summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/block-group.h1
-rw-r--r--fs/btrfs/check-integrity.c4
-rw-r--r--fs/btrfs/compression.c6
-rw-r--r--fs/btrfs/compression.h2
-rw-r--r--fs/btrfs/ctree.h20
-rw-r--r--fs/btrfs/delayed-inode.c84
-rw-r--r--fs/btrfs/disk-io.c214
-rw-r--r--fs/btrfs/extent-tree.c22
-rw-r--r--fs/btrfs/extent_io.c143
-rw-r--r--fs/btrfs/file.c111
-rw-r--r--fs/btrfs/inode.c65
-rw-r--r--fs/btrfs/locking.c3
-rw-r--r--fs/btrfs/raid56.c4
-rw-r--r--fs/btrfs/reflink.c16
-rw-r--r--fs/btrfs/send.c40
-rw-r--r--fs/btrfs/super.c47
-rw-r--r--fs/btrfs/tests/btrfs-tests.c24
-rw-r--r--fs/btrfs/transaction.c112
-rw-r--r--fs/btrfs/zoned.c61
-rw-r--r--fs/btrfs/zoned.h5
20 files changed, 604 insertions, 380 deletions
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 3ac668ace50a..35e0e860cc0b 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -104,6 +104,7 @@ struct btrfs_block_group {
unsigned int relocating_repair:1;
unsigned int chunk_item_inserted:1;
unsigned int zone_is_active:1;
+ unsigned int zoned_data_reloc_ongoing:1;
int disk_cache_state;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 5d20137b7b67..98c6e5feab19 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -152,7 +152,7 @@ struct btrfsic_block {
struct btrfsic_block *next_in_same_bio;
void *orig_bio_private;
bio_end_io_t *orig_bio_end_io;
- int submit_bio_bh_rw;
+ blk_opf_t submit_bio_bh_rw;
u64 flush_gen; /* only valid if !never_written */
};
@@ -1681,7 +1681,7 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state,
u64 dev_bytenr, char **mapped_datav,
unsigned int num_pages,
struct bio *bio, int *bio_is_patched,
- int submit_bio_bh_rw)
+ blk_opf_t submit_bio_bh_rw)
{
int is_metadata;
struct btrfsic_block *block;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index f4564f32f6d9..a82b9f17f476 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -455,7 +455,7 @@ static blk_status_t submit_compressed_bio(struct btrfs_fs_info *fs_info,
static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
- unsigned int opf, bio_end_io_t endio_func,
+ blk_opf_t opf, bio_end_io_t endio_func,
u64 *next_stripe_start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
@@ -505,7 +505,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
unsigned int compressed_len,
struct page **compressed_pages,
unsigned int nr_pages,
- unsigned int write_flags,
+ blk_opf_t write_flags,
struct cgroup_subsys_state *blkcg_css,
bool writeback)
{
@@ -517,7 +517,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
blk_status_t ret;
int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
const bool use_append = btrfs_use_zone_append(inode, disk_start);
- const unsigned int bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
+ const enum req_op bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(len, fs_info->sectorsize));
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 2707404389a5..2b56d63e01ce 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -99,7 +99,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
unsigned int compressed_len,
struct page **compressed_pages,
unsigned int nr_pages,
- unsigned int write_flags,
+ blk_opf_t write_flags,
struct cgroup_subsys_state *blkcg_css,
bool writeback);
void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0e49b1a0c071..9c21e214d29e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -675,9 +675,8 @@ struct btrfs_fs_info {
rwlock_t global_root_lock;
struct rb_root global_root_tree;
- /* The xarray that holds all the FS roots */
- spinlock_t fs_roots_lock;
- struct xarray fs_roots;
+ spinlock_t fs_roots_radix_lock;
+ struct radix_tree_root fs_roots_radix;
/* block group cache stuff */
rwlock_t block_group_cache_lock;
@@ -995,10 +994,10 @@ struct btrfs_fs_info {
struct btrfs_delayed_root *delayed_root;
- /* Extent buffer xarray */
+ /* Extent buffer radix tree */
spinlock_t buffer_lock;
/* Entries are eb->start / sectorsize */
- struct xarray extent_buffers;
+ struct radix_tree_root buffer_radix;
/* next backup root to be overwritten */
int backup_root_index;
@@ -1119,8 +1118,7 @@ enum {
*/
BTRFS_ROOT_SHAREABLE,
BTRFS_ROOT_TRACK_DIRTY,
- /* The root is tracked in fs_info::fs_roots */
- BTRFS_ROOT_REGISTERED,
+ BTRFS_ROOT_IN_RADIX,
BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
BTRFS_ROOT_DEFRAG_RUNNING,
BTRFS_ROOT_FORCE_COW,
@@ -1224,10 +1222,10 @@ struct btrfs_root {
struct rb_root inode_tree;
/*
- * Xarray that keeps track of delayed nodes of every inode, protected
- * by inode_lock
+ * radix tree that keeps track of delayed nodes of every inode,
+ * protected by inode_lock
*/
- struct xarray delayed_nodes;
+ struct radix_tree_root delayed_nodes_tree;
/*
* right now this just gets used so that a root has its own devid
* for stat. It may be used for more later
@@ -1330,6 +1328,8 @@ struct btrfs_replace_extent_info {
* existing extent into a file range.
*/
bool is_new_extent;
+ /* Indicate if we should update the inode's mtime and ctime. */
+ bool update_times;
/* Meaningful only if is_new_extent is true. */
int qgroup_reserved;
/*
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 66779ab3ed4a..748bf6b0d860 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -78,7 +78,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
}
spin_lock(&root->inode_lock);
- node = xa_load(&root->delayed_nodes, ino);
+ node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
if (node) {
if (btrfs_inode->delayed_node) {
@@ -90,9 +90,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
/*
* It's possible that we're racing into the middle of removing
- * this node from the xarray. In this case, the refcount
+ * this node from the radix tree. In this case, the refcount
* was zero and it should never go back to one. Just return
- * NULL like it was never in the xarray at all; our release
+ * NULL like it was never in the radix at all; our release
* function is in the process of removing it.
*
* Some implementations of refcount_inc refuse to bump the
@@ -100,7 +100,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
* here, refcount_inc() may decide to just WARN_ONCE() instead
* of actually bumping the refcount.
*
- * If this node is properly in the xarray, we want to bump the
+ * If this node is properly in the radix, we want to bump the
* refcount twice, once for the inode and once for this get
* operation.
*/
@@ -128,30 +128,36 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
u64 ino = btrfs_ino(btrfs_inode);
int ret;
- do {
- node = btrfs_get_delayed_node(btrfs_inode);
- if (node)
- return node;
+again:
+ node = btrfs_get_delayed_node(btrfs_inode);
+ if (node)
+ return node;
- node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
- if (!node)
- return ERR_PTR(-ENOMEM);
- btrfs_init_delayed_node(node, root, ino);
+ node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
+ if (!node)
+ return ERR_PTR(-ENOMEM);
+ btrfs_init_delayed_node(node, root, ino);
- /* Cached in the inode and can be accessed */
- refcount_set(&node->refs, 2);
+ /* cached in the btrfs inode and can be accessed */
+ refcount_set(&node->refs, 2);
- spin_lock(&root->inode_lock);
- ret = xa_insert(&root->delayed_nodes, ino, node, GFP_NOFS);
- if (ret) {
- spin_unlock(&root->inode_lock);
- kmem_cache_free(delayed_node_cache, node);
- if (ret != -EBUSY)
- return ERR_PTR(ret);
- }
- } while (ret);
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ kmem_cache_free(delayed_node_cache, node);
+ return ERR_PTR(ret);
+ }
+
+ spin_lock(&root->inode_lock);
+ ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node);
+ if (ret == -EEXIST) {
+ spin_unlock(&root->inode_lock);
+ kmem_cache_free(delayed_node_cache, node);
+ radix_tree_preload_end();
+ goto again;
+ }
btrfs_inode->delayed_node = node;
spin_unlock(&root->inode_lock);
+ radix_tree_preload_end();
return node;
}
@@ -270,7 +276,8 @@ static void __btrfs_release_delayed_node(
* back up. We can delete it now.
*/
ASSERT(refcount_read(&delayed_node->refs) == 0);
- xa_erase(&root->delayed_nodes, delayed_node->inode_id);
+ radix_tree_delete(&root->delayed_nodes_tree,
+ delayed_node->inode_id);
spin_unlock(&root->inode_lock);
kmem_cache_free(delayed_node_cache, delayed_node);
}
@@ -1863,35 +1870,34 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode)
void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
{
- unsigned long index = 0;
- struct btrfs_delayed_node *delayed_node;
+ u64 inode_id = 0;
struct btrfs_delayed_node *delayed_nodes[8];
+ int i, n;
while (1) {
- int n = 0;
-
spin_lock(&root->inode_lock);
- if (xa_empty(&root->delayed_nodes)) {
+ n = radix_tree_gang_lookup(&root->delayed_nodes_tree,
+ (void **)delayed_nodes, inode_id,
+ ARRAY_SIZE(delayed_nodes));
+ if (!n) {
spin_unlock(&root->inode_lock);
- return;
+ break;
}
- xa_for_each_start(&root->delayed_nodes, index, delayed_node, index) {
+ inode_id = delayed_nodes[n - 1]->inode_id + 1;
+ for (i = 0; i < n; i++) {
/*
* Don't increase refs in case the node is dead and
* about to be removed from the tree in the loop below
*/
- if (refcount_inc_not_zero(&delayed_node->refs)) {
- delayed_nodes[n] = delayed_node;
- n++;
- }
- if (n >= ARRAY_SIZE(delayed_nodes))
- break;
+ if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+ delayed_nodes[i] = NULL;
}
- index++;
spin_unlock(&root->inode_lock);
- for (int i = 0; i < n; i++) {
+ for (i = 0; i < n; i++) {
+ if (!delayed_nodes[i])
+ continue;
__btrfs_kill_delayed_node(delayed_nodes[i]);
btrfs_release_delayed_node(delayed_nodes[i]);
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 89e94ea2fef5..1b23d806a647 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -5,6 +5,7 @@
#include <linux/fs.h>
#include <linux/blkdev.h>
+#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
@@ -485,7 +486,7 @@ static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
fs_info->nodesize);
- /* A dirty eb shouldn't disappear from extent_buffers */
+ /* A dirty eb shouldn't disappear from buffer_radix */
if (WARN_ON(!eb))
return -EUCLEAN;
@@ -952,28 +953,28 @@ void btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int mirror_
}
#ifdef CONFIG_MIGRATION
-static int btree_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page,
- enum migrate_mode mode)
+static int btree_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
/*
* we can't safely write a btree page from here,
* we haven't done the locking hook
*/
- if (PageDirty(page))
+ if (folio_test_dirty(src))
return -EAGAIN;
/*
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
- if (page_has_private(page) &&
- !try_to_release_page(page, GFP_KERNEL))
+ if (folio_get_private(src) &&
+ !filemap_release_folio(src, GFP_KERNEL))
return -EAGAIN;
- return migrate_page(mapping, newpage, page, mode);
+ return migrate_folio(mapping, dst, src, mode);
}
+#else
+#define btree_migrate_folio NULL
#endif
-
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -1073,10 +1074,8 @@ static const struct address_space_operations btree_aops = {
.writepages = btree_writepages,
.release_folio = btree_release_folio,
.invalidate_folio = btree_invalidate_folio,
-#ifdef CONFIG_MIGRATION
- .migratepage = btree_migratepage,
-#endif
- .dirty_folio = btree_dirty_folio,
+ .migrate_folio = btree_migrate_folio,
+ .dirty_folio = btree_dirty_folio,
};
struct extent_buffer *btrfs_find_create_tree_block(
@@ -1158,7 +1157,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
root->nr_delalloc_inodes = 0;
root->nr_ordered_extents = 0;
root->inode_tree = RB_ROOT;
- xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
+ INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
btrfs_init_root_block_rsv(root);
@@ -1210,9 +1209,9 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
#ifdef CONFIG_BTRFS_DEBUG
INIT_LIST_HEAD(&root->leak_list);
- spin_lock(&fs_info->fs_roots_lock);
+ spin_lock(&fs_info->fs_roots_radix_lock);
list_add_tail(&root->leak_list, &fs_info->allocated_roots);
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
#endif
}
@@ -1659,11 +1658,12 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
{
struct btrfs_root *root;
- spin_lock(&fs_info->fs_roots_lock);
- root = xa_load(&fs_info->fs_roots, (unsigned long)root_id);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)root_id);
if (root)
root = btrfs_grab_root(root);
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return root;
}
@@ -1705,14 +1705,20 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
{
int ret;
- spin_lock(&fs_info->fs_roots_lock);
- ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid,
- root, GFP_NOFS);
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret)
+ return ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ ret = radix_tree_insert(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ root);
if (ret == 0) {
btrfs_grab_root(root);
- set_bit(BTRFS_ROOT_REGISTERED, &root->state);
+ set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ radix_tree_preload_end();
return ret;
}
@@ -2342,9 +2348,9 @@ void btrfs_put_root(struct btrfs_root *root)
btrfs_drew_lock_destroy(&root->snapshot_lock);
free_root_extent_buffers(root);
#ifdef CONFIG_BTRFS_DEBUG
- spin_lock(&root->fs_info->fs_roots_lock);
+ spin_lock(&root->fs_info->fs_roots_radix_lock);
list_del_init(&root->leak_list);
- spin_unlock(&root->fs_info->fs_roots_lock);
+ spin_unlock(&root->fs_info->fs_roots_radix_lock);
#endif
kfree(root);
}
@@ -2352,21 +2358,28 @@ void btrfs_put_root(struct btrfs_root *root)
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *root;
- unsigned long index = 0;
+ int ret;
+ struct btrfs_root *gang[8];
+ int i;
while (!list_empty(&fs_info->dead_roots)) {
- root = list_entry(fs_info->dead_roots.next,
- struct btrfs_root, root_list);
- list_del(&root->root_list);
+ gang[0] = list_entry(fs_info->dead_roots.next,
+ struct btrfs_root, root_list);
+ list_del(&gang[0]->root_list);
- if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
- btrfs_drop_and_free_fs_root(fs_info, root);
- btrfs_put_root(root);
+ if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state))
+ btrfs_drop_and_free_fs_root(fs_info, gang[0]);
+ btrfs_put_root(gang[0]);
}
- xa_for_each(&fs_info->fs_roots, index, root) {
- btrfs_drop_and_free_fs_root(fs_info, root);
+ while (1) {
+ ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang));
+ if (!ret)
+ break;
+ for (i = 0; i < ret; i++)
+ btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
}
@@ -3134,8 +3147,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
{
- xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC);
- xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
@@ -3143,7 +3156,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
INIT_LIST_HEAD(&fs_info->caching_block_groups);
spin_lock_init(&fs_info->delalloc_root_lock);
spin_lock_init(&fs_info->trans_lock);
- spin_lock_init(&fs_info->fs_roots_lock);
+ spin_lock_init(&fs_info->fs_roots_radix_lock);
spin_lock_init(&fs_info->delayed_iput_lock);
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->super_lock);
@@ -3374,7 +3387,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
/*
* btrfs_find_orphan_roots() is responsible for finding all the dead
* roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
- * them into the fs_info->fs_roots. This must be done before
+ * them into the fs_info->fs_roots_radix tree. This must be done before
* calling btrfs_orphan_cleanup() on the tree root. If we don't do it
* first, then btrfs_orphan_cleanup() will delete a dead root's orphan
* item before the root's tree is deleted - this means that if we unmount
@@ -4499,11 +4512,12 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
{
bool drop_ref = false;
- spin_lock(&fs_info->fs_roots_lock);
- xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid);
- if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state))
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ radix_tree_delete(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid);
+ if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state))
drop_ref = true;
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
if (BTRFS_FS_ERROR(fs_info)) {
ASSERT(root->log_root == NULL);
@@ -4519,48 +4533,50 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *roots[8];
- unsigned long index = 0;
- int i;
+ u64 root_objectid = 0;
+ struct btrfs_root *gang[8];
+ int i = 0;
int err = 0;
- int grabbed;
+ unsigned int ret = 0;
while (1) {
- struct btrfs_root *root;
-
- spin_lock(&fs_info->fs_roots_lock);
- if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) {
- spin_unlock(&fs_info->fs_roots_lock);
- return err;
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang));
+ if (!ret) {
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ break;
}
+ root_objectid = gang[ret - 1]->root_key.objectid + 1;
- grabbed = 0;
- xa_for_each_start(&fs_info->fs_roots, index, root, index) {
- /* Avoid grabbing roots in dead_roots */
- if (btrfs_root_refs(&root->root_item) > 0)
- roots[grabbed++] = btrfs_grab_root(root);
- if (grabbed >= ARRAY_SIZE(roots))
- break;
+ for (i = 0; i < ret; i++) {
+ /* Avoid to grab roots in dead_roots */
+ if (btrfs_root_refs(&gang[i]->root_item) == 0) {
+ gang[i] = NULL;
+ continue;
+ }
+ /* grab all the search result for later use */
+ gang[i] = btrfs_grab_root(gang[i]);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
- for (i = 0; i < grabbed; i++) {
- if (!roots[i])
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
continue;
- index = roots[i]->root_key.objectid;
- err = btrfs_orphan_cleanup(roots[i]);
+ root_objectid = gang[i]->root_key.objectid;
+ err = btrfs_orphan_cleanup(gang[i]);
if (err)
- goto out;
- btrfs_put_root(roots[i]);
+ break;
+ btrfs_put_root(gang[i]);
}
- index++;
+ root_objectid++;
}
-out:
- /* Release the roots that remain uncleaned due to error */
- for (; i < grabbed; i++) {
- if (roots[i])
- btrfs_put_root(roots[i]);
+ /* release the uncleaned roots due to error */
+ for (; i < ret; i++) {
+ if (gang[i])
+ btrfs_put_root(gang[i]);
}
return err;
}
@@ -4632,6 +4648,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
int ret;
set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
+
+ /*
+ * We may have the reclaim task running and relocating a data block group,
+ * in which case it may create delayed iputs. So stop it before we park
+ * the cleaner kthread otherwise we can get new delayed iputs after
+ * parking the cleaner, and that can make the async reclaim task to hang
+ * if it's waiting for delayed iputs to complete, since the cleaner is
+ * parked and can not run delayed iputs - this will make us hang when
+ * trying to stop the async reclaim task.
+ */
+ cancel_work_sync(&fs_info->reclaim_bgs_work);
/*
* We don't want the cleaner to start new transactions, add more delayed
* iputs, etc. while we're closing. We can't use kthread_stop() yet
@@ -4672,8 +4699,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
cancel_work_sync(&fs_info->async_data_reclaim_work);
cancel_work_sync(&fs_info->preempt_reclaim_work);
- cancel_work_sync(&fs_info->reclaim_bgs_work);
-
/* Cancel or finish ongoing discard work */
btrfs_discard_cleanup(fs_info);
@@ -4870,28 +4895,31 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
{
- unsigned long index = 0;
- int grabbed = 0;
- struct btrfs_root *roots[8];
+ struct btrfs_root *gang[8];
+ u64 root_objectid = 0;
+ int ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang))) != 0) {
+ int i;
- spin_lock(&fs_info->fs_roots_lock);
- while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index,
- ULONG_MAX, 8, XA_PRESENT))) {
- for (int i = 0; i < grabbed; i++)
- roots[i] = btrfs_grab_root(roots[i]);
- spin_unlock(&fs_info->fs_roots_lock);
+ for (i = 0; i < ret; i++)
+ gang[i] = btrfs_grab_root(gang[i]);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
- for (int i = 0; i < grabbed; i++) {
- if (!roots[i])
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
continue;
- index = roots[i]->root_key.objectid;
- btrfs_free_log(NULL, roots[i]);
- btrfs_put_root(roots[i]);
+ root_objectid = gang[i]->root_key.objectid;
+ btrfs_free_log(NULL, gang[i]);
+ btrfs_put_root(gang[i]);
}
- index++;
- spin_lock(&fs_info->fs_roots_lock);
+ root_objectid++;
+ spin_lock(&fs_info->fs_roots_radix_lock);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
btrfs_free_log_root_tree(NULL, fs_info);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0867c5cd6e01..a3afc15430ce 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3832,7 +3832,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
block_group->start == fs_info->data_reloc_bg ||
fs_info->data_reloc_bg == 0);
- if (block_group->ro) {
+ if (block_group->ro || block_group->zoned_data_reloc_ongoing) {
ret = 1;
goto out;
}
@@ -3894,8 +3894,24 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
out:
if (ret && ffe_ctl->for_treelog)
fs_info->treelog_bg = 0;
- if (ret && ffe_ctl->for_data_reloc)
+ if (ret && ffe_ctl->for_data_reloc &&
+ fs_info->data_reloc_bg == block_group->start) {
+ /*
+ * Do not allow further allocations from this block group.
+ * Compared to increasing the ->ro, setting the
+ * ->zoned_data_reloc_ongoing flag still allows nocow
+ * writers to come in. See btrfs_inc_nocow_writers().
+ *
+ * We need to disable an allocation to avoid an allocation of
+ * regular (non-relocation data) extent. With mix of relocation
+ * extents and regular extents, we can dispatch WRITE commands
+ * (for relocation extents) and ZONE APPEND commands (for
+ * regular extents) at the same time to the same zone, which
+ * easily break the write pointer.
+ */
+ block_group->zoned_data_reloc_ongoing = 1;
fs_info->data_reloc_bg = 0;
+ }
spin_unlock(&fs_info->relocation_bg_lock);
spin_unlock(&fs_info->treelog_bg_lock);
spin_unlock(&block_group->lock);
@@ -5813,7 +5829,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
btrfs_qgroup_convert_reserved_meta(root, INT_MAX);
btrfs_qgroup_free_meta_all_pertrans(root);
- if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
+ if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state))
btrfs_add_dropped_root(trans, root);
else
btrfs_put_root(root);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 8f6b544ae616..9eb3056b94d4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2966,7 +2966,7 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
}
/*
- * Find extent buffer for a given bytenr.
+ * Find extent buffer for a givne bytenr.
*
* This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
* in endio context.
@@ -2985,9 +2985,11 @@ static struct extent_buffer *find_extent_buffer_readpage(
return (struct extent_buffer *)page->private;
}
- /* For subpage case, we need to lookup extent buffer xarray */
- eb = xa_load(&fs_info->extent_buffers,
- bytenr >> fs_info->sectorsize_bits);
+ /* For subpage case, we need to lookup buffer radix tree */
+ rcu_read_lock();
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ bytenr >> fs_info->sectorsize_bits);
+ rcu_read_unlock();
ASSERT(eb);
return eb;
}
@@ -3357,7 +3359,7 @@ static int calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
static int alloc_new_bio(struct btrfs_inode *inode,
struct btrfs_bio_ctrl *bio_ctrl,
struct writeback_control *wbc,
- unsigned int opf,
+ blk_opf_t opf,
bio_end_io_t end_io_func,
u64 disk_bytenr, u32 offset, u64 file_offset,
enum btrfs_compression_type compress_type)
@@ -3437,7 +3439,7 @@ error:
* @prev_bio_flags: flags of previous bio to see if we can merge the current one
* @compress_type: compress type for current bio
*/
-static int submit_extent_page(unsigned int opf,
+static int submit_extent_page(blk_opf_t opf,
struct writeback_control *wbc,
struct btrfs_bio_ctrl *bio_ctrl,
struct page *page, u64 disk_bytenr,
@@ -3615,7 +3617,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
*/
static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
struct btrfs_bio_ctrl *bio_ctrl,
- unsigned int read_flags, u64 *prev_em_start)
+ blk_opf_t read_flags, u64 *prev_em_start)
{
struct inode *inode = page->mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -3983,8 +3985,8 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
int saved_ret = 0;
int ret = 0;
int nr = 0;
- u32 opf = REQ_OP_WRITE;
- const unsigned int write_flags = wbc_to_write_flags(wbc);
+ enum req_op op = REQ_OP_WRITE;
+ const blk_opf_t write_flags = wbc_to_write_flags(wbc);
bool has_error = false;
bool compressed;
@@ -4058,7 +4060,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
iosize = min(min(em_end, end + 1), dirty_range_end) - cur;
if (btrfs_use_zone_append(inode, em->block_start))
- opf = REQ_OP_ZONE_APPEND;
+ op = REQ_OP_ZONE_APPEND;
free_extent_map(em);
em = NULL;
@@ -4094,7 +4096,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
*/
btrfs_page_clear_dirty(fs_info, page, cur, iosize);
- ret = submit_extent_page(opf | write_flags, wbc,
+ ret = submit_extent_page(op | write_flags, wbc,
&epd->bio_ctrl, page,
disk_bytenr, iosize,
cur - page_offset(page),
@@ -4435,8 +4437,8 @@ static struct extent_buffer *find_extent_buffer_nolock(
struct extent_buffer *eb;
rcu_read_lock();
- eb = xa_load(&fs_info->extent_buffers,
- start >> fs_info->sectorsize_bits);
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
return eb;
@@ -4575,7 +4577,7 @@ static int write_one_subpage_eb(struct extent_buffer *eb,
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct page *page = eb->pages[0];
- unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+ blk_opf_t write_flags = wbc_to_write_flags(wbc) | REQ_META;
bool no_dirty_ebs = false;
int ret;
@@ -4620,7 +4622,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
{
u64 disk_bytenr = eb->start;
int i, num_pages;
- unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+ blk_opf_t write_flags = wbc_to_write_flags(wbc) | REQ_META;
int ret = 0;
prepare_eb_write(eb);
@@ -5241,13 +5243,14 @@ int extent_writepages(struct address_space *mapping,
*/
btrfs_zoned_data_reloc_lock(BTRFS_I(inode));
ret = extent_write_cache_pages(mapping, wbc, &epd);
- btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
ASSERT(ret <= 0);
if (ret < 0) {
+ btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
end_write_bio(&epd, ret);
return ret;
}
flush_write_bio(&epd);
+ btrfs_zoned_data_reloc_unlock(BTRFS_I(inode));
return ret;
}
@@ -6128,22 +6131,24 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
if (!eb)
return ERR_PTR(-ENOMEM);
eb->fs_info = fs_info;
-
- do {
- ret = xa_insert(&fs_info->extent_buffers,
- start >> fs_info->sectorsize_bits,
- eb, GFP_NOFS);
- if (ret == -ENOMEM) {
- exists = ERR_PTR(ret);
+again:
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ exists = ERR_PTR(ret);
+ goto free_eb;
+ }
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits, eb);
+ spin_unlock(&fs_info->buffer_lock);
+ radix_tree_preload_end();
+ if (ret == -EEXIST) {
+ exists = find_extent_buffer(fs_info, start);
+ if (exists)
goto free_eb;
- }
- if (ret == -EBUSY) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
- goto free_eb;
- }
- } while (ret);
-
+ else
+ goto again;
+ }
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
@@ -6318,22 +6323,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-
- do {
- ret = xa_insert(&fs_info->extent_buffers,
- start >> fs_info->sectorsize_bits,
- eb, GFP_NOFS);
- if (ret == -ENOMEM) {
- exists = ERR_PTR(ret);
+again:
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ exists = ERR_PTR(ret);
+ goto free_eb;
+ }
+
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits, eb);
+ spin_unlock(&fs_info->buffer_lock);
+ radix_tree_preload_end();
+ if (ret == -EEXIST) {
+ exists = find_extent_buffer(fs_info, start);
+ if (exists)
goto free_eb;
- }
- if (ret == -EBUSY) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
- goto free_eb;
- }
- } while (ret);
-
+ else
+ goto again;
+ }
/* add one reference for the tree */
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
@@ -6378,8 +6386,10 @@ static int release_extent_buffer(struct extent_buffer *eb)
spin_unlock(&eb->refs_lock);
- xa_erase(&fs_info->extent_buffers,
- eb->start >> fs_info->sectorsize_bits);
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_delete(&fs_info->buffer_radix,
+ eb->start >> fs_info->sectorsize_bits);
+ spin_unlock(&fs_info->buffer_lock);
} else {
spin_unlock(&eb->refs_lock);
}
@@ -7324,25 +7334,42 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
}
}
+#define GANG_LOOKUP_SIZE 16
static struct extent_buffer *get_next_extent_buffer(
struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
{
- struct extent_buffer *eb;
- unsigned long index;
+ struct extent_buffer *gang[GANG_LOOKUP_SIZE];
+ struct extent_buffer *found = NULL;
u64 page_start = page_offset(page);
+ u64 cur = page_start;
ASSERT(in_range(bytenr, page_start, PAGE_SIZE));
lockdep_assert_held(&fs_info->buffer_lock);
- xa_for_each_start(&fs_info->extent_buffers, index, eb,
- page_start >> fs_info->sectorsize_bits) {
- if (in_range(eb->start, page_start, PAGE_SIZE))
- return eb;
- else if (eb->start >= page_start + PAGE_SIZE)
- /* Already beyond page end */
- return NULL;
+ while (cur < page_start + PAGE_SIZE) {
+ int ret;
+ int i;
+
+ ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
+ (void **)gang, cur >> fs_info->sectorsize_bits,
+ min_t(unsigned int, GANG_LOOKUP_SIZE,
+ PAGE_SIZE / fs_info->nodesize));
+ if (ret == 0)
+ goto out;
+ for (i = 0; i < ret; i++) {
+ /* Already beyond page end */
+ if (gang[i]->start >= page_start + PAGE_SIZE)
+ goto out;
+ /* Found one */
+ if (gang[i]->start >= bytenr) {
+ found = gang[i];
+ goto out;
+ }
+ }
+ cur = gang[ret - 1]->start + gang[ret - 1]->len;
}
- return NULL;
+out:
+ return found;
}
static int try_release_subpage_extent_buffer(struct page *page)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1fd827b99c1b..30e6aef9739f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1848,7 +1848,6 @@ static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
- const bool is_sync_write = (iocb->ki_flags & IOCB_DSYNC);
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -1902,15 +1901,6 @@ relock:
}
/*
- * We remove IOCB_DSYNC so that we don't deadlock when iomap_dio_rw()
- * calls generic_write_sync() (through iomap_dio_complete()), because
- * that results in calling fsync (btrfs_sync_file()) which will try to
- * lock the inode in exclusive/write mode.
- */
- if (is_sync_write)
- iocb->ki_flags &= ~IOCB_DSYNC;
-
- /*
* The iov_iter can be mapped to the same file range we are writing to.
* If that's the case, then we will deadlock in the iomap code, because
* it first calls our callback btrfs_dio_iomap_begin(), which will create
@@ -1964,13 +1954,6 @@ again:
btrfs_inode_unlock(inode, ilock_flags);
- /*
- * Add back IOCB_DSYNC. Our caller, btrfs_file_write_iter(), will do
- * the fsync (call generic_write_sync()).
- */
- if (is_sync_write)
- iocb->ki_flags |= IOCB_DSYNC;
-
/* If 'err' is -ENOTBLK then it means we must fallback to buffered IO. */
if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from))
goto out;
@@ -2038,7 +2021,7 @@ ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
struct file *file = iocb->ki_filp;
struct btrfs_inode *inode = BTRFS_I(file_inode(file));
ssize_t num_written, num_sync;
- const bool sync = iocb->ki_flags & IOCB_DSYNC;
+ const bool sync = iocb_is_dsync(iocb);
/*
* If the fs flips readonly due to some impossible error, although we
@@ -2323,25 +2306,62 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
- if (ret != BTRFS_NO_LOG_SYNC) {
+ if (ret == BTRFS_NO_LOG_SYNC) {
+ ret = btrfs_end_transaction(trans);
+ goto out;
+ }
+
+ /* We successfully logged the inode, attempt to sync the log. */
+ if (!ret) {
+ ret = btrfs_sync_log(trans, root, &ctx);
if (!ret) {
- ret = btrfs_sync_log(trans, root, &ctx);
- if (!ret) {
- ret = btrfs_end_transaction(trans);
- goto out;
- }
- }
- if (!full_sync) {
- ret = btrfs_wait_ordered_range(inode, start, len);
- if (ret) {
- btrfs_end_transaction(trans);
- goto out;
- }
+ ret = btrfs_end_transaction(trans);
+ goto out;
}
- ret = btrfs_commit_transaction(trans);
- } else {
+ }
+
+ /*
+ * At this point we need to commit the transaction because we had
+ * btrfs_need_log_full_commit() or some other error.
+ *
+ * If we didn't do a full sync we have to stop the trans handle, wait on
+ * the ordered extents, start it again and commit the transaction. If
+ * we attempt to wait on the ordered extents here we could deadlock with
+ * something like fallocate() that is holding the extent lock trying to
+ * start a transaction while some other thread is trying to commit the
+ * transaction while we (fsync) are currently holding the transaction
+ * open.
+ */
+ if (!full_sync) {
ret = btrfs_end_transaction(trans);
+ if (ret)
+ goto out;
+ ret = btrfs_wait_ordered_range(inode, start, len);
+ if (ret)
+ goto out;
+
+ /*
+ * This is safe to use here because we're only interested in
+ * making sure the transaction that had the ordered extents is
+ * committed. We aren't waiting on anything past this point,
+ * we're purely getting the transaction and committing it.
+ */
+ trans = btrfs_attach_transaction_barrier(root);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+
+ /*
+ * We committed the transaction and there's no currently
+ * running transaction, this means everything we care
+ * about made it to disk and we are done.
+ */
+ if (ret == -ENOENT)
+ ret = 0;
+ goto out;
+ }
}
+
+ ret = btrfs_commit_transaction(trans);
out:
ASSERT(list_empty(&ctx.list));
err = file_check_and_advance_wb_err(file);
@@ -2719,7 +2739,8 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv,
min_size, false);
- BUG_ON(ret);
+ if (WARN_ON(ret))
+ goto out_trans;
trans->block_rsv = rsv;
cur_offset = start;
@@ -2803,6 +2824,25 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
extent_info->file_offset += replace_len;
}
+ /*
+ * We are releasing our handle on the transaction, balance the
+ * dirty pages of the btree inode and flush delayed items, and
+ * then get a new transaction handle, which may now point to a
+ * new transaction in case someone else may have committed the
+ * transaction we used to replace/drop file extent items. So
+ * bump the inode's iversion and update mtime and ctime except
+ * if we are called from a dedupe context. This is because a
+ * power failure/crash may happen after the transaction is
+ * committed and before we finish replacing/dropping all the
+ * file extent items we need.
+ */
+ inode_inc_iversion(&inode->vfs_inode);
+
+ if (!extent_info || extent_info->update_times) {
+ inode->vfs_inode.i_mtime = current_time(&inode->vfs_inode);
+ inode->vfs_inode.i_ctime = inode->vfs_inode.i_mtime;
+ }
+
ret = btrfs_update_inode(trans, root, inode);
if (ret)
break;
@@ -2819,7 +2859,8 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
rsv, min_size, false);
- BUG_ON(ret); /* shouldn't happen */
+ if (WARN_ON(ret))
+ break;
trans->block_rsv = rsv;
cur_offset = drop_args.drop_end;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 81737eff92f3..3867cb0646e9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -485,7 +485,7 @@ struct async_chunk {
struct page *locked_page;
u64 start;
u64 end;
- unsigned int write_flags;
+ blk_opf_t write_flags;
struct list_head extents;
struct cgroup_subsys_state *blkcg_css;
struct btrfs_work work;
@@ -1435,7 +1435,7 @@ static int cow_file_range_async(struct btrfs_inode *inode,
int i;
bool should_compress;
unsigned nofs_flag;
- const unsigned int write_flags = wbc_to_write_flags(wbc);
+ const blk_opf_t write_flags = wbc_to_write_flags(wbc);
unlock_extent(&inode->io_tree, start, end);
@@ -3195,6 +3195,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
ordered_extent->file_offset,
ordered_extent->file_offset +
logical_len);
+ btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr,
+ ordered_extent->disk_num_bytes);
} else {
BUG_ON(root == fs_info->tree_root);
ret = insert_ordered_extent_file_extent(trans, ordered_extent);
@@ -3576,7 +3578,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
u64 last_objectid = 0;
int ret = 0, nr_unlink = 0;
- /* Bail out if the cleanup is already running. */
if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state))
return 0;
@@ -3659,17 +3660,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
*
* btrfs_find_orphan_roots() ran before us, which has
* found all deleted roots and loaded them into
- * fs_info->fs_roots. So here we can find if an
+ * fs_info->fs_roots_radix. So here we can find if an
* orphan item corresponds to a deleted root by looking
- * up the root from that xarray.
+ * up the root from that radix tree.
*/
- spin_lock(&fs_info->fs_roots_lock);
- dead_root = xa_load(&fs_info->fs_roots,
- (unsigned long)found_key.objectid);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)found_key.objectid);
if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
is_dead_root = 1;
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
if (is_dead_root) {
/* prevent this orphan from being found again */
@@ -3909,7 +3910,7 @@ cache_index:
* cache.
*
* This is required for both inode re-read from disk and delayed inode
- * in the delayed_nodes xarray.
+ * in delayed_nodes_tree.
*/
if (BTRFS_I(inode)->last_trans == fs_info->generation)
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
@@ -7679,7 +7680,19 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) ||
em->block_start == EXTENT_MAP_INLINE) {
free_extent_map(em);
- ret = -ENOTBLK;
+ /*
+ * If we are in a NOWAIT context, return -EAGAIN in order to
+ * fallback to buffered IO. This is not only because we can
+ * block with buffered IO (no support for NOWAIT semantics at
+ * the moment) but also to avoid returning short reads to user
+ * space - this happens if we were able to read some data from
+ * previous non-compressed extents and then when we fallback to
+ * buffered IO, at btrfs_file_read_iter() by calling
+ * filemap_read(), we fail to fault in pages for the read buffer,
+ * in which case filemap_read() returns a short read (the number
+ * of bytes previously read is > 0, so it does not return -EFAULT).
+ */
+ ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
goto unlock_err;
}
@@ -8152,7 +8165,8 @@ ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_befo
struct btrfs_dio_data data;
return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
- IOMAP_DIO_PARTIAL, &data, done_before);
+ IOMAP_DIO_PARTIAL | IOMAP_DIO_NOSYNC,
+ &data, done_before);
}
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
@@ -8255,30 +8269,24 @@ static bool btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
}
#ifdef CONFIG_MIGRATION
-static int btrfs_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page,
+static int btrfs_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src,
enum migrate_mode mode)
{
- int ret;
+ int ret = filemap_migrate_folio(mapping, dst, src, mode);
- ret = migrate_page_move_mapping(mapping, newpage, page, 0);
if (ret != MIGRATEPAGE_SUCCESS)
return ret;
- if (page_has_private(page))
- attach_page_private(newpage, detach_page_private(page));
-
- if (PageOrdered(page)) {
- ClearPageOrdered(page);
- SetPageOrdered(newpage);
+ if (folio_test_ordered(src)) {
+ folio_clear_ordered(src);
+ folio_set_ordered(dst);
}
- if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
- else
- migrate_page_states(newpage, page);
return MIGRATEPAGE_SUCCESS;
}
+#else
+#define btrfs_migrate_folio NULL
#endif
static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
@@ -9897,6 +9905,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
extent_info.file_offset = file_offset;
extent_info.extent_buf = (char *)&stack_fi;
extent_info.is_new_extent = true;
+ extent_info.update_times = true;
extent_info.qgroup_reserved = qgroup_released;
extent_info.insertions = 0;
@@ -11422,9 +11431,7 @@ static const struct address_space_operations btrfs_aops = {
.direct_IO = noop_direct_IO,
.invalidate_folio = btrfs_invalidate_folio,
.release_folio = btrfs_release_folio,
-#ifdef CONFIG_MIGRATION
- .migratepage = btrfs_migratepage,
-#endif
+ .migrate_folio = btrfs_migrate_folio,
.dirty_folio = filemap_dirty_folio,
.error_remove_page = generic_error_remove_page,
.swap_activate = btrfs_swap_activate,
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 313d9d685adb..33461b4f9c8b 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -45,7 +45,6 @@ void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting ne
start_ns = ktime_get_ns();
down_read_nested(&eb->lock, nest);
- eb->lock_owner = current->pid;
trace_btrfs_tree_read_lock(eb, start_ns);
}
@@ -62,7 +61,6 @@ void btrfs_tree_read_lock(struct extent_buffer *eb)
int btrfs_try_tree_read_lock(struct extent_buffer *eb)
{
if (down_read_trylock(&eb->lock)) {
- eb->lock_owner = current->pid;
trace_btrfs_try_tree_read_lock(eb);
return 1;
}
@@ -90,7 +88,6 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
void btrfs_tree_read_unlock(struct extent_buffer *eb)
{
trace_btrfs_tree_read_unlock(eb);
- eb->lock_owner = 0;
up_read(&eb->lock);
}
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index a5b623ee6fac..c520412d1f86 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1136,7 +1136,7 @@ static int rbio_add_io_sector(struct btrfs_raid_bio *rbio,
unsigned int stripe_nr,
unsigned int sector_nr,
unsigned long bio_max_len,
- unsigned int opf)
+ enum req_op op)
{
const u32 sectorsize = rbio->bioc->fs_info->sectorsize;
struct bio *last = bio_list->tail;
@@ -1181,7 +1181,7 @@ static int rbio_add_io_sector(struct btrfs_raid_bio *rbio,
/* put a new bio on the list */
bio = bio_alloc(stripe->dev->bdev, max(bio_max_len >> PAGE_SHIFT, 1UL),
- opf, GFP_NOFS);
+ op, GFP_NOFS);
bio->bi_iter.bi_sector = disk_start >> 9;
bio->bi_private = rbio;
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index c39f8b3a5a4a..a3549d587464 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -344,6 +344,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
int ret;
const u64 len = olen_aligned;
u64 last_dest_end = destoff;
+ u64 prev_extent_end = off;
ret = -ENOMEM;
buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
@@ -363,7 +364,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
key.offset = off;
while (1) {
- u64 next_key_min_offset = key.offset + 1;
struct btrfs_file_extent_item *extent;
u64 extent_gen;
int type;
@@ -431,14 +431,21 @@ process_slot:
* The first search might have left us at an extent item that
* ends before our target range's start, can happen if we have
* holes and NO_HOLES feature enabled.
+ *
+ * Subsequent searches may leave us on a file range we have
+ * processed before - this happens due to a race with ordered
+ * extent completion for a file range that is outside our source
+ * range, but that range was part of a file extent item that
+ * also covered a leading part of our source range.
*/
- if (key.offset + datal <= off) {
+ if (key.offset + datal <= prev_extent_end) {
path->slots[0]++;
goto process_slot;
} else if (key.offset >= off + len) {
break;
}
- next_key_min_offset = key.offset + datal;
+
+ prev_extent_end = key.offset + datal;
size = btrfs_item_size(leaf, slot);
read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot),
size);
@@ -489,6 +496,7 @@ process_slot:
clone_info.file_offset = new_key.offset;
clone_info.extent_buf = buf;
clone_info.is_new_extent = false;
+ clone_info.update_times = !no_time_update;
ret = btrfs_replace_file_extents(BTRFS_I(inode), path,
drop_start, new_key.offset + datal - 1,
&clone_info, &trans);
@@ -550,7 +558,7 @@ process_slot:
break;
btrfs_release_path(path);
- key.offset = next_key_min_offset;
+ key.offset = prev_extent_end;
if (fatal_signal_pending(current)) {
ret = -EINTR;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index fa56890ff81f..c7dea639a56f 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -10,6 +10,7 @@
#include <linux/mount.h>
#include <linux/xattr.h>
#include <linux/posix_acl_xattr.h>
+#include <linux/radix-tree.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/compat.h>
@@ -127,7 +128,7 @@ struct send_ctx {
struct list_head new_refs;
struct list_head deleted_refs;
- struct xarray name_cache;
+ struct radix_tree_root name_cache;
struct list_head name_cache_list;
int name_cache_size;
@@ -268,13 +269,14 @@ struct orphan_dir_info {
struct name_cache_entry {
struct list_head list;
/*
- * On 32bit kernels, xarray has only 32bit indices, but we need to
- * handle 64bit inums. We use the lower 32bit of the 64bit inum to store
- * it in the tree. If more than one inum would fall into the same entry,
- * we use inum_aliases to store the additional entries. inum_aliases is
- * also used to store entries with the same inum but different generations.
+ * radix_tree has only 32bit entries but we need to handle 64bit inums.
+ * We use the lower 32bit of the 64bit inum to store it in the tree. If
+ * more then one inum would fall into the same entry, we use radix_list
+ * to store the additional entries. radix_list is also used to store
+ * entries where two entries have the same inum but different
+ * generations.
*/
- struct list_head inum_aliases;
+ struct list_head radix_list;
u64 ino;
u64 gen;
u64 parent_ino;
@@ -2024,9 +2026,9 @@ out:
}
/*
- * Insert a name cache entry. On 32bit kernels the xarray index is 32bit,
+ * Insert a name cache entry. On 32bit kernels the radix tree index is 32bit,
* so we need to do some special handling in case we have clashes. This function
- * takes care of this with the help of name_cache_entry::inum_aliases.
+ * takes care of this with the help of name_cache_entry::radix_list.
* In case of error, nce is kfreed.
*/
static int name_cache_insert(struct send_ctx *sctx,
@@ -2035,7 +2037,8 @@ static int name_cache_insert(struct send_ctx *sctx,
int ret = 0;
struct list_head *nce_head;
- nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino);
+ nce_head = radix_tree_lookup(&sctx->name_cache,
+ (unsigned long)nce->ino);
if (!nce_head) {
nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
if (!nce_head) {
@@ -2044,14 +2047,14 @@ static int name_cache_insert(struct send_ctx *sctx,
}
INIT_LIST_HEAD(nce_head);
- ret = xa_insert(&sctx->name_cache, nce->ino, nce_head, GFP_KERNEL);
+ ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
if (ret < 0) {
kfree(nce_head);
kfree(nce);
return ret;
}
}
- list_add_tail(&nce->inum_aliases, nce_head);
+ list_add_tail(&nce->radix_list, nce_head);
list_add_tail(&nce->list, &sctx->name_cache_list);
sctx->name_cache_size++;
@@ -2063,14 +2066,15 @@ static void name_cache_delete(struct send_ctx *sctx,
{
struct list_head *nce_head;
- nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino);
+ nce_head = radix_tree_lookup(&sctx->name_cache,
+ (unsigned long)nce->ino);
if (!nce_head) {
btrfs_err(sctx->send_root->fs_info,
"name_cache_delete lookup failed ino %llu cache size %d, leaking memory",
nce->ino, sctx->name_cache_size);
}
- list_del(&nce->inum_aliases);
+ list_del(&nce->radix_list);
list_del(&nce->list);
sctx->name_cache_size--;
@@ -2078,7 +2082,7 @@ static void name_cache_delete(struct send_ctx *sctx,
* We may not get to the final release of nce_head if the lookup fails
*/
if (nce_head && list_empty(nce_head)) {
- xa_erase(&sctx->name_cache, (unsigned long)nce->ino);
+ radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino);
kfree(nce_head);
}
}
@@ -2089,11 +2093,11 @@ static struct name_cache_entry *name_cache_search(struct send_ctx *sctx,
struct list_head *nce_head;
struct name_cache_entry *cur;
- nce_head = xa_load(&sctx->name_cache, (unsigned long)ino);
+ nce_head = radix_tree_lookup(&sctx->name_cache, (unsigned long)ino);
if (!nce_head)
return NULL;
- list_for_each_entry(cur, nce_head, inum_aliases) {
+ list_for_each_entry(cur, nce_head, radix_list) {
if (cur->ino == ino && cur->gen == gen)
return cur;
}
@@ -7518,7 +7522,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
INIT_LIST_HEAD(&sctx->new_refs);
INIT_LIST_HEAD(&sctx->deleted_refs);
- xa_init_flags(&sctx->name_cache, GFP_KERNEL);
+ INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
INIT_LIST_HEAD(&sctx->name_cache_list);
sctx->flags = arg->flags;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index b1fdc6a26c76..6627dd7875ee 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -763,6 +763,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
compress_force = false;
no_compress++;
} else {
+ btrfs_err(info, "unrecognized compression value %s",
+ args[0].from);
ret = -EINVAL;
goto out;
}
@@ -821,8 +823,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
case Opt_thread_pool:
ret = match_int(&args[0], &intarg);
if (ret) {
+ btrfs_err(info, "unrecognized thread_pool value %s",
+ args[0].from);
goto out;
} else if (intarg == 0) {
+ btrfs_err(info, "invalid value 0 for thread_pool");
ret = -EINVAL;
goto out;
}
@@ -883,8 +888,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
break;
case Opt_ratio:
ret = match_int(&args[0], &intarg);
- if (ret)
+ if (ret) {
+ btrfs_err(info, "unrecognized metadata_ratio value %s",
+ args[0].from);
goto out;
+ }
info->metadata_ratio = intarg;
btrfs_info(info, "metadata ratio %u",
info->metadata_ratio);
@@ -901,6 +909,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
btrfs_set_and_info(info, DISCARD_ASYNC,
"turning on async discard");
} else {
+ btrfs_err(info, "unrecognized discard mode value %s",
+ args[0].from);
ret = -EINVAL;
goto out;
}
@@ -933,6 +943,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
btrfs_set_and_info(info, FREE_SPACE_TREE,
"enabling free space tree");
} else {
+ btrfs_err(info, "unrecognized space_cache value %s",
+ args[0].from);
ret = -EINVAL;
goto out;
}
@@ -1014,8 +1026,12 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
break;
case Opt_check_integrity_print_mask:
ret = match_int(&args[0], &intarg);
- if (ret)
+ if (ret) {
+ btrfs_err(info,
+ "unrecognized check_integrity_print_mask value %s",
+ args[0].from);
goto out;
+ }
info->check_integrity_print_mask = intarg;
btrfs_info(info, "check_integrity_print_mask 0x%x",
info->check_integrity_print_mask);
@@ -1030,13 +1046,15 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
goto out;
#endif
case Opt_fatal_errors:
- if (strcmp(args[0].from, "panic") == 0)
+ if (strcmp(args[0].from, "panic") == 0) {
btrfs_set_opt(info->mount_opt,
PANIC_ON_FATAL_ERROR);
- else if (strcmp(args[0].from, "bug") == 0)
+ } else if (strcmp(args[0].from, "bug") == 0) {
btrfs_clear_opt(info->mount_opt,
PANIC_ON_FATAL_ERROR);
- else {
+ } else {
+ btrfs_err(info, "unrecognized fatal_errors value %s",
+ args[0].from);
ret = -EINVAL;
goto out;
}
@@ -1044,8 +1062,12 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
case Opt_commit_interval:
intarg = 0;
ret = match_int(&args[0], &intarg);
- if (ret)
+ if (ret) {
+ btrfs_err(info, "unrecognized commit_interval value %s",
+ args[0].from);
+ ret = -EINVAL;
goto out;
+ }
if (intarg == 0) {
btrfs_info(info,
"using default commit interval %us",
@@ -1059,8 +1081,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
break;
case Opt_rescue:
ret = parse_rescue_options(info, args[0].from);
- if (ret < 0)
+ if (ret < 0) {
+ btrfs_err(info, "unrecognized rescue value %s",
+ args[0].from);
goto out;
+ }
break;
#ifdef CONFIG_BTRFS_DEBUG
case Opt_fragment_all:
@@ -1985,6 +2010,14 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
if (ret)
goto restore;
+ /* V1 cache is not supported for subpage mount. */
+ if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) {
+ btrfs_warn(fs_info,
+ "v1 space cache is not supported for page size %lu with sectorsize %u",
+ PAGE_SIZE, fs_info->sectorsize);
+ ret = -EINVAL;
+ goto restore;
+ }
btrfs_remount_begin(fs_info, old_opts, *flags);
btrfs_resize_thread_pool(fs_info,
fs_info->thread_pool_size, old_thread_pool_size);
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 1591bfa55bcc..d8e56edd6991 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -150,8 +150,8 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
{
- unsigned long index;
- struct extent_buffer *eb;
+ struct radix_tree_iter iter;
+ void **slot;
struct btrfs_device *dev, *tmp;
if (!fs_info)
@@ -163,9 +163,25 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
test_mnt->mnt_sb->s_fs_info = NULL;
- xa_for_each(&fs_info->extent_buffers, index, eb) {
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
+ struct extent_buffer *eb;
+
+ eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock);
+ if (!eb)
+ continue;
+ /* Shouldn't happen but that kind of thinking creates CVE's */
+ if (radix_tree_exception(eb)) {
+ if (radix_tree_deref_retry(eb))
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+ slot = radix_tree_iter_resume(slot, &iter);
+ spin_unlock(&fs_info->buffer_lock);
free_extent_buffer_stale(eb);
+ spin_lock(&fs_info->buffer_lock);
}
+ spin_unlock(&fs_info->buffer_lock);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices,
@@ -186,7 +202,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
if (!root)
return;
/* Will be freed by btrfs_free_fs_roots */
- if (WARN_ON(test_bit(BTRFS_ROOT_REGISTERED, &root->state)))
+ if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state)))
return;
btrfs_global_root_delete(root);
btrfs_put_root(root);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 06c0a958d114..875b801ab3d7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -23,7 +23,7 @@
#include "space-info.h"
#include "zoned.h"
-#define BTRFS_ROOT_TRANS_TAG XA_MARK_0
+#define BTRFS_ROOT_TRANS_TAG 0
/*
* Transaction states and transitions
@@ -437,15 +437,15 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
*/
smp_wmb();
- spin_lock(&fs_info->fs_roots_lock);
+ spin_lock(&fs_info->fs_roots_radix_lock);
if (root->last_trans == trans->transid && !force) {
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return 0;
}
- xa_set_mark(&fs_info->fs_roots,
- (unsigned long)root->root_key.objectid,
- BTRFS_ROOT_TRANS_TAG);
- spin_unlock(&fs_info->fs_roots_lock);
+ radix_tree_tag_set(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
root->last_trans = trans->transid;
/* this is pretty tricky. We don't want to
@@ -487,9 +487,11 @@ void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
spin_unlock(&cur_trans->dropped_roots_lock);
/* Make sure we don't try to update the root at commit time */
- xa_clear_mark(&fs_info->fs_roots,
- (unsigned long)root->root_key.objectid,
- BTRFS_ROOT_TRANS_TAG);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ radix_tree_tag_clear(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
}
int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
@@ -1402,8 +1404,9 @@ void btrfs_add_dead_root(struct btrfs_root *root)
static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *root;
- unsigned long index;
+ struct btrfs_root *gang[8];
+ int i;
+ int ret;
/*
* At this point no one can be using this transaction to modify any tree
@@ -1411,46 +1414,57 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
*/
ASSERT(trans->transaction->state == TRANS_STATE_COMMIT_DOING);
- spin_lock(&fs_info->fs_roots_lock);
- xa_for_each_marked(&fs_info->fs_roots, index, root, BTRFS_ROOT_TRANS_TAG) {
- int ret;
-
- /*
- * At this point we can neither have tasks logging inodes
- * from a root nor trying to commit a log tree.
- */
- ASSERT(atomic_read(&root->log_writers) == 0);
- ASSERT(atomic_read(&root->log_commit[0]) == 0);
- ASSERT(atomic_read(&root->log_commit[1]) == 0);
-
- xa_clear_mark(&fs_info->fs_roots,
- (unsigned long)root->root_key.objectid,
- BTRFS_ROOT_TRANS_TAG);
- spin_unlock(&fs_info->fs_roots_lock);
-
- btrfs_free_log(trans, root);
- ret = btrfs_update_reloc_root(trans, root);
- if (ret)
- return ret;
-
- /* See comments in should_cow_block() */
- clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
- smp_mb__after_atomic();
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while (1) {
+ ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang),
+ BTRFS_ROOT_TRANS_TAG);
+ if (ret == 0)
+ break;
+ for (i = 0; i < ret; i++) {
+ struct btrfs_root *root = gang[i];
+ int ret2;
+
+ /*
+ * At this point we can neither have tasks logging inodes
+ * from a root nor trying to commit a log tree.
+ */
+ ASSERT(atomic_read(&root->log_writers) == 0);
+ ASSERT(atomic_read(&root->log_commit[0]) == 0);
+ ASSERT(atomic_read(&root->log_commit[1]) == 0);
+
+ radix_tree_tag_clear(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+
+ btrfs_free_log(trans, root);
+ ret2 = btrfs_update_reloc_root(trans, root);
+ if (ret2)
+ return ret2;
+
+ /* see comments in should_cow_block() */
+ clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
+ smp_mb__after_atomic();
+
+ if (root->commit_root != root->node) {
+ list_add_tail(&root->dirty_list,
+ &trans->transaction->switch_commits);
+ btrfs_set_root_node(&root->root_item,
+ root->node);
+ }
- if (root->commit_root != root->node) {
- list_add_tail(&root->dirty_list,
- &trans->transaction->switch_commits);
- btrfs_set_root_node(&root->root_item, root->node);
+ ret2 = btrfs_update_root(trans, fs_info->tree_root,
+ &root->root_key,
+ &root->root_item);
+ if (ret2)
+ return ret2;
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ btrfs_qgroup_free_meta_all_pertrans(root);
}
-
- ret = btrfs_update_root(trans, fs_info->tree_root,
- &root->root_key, &root->root_item);
- if (ret)
- return ret;
- spin_lock(&fs_info->fs_roots_lock);
- btrfs_qgroup_free_meta_all_pertrans(root);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return 0;
}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 11237a913bee..d99026df6f67 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1735,12 +1735,14 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
&mapped_length, &bioc);
if (ret || !bioc || mapped_length < PAGE_SIZE) {
- btrfs_put_bioc(bioc);
- return -EIO;
+ ret = -EIO;
+ goto out_put_bioc;
}
- if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK)
- return -EINVAL;
+ if (bioc->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+ ret = -EINVAL;
+ goto out_put_bioc;
+ }
nofs_flag = memalloc_nofs_save();
nmirrors = (int)bioc->num_stripes;
@@ -1759,7 +1761,8 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
break;
}
memalloc_nofs_restore(nofs_flag);
-
+out_put_bioc:
+ btrfs_put_bioc(bioc);
return ret;
}
@@ -1885,7 +1888,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct map_lookup *map;
- bool need_zone_finish;
int ret = 0;
int i;
@@ -1942,12 +1944,6 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
}
}
- /*
- * The block group is not fully allocated, so not fully written yet. We
- * need to send ZONE_FINISH command to free up an active zone.
- */
- need_zone_finish = !btrfs_zoned_bg_is_full(block_group);
-
block_group->zone_is_active = 0;
block_group->alloc_offset = block_group->zone_capacity;
block_group->free_space_ctl->free_space = 0;
@@ -1963,15 +1959,13 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
if (device->zone_info->max_active_zones == 0)
continue;
- if (need_zone_finish) {
- ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
- physical >> SECTOR_SHIFT,
- device->zone_info->zone_size >> SECTOR_SHIFT,
- GFP_NOFS);
+ ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
+ physical >> SECTOR_SHIFT,
+ device->zone_info->zone_size >> SECTOR_SHIFT,
+ GFP_NOFS);
- if (ret)
- return ret;
- }
+ if (ret)
+ return ret;
btrfs_dev_clear_active_zone(device, physical);
}
@@ -2139,3 +2133,30 @@ bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info)
factor = div64_u64(used * 100, total);
return factor >= fs_info->bg_reclaim_threshold;
}
+
+void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
+ u64 length)
+{
+ struct btrfs_block_group *block_group;
+
+ if (!btrfs_is_zoned(fs_info))
+ return;
+
+ block_group = btrfs_lookup_block_group(fs_info, logical);
+ /* It should be called on a previous data relocation block group. */
+ ASSERT(block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA));
+
+ spin_lock(&block_group->lock);
+ if (!block_group->zoned_data_reloc_ongoing)
+ goto out;
+
+ /* All relocation extents are written. */
+ if (block_group->start + block_group->alloc_offset == logical + length) {
+ /* Now, release this block group for further allocations. */
+ block_group->zoned_data_reloc_ongoing = 0;
+ }
+
+out:
+ spin_unlock(&block_group->lock);
+ btrfs_put_block_group(block_group);
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index bb1a189e11f9..6b2eec99162b 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -77,6 +77,8 @@ void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,
void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg);
void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info);
bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info);
+void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
+ u64 length);
#else /* CONFIG_BLK_DEV_ZONED */
static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
struct blk_zone *zone)
@@ -243,6 +245,9 @@ static inline bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info)
{
return false;
}
+
+static inline void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length) { }
#endif
static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-21 21:45:07 +0000