true;
}
- ret = btrfs_delalloc_reserve_space(inode, count);
+ ret = btrfs_delalloc_reserve_space(inode, offset, count);
if (ret)
goto out;
dio_data.outstanding_extents = div64_u64(count +
@@ -8453,10 +8496,10 @@
current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED) {
if (dio_data.reserve)
- btrfs_delalloc_release_space(inode,
- dio_data.reserve);
+ btrfs_delalloc_release_space(inode, offset,
+ dio_data.reserve);
} else if (ret >= 0 && (size_t)ret < count)
- btrfs_delalloc_release_space(inode,
+ btrfs_delalloc_release_space(inode, offset,
count - (size_t)ret);
}
out:
@@ -8615,6 +8658,18 @@
}
}
+ /*
+ * Qgroup reserved space handler
+ * Page here will be either
+ * 1) Already written to disk
+ * In this case, its reserved space is released from data rsv map
+ * and will be freed by delayed_ref handler finally.
+ * So even we call qgroup_free_data(), it won't decrease reserved
+ * space.
+ * 2) Not written to disk
+ * This means the reserved space should be freed here.
+ */
+ btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE);
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
@@ -8665,7 +8720,11 @@
u64 page_end;
sb_start_pagefault(inode->i_sb);
- ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ page_start = page_offset(page);
+ page_end = page_start + PAGE_CACHE_SIZE - 1;
+
+ ret = btrfs_delalloc_reserve_space(inode, page_start,
+ PAGE_CACHE_SIZE);
if (!ret) {
ret = file_update_time(vma->vm_file);
reserved = 1;
@@ -8684,8 +8743,6 @@
again:
lock_page(page);
size = i_size_read(inode);
- page_start = page_offset(page);
- page_end = page_start + PAGE_CACHE_SIZE - 1;
if ((page->mapping != inode->i_mapping) ||
(page_start >= size)) {
@@ -8762,7 +8819,7 @@
}
unlock_page(page);
out:
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE);
out_noreserve:
sb_end_pagefault(inode->i_sb);
return ret;
@@ -9051,6 +9108,7 @@
btrfs_put_ordered_extent(ordered);
}
}
+ btrfs_qgroup_check_reserved_leak(inode);
inode_tree_del(inode);
btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
free:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 685df7e..7ed033a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1120,7 +1120,8 @@
page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
ret = btrfs_delalloc_reserve_space(inode,
- page_cnt << PAGE_CACHE_SHIFT);
+ start_index << PAGE_CACHE_SHIFT,
+ page_cnt << PAGE_CACHE_SHIFT);
if (ret)
return ret;
i_done = 0;
@@ -1210,7 +1211,8 @@
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(inode,
- (page_cnt - i_done) << PAGE_CACHE_SHIFT);
+ start_index << PAGE_CACHE_SHIFT,
+ (page_cnt - i_done) << PAGE_CACHE_SHIFT);
}
@@ -1235,7 +1237,9 @@
unlock_page(pages[i]);
page_cache_release(pages[i]);
}
- btrfs_delalloc_release_space(inode, page_cnt << PAGE_CACHE_SHIFT);
+ btrfs_delalloc_release_space(inode,
+ start_index << PAGE_CACHE_SHIFT,
+ page_cnt << PAGE_CACHE_SHIFT);
return ret;
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d904ee1..158633c 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2035,7 +2035,7 @@
return ret;
}
-int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
+static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
{
struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
@@ -2116,14 +2116,13 @@
return ret;
}
-void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes)
+void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
+ u64 ref_root, u64 num_bytes)
{
struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
- struct btrfs_fs_info *fs_info = root->fs_info;
struct ulist_node *unode;
struct ulist_iterator uiter;
- u64 ref_root = root->root_key.objectid;
int ret = 0;
if (!is_fstree(ref_root))
@@ -2169,6 +2168,11 @@
spin_unlock(&fs_info->qgroup_lock);
}
+static inline void qgroup_free(struct btrfs_root *root, u64 num_bytes)
+{
+ return btrfs_qgroup_free_refroot(root->fs_info, root->objectid,
+ num_bytes);
+}
void assert_qgroups_uptodate(struct btrfs_trans_handle *trans)
{
if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq)
@@ -2486,3 +2490,190 @@
btrfs_queue_work(fs_info->qgroup_rescan_workers,
&fs_info->qgroup_rescan_work);
}
+
+/*
+ * Reserve qgroup space for range [start, start + len).
+ *
+ * This function will either reserve space from related qgroups or doing
+ * nothing if the range is already reserved.
+ *
+ * Return 0 for successful reserve
+ * Return <0 for error (including -EQUOT)
+ *
+ * NOTE: this function may sleep for memory allocation.
+ */
+int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct extent_changeset changeset;
+ struct ulist_node *unode;
+ struct ulist_iterator uiter;
+ int ret;
+
+ if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) ||
+ len == 0)
+ return 0;
+
+ changeset.bytes_changed = 0;
+ changeset.range_changed = ulist_alloc(GFP_NOFS);
+ ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
+ start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
+ &changeset);
+ trace_btrfs_qgroup_reserve_data(inode, start, len,
+ changeset.bytes_changed,
+ QGROUP_RESERVE);
+ if (ret < 0)
+ goto cleanup;
+ ret = qgroup_reserve(root, changeset.bytes_changed);
+ if (ret < 0)
+ goto cleanup;
+
+ ulist_free(changeset.range_changed);
+ return ret;
+
+cleanup:
+ /* cleanup already reserved ranges */
+ ULIST_ITER_INIT(&uiter);
+ while ((unode = ulist_next(changeset.range_changed, &uiter)))
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
+ unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL,
+ GFP_NOFS);
+ ulist_free(changeset.range_changed);
+ return ret;
+}
+
+static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
+ int free)
+{
+ struct extent_changeset changeset;
+ int trace_op = QGROUP_RELEASE;
+ int ret;
+
+ changeset.bytes_changed = 0;
+ changeset.range_changed = ulist_alloc(GFP_NOFS);
+ if (!changeset.range_changed)
+ return -ENOMEM;
+
+ ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
+ start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
+ &changeset);
+ if (ret < 0)
+ goto out;
+
+ if (free) {
+ qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed);
+ trace_op = QGROUP_FREE;
+ }
+ trace_btrfs_qgroup_release_data(inode, start, len,
+ changeset.bytes_changed, trace_op);
+out:
+ ulist_free(changeset.range_changed);
+ return ret;
+}
+
+/*
+ * Free a reserved space range from io_tree and related qgroups
+ *
+ * Should be called when a range of pages get invalidated before reaching disk.
+ * Or for error cleanup case.
+ *
+ * For data written to disk, use btrfs_qgroup_release_data().
+ *
+ * NOTE: This function may sleep for memory allocation.
+ */
+int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len)
+{
+ return __btrfs_qgroup_release_data(inode, start, len, 1);
+}
+
+/*
+ * Release a reserved space range from io_tree only.
+ *
+ * Should be called when a range of pages get written to disk and corresponding
+ * FILE_EXTENT is inserted into corresponding root.
+ *
+ * Since new qgroup accounting framework will only update qgroup numbers at
+ * commit_transaction() time, its reserved space shouldn't be freed from
+ * related qgroups.
+ *
+ * But we should release the range from io_tree, to allow further write to be
+ * COWed.
+ *
+ * NOTE: This function may sleep for memory allocation.
+ */
+int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len)
+{
+ return __btrfs_qgroup_release_data(inode, start, len, 0);
+}
+
+int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes)
+{
+ int ret;
+
+ if (!root->fs_info->quota_enabled || !is_fstree(root->objectid) ||
+ num_bytes == 0)
+ return 0;
+
+ BUG_ON(num_bytes != round_down(num_bytes, root->nodesize));
+ ret = qgroup_reserve(root, num_bytes);
+ if (ret < 0)
+ return ret;
+ atomic_add(num_bytes, &root->qgroup_meta_rsv);
+ return ret;
+}
+
+void btrfs_qgroup_free_meta_all(struct btrfs_root *root)
+{
+ int reserved;
+
+ if (!root->fs_info->quota_enabled || !is_fstree(root->objectid))
+ return;
+
+ reserved = atomic_xchg(&root->qgroup_meta_rsv, 0);
+ if (reserved == 0)
+ return;
+ qgroup_free(root, reserved);
+}
+
+void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
+{
+ if (!root->fs_info->quota_enabled || !is_fstree(root->objectid))
+ return;
+
+ BUG_ON(num_bytes != round_down(num_bytes, root->nodesize));
+ WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes);
+ atomic_sub(num_bytes, &root->qgroup_meta_rsv);
+ qgroup_free(root, num_bytes);
+}
+
+/*
+ * Check qgroup reserved space leaking, normally at destory inode
+ * time
+ */
+void btrfs_qgroup_check_reserved_leak(struct inode *inode)
+{
+ struct extent_changeset changeset;
+ struct ulist_node *unode;
+ struct ulist_iterator iter;
+ int ret;
+
+ changeset.bytes_changed = 0;
+ changeset.range_changed = ulist_alloc(GFP_NOFS);
+ if (WARN_ON(!changeset.range_changed))
+ return;
+
+ ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+ EXTENT_QGROUP_RESERVED, GFP_NOFS, &changeset);
+
+ WARN_ON(ret < 0);
+ if (WARN_ON(changeset.bytes_changed)) {
+ ULIST_ITER_INIT(&iter);
+ while ((unode = ulist_next(changeset.range_changed, &iter))) {
+ btrfs_warn(BTRFS_I(inode)->root->fs_info,
+ "leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu",
+ inode->i_ino, unode->val, unode->aux);
+ }
+ qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed);
+ }
+ ulist_free(changeset.range_changed);
+}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 6387dcf..ecb2c14 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -33,6 +33,13 @@
struct ulist *old_roots;
};
+/*
+ * For qgroup event trace points only
+ */
+#define QGROUP_RESERVE (1<<0)
+#define QGROUP_RELEASE (1<<1)
+#define QGROUP_FREE (1<<2)
+
int btrfs_quota_enable(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
int btrfs_quota_disable(struct btrfs_trans_handle *trans,
@@ -71,9 +78,18 @@
int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
struct btrfs_qgroup_inherit *inherit);
-int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes);
-void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes);
-
+void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
+ u64 ref_root, u64 num_bytes);
+/*
+ * TODO: Add proper trace point for it, as btrfs_qgroup_free() is
+ * called by everywhere, can't provide good trace for delayed ref case.
+ */
+static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
+ u64 ref_root, u64 num_bytes)
+{
+ btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes);
+ trace_btrfs_qgroup_free_delayed_ref(ref_root, num_bytes);
+}
void assert_qgroups_uptodate(struct btrfs_trans_handle *trans);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
@@ -81,4 +97,13 @@
u64 rfer, u64 excl);
#endif
+/* New io_tree based accurate qgroup reserve API */
+int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len);
+int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len);
+int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len);
+
+int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes);
+void btrfs_qgroup_free_meta_all(struct btrfs_root *root);
+void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes);
+void btrfs_qgroup_check_reserved_leak(struct inode *inode);
#endif /* __BTRFS_QGROUP__ */
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 58ede0a..a7dc456 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3034,8 +3034,8 @@
BUG_ON(cluster->start != cluster->boundary[0]);
mutex_lock(&inode->i_mutex);
- ret = btrfs_check_data_free_space(inode, cluster->end +
- 1 - cluster->start, 0);
+ ret = btrfs_check_data_free_space(inode, cluster->start,
+ cluster->end + 1 - cluster->start);
if (ret)
goto out;
@@ -3056,8 +3056,8 @@
break;
nr++;
}
- btrfs_free_reserved_data_space(inode, cluster->end +
- 1 - cluster->start);
+ btrfs_free_reserved_data_space(inode, cluster->start,
+ cluster->end + 1 - cluster->start);
out:
mutex_unlock(&inode->i_mutex);
return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 222f9a9..418c6a2 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -480,13 +480,10 @@
* the appropriate flushing if need be.
*/
if (num_items > 0 && root != root->fs_info->chunk_root) {
- if (root->fs_info->quota_enabled &&
- is_fstree(root->root_key.objectid)) {
- qgroup_reserved = num_items * root->nodesize;
- ret = btrfs_qgroup_reserve(root, qgroup_reserved);
- if (ret)
- return ERR_PTR(ret);
- }
+ qgroup_reserved = num_items * root->nodesize;
+ ret = btrfs_qgroup_reserve_meta(root, qgroup_reserved);
+ if (ret)
+ return ERR_PTR(ret);
num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
/*
@@ -547,6 +544,7 @@
h->transaction = cur_trans;
h->root = root;
h->use_count = 1;
+
h->type = type;
h->can_flush_pending_bgs = true;
INIT_LIST_HEAD(&h->qgroup_ref_list);
@@ -567,7 +565,6 @@
h->bytes_reserved = num_bytes;
h->reloc_reserved = reloc_reserved;
}
- h->qgroup_reserved = qgroup_reserved;
got_it:
btrfs_record_root_in_trans(h, root);
@@ -585,8 +582,7 @@
btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
num_bytes);
reserve_fail:
- if (qgroup_reserved)
- btrfs_qgroup_free(root, qgroup_reserved);
+ btrfs_qgroup_free_meta(root, qgroup_reserved);
return ERR_PTR(ret);
}
@@ -798,15 +794,6 @@
must_run_delayed_refs = 2;
}
- if (trans->qgroup_reserved) {
- /*
- * the same root has to be passed here between start_transaction
- * and end_transaction. Subvolume quota depends on this.
- */
- btrfs_qgroup_free(trans->root, trans->qgroup_reserved);
- trans->qgroup_reserved = 0;
- }
-
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
@@ -1224,6 +1211,7 @@
spin_lock(&fs_info->fs_roots_radix_lock);
if (err)
break;
+ btrfs_qgroup_free_meta_all(root);
}
}
spin_unlock(&fs_info->fs_roots_radix_lock);
@@ -1813,10 +1801,6 @@
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
- if (trans->qgroup_reserved) {
- btrfs_qgroup_free(root, trans->qgroup_reserved);
- trans->qgroup_reserved = 0;
- }
cur_trans = trans->transaction;
@@ -2167,10 +2151,6 @@
btrfs_trans_release_metadata(trans, root);
btrfs_trans_release_chunk_metadata(trans);
trans->block_rsv = NULL;
- if (trans->qgroup_reserved) {
- btrfs_qgroup_free(root, trans->qgroup_reserved);
- trans->qgroup_reserved = 0;
- }
btrfs_warn(root->fs_info, "Skipping commit of aborted transaction.");
if (current->journal_info == trans)
current->journal_info = NULL;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 30ae750..b05b2f6 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -108,7 +108,6 @@
u64 transid;
u64 bytes_reserved;
u64 chunk_bytes_reserved;
- u64 qgroup_reserved;
unsigned long use_count;
unsigned long blocks_reserved;
unsigned long blocks_used;
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 0b73af9..b4473da 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1117,6 +1117,119 @@
TP_ARGS(wq)
);
+DECLARE_EVENT_CLASS(btrfs__qgroup_data_map,
+
+ TP_PROTO(struct inode *inode, u64 free_reserved),
+
+ TP_ARGS(inode, free_reserved),
+
+ TP_STRUCT__entry(
+ __field( u64, rootid )
+ __field( unsigned long, ino )
+ __field( u64, free_reserved )
+ ),
+
+ TP_fast_assign(
+ __entry->rootid = BTRFS_I(inode)->root->objectid;
+ __entry->ino = inode->i_ino;
+ __entry->free_reserved = free_reserved;
+ ),
+
+ TP_printk("rootid=%llu, ino=%lu, free_reserved=%llu",
+ __entry->rootid, __entry->ino, __entry->free_reserved)
+);
+
+DEFINE_EVENT(btrfs__qgroup_data_map, btrfs_qgroup_init_data_rsv_map,
+
+ TP_PROTO(struct inode *inode, u64 free_reserved),
+
+ TP_ARGS(inode, free_reserved)
+);
+
+DEFINE_EVENT(btrfs__qgroup_data_map, btrfs_qgroup_free_data_rsv_map,
+
+ TP_PROTO(struct inode *inode, u64 free_reserved),
+
+ TP_ARGS(inode, free_reserved)
+);
+
+#define BTRFS_QGROUP_OPERATIONS \
+ { QGROUP_RESERVE, "reserve" }, \
+ { QGROUP_RELEASE, "release" }, \
+ { QGROUP_FREE, "free" }
+
+DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data,
+
+ TP_PROTO(struct inode *inode, u64 start, u64 len, u64 reserved, int op),
+
+ TP_ARGS(inode, start, len, reserved, op),
+
+ TP_STRUCT__entry(
+ __field( u64, rootid )
+ __field( unsigned long, ino )
+ __field( u64, start )
+ __field( u64, len )
+ __field( u64, reserved )
+ __field( int, op )
+ ),
+
+ TP_fast_assign(
+ __entry->rootid = BTRFS_I(inode)->root->objectid;
+ __entry->ino = inode->i_ino;
+ __entry->start = start;
+ __entry->len = len;
+ __entry->reserved = reserved;
+ __entry->op = op;
+ ),
+
+ TP_printk("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s",
+ __entry->rootid, __entry->ino, __entry->start, __entry->len,
+ __entry->reserved,
+ __print_flags((unsigned long)__entry->op, "",
+ BTRFS_QGROUP_OPERATIONS)
+ )
+);
+
+DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_reserve_data,
+
+ TP_PROTO(struct inode *inode, u64 start, u64 len, u64 reserved, int op),
+
+ TP_ARGS(inode, start, len, reserved, op)
+);
+
+DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data,
+
+ TP_PROTO(struct inode *inode, u64 start, u64 len, u64 reserved, int op),
+
+ TP_ARGS(inode, start, len, reserved, op)
+);
+
+DECLARE_EVENT_CLASS(btrfs__qgroup_delayed_ref,
+
+ TP_PROTO(u64 ref_root, u64 reserved),
+
+ TP_ARGS(ref_root, reserved),
+
+ TP_STRUCT__entry(
+ __field( u64, ref_root )
+ __field( u64, reserved )
+ ),
+
+ TP_fast_assign(
+ __entry->ref_root = ref_root;
+ __entry->reserved = reserved;
+ ),
+
+ TP_printk("root=%llu, reserved=%llu, op=free",
+ __entry->ref_root, __entry->reserved)
+);
+
+DEFINE_EVENT(btrfs__qgroup_delayed_ref, btrfs_qgroup_free_delayed_ref,
+
+ TP_PROTO(u64 ref_root, u64 reserved),
+
+ TP_ARGS(ref_root, reserved)
+);
#endif /* _TRACE_BTRFS_H */
/* This part must be outside protection */