summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/bio.c26
-rw-r--r--fs/btrfs/block-group.c13
-rw-r--r--fs/btrfs/delayed-ref.c67
-rw-r--r--fs/btrfs/delayed-ref.h2
-rw-r--r--fs/btrfs/direct-io.c28
-rw-r--r--fs/btrfs/extent-tree.c54
-rw-r--r--fs/btrfs/extent_io.c14
-rw-r--r--fs/btrfs/extent_map.c24
-rw-r--r--fs/btrfs/fiemap.c2
-rw-r--r--fs/btrfs/file.c27
-rw-r--r--fs/btrfs/free-space-cache.c18
-rw-r--r--fs/btrfs/inode.c29
-rw-r--r--fs/btrfs/print-tree.c2
-rw-r--r--fs/btrfs/qgroup.c5
-rw-r--r--fs/btrfs/scrub.c25
-rw-r--r--fs/btrfs/send.c54
-rw-r--r--fs/btrfs/space-info.c22
-rw-r--r--fs/btrfs/space-info.h3
-rw-r--r--fs/btrfs/super.c23
-rw-r--r--fs/btrfs/tests/extent-map-tests.c99
-rw-r--r--fs/btrfs/transaction.h6
-rw-r--r--fs/btrfs/tree-checker.c123
-rw-r--r--fs/btrfs/zoned.c30
23 files changed, 574 insertions, 122 deletions
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index f04d93109960..b4e31ae17cd9 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -668,7 +668,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
{
struct btrfs_inode *inode = bbio->inode;
struct btrfs_fs_info *fs_info = bbio->fs_info;
- struct btrfs_bio *orig_bbio = bbio;
struct bio *bio = &bbio->bio;
u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
u64 length = bio->bi_iter.bi_size;
@@ -706,7 +705,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
bbio->saved_iter = bio->bi_iter;
ret = btrfs_lookup_bio_sums(bbio);
if (ret)
- goto fail_put_bio;
+ goto fail;
}
if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
@@ -740,13 +739,13 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
ret = btrfs_bio_csum(bbio);
if (ret)
- goto fail_put_bio;
+ goto fail;
} else if (use_append ||
(btrfs_is_zoned(fs_info) && inode &&
inode->flags & BTRFS_INODE_NODATASUM)) {
ret = btrfs_alloc_dummy_sum(bbio);
if (ret)
- goto fail_put_bio;
+ goto fail;
}
}
@@ -754,12 +753,23 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
done:
return map_length == length;
-fail_put_bio:
- if (map_length < length)
- btrfs_cleanup_bio(bbio);
fail:
btrfs_bio_counter_dec(fs_info);
- btrfs_bio_end_io(orig_bbio, ret);
+ /*
+ * We have split the original bbio, now we have to end both the current
+ * @bbio and remaining one, as the remaining one will never be submitted.
+ */
+ if (map_length < length) {
+ struct btrfs_bio *remaining = bbio->private;
+
+ ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset);
+ ASSERT(remaining);
+
+ remaining->bio.bi_status = ret;
+ btrfs_orig_bbio_end_io(remaining);
+ }
+ bbio->bio.bi_status = ret;
+ btrfs_orig_bbio_end_io(bbio);
/* Do not submit another chunk */
return true;
}
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 498442d0c216..2e49d978f504 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1223,8 +1223,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
block_group->space_info->total_bytes -= block_group->length;
block_group->space_info->bytes_readonly -=
(block_group->length - block_group->zone_unusable);
- block_group->space_info->bytes_zone_unusable -=
- block_group->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info,
+ -block_group->zone_unusable);
block_group->space_info->disk_total -= block_group->length * factor;
spin_unlock(&block_group->space_info->lock);
@@ -1396,7 +1396,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes to readonly */
sinfo->bytes_readonly += cache->zone_unusable;
- sinfo->bytes_zone_unusable -= cache->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
+ -cache->zone_unusable);
cache->zone_unusable = 0;
}
cache->ro++;
@@ -3056,9 +3057,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes back */
cache->zone_unusable =
- (cache->alloc_offset - cache->used) +
+ (cache->alloc_offset - cache->used - cache->pinned -
+ cache->reserved) +
(cache->length - cache->zone_capacity);
- sinfo->bytes_zone_unusable += cache->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
+ cache->zone_unusable);
sinfo->bytes_readonly -= cache->zone_unusable;
}
num_bytes = cache->length - cache->reserved -
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 2ac9296edccb..06a9e0542d70 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -1134,6 +1134,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt
return find_ref_head(delayed_refs, bytenr, false);
}
+static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent)
+{
+ int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY;
+
+ if (type < entry->type)
+ return -1;
+ if (type > entry->type)
+ return 1;
+
+ if (type == BTRFS_TREE_BLOCK_REF_KEY) {
+ if (root < entry->ref_root)
+ return -1;
+ if (root > entry->ref_root)
+ return 1;
+ } else {
+ if (parent < entry->parent)
+ return -1;
+ if (parent > entry->parent)
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * Check to see if a given root/parent reference is attached to the head. This
+ * only checks for BTRFS_ADD_DELAYED_REF references that match, as that
+ * indicates the reference exists for the given root or parent. This is for
+ * tree blocks only.
+ *
+ * @head: the head of the bytenr we're searching.
+ * @root: the root objectid of the reference if it is a normal reference.
+ * @parent: the parent if this is a shared backref.
+ */
+bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
+ u64 root, u64 parent)
+{
+ struct rb_node *node;
+ bool found = false;
+
+ lockdep_assert_held(&head->mutex);
+
+ spin_lock(&head->lock);
+ node = head->ref_tree.rb_root.rb_node;
+ while (node) {
+ struct btrfs_delayed_ref_node *entry;
+ int ret;
+
+ entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
+ ret = find_comp(entry, root, parent);
+ if (ret < 0) {
+ node = node->rb_left;
+ } else if (ret > 0) {
+ node = node->rb_right;
+ } else {
+ /*
+ * We only want to count ADD actions, as drops mean the
+ * ref doesn't exist.
+ */
+ if (entry->action == BTRFS_ADD_DELAYED_REF)
+ found = true;
+ break;
+ }
+ }
+ spin_unlock(&head->lock);
+ return found;
+}
+
void __cold btrfs_delayed_ref_exit(void)
{
kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index ef15e998be03..05f634eb472d 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -389,6 +389,8 @@ void btrfs_dec_delayed_refs_rsv_bg_updates(struct btrfs_fs_info *fs_info);
int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
enum btrfs_reserve_flush_enum flush);
bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
+bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
+ u64 root, u64 parent);
static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node)
{
diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index f9fb2db6a1e4..364bce34f034 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -856,21 +856,27 @@ relock:
* So here we disable page faults in the iov_iter and then retry if we
* got -EFAULT, faulting in the pages before the retry.
*/
+again:
from->nofault = true;
dio = btrfs_dio_write(iocb, from, written);
from->nofault = false;
- /*
- * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
- * iocb, and that needs to lock the inode. So unlock it before calling
- * iomap_dio_complete() to avoid a deadlock.
- */
- btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-
- if (IS_ERR_OR_NULL(dio))
+ if (IS_ERR_OR_NULL(dio)) {
ret = PTR_ERR_OR_ZERO(dio);
- else
+ } else {
+ /*
+ * If we have a synchronous write, we must make sure the fsync
+ * triggered by the iomap_dio_complete() call below doesn't
+ * deadlock on the inode lock - we are already holding it and we
+ * can't call it after unlocking because we may need to complete
+ * partial writes due to the input buffer (or parts of it) not
+ * being already faulted in.
+ */
+ ASSERT(current->journal_info == NULL);
+ current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB;
ret = iomap_dio_complete(dio);
+ current->journal_info = NULL;
+ }
/* No increment (+=) because iomap returns a cumulative value. */
if (ret > 0)
@@ -897,10 +903,12 @@ relock:
} else {
fault_in_iov_iter_readable(from, left);
prev_left = left;
- goto relock;
+ goto again;
}
}
+ btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+
/*
* If 'ret' is -ENOTBLK or we have not written all data, then it means
* we must fallback to buffered IO.
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d77498e7671c..feec49e6f9c8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2793,7 +2793,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
readonly = true;
} else if (btrfs_is_zoned(fs_info)) {
/* Need reset before reusing in a zoned block group */
- space_info->bytes_zone_unusable += len;
+ btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info,
+ len);
readonly = true;
}
spin_unlock(&cache->lock);
@@ -5471,23 +5472,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr, u64 parent,
int level)
{
+ struct btrfs_delayed_ref_root *delayed_refs;
+ struct btrfs_delayed_ref_head *head;
struct btrfs_path *path;
struct btrfs_extent_inline_ref *iref;
int ret;
+ bool exists = false;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
-
+again:
ret = lookup_extent_backref(trans, path, &iref, bytenr,
root->fs_info->nodesize, parent,
btrfs_root_id(root), level, 0);
+ if (ret != -ENOENT) {
+ /*
+ * If we get 0 then we found our reference, return 1, else
+ * return the error if it's not -ENOENT;
+ */
+ btrfs_free_path(path);
+ return (ret < 0 ) ? ret : 1;
+ }
+
+ /*
+ * We could have a delayed ref with this reference, so look it up while
+ * we're holding the path open to make sure we don't race with the
+ * delayed ref running.
+ */
+ delayed_refs = &trans->transaction->delayed_refs;
+ spin_lock(&delayed_refs->lock);
+ head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
+ if (!head)
+ goto out;
+ if (!mutex_trylock(&head->mutex)) {
+ /*
+ * We're contended, means that the delayed ref is running, get a
+ * reference and wait for the ref head to be complete and then
+ * try again.
+ */
+ refcount_inc(&head->refs);
+ spin_unlock(&delayed_refs->lock);
+
+ btrfs_release_path(path);
+
+ mutex_lock(&head->mutex);
+ mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref_head(head);
+ goto again;
+ }
+
+ exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent);
+ mutex_unlock(&head->mutex);
+out:
+ spin_unlock(&delayed_refs->lock);
btrfs_free_path(path);
- if (ret == -ENOENT)
- return 0;
- if (ret < 0)
- return ret;
- return 1;
+ return exists ? 1 : 0;
}
/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index aa7f8148cd0d..c73cd4f89015 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1496,6 +1496,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
free_extent_map(em);
em = NULL;
+ /*
+ * Although the PageDirty bit might be cleared before entering
+ * this function, subpage dirty bit is not cleared.
+ * So clear subpage dirty bit here so next time we won't submit
+ * page for range already written to disk.
+ */
+ btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
btrfs_set_range_writeback(inode, cur, cur + iosize - 1);
if (!PageWriteback(page)) {
btrfs_err(inode->root->fs_info,
@@ -1503,13 +1510,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
page->index, cur, end);
}
- /*
- * Although the PageDirty bit is cleared before entering this
- * function, subpage dirty bit is not cleared.
- * So clear subpage dirty bit here so next time we won't submit
- * page for range already written to disk.
- */
- btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
submit_extent_page(bio_ctrl, disk_bytenr, page, iosize,
cur - page_offset(page));
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 81558f90ee80..10ac5f657e38 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -664,7 +664,7 @@ static noinline int merge_extent_mapping(struct btrfs_inode *inode,
start_diff = start - em->start;
em->start = start;
em->len = end - start;
- if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE && !extent_map_is_compressed(em))
+ if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
em->offset += start_diff;
return add_extent_mapping(inode, em, 0);
}
@@ -1147,8 +1147,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
return 0;
/*
- * We want to be fast because we can be called from any path trying to
- * allocate memory, so if the lock is busy we don't want to spend time
+ * We want to be fast so if the lock is busy we don't want to spend time
* waiting for it - either some task is about to do IO for the inode or
* we may have another task shrinking extent maps, here in this code, so
* skip this inode.
@@ -1191,9 +1190,7 @@ next:
/*
* Stop if we need to reschedule or there's contention on the
* lock. This is to avoid slowing other tasks trying to take the
- * lock and because the shrinker might be called during a memory
- * allocation path and we want to avoid taking a very long time
- * and slowing down all sorts of tasks.
+ * lock.
*/
if (need_resched() || rwlock_needbreak(&tree->lock))
break;
@@ -1222,12 +1219,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
if (ctx->scanned >= ctx->nr_to_scan)
break;
- /*
- * We may be called from memory allocation paths, so we don't
- * want to take too much time and slowdown tasks.
- */
- if (need_resched())
- break;
+ cond_resched();
inode = btrfs_find_first_inode(root, min_ino);
}
@@ -1285,14 +1277,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
ctx.last_ino);
}
- /*
- * We may be called from memory allocation paths, so we don't want to
- * take too much time and slowdown tasks, so stop if we need reschedule.
- */
- while (ctx.scanned < ctx.nr_to_scan && !need_resched()) {
+ while (ctx.scanned < ctx.nr_to_scan) {
struct btrfs_root *root;
unsigned long count;
+ cond_resched();
+
spin_lock(&fs_info->fs_roots_radix_lock);
count = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)&root,
diff --git a/fs/btrfs/fiemap.c b/fs/btrfs/fiemap.c
index 8f95f3e44e99..df7f09f3b02e 100644
--- a/fs/btrfs/fiemap.c
+++ b/fs/btrfs/fiemap.c
@@ -637,7 +637,7 @@ static int extent_fiemap(struct btrfs_inode *inode,
struct btrfs_path *path;
struct fiemap_cache cache = { 0 };
struct btrfs_backref_share_check_ctx *backref_ctx;
- u64 last_extent_end;
+ u64 last_extent_end = 0;
u64 prev_extent_end;
u64 range_start;
u64 range_end;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 21381de906f6..2aeb8116549c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1612,6 +1612,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
int ret = 0, err;
u64 len;
bool full_sync;
+ bool skip_ilock = false;
+
+ if (current->journal_info == BTRFS_TRANS_DIO_WRITE_STUB) {
+ skip_ilock = true;
+ current->journal_info = NULL;
+ lockdep_assert_held(&inode->vfs_inode.i_rwsem);
+ }
trace_btrfs_sync_file(file, datasync);
@@ -1639,7 +1646,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
goto out;
- btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ down_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
atomic_inc(&root->log_batch);
@@ -1663,7 +1673,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
ret = start_ordered_ops(inode, start, end);
if (ret) {
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
@@ -1788,7 +1801,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* file again, but that will end up using the synchronization
* inside btrfs_sync_log to keep things safe.
*/
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
if (ret == BTRFS_NO_LOG_SYNC) {
ret = btrfs_end_transaction(trans);
@@ -1857,7 +1873,10 @@ out:
out_release_extents:
btrfs_release_log_ctx_extents(&ctx);
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 3f9b7507543a..eaa1dbd31352 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2697,15 +2697,16 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
u64 offset = bytenr - block_group->start;
u64 to_free, to_unusable;
int bg_reclaim_threshold = 0;
- bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
+ bool initial;
u64 reclaimable_unusable;
- WARN_ON(!initial && offset + size > block_group->zone_capacity);
+ spin_lock(&block_group->lock);
+ initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
+ WARN_ON(!initial && offset + size > block_group->zone_capacity);
if (!initial)
bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);
- spin_lock(&ctl->tree_lock);
if (!used)
to_free = size;
else if (initial)
@@ -2718,18 +2719,19 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
to_free = offset + size - block_group->alloc_offset;
to_unusable = size - to_free;
+ spin_lock(&ctl->tree_lock);
ctl->free_space += to_free;
+ spin_unlock(&ctl->tree_lock);
/*
* If the block group is read-only, we should account freed space into
* bytes_readonly.
*/
- if (!block_group->ro)
+ if (!block_group->ro) {
block_group->zone_unusable += to_unusable;
- spin_unlock(&ctl->tree_lock);
+ WARN_ON(block_group->zone_unusable > block_group->length);
+ }
if (!used) {
- spin_lock(&block_group->lock);
block_group->alloc_offset -= size;
- spin_unlock(&block_group->lock);
}
reclaimable_unusable = block_group->zone_unusable -
@@ -2743,6 +2745,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
btrfs_mark_bg_to_reclaim(block_group);
}
+ spin_unlock(&block_group->lock);
+
return 0;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 01eab6955647..b1b6564ab68f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -714,8 +714,9 @@ out:
return ret;
}
-static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
- u64 end,
+static noinline int cow_file_range_inline(struct btrfs_inode *inode,
+ struct page *locked_page,
+ u64 offset, u64 end,
size_t compressed_size,
int compress_type,
struct folio *compressed_folio,
@@ -739,7 +740,10 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
return ret;
}
- extent_clear_unlock_delalloc(inode, offset, end, NULL, &cached,
+ if (ret == 0)
+ locked_page = NULL;
+
+ extent_clear_unlock_delalloc(inode, offset, end, locked_page, &cached,
clear_flags,
PAGE_UNLOCK | PAGE_START_WRITEBACK |
PAGE_END_WRITEBACK);
@@ -1043,10 +1047,10 @@ again:
* extent for the subpage case.
*/
if (total_in < actual_end)
- ret = cow_file_range_inline(inode, start, end, 0,
+ ret = cow_file_range_inline(inode, NULL, start, end, 0,
BTRFS_COMPRESS_NONE, NULL, false);
else
- ret = cow_file_range_inline(inode, start, end, total_compressed,
+ ret = cow_file_range_inline(inode, NULL, start, end, total_compressed,
compress_type, folios[0], false);
if (ret <= 0) {
if (ret < 0)
@@ -1359,7 +1363,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
if (!no_inline) {
/* lets try to make an inline extent */
- ret = cow_file_range_inline(inode, start, end, 0,
+ ret = cow_file_range_inline(inode, locked_page, start, end, 0,
BTRFS_COMPRESS_NONE, NULL, false);
if (ret <= 0) {
/*
@@ -1581,6 +1585,7 @@ out_unlock:
locked_page, &cached,
clear_bits,
page_ops);
+ btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
start += cur_alloc_size;
}
@@ -1594,6 +1599,7 @@ out_unlock:
clear_bits |= EXTENT_CLEAR_DATA_RESV;
extent_clear_unlock_delalloc(inode, start, end, locked_page,
&cached, clear_bits, page_ops);
+ btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
}
return ret;
}
@@ -2255,6 +2261,7 @@ error:
EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
PAGE_START_WRITEBACK |
PAGE_END_WRITEBACK);
+ btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL);
}
btrfs_free_path(path);
return ret;
@@ -4188,6 +4195,7 @@ err:
btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2);
inode_inc_iversion(&inode->vfs_inode);
+ inode_set_ctime_current(&inode->vfs_inode);
inode_inc_iversion(&dir->vfs_inode);
inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
ret = btrfs_update_inode(trans, dir);
@@ -5660,7 +5668,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
struct inode *inode;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *sub_root = root;
- struct btrfs_key location;
+ struct btrfs_key location = { 0 };
u8 di_type = 0;
int ret = 0;
@@ -7198,6 +7206,12 @@ static void wait_subpage_spinlock(struct page *page)
spin_unlock_irq(&subpage->lock);
}
+static int btrfs_launder_folio(struct folio *folio)
+{
+ return btrfs_qgroup_free_data(folio_to_inode(folio), NULL, folio_pos(folio),
+ PAGE_SIZE, NULL);
+}
+
static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
{
if (try_release_extent_mapping(&folio->page, gfp_flags)) {
@@ -10133,6 +10147,7 @@ static const struct address_space_operations btrfs_aops = {
.writepages = btrfs_writepages,
.readahead = btrfs_readahead,
.invalidate_folio = btrfs_invalidate_folio,
+ .launder_folio = btrfs_launder_folio,
.release_folio = btrfs_release_folio,
.migrate_folio = btrfs_migrate_folio,
.dirty_folio = filemap_dirty_folio,
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 32dcea662da3..fc821aa446f0 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -14,7 +14,7 @@
struct root_name_map {
u64 id;
- char name[16];
+ const char *name;
};
static const struct root_name_map root_map[] = {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5d57a285d59b..feb8f9f2f358 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -4185,6 +4185,8 @@ static int try_flush_qgroup(struct btrfs_root *root)
return 0;
}
+ btrfs_run_delayed_iputs(root->fs_info);
+ btrfs_wait_on_delayed_iputs(root->fs_info);
ret = btrfs_start_delalloc_snapshot(root, true);
if (ret < 0)
goto out;
@@ -4344,10 +4346,9 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
int ret;
if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
- extent_changeset_init(&changeset);
return clear_record_extent_bits(&inode->io_tree, start,
start + len - 1,
- EXTENT_QGROUP_RESERVED, &changeset);
+ EXTENT_QGROUP_RESERVED, NULL);
}
/* In release case, we shouldn't have @reserved */
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 14a8d7100018..0de9162ff481 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1648,14 +1648,20 @@ static void scrub_reset_stripe(struct scrub_stripe *stripe)
}
}
+static u32 stripe_length(const struct scrub_stripe *stripe)
+{
+ ASSERT(stripe->bg);
+
+ return min(BTRFS_STRIPE_LEN,
+ stripe->bg->start + stripe->bg->length - stripe->logical);
+}
+
static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
struct scrub_stripe *stripe)
{
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
struct btrfs_bio *bbio = NULL;
- unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
- stripe->bg->length - stripe->logical) >>
- fs_info->sectorsize_bits;
+ unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
u64 stripe_len = BTRFS_STRIPE_LEN;
int mirror = stripe->mirror_num;
int i;
@@ -1729,9 +1735,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct btrfs_bio *bbio;
- unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
- stripe->bg->length - stripe->logical) >>
- fs_info->sectorsize_bits;
+ unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
int mirror = stripe->mirror_num;
ASSERT(stripe->bg);
@@ -1871,6 +1875,9 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)
stripe = &sctx->stripes[i];
wait_scrub_stripe_io(stripe);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.last_physical = stripe->physical + stripe_length(stripe);
+ spin_unlock(&sctx->stat_lock);
scrub_reset_stripe(stripe);
}
out:
@@ -2139,7 +2146,9 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
cur_physical, &found_logical);
if (ret > 0) {
/* No more extent, just update the accounting */
+ spin_lock(&sctx->stat_lock);
sctx->stat.last_physical = physical + logical_length;
+ spin_unlock(&sctx->stat_lock);
ret = 0;
break;
}
@@ -2336,6 +2345,10 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
stripe_logical += chunk_logical;
ret = scrub_raid56_parity_stripe(sctx, scrub_dev, bg,
map, stripe_logical);
+ spin_lock(&sctx->stat_lock);
+ sctx->stat.last_physical = min(physical + BTRFS_STRIPE_LEN,
+ physical_end);
+ spin_unlock(&sctx->stat_lock);
if (ret)
goto out;
goto next;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4ca711a773ef..619fa0b8b3f6 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -347,7 +347,7 @@ struct name_cache_entry {
int ret;
int need_later_update;
int name_len;
- char name[];
+ char name[] __counted_by(name_len);
};
/* See the comment at lru_cache.h about struct btrfs_lru_cache_entry. */
@@ -6157,25 +6157,51 @@ static int send_write_or_clone(struct send_ctx *sctx,
u64 offset = key->offset;
u64 end;
u64 bs = sctx->send_root->fs_info->sectorsize;
+ struct btrfs_file_extent_item *ei;
+ u64 disk_byte;
+ u64 data_offset;
+ u64 num_bytes;
+ struct btrfs_inode_info info = { 0 };
end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size);
if (offset >= end)
return 0;
- if (clone_root && IS_ALIGNED(end, bs)) {
- struct btrfs_file_extent_item *ei;
- u64 disk_byte;
- u64 data_offset;
+ num_bytes = end - offset;
- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
- disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
- data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
- ret = clone_range(sctx, path, clone_root, disk_byte,
- data_offset, offset, end - offset);
- } else {
- ret = send_extent_data(sctx, path, offset, end - offset);
- }
+ if (!clone_root)
+ goto write_data;
+
+ if (IS_ALIGNED(end, bs))
+ goto clone_data;
+
+ /*
+ * If the extent end is not aligned, we can clone if the extent ends at
+ * the i_size of the inode and the clone range ends at the i_size of the
+ * source inode, otherwise the clone operation fails with -EINVAL.
+ */
+ if (end != sctx->cur_inode_size)
+ goto write_data;
+
+ ret = get_inode_info(clone_root->root, clone_root->ino, &info);
+ if (ret < 0)
+ return ret;
+
+ if (clone_root->offset + num_bytes == info.size)
+ goto clone_data;
+
+write_data:
+ ret = send_extent_data(sctx, path, offset, num_bytes);
+ sctx->cur_inode_next_write_offset = end;
+ return ret;
+
+clone_data:
+ ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
+ data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
+ ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset,
+ num_bytes);
sctx->cur_inode_next_write_offset = end;
return ret;
}
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 9ac94d3119e8..c691784b4660 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -316,7 +316,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
found->bytes_used += block_group->used;
found->disk_used += block_group->used * factor;
found->bytes_readonly += block_group->bytes_super;
- found->bytes_zone_unusable += block_group->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable);
if (block_group->length > 0)
found->full = 0;
btrfs_try_granting_tickets(info, found);
@@ -583,8 +583,7 @@ again:
spin_lock(&cache->lock);
avail = cache->length - cache->used - cache->pinned -
- cache->reserved - cache->delalloc_bytes -
- cache->bytes_super - cache->zone_unusable;
+ cache->reserved - cache->bytes_super - cache->zone_unusable;
btrfs_info(fs_info,
"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu delalloc %llu super %llu zone_unusable (%llu bytes available) %s",
cache->start, cache->length, cache->used, cache->pinned,
@@ -1986,8 +1985,8 @@ static bool is_reclaim_urgent(struct btrfs_space_info *space_info)
return unalloc < data_chunk_size;
}
-static int do_reclaim_sweep(struct btrfs_fs_info *fs_info,
- struct btrfs_space_info *space_info, int raid)
+static void do_reclaim_sweep(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info, int raid)
{
struct btrfs_block_group *bg;
int thresh_pct;
@@ -2032,7 +2031,6 @@ again:
}
up_read(&space_info->groups_sem);
- return 0;
}
void btrfs_space_info_update_reclaimable(struct btrfs_space_info *space_info, s64 bytes)
@@ -2075,21 +2073,15 @@ bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info)
return ret;
}
-int btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info)
+void btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info)
{
- int ret;
int raid;
struct btrfs_space_info *space_info;
list_for_each_entry(space_info, &fs_info->space_info, list) {
if (!btrfs_should_periodic_reclaim(space_info))
continue;
- for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) {
- ret = do_reclaim_sweep(fs_info, space_info, raid);
- if (ret)
- return ret;
- }
+ for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++)
+ do_reclaim_sweep(fs_info, space_info, raid);
}
-
- return ret;
}
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 4db8a0267c16..5602026c5e14 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -249,6 +249,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \
DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info");
DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned");
+DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable");
int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
@@ -293,6 +294,6 @@ void btrfs_space_info_update_reclaimable(struct btrfs_space_info *space_info, s6
void btrfs_set_periodic_reclaim_ready(struct btrfs_space_info *space_info, bool ready);
bool btrfs_should_periodic_reclaim(struct btrfs_space_info *space_info);
int btrfs_calc_reclaim_threshold(struct btrfs_space_info *space_info);
-int btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info);
+void btrfs_reclaim_sweep(struct btrfs_fs_info *fs_info);
#endif /* BTRFS_SPACE_INFO_H */
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 08d33cb372fb..98fa0f382480 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -28,6 +28,7 @@
#include <linux/btrfs.h>
#include <linux/security.h>
#include <linux/fs_parser.h>
+#include <linux/swap.h>
#include "messages.h"
#include "delayed-inode.h"
#include "ctree.h"
@@ -683,8 +684,11 @@ bool btrfs_check_options(const struct btrfs_fs_info *info,
ret = false;
if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) {
- if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE))
+ if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) {
btrfs_info(info, "disk space caching is enabled");
+ btrfs_warn(info,
+"space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2");
+ }
if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE))
btrfs_info(info, "using free-space-tree");
}
@@ -2398,7 +2402,13 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro
trace_btrfs_extent_map_shrinker_count(fs_info, nr);
- return nr;
+ /*
+ * Only report the real number for DEBUG builds, as there are reports of
+ * serious performance degradation caused by too frequent shrinks.
+ */
+ if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
+ return nr;
+ return 0;
}
static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc)
@@ -2406,6 +2416,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan);
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+ /*
+ * We may be called from any task trying to allocate memory and we don't
+ * want to slow it down with scanning and dropping extent maps. It would
+ * also cause heavy lock contention if many tasks concurrently enter
+ * here. Therefore only allow kswapd tasks to scan and drop extent maps.
+ */
+ if (!current_is_kswapd())
+ return 0;
+
return btrfs_free_extent_maps(fs_info, nr_to_scan);
}
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index ebec4ab361b8..56e61ac1cc64 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -900,6 +900,102 @@ out:
return ret;
}
+/*
+ * Test a regression for compressed extent map adjustment when we attempt to
+ * add an extent map that is partially overlapped by another existing extent
+ * map. The resulting extent map offset was left unchanged despite having
+ * incremented its start offset.
+ */
+static int test_case_8(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
+{
+ struct extent_map_tree *em_tree = &inode->extent_tree;
+ struct extent_map *em;
+ int ret;
+ int ret2;
+
+ em = alloc_extent_map();
+ if (!em) {
+ test_std_err(TEST_ALLOC_EXTENT_MAP);
+ return -ENOMEM;
+ }
+
+ /* Compressed extent for the file range [120K, 128K). */
+ em->start = SZ_1K * 120;
+ em->len = SZ_8K;
+ em->disk_num_bytes = SZ_4K;
+ em->ram_bytes = SZ_8K;
+ em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+ write_lock(&em_tree->lock);
+ ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
+ write_unlock(&em_tree->lock);
+ free_extent_map(em);
+ if (ret < 0) {
+ test_err("couldn't add extent map for range [120K, 128K)");
+ goto out;
+ }
+
+ em = alloc_extent_map();
+ if (!em) {
+ test_std_err(TEST_ALLOC_EXTENT_MAP);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * Compressed extent for the file range [108K, 144K), which overlaps
+ * with the [120K, 128K) we previously inserted.
+ */
+ em->start = SZ_1K * 108;
+ em->len = SZ_1K * 36;
+ em->disk_num_bytes = SZ_4K;
+ em->ram_bytes = SZ_1K * 36;
+ em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+
+ /*
+ * Try to add the extent map but with a search range of [140K, 144K),
+ * this should succeed and adjust the extent map to the range
+ * [128K, 144K), with a length of 16K and an offset of 20K.
+ *
+ * This simulates a scenario where in the subvolume tree of an inode we
+ * have a compressed file extent item for the range [108K, 144K) and we
+ * have an overlapping compressed extent map for the range [120K, 128K),
+ * which was created by an encoded write, but its ordered extent was not
+ * yet completed, so the subvolume tree doesn't have yet the file extent
+ * item for that range - we only have the extent map in the inode's
+ * extent map tree.
+ */
+ write_lock(&em_tree->lock);
+ ret = btrfs_add_extent_mapping(inode, &em, SZ_1K * 140, SZ_4K);
+ write_unlock(&em_tree->lock);
+ free_extent_map(em);
+ if (ret < 0) {
+ test_err("couldn't add extent map for range [108K, 144K)");
+ goto out;
+ }
+
+ if (em->start != SZ_128K) {
+ test_err("unexpected extent map start %llu (should be 128K)", em->start);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->len != SZ_16K) {
+ test_err("unexpected extent map length %llu (should be 16K)", em->len);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->offset != SZ_1K * 20) {
+ test_err("unexpected extent map offset %llu (should be 20K)", em->offset);
+ ret = -EINVAL;
+ goto out;
+ }
+out:
+ ret2 = free_extent_map_tree(inode);
+ if (ret == 0)
+ ret = ret2;
+
+ return ret;
+}
+
struct rmap_test_vector {
u64 raid_type;
u64 physical_start;
@@ -1078,6 +1174,9 @@ int btrfs_test_extent_map(void)
ret = test_case_7(fs_info, BTRFS_I(inode));
if (ret)
goto out;
+ ret = test_case_8(fs_info, BTRFS_I(inode));
+ if (ret)
+ goto out;
test_msg("running rmap tests");
for (i = 0; i < ARRAY_SIZE(rmap_tests); i++) {
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 98c03ddc760b..dd9ce9b9f69e 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -27,6 +27,12 @@ struct btrfs_root_item;
struct btrfs_root;
struct btrfs_path;
+/*
+ * Signal that a direct IO write is in progress, to avoid deadlock for sync
+ * direct IO writes when fsync is called during the direct IO write path.
+ */
+#define BTRFS_TRANS_DIO_WRITE_STUB ((void *) 1)
+
/* Radix-tree tag for roots that are part of the trasaction. */
#define BTRFS_ROOT_TRANS_TAG 0
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 6388786fd8b5..634d69964fe4 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -569,9 +569,10 @@ static int check_dir_item(struct extent_buffer *leaf,
/* dir type check */
dir_type = btrfs_dir_ftype(leaf, di);
- if (unlikely(dir_type >= BTRFS_FT_MAX)) {
+ if (unlikely(dir_type <= BTRFS_FT_UNKNOWN ||
+ dir_type >= BTRFS_FT_MAX)) {
dir_item_err(leaf, slot,
- "invalid dir item type, have %u expect [0, %u)",
+ "invalid dir item type, have %u expect (0, %u)",
dir_type, BTRFS_FT_MAX);
return -EUCLEAN;
}
@@ -634,7 +635,7 @@ static int check_dir_item(struct extent_buffer *leaf,
*/
if (key->type == BTRFS_DIR_ITEM_KEY ||
key->type == BTRFS_XATTR_ITEM_KEY) {
- char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+ char namebuf[MAX(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
read_extent_buffer(leaf, namebuf,
(unsigned long)(di + 1), name_len);
@@ -1289,6 +1290,19 @@ static void extent_err(const struct extent_buffer *eb, int slot,
va_end(args);
}
+static bool is_valid_dref_root(u64 rootid)
+{
+ /*
+ * The following tree root objectids are allowed to have a data backref:
+ * - subvolume trees
+ * - data reloc tree
+ * - tree root
+ * For v1 space cache
+ */
+ return is_fstree(rootid) || rootid == BTRFS_DATA_RELOC_TREE_OBJECTID ||
+ rootid == BTRFS_ROOT_TREE_OBJECTID;
+}
+
static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
@@ -1441,6 +1455,8 @@ static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_extent_data_ref *dref;
struct btrfs_shared_data_ref *sref;
u64 seq;
+ u64 dref_root;
+ u64 dref_objectid;
u64 dref_offset;
u64 inline_offset;
u8 inline_type;
@@ -1484,11 +1500,26 @@ static int check_extent_item(struct extent_buffer *leaf,
*/
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ dref_root = btrfs_extent_data_ref_root(leaf, dref);
+ dref_objectid = btrfs_extent_data_ref_objectid(leaf, dref);
dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
seq = hash_extent_data_ref(
btrfs_extent_data_ref_root(leaf, dref),
btrfs_extent_data_ref_objectid(leaf, dref),
btrfs_extent_data_ref_offset(leaf, dref));
+ if (unlikely(!is_valid_dref_root(dref_root))) {
+ extent_err(leaf, slot,
+ "invalid data ref root value %llu",
+ dref_root);
+ return -EUCLEAN;
+ }
+ if (unlikely(dref_objectid < BTRFS_FIRST_FREE_OBJECTID ||
+ dref_objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid data ref objectid value %llu",
+ dref_root);
+ return -EUCLEAN;
+ }
if (unlikely(!IS_ALIGNED(dref_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
@@ -1627,6 +1658,8 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
return -EUCLEAN;
}
for (; ptr < end; ptr += sizeof(*dref)) {
+ u64 root;
+ u64 objectid;
u64 offset;
/*
@@ -1634,7 +1667,22 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
* overflow from the leaf due to hash collisions.
*/
dref = (struct btrfs_extent_data_ref *)ptr;
+ root = btrfs_extent_data_ref_root(leaf, dref);
+ objectid = btrfs_extent_data_ref_objectid(leaf, dref);
offset = btrfs_extent_data_ref_offset(leaf, dref);
+ if (unlikely(!is_valid_dref_root(root))) {
+ extent_err(leaf, slot,
+ "invalid extent data backref root value %llu",
+ root);
+ return -EUCLEAN;
+ }
+ if (unlikely(objectid < BTRFS_FIRST_FREE_OBJECTID ||
+ objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid extent data backref objectid value %llu",
+ root);
+ return -EUCLEAN;
+ }
if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid extent data backref offset, have %llu expect aligned to %u",
@@ -1716,6 +1764,72 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf,
return 0;
}
+static int check_dev_extent_item(const struct extent_buffer *leaf,
+ const struct btrfs_key *key,
+ int slot,
+ struct btrfs_key *prev_key)
+{
+ struct btrfs_dev_extent *de;
+ const u32 sectorsize = leaf->fs_info->sectorsize;
+
+ de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+ /* Basic fixed member checks. */
+ if (unlikely(btrfs_dev_extent_chunk_tree(leaf, de) !=
+ BTRFS_CHUNK_TREE_OBJECTID)) {
+ generic_err(leaf, slot,
+ "invalid dev extent chunk tree id, has %llu expect %llu",
+ btrfs_dev_extent_chunk_tree(leaf, de),
+ BTRFS_CHUNK_TREE_OBJECTID);
+ return -EUCLEAN;
+ }
+ if (unlikely(btrfs_dev_extent_chunk_objectid(leaf, de) !=
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID)) {
+ generic_err(leaf, slot,
+ "invalid dev extent chunk objectid, has %llu expect %llu",
+ btrfs_dev_extent_chunk_objectid(leaf, de),
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+ return -EUCLEAN;
+ }
+ /* Alignment check. */
+ if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
+ generic_err(leaf, slot,
+ "invalid dev extent key.offset, has %llu not aligned to %u",
+ key->offset, sectorsize);
+ return -EUCLEAN;
+ }
+ if (unlikely(!IS_ALIGNED(btrfs_dev_extent_chunk_offset(leaf, de),
+ sectorsize))) {
+ generic_err(leaf, slot,
+ "invalid dev extent chunk offset, has %llu not aligned to %u",
+ btrfs_dev_extent_chunk_objectid(leaf, de),
+ sectorsize);
+ return -EUCLEAN;
+ }
+ if (unlikely(!IS_ALIGNED(btrfs_dev_extent_length(leaf, de),
+ sectorsize))) {
+ generic_err(leaf, slot,
+ "invalid dev extent length, has %llu not aligned to %u",
+ btrfs_dev_extent_length(leaf, de), sectorsize);
+ return -EUCLEAN;
+ }
+ /* Overlap check with previous dev extent. */
+ if (slot && prev_key->objectid == key->objectid &&
+ prev_key->type == key->type) {
+ struct btrfs_dev_extent *prev_de;
+ u64 prev_len;
+
+ prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent);
+ prev_len = btrfs_dev_extent_length(leaf, prev_de);
+ if (unlikely(prev_key->offset + prev_len > key->offset)) {
+ generic_err(leaf, slot,
+ "dev extent overlap, prev offset %llu len %llu current offset %llu",
+ prev_key->objectid, prev_len, key->offset);
+ return -EUCLEAN;
+ }
+ }
+ return 0;
+}
+
/*
* Common point to switch the item-specific validation.
*/
@@ -1752,6 +1866,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf,
case BTRFS_DEV_ITEM_KEY:
ret = check_dev_item(leaf, key, slot);
break;
+ case BTRFS_DEV_EXTENT_KEY:
+ ret = check_dev_extent_item(leaf, key, slot, prev_key);
+ break;
case BTRFS_INODE_ITEM_KEY:
ret = check_inode_item(leaf, key, slot);
break;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 66f63e82af79..047e3337852e 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1406,6 +1406,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
return -EINVAL;
}
+ bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity);
+
if (zone_info[0].alloc_offset == WP_MISSING_DEV) {
btrfs_err(bg->fs_info,
"zoned: cannot recover write pointer for zone %llu",
@@ -1432,7 +1434,6 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
}
bg->alloc_offset = zone_info[0].alloc_offset;
- bg->zone_capacity = min(zone_info[0].capacity, zone_info[1].capacity);
return 0;
}
@@ -1450,6 +1451,9 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
return -EINVAL;
}
+ /* In case a device is missing we have a cap of 0, so don't use it. */
+ bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity);
+
for (i = 0; i < map->num_stripes; i++) {
if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
zone_info[i].alloc_offset == WP_CONVENTIONAL)
@@ -1471,9 +1475,6 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
if (test_bit(0, active))
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
}
- /* In case a device is missing we have a cap of 0, so don't use it. */
- bg->zone_capacity = min_not_zero(zone_info[0].capacity,
- zone_info[1].capacity);
}
if (zone_info[0].alloc_offset != WP_MISSING_DEV)
@@ -1563,6 +1564,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
unsigned long *active = NULL;
u64 last_alloc = 0;
u32 num_sequential = 0, num_conventional = 0;
+ u64 profile;
if (!btrfs_is_zoned(fs_info))
return 0;
@@ -1623,7 +1625,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
}
}
- switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK;
+ switch (profile) {
case 0: /* single */
ret = btrfs_load_block_group_single(cache, &zone_info[0], active);
break;
@@ -1650,6 +1653,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
goto out;
}
+ if (ret == -EIO && profile != 0 && profile != BTRFS_BLOCK_GROUP_RAID0 &&
+ profile != BTRFS_BLOCK_GROUP_RAID10) {
+ /*
+ * Detected broken write pointer. Make this block group
+ * unallocatable by setting the allocation pointer at the end of
+ * allocatable region. Relocating this block group will fix the
+ * mismatch.
+ *
+ * Currently, we cannot handle RAID0 or RAID10 case like this
+ * because we don't have a proper zone_capacity value. But,
+ * reading from this block group won't work anyway by a missing
+ * stripe.
+ */
+ cache->alloc_offset = cache->zone_capacity;
+ ret = 0;
+ }
+
out:
/* Reject non SINGLE data profiles without RST */
if ((map->type & BTRFS_BLOCK_GROUP_DATA) &&
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-29 19:15:15 +0300