summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/Makefile10
-rw-r--r--fs/btrfs/block-group.c33
-rw-r--r--fs/btrfs/block-group.h9
-rw-r--r--fs/btrfs/compression.c68
-rw-r--r--fs/btrfs/ctree.c2
-rw-r--r--fs/btrfs/ctree.h5
-rw-r--r--fs/btrfs/delayed-inode.c5
-rw-r--r--fs/btrfs/dev-replace.c3
-rw-r--r--fs/btrfs/disk-io.c19
-rw-r--r--fs/btrfs/extent-tree.c23
-rw-r--r--fs/btrfs/extent_io.c54
-rw-r--r--fs/btrfs/file.c5
-rw-r--r--fs/btrfs/free-space-cache.c21
-rw-r--r--fs/btrfs/inode.c101
-rw-r--r--fs/btrfs/ioctl.c19
-rw-r--r--fs/btrfs/lzo.c4
-rw-r--r--fs/btrfs/qgroup.c20
-rw-r--r--fs/btrfs/qgroup.h2
-rw-r--r--fs/btrfs/raid56.c31
-rw-r--r--fs/btrfs/reada.c35
-rw-r--r--fs/btrfs/ref-verify.c4
-rw-r--r--fs/btrfs/reflink.c24
-rw-r--r--fs/btrfs/scrub.c11
-rw-r--r--fs/btrfs/send.c7
-rw-r--r--fs/btrfs/super.c4
-rw-r--r--fs/btrfs/tree-checker.c16
-rw-r--r--fs/btrfs/tree-log.c11
-rw-r--r--fs/btrfs/volumes.c3
-rw-r--r--fs/btrfs/xattr.c31
-rw-r--r--fs/btrfs/zlib.c5
-rw-r--r--fs/btrfs/zoned.c4
-rw-r--r--fs/btrfs/zstd.c6
32 files changed, 426 insertions, 169 deletions
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index b634c42115ea..b4fb997eda16 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute
subdir-ccflags-y += -Wmissing-prototypes
subdir-ccflags-y += -Wold-style-definition
subdir-ccflags-y += -Wmissing-include-dirs
-subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
-subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
-subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
-subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+condflags := \
+ $(call cc-option, -Wunused-but-set-variable) \
+ $(call cc-option, -Wunused-const-variable) \
+ $(call cc-option, -Wpacked-not-aligned) \
+ $(call cc-option, -Wstringop-truncation)
+subdir-ccflags-y += $(condflags)
# The following turn off the warnings enabled by -Wextra
subdir-ccflags-y += -Wno-missing-field-initializers
subdir-ccflags-y += -Wno-sign-compare
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5064be59dac5..744b99ddc28c 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1162,6 +1162,11 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
spin_lock(&sinfo->lock);
spin_lock(&cache->lock);
+ if (cache->swap_extents) {
+ ret = -ETXTBSY;
+ goto out;
+ }
+
if (cache->ro) {
cache->ro++;
ret = 0;
@@ -2307,7 +2312,7 @@ again:
}
ret = inc_block_group_ro(cache, 0);
- if (!do_chunk_alloc)
+ if (!do_chunk_alloc || ret == -ETXTBSY)
goto unlock_out;
if (!ret)
goto out;
@@ -2316,6 +2321,8 @@ again:
if (ret < 0)
goto out;
ret = inc_block_group_ro(cache, 0);
+ if (ret == -ETXTBSY)
+ goto unlock_out;
out:
if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
alloc_flags = btrfs_get_alloc_profile(fs_info, cache->flags);
@@ -3406,6 +3413,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
ASSERT(list_empty(&block_group->io_list));
ASSERT(list_empty(&block_group->bg_list));
ASSERT(refcount_read(&block_group->refs) == 1);
+ ASSERT(block_group->swap_extents == 0);
btrfs_put_block_group(block_group);
spin_lock(&info->block_group_cache_lock);
@@ -3472,3 +3480,26 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
__btrfs_remove_free_space_cache(block_group->free_space_ctl);
}
}
+
+bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg)
+{
+ bool ret = true;
+
+ spin_lock(&bg->lock);
+ if (bg->ro)
+ ret = false;
+ else
+ bg->swap_extents++;
+ spin_unlock(&bg->lock);
+
+ return ret;
+}
+
+void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount)
+{
+ spin_lock(&bg->lock);
+ ASSERT(!bg->ro);
+ ASSERT(bg->swap_extents >= amount);
+ bg->swap_extents -= amount;
+ spin_unlock(&bg->lock);
+}
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 29678426247d..3ecc3372a5ce 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -186,6 +186,12 @@ struct btrfs_block_group {
/* Flag indicating this block group is placed on a sequential zone */
bool seq_zone;
+ /*
+ * Number of extents in this block group used for swap files.
+ * All accesses protected by the spinlock 'lock'.
+ */
+ int swap_extents;
+
/* Record locked full stripes for RAID5/6 block group */
struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
@@ -312,4 +318,7 @@ static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
void btrfs_freeze_block_group(struct btrfs_block_group *cache);
void btrfs_unfreeze_block_group(struct btrfs_block_group *cache);
+bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg);
+void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount);
+
#endif /* BTRFS_BLOCK_GROUP_H */
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 6d203acfdeb3..3f4c832abfed 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -141,6 +141,7 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
struct btrfs_fs_info *fs_info = inode->root->fs_info;
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
const u32 csum_size = fs_info->csum_size;
+ const u32 sectorsize = fs_info->sectorsize;
struct page *page;
unsigned long i;
char *kaddr;
@@ -154,22 +155,34 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
shash->tfm = fs_info->csum_shash;
for (i = 0; i < cb->nr_pages; i++) {
+ u32 pg_offset;
+ u32 bytes_left = PAGE_SIZE;
page = cb->compressed_pages[i];
- kaddr = kmap_atomic(page);
- crypto_shash_digest(shash, kaddr, PAGE_SIZE, csum);
- kunmap_atomic(kaddr);
-
- if (memcmp(&csum, cb_sum, csum_size)) {
- btrfs_print_data_csum_error(inode, disk_start,
- csum, cb_sum, cb->mirror_num);
- if (btrfs_io_bio(bio)->device)
- btrfs_dev_stat_inc_and_print(
- btrfs_io_bio(bio)->device,
- BTRFS_DEV_STAT_CORRUPTION_ERRS);
- return -EIO;
+ /* Determine the remaining bytes inside the page first */
+ if (i == cb->nr_pages - 1)
+ bytes_left = cb->compressed_len - i * PAGE_SIZE;
+
+ /* Hash through the page sector by sector */
+ for (pg_offset = 0; pg_offset < bytes_left;
+ pg_offset += sectorsize) {
+ kaddr = kmap_atomic(page);
+ crypto_shash_digest(shash, kaddr + pg_offset,
+ sectorsize, csum);
+ kunmap_atomic(kaddr);
+
+ if (memcmp(&csum, cb_sum, csum_size) != 0) {
+ btrfs_print_data_csum_error(inode, disk_start,
+ csum, cb_sum, cb->mirror_num);
+ if (btrfs_io_bio(bio)->device)
+ btrfs_dev_stat_inc_and_print(
+ btrfs_io_bio(bio)->device,
+ BTRFS_DEV_STAT_CORRUPTION_ERRS);
+ return -EIO;
+ }
+ cb_sum += csum_size;
+ disk_start += sectorsize;
}
- cb_sum += csum_size;
}
return 0;
}
@@ -640,7 +653,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree,
page_offset(bio_first_page_all(bio)),
- PAGE_SIZE);
+ fs_info->sectorsize);
read_unlock(&em_tree->lock);
if (!em)
return BLK_STS_IOERR;
@@ -698,19 +711,30 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
refcount_set(&cb->pending_bios, 1);
for (pg_index = 0; pg_index < nr_pages; pg_index++) {
+ u32 pg_len = PAGE_SIZE;
int submit = 0;
+ /*
+ * To handle subpage case, we need to make sure the bio only
+ * covers the range we need.
+ *
+ * If we're at the last page, truncate the length to only cover
+ * the remaining part.
+ */
+ if (pg_index == nr_pages - 1)
+ pg_len = min_t(u32, PAGE_SIZE,
+ compressed_len - pg_index * PAGE_SIZE);
+
page = cb->compressed_pages[pg_index];
page->mapping = inode->i_mapping;
page->index = em_start >> PAGE_SHIFT;
if (comp_bio->bi_iter.bi_size)
- submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE,
+ submit = btrfs_bio_fits_in_stripe(page, pg_len,
comp_bio, 0);
page->mapping = NULL;
- if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
- PAGE_SIZE) {
+ if (submit || bio_add_page(comp_bio, page, pg_len, 0) < pg_len) {
unsigned int nr_sectors;
ret = btrfs_bio_wq_end_io(fs_info, comp_bio,
@@ -743,9 +767,9 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
- bio_add_page(comp_bio, page, PAGE_SIZE, 0);
+ bio_add_page(comp_bio, page, pg_len, 0);
}
- cur_disk_byte += PAGE_SIZE;
+ cur_disk_byte += pg_len;
}
ret = btrfs_bio_wq_end_io(fs_info, comp_bio, BTRFS_WQ_ENDIO_DATA);
@@ -1237,7 +1261,6 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
unsigned long prev_start_byte;
unsigned long working_bytes = total_out - buf_start;
unsigned long bytes;
- char *kaddr;
struct bio_vec bvec = bio_iter_iovec(bio, bio->bi_iter);
/*
@@ -1268,9 +1291,8 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
PAGE_SIZE - (buf_offset % PAGE_SIZE));
bytes = min(bytes, working_bytes);
- kaddr = kmap_atomic(bvec.bv_page);
- memcpy(kaddr + bvec.bv_offset, buf + buf_offset, bytes);
- kunmap_atomic(kaddr);
+ memcpy_to_page(bvec.bv_page, bvec.bv_offset, buf + buf_offset,
+ bytes);
flush_dcache_page(bvec.bv_page);
buf_offset += bytes;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index d56730a67885..34b929bd5c1a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1365,7 +1365,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
"failed to read tree block %llu from get_old_root",
logical);
} else {
+ btrfs_tree_read_lock(old);
eb = btrfs_clone_extent_buffer(old);
+ btrfs_tree_read_unlock(old);
free_extent_buffer(old);
}
} else if (old_root) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index bd659354d043..9ae776ab3967 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -524,6 +524,11 @@ struct btrfs_swapfile_pin {
* points to a struct btrfs_device.
*/
bool is_block_group;
+ /*
+ * Only used when 'is_block_group' is true and it is the number of
+ * extents used by a swapfile for this block group ('ptr' field).
+ */
+ int bg_extent_count;
};
bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index ec0b50b8c5d6..bf25401c9768 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -627,7 +627,8 @@ static int btrfs_delayed_inode_reserve_metadata(
*/
if (!src_rsv || (!trans->bytes_reserved &&
src_rsv->type != BTRFS_BLOCK_RSV_DELALLOC)) {
- ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true);
+ ret = btrfs_qgroup_reserve_meta(root, num_bytes,
+ BTRFS_QGROUP_RSV_META_PREALLOC, true);
if (ret < 0)
return ret;
ret = btrfs_block_rsv_add(root, dst_rsv, num_bytes,
@@ -649,7 +650,7 @@ static int btrfs_delayed_inode_reserve_metadata(
btrfs_ino(inode),
num_bytes, 1);
} else {
- btrfs_qgroup_free_meta_prealloc(root, fs_info->nodesize);
+ btrfs_qgroup_free_meta_prealloc(root, num_bytes);
}
return ret;
}
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 3a9c1e046ebe..d05f73530af7 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
struct btrfs_dev_replace_item *ptr;
u64 src_devid;
+ if (!dev_root)
+ return 0;
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 41b718cfea40..289f1f09481d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2387,8 +2387,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->dev_root = root;
- btrfs_init_devices_late(fs_info);
}
+ /* Initialize fs_info for all devices in any case */
+ btrfs_init_devices_late(fs_info);
/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
@@ -3009,6 +3010,21 @@ 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_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
+ * or crash before the deletion completes, on the next mount we will not
+ * delete what remains of the tree because the orphan item does not
+ * exists anymore, which is what tells us we have a pending deletion.
+ */
+ ret = btrfs_find_orphan_roots(fs_info);
+ if (ret)
+ goto out;
+
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto out;
@@ -3068,7 +3084,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
}
}
- ret = btrfs_find_orphan_roots(fs_info);
out:
return ret;
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 78ad31a59e59..36a3c973fda1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3323,6 +3323,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
if (last_ref && btrfs_header_generation(buf) == trans->transid) {
struct btrfs_block_group *cache;
+ bool must_pin = false;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
@@ -3340,7 +3341,27 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
goto out;
}
- if (btrfs_is_zoned(fs_info)) {
+ /*
+ * If this is a leaf and there are tree mod log users, we may
+ * have recorded mod log operations that point to this leaf.
+ * So we must make sure no one reuses this leaf's extent before
+ * mod log operations are applied to a node, otherwise after
+ * rewinding a node using the mod log operations we get an
+ * inconsistent btree, as the leaf's extent may now be used as
+ * a node or leaf for another different btree.
+ * We are safe from races here because at this point no other
+ * node or root points to this extent buffer, so if after this
+ * check a new tree mod log user joins, it will not be able to
+ * find a node pointing to this leaf and record operations that
+ * point to this leaf.
+ */
+ if (btrfs_header_level(buf) == 0) {
+ read_lock(&fs_info->tree_mod_log_lock);
+ must_pin = !list_empty(&fs_info->tree_mod_seq_list);
+ read_unlock(&fs_info->tree_mod_log_lock);
+ }
+
+ if (must_pin || btrfs_is_zoned(fs_info)) {
btrfs_redirty_list_add(trans->transaction, buf);
pin_down_extent(trans, cache, buf->start, buf->len, 1);
btrfs_put_block_group(cache);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4dfb3ead1175..910769d5fcdb 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2886,6 +2886,35 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len)
}
/*
+ * 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.
+ */
+static struct extent_buffer *find_extent_buffer_readpage(
+ struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
+{
+ struct extent_buffer *eb;
+
+ /*
+ * For regular sectorsize, we can use page->private to grab extent
+ * buffer
+ */
+ if (fs_info->sectorsize == PAGE_SIZE) {
+ ASSERT(PagePrivate(page) && page->private);
+ return (struct extent_buffer *)page->private;
+ }
+
+ /* 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;
+}
+
+/*
* after a readpage IO is done, we need to:
* clear the uptodate bits on error
* set the uptodate bits if things worked
@@ -2996,7 +3025,7 @@ static void end_bio_extent_readpage(struct bio *bio)
} else {
struct extent_buffer *eb;
- eb = (struct extent_buffer *)page->private;
+ eb = find_extent_buffer_readpage(fs_info, page, start);
set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = mirror;
atomic_dec(&eb->io_pages);
@@ -3008,12 +3037,23 @@ readpage_ok:
if (likely(uptodate)) {
loff_t i_size = i_size_read(inode);
pgoff_t end_index = i_size >> PAGE_SHIFT;
- unsigned off;
- /* Zero out the end if this page straddles i_size */
- off = offset_in_page(i_size);
- if (page->index == end_index && off)
- zero_user_segment(page, off, PAGE_SIZE);
+ /*
+ * Zero out the remaining part if this range straddles
+ * i_size.
+ *
+ * Here we should only zero the range inside the bvec,
+ * not touch anything else.
+ *
+ * NOTE: i_size is exclusive while end is inclusive.
+ */
+ if (page->index == end_index && i_size <= end) {
+ u32 zero_start = max(offset_in_page(i_size),
+ offset_in_page(start));
+
+ zero_user_segment(page, zero_start,
+ offset_in_page(end) + 1);
+ }
}
ASSERT(bio_offset + len > bio_offset);
bio_offset += len;
@@ -3048,7 +3088,7 @@ struct bio *btrfs_bio_alloc(u64 first_byte)
{
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &btrfs_bioset);
bio->bi_iter.bi_sector = first_byte >> 9;
btrfs_io_bio_init(btrfs_io_bio(bio));
return bio;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index bf2c51a9607a..0e155f013839 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3260,8 +3260,11 @@ reserve_space:
goto out;
ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), &data_reserved,
alloc_start, bytes_to_reserve);
- if (ret)
+ if (ret) {
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
+ lockend, &cached_state);
goto out;
+ }
ret = btrfs_prealloc_file_range(inode, mode, alloc_start,
alloc_end - alloc_start,
i_blocksize(inode),
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 5400294bd271..9988decd5717 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2555,7 +2555,12 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
to_unusable = size - to_free;
ctl->free_space += to_free;
- block_group->zone_unusable += to_unusable;
+ /*
+ * If the block group is read-only, we should account freed space into
+ * bytes_readonly.
+ */
+ if (!block_group->ro)
+ block_group->zone_unusable += to_unusable;
spin_unlock(&ctl->tree_lock);
if (!used) {
spin_lock(&block_group->lock);
@@ -2801,8 +2806,10 @@ static void __btrfs_return_cluster_to_free_space(
struct rb_node *node;
spin_lock(&cluster->lock);
- if (cluster->block_group != block_group)
- goto out;
+ if (cluster->block_group != block_group) {
+ spin_unlock(&cluster->lock);
+ return;
+ }
cluster->block_group = NULL;
cluster->window_start = 0;
@@ -2840,8 +2847,6 @@ static void __btrfs_return_cluster_to_free_space(
entry->offset, &entry->offset_index, bitmap);
}
cluster->root = RB_ROOT;
-
-out:
spin_unlock(&cluster->lock);
btrfs_put_block_group(block_group);
}
@@ -3125,8 +3130,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
entry->bytes -= bytes;
}
- if (entry->bytes == 0)
- rb_erase(&entry->offset_index, &cluster->root);
break;
}
out:
@@ -3143,7 +3146,10 @@ out:
ctl->free_space -= bytes;
if (!entry->bitmap && !btrfs_free_space_trimmed(entry))
ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes;
+
+ spin_lock(&cluster->lock);
if (entry->bytes == 0) {
+ rb_erase(&entry->offset_index, &cluster->root);
ctl->free_extents--;
if (entry->bitmap) {
kmem_cache_free(btrfs_free_space_bitmap_cachep,
@@ -3156,6 +3162,7 @@ out:
kmem_cache_free(btrfs_free_space_cachep, entry);
}
+ spin_unlock(&cluster->lock);
spin_unlock(&ctl->tree_lock);
return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2e1c282c202d..a520775949a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1674,9 +1674,6 @@ next_slot:
*/
btrfs_release_path(path);
- /* If extent is RO, we must COW it */
- if (btrfs_extent_readonly(fs_info, disk_bytenr))
- goto out_check;
ret = btrfs_cross_ref_exist(root, ino,
found_key.offset -
extent_offset, disk_bytenr, false);
@@ -1723,6 +1720,7 @@ next_slot:
WARN_ON_ONCE(freespace_inode);
goto out_check;
}
+ /* If the extent's block group is RO, we must COW */
if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
goto out_check;
nocow = true;
@@ -3101,11 +3099,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
* @bio_offset: offset to the beginning of the bio (in bytes)
* @page: page where is the data to be verified
* @pgoff: offset inside the page
+ * @start: logical offset in the file
*
* The length of such check is always one sector size.
*/
static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
- u32 bio_offset, struct page *page, u32 pgoff)
+ u32 bio_offset, struct page *page, u32 pgoff,
+ u64 start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -3132,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
kunmap_atomic(kaddr);
return 0;
zeroit:
- btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
- csum, csum_expected, io_bio->mirror_num);
+ btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+ io_bio->mirror_num);
if (io_bio->device)
btrfs_dev_stat_inc_and_print(io_bio->device,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3186,7 +3186,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
pg_off += sectorsize, bio_offset += sectorsize) {
int ret;
- ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+ ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+ page_offset(page) + pg_off);
if (ret < 0)
return -EIO;
}
@@ -6085,7 +6086,7 @@ static int btrfs_dirty_inode(struct inode *inode)
return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
- if (ret && ret == -ENOSPC) {
+ if (ret && (ret == -ENOSPC || ret == -EDQUOT)) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans);
trans = btrfs_start_transaction(root, 1);
@@ -7912,7 +7913,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
ASSERT(pgoff < PAGE_SIZE);
if (uptodate &&
(!csum || !check_data_csum(inode, io_bio,
- bio_offset, bvec.bv_page, pgoff))) {
+ bio_offset, bvec.bv_page,
+ pgoff, start))) {
clean_io_failure(fs_info, failure_tree, io_tree,
start, bvec.bv_page,
btrfs_ino(BTRFS_I(inode)),
@@ -8171,10 +8173,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
- WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
- fs_info->max_zone_append_size &&
- bio_op(bio) != REQ_OP_ZONE_APPEND);
-
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
status = extract_ordered_extent(BTRFS_I(inode), bio,
file_offset);
@@ -9010,7 +9008,7 @@ int __init btrfs_init_cachep(void)
btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
PAGE_SIZE, PAGE_SIZE,
- SLAB_RED_ZONE, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!btrfs_free_space_bitmap_cachep)
goto fail;
@@ -9879,6 +9877,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
struct btrfs_path *path;
u64 start = ins->objectid;
u64 len = ins->offset;
+ int qgroup_released;
int ret;
memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9891,16 +9890,16 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
/* Encryption and other encoding is reserved and all 0 */
- ret = btrfs_qgroup_release_data(inode, file_offset, len);
- if (ret < 0)
- return ERR_PTR(ret);
+ qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
+ if (qgroup_released < 0)
+ return ERR_PTR(qgroup_released);
if (trans) {
ret = insert_reserved_file_extent(trans, inode,
file_offset, &stack_fi,
- true, ret);
+ true, qgroup_released);
if (ret)
- return ERR_PTR(ret);
+ goto free_qgroup;
return trans;
}
@@ -9911,21 +9910,35 @@ 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.qgroup_reserved = ret;
+ extent_info.qgroup_reserved = qgroup_released;
extent_info.insertions = 0;
path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
+ if (!path) {
+ ret = -ENOMEM;
+ goto free_qgroup;
+ }
ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset,
file_offset + len - 1, &extent_info,
&trans);
btrfs_free_path(path);
if (ret)
- return ERR_PTR(ret);
-
+ goto free_qgroup;
return trans;
+
+free_qgroup:
+ /*
+ * We have released qgroup data range at the beginning of the function,
+ * and normally qgroup_released bytes will be freed when committing
+ * transaction.
+ * But if we error out early, we have to free what we have released
+ * or we leak qgroup data reservation.
+ */
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid, qgroup_released,
+ BTRFS_QGROUP_RSV_DATA);
+ return ERR_PTR(ret);
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -10200,6 +10213,7 @@ static int btrfs_add_swapfile_pin(struct inode *inode, void *ptr,
sp->ptr = ptr;
sp->inode = inode;
sp->is_block_group = is_block_group;
+ sp->bg_extent_count = 1;
spin_lock(&fs_info->swapfile_pins_lock);
p = &fs_info->swapfile_pins.rb_node;
@@ -10213,6 +10227,8 @@ static int btrfs_add_swapfile_pin(struct inode *inode, void *ptr,
(sp->ptr == entry->ptr && sp->inode > entry->inode)) {
p = &(*p)->rb_right;
} else {
+ if (is_block_group)
+ entry->bg_extent_count++;
spin_unlock(&fs_info->swapfile_pins_lock);
kfree(sp);
return 1;
@@ -10238,8 +10254,11 @@ static void btrfs_free_swapfile_pins(struct inode *inode)
sp = rb_entry(node, struct btrfs_swapfile_pin, node);
if (sp->inode == inode) {
rb_erase(&sp->node, &fs_info->swapfile_pins);
- if (sp->is_block_group)
+ if (sp->is_block_group) {
+ btrfs_dec_block_group_swap_extents(sp->ptr,
+ sp->bg_extent_count);
btrfs_put_block_group(sp->ptr);
+ }
kfree(sp);
}
node = next;
@@ -10300,7 +10319,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
struct inode *inode = file_inode(file);
- struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_state *cached_state = NULL;
struct extent_map *em = NULL;
@@ -10351,13 +10371,27 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
"cannot activate swapfile while exclusive operation is running");
return -EBUSY;
}
+
+ /*
+ * Prevent snapshot creation while we are activating the swap file.
+ * We do not want to race with snapshot creation. If snapshot creation
+ * already started before we bumped nr_swapfiles from 0 to 1 and
+ * completes before the first write into the swap file after it is
+ * activated, than that write would fallback to COW.
+ */
+ if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) {
+ btrfs_exclop_finish(fs_info);
+ btrfs_warn(fs_info,
+ "cannot activate swapfile because snapshot creation is in progress");
+ return -EINVAL;
+ }
/*
* Snapshots can create extents which require COW even if NODATACOW is
* set. We use this counter to prevent snapshots. We must increment it
* before walking the extents because we don't want a concurrent
* snapshot to run after we've already checked the extents.
*/
- atomic_inc(&BTRFS_I(inode)->root->nr_swapfiles);
+ atomic_inc(&root->nr_swapfiles);
isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);
@@ -10454,6 +10488,17 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
goto out;
}
+ if (!btrfs_inc_block_group_swap_extents(bg)) {
+ btrfs_warn(fs_info,
+ "block group for swapfile at %llu is read-only%s",
+ bg->start,
+ atomic_read(&fs_info->scrubs_running) ?
+ " (scrub running)" : "");
+ btrfs_put_block_group(bg);
+ ret = -EINVAL;
+ goto out;
+ }
+
ret = btrfs_add_swapfile_pin(inode, bg, true);
if (ret) {
btrfs_put_block_group(bg);
@@ -10492,6 +10537,8 @@ out:
if (ret)
btrfs_swap_deactivate(file);
+ btrfs_drew_write_unlock(&root->snapshot_lock);
+
btrfs_exclop_finish(fs_info);
if (ret)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 072e77726e94..e8d53fea4c61 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1936,7 +1936,10 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
readonly = true;
if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) {
- if (vol_args->size > PAGE_SIZE) {
+ u64 nums;
+
+ if (vol_args->size < sizeof(*inherit) ||
+ vol_args->size > PAGE_SIZE) {
ret = -EINVAL;
goto free_args;
}
@@ -1945,6 +1948,20 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
ret = PTR_ERR(inherit);
goto free_args;
}
+
+ if (inherit->num_qgroups > PAGE_SIZE ||
+ inherit->num_ref_copies > PAGE_SIZE ||
+ inherit->num_excl_copies > PAGE_SIZE) {
+ ret = -EINVAL;
+ goto free_inherit;
+ }
+
+ nums = inherit->num_qgroups + 2 * inherit->num_ref_copies +
+ 2 * inherit->num_excl_copies;
+ if (vol_args->size != struct_size(inherit, qgroups, nums)) {
+ ret = -EINVAL;
+ goto free_inherit;
+ }
}
ret = __btrfs_ioctl_snap_create(file, vol_args->name, vol_args->fd,
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index aa9cd11f4b78..9084a950dc09 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -467,7 +467,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
- kaddr = kmap_atomic(dest_page);
+ kaddr = kmap_local_page(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
/*
@@ -477,7 +477,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
*/
if (bytes < destlen)
memset(kaddr+bytes, 0, destlen-bytes);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
out:
return ret;
}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 808370ada888..f0b9ef13153a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -226,7 +226,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
{
struct btrfs_qgroup_list *list;
- btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
list_del(&qgroup->dirty);
while (!list_empty(&qgroup->groups)) {
list = list_first_entry(&qgroup->groups,
@@ -243,7 +242,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
list_del(&list->next_member);
kfree(list);
}
- kfree(qgroup);
}
/* must be called with qgroup_lock held */
@@ -569,6 +567,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
qgroup = rb_entry(n, struct btrfs_qgroup, node);
rb_erase(n, &fs_info->qgroup_tree);
__del_qgroup_rb(fs_info, qgroup);
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
}
/*
* We call btrfs_free_qgroup_config() when unmounting
@@ -1578,6 +1578,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
spin_lock(&fs_info->qgroup_lock);
del_qgroup_rb(fs_info, qgroupid);
spin_unlock(&fs_info->qgroup_lock);
+
+ /*
+ * Remove the qgroup from sysfs now without holding the qgroup_lock
+ * spinlock, since the sysfs_remove_group() function needs to take
+ * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+ */
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
return ret;
@@ -3841,8 +3849,8 @@ static int sub_root_meta_rsv(struct btrfs_root *root, int num_bytes,
return num_bytes;
}
-static int qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
- enum btrfs_qgroup_rsv_type type, bool enforce)
+int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type, bool enforce)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
@@ -3873,14 +3881,14 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
{
int ret;
- ret = qgroup_reserve_meta(root, num_bytes, type, enforce);
+ ret = btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce);
if (ret <= 0 && ret != -EDQUOT)
return ret;
ret = try_flush_qgroup(root);
if (ret < 0)
return ret;
- return qgroup_reserve_meta(root, num_bytes, type, enforce);
+ return btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce);
}
void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 50dea9a2d8fb..7283e4f549af 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -361,6 +361,8 @@ int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len);
int btrfs_qgroup_free_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start,
u64 len);
+int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type, bool enforce);
int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
enum btrfs_qgroup_rsv_type type, bool enforce);
/* Reserve metadata space for pertrans and prealloc type */
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 8ec34ecb6d68..8c31357f08ed 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -249,8 +249,6 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info)
static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
{
int i;
- char *s;
- char *d;
int ret;
ret = alloc_rbio_pages(rbio);
@@ -261,13 +259,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
if (!rbio->bio_pages[i])
continue;
- s = kmap(rbio->bio_pages[i]);
- d = kmap(rbio->stripe_pages[i]);
-
- copy_page(d, s);
-
- kunmap(rbio->bio_pages[i]);
- kunmap(rbio->stripe_pages[i]);
+ copy_highpage(rbio->stripe_pages[i], rbio->bio_pages[i]);
SetPageUptodate(rbio->stripe_pages[i]);
}
set_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
@@ -2359,16 +2351,21 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
SetPageUptodate(p_page);
if (has_qstripe) {
+ /* RAID6, allocate and map temp space for the Q stripe */
q_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
if (!q_page) {
__free_page(p_page);
goto cleanup;
}
SetPageUptodate(q_page);
+ pointers[rbio->real_stripes - 1] = kmap(q_page);
}
atomic_set(&rbio->error, 0);
+ /* Map the parity stripe just once */
+ pointers[nr_data] = kmap(p_page);
+
for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
struct page *p;
void *parity;
@@ -2378,16 +2375,8 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
pointers[stripe] = kmap(p);
}
- /* then add the parity stripe */
- pointers[stripe++] = kmap(p_page);
-
if (has_qstripe) {
- /*
- * raid6, add the qstripe and call the
- * library function to fill in our p/q
- */
- pointers[stripe++] = kmap(q_page);
-
+ /* RAID6, call the library function to fill in our P/Q */
raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE,
pointers);
} else {
@@ -2408,12 +2397,14 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
for (stripe = 0; stripe < nr_data; stripe++)
kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
- kunmap(p_page);
}
+ kunmap(p_page);
__free_page(p_page);
- if (q_page)
+ if (q_page) {
+ kunmap(q_page);
__free_page(q_page);
+ }
writeback:
/*
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 20fd4aa48a8c..06713a8fe26b 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -209,7 +209,7 @@ int btree_readahead_hook(struct extent_buffer *eb, int err)
/* find extent */
spin_lock(&fs_info->reada_lock);
re = radix_tree_lookup(&fs_info->reada_tree,
- eb->start >> PAGE_SHIFT);
+ eb->start >> fs_info->sectorsize_bits);
if (re)
re->refcnt++;
spin_unlock(&fs_info->reada_lock);
@@ -240,7 +240,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
zone = NULL;
spin_lock(&fs_info->reada_lock);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
- logical >> PAGE_SHIFT, 1);
+ logical >> fs_info->sectorsize_bits, 1);
if (ret == 1 && logical >= zone->start && logical <= zone->end) {
kref_get(&zone->refcnt);
spin_unlock(&fs_info->reada_lock);
@@ -283,13 +283,13 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&dev->reada_zones,
- (unsigned long)(zone->end >> PAGE_SHIFT),
- zone);
+ (unsigned long)(zone->end >> fs_info->sectorsize_bits),
+ zone);
if (ret == -EEXIST) {
kfree(zone);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
- logical >> PAGE_SHIFT, 1);
+ logical >> fs_info->sectorsize_bits, 1);
if (ret == 1 && logical >= zone->start && logical <= zone->end)
kref_get(&zone->refcnt);
else
@@ -315,7 +315,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
u64 length;
int real_stripes;
int nzones = 0;
- unsigned long index = logical >> PAGE_SHIFT;
+ unsigned long index = logical >> fs_info->sectorsize_bits;
int dev_replace_is_ongoing;
int have_zone = 0;
@@ -497,7 +497,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
struct reada_extent *re)
{
int i;
- unsigned long index = re->logical >> PAGE_SHIFT;
+ unsigned long index = re->logical >> fs_info->sectorsize_bits;
spin_lock(&fs_info->reada_lock);
if (--re->refcnt) {
@@ -538,11 +538,12 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
static void reada_zone_release(struct kref *kref)
{
struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
+ struct btrfs_fs_info *fs_info = zone->device->fs_info;
- lockdep_assert_held(&zone->device->fs_info->reada_lock);
+ lockdep_assert_held(&fs_info->reada_lock);
radix_tree_delete(&zone->device->reada_zones,
- zone->end >> PAGE_SHIFT);
+ zone->end >> fs_info->sectorsize_bits);
kfree(zone);
}
@@ -593,7 +594,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical,
static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock)
{
int i;
- unsigned long index = zone->end >> PAGE_SHIFT;
+ unsigned long index = zone->end >> zone->device->fs_info->sectorsize_bits;
for (i = 0; i < zone->ndevs; ++i) {
struct reada_zone *peer;
@@ -628,7 +629,7 @@ static int reada_pick_zone(struct btrfs_device *dev)
(void **)&zone, index, 1);
if (ret == 0)
break;
- index = (zone->end >> PAGE_SHIFT) + 1;
+ index = (zone->end >> dev->fs_info->sectorsize_bits) + 1;
if (zone->locked) {
if (zone->elems > top_locked_elems) {
top_locked_elems = zone->elems;
@@ -709,7 +710,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
* plugging to speed things up
*/
ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
- dev->reada_next >> PAGE_SHIFT, 1);
+ dev->reada_next >> fs_info->sectorsize_bits, 1);
if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
ret = reada_pick_zone(dev);
if (!ret) {
@@ -718,7 +719,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
}
re = NULL;
ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
- dev->reada_next >> PAGE_SHIFT, 1);
+ dev->reada_next >> fs_info->sectorsize_bits, 1);
}
if (ret == 0) {
spin_unlock(&fs_info->reada_lock);
@@ -885,7 +886,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
pr_cont(" curr off %llu",
device->reada_next - zone->start);
pr_cont("\n");
- index = (zone->end >> PAGE_SHIFT) + 1;
+ index = (zone->end >> fs_info->sectorsize_bits) + 1;
}
cnt = 0;
index = 0;
@@ -910,7 +911,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
}
}
pr_cont("\n");
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
if (++cnt > 15)
break;
}
@@ -926,7 +927,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
if (ret == 0)
break;
if (!re->scheduled) {
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
continue;
}
pr_debug("re: logical %llu size %u list empty %d scheduled %d",
@@ -942,7 +943,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all)
}
}
pr_cont("\n");
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
}
spin_unlock(&fs_info->reada_lock);
}
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 2b490becbe67..8e026de74c44 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -218,11 +218,11 @@ static void __print_stack_trace(struct btrfs_fs_info *fs_info,
stack_trace_print(ra->trace, ra->trace_len, 2);
}
#else
-static void inline __save_stack_trace(struct ref_action *ra)
+static inline void __save_stack_trace(struct ref_action *ra)
{
}
-static void inline __print_stack_trace(struct btrfs_fs_info *fs_info,
+static inline void __print_stack_trace(struct btrfs_fs_info *fs_info,
struct ref_action *ra)
{
btrfs_err(fs_info, " ref-verify: no stacktrace support");
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index b24396cf2f99..762881b777b3 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -106,12 +106,8 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags);
if (comp_type == BTRFS_COMPRESS_NONE) {
- char *map;
-
- map = kmap(page);
- memcpy(map, data_start, datal);
+ memcpy_to_page(page, 0, data_start, datal);
flush_dcache_page(page);
- kunmap(page);
} else {
ret = btrfs_decompress(comp_type, data_start, page, 0,
inline_size, datal);
@@ -553,6 +549,24 @@ process_slot:
*/
btrfs_release_path(path);
+ /*
+ * When using NO_HOLES and we are cloning a range that covers
+ * only a hole (no extents) into a range beyond the current
+ * i_size, punching a hole in the target range will not create
+ * an extent map defining a hole, because the range starts at or
+ * beyond current i_size. If the file previously had an i_size
+ * greater than the new i_size set by this clone operation, we
+ * need to make sure the next fsync is a full fsync, so that it
+ * detects and logs a hole covering a range from the current
+ * i_size to the new i_size. If the clone range covers extents,
+ * besides a hole, then we know the full sync flag was already
+ * set by previous calls to btrfs_replace_file_extents() that
+ * replaced file extent items.
+ */
+ if (last_dest_end >= i_size_read(inode))
+ set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+ &BTRFS_I(inode)->runtime_flags);
+
ret = btrfs_replace_file_extents(inode, path, last_dest_end,
destoff + len - 1, NULL, &trans);
if (ret)
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 582df11d298a..3d9088eab2fc 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1428,7 +1428,7 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info,
if (!first_page->dev->bdev)
goto out;
- bio = btrfs_io_bio_alloc(BIO_MAX_PAGES);
+ bio = btrfs_io_bio_alloc(BIO_MAX_VECS);
bio_set_dev(bio, first_page->dev->bdev);
for (page_num = 0; page_num < sblock->page_count; page_num++) {
@@ -3767,6 +3767,13 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
* commit_transactions.
*/
ro_set = 0;
+ } else if (ret == -ETXTBSY) {
+ btrfs_warn(fs_info,
+ "skipping scrub of block group %llu due to active swapfile",
+ cache->start);
+ scrub_pause_off(fs_info);
+ ret = 0;
+ goto skip_unfreeze;
} else {
btrfs_warn(fs_info,
"failed setting block group ro: %d", ret);
@@ -3862,7 +3869,7 @@ done:
} else {
spin_unlock(&cache->lock);
}
-
+skip_unfreeze:
btrfs_unfreeze_block_group(cache);
btrfs_put_block_group(cache);
if (ret)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index f87878274e9f..8f323859156b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4932,7 +4932,6 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
struct btrfs_fs_info *fs_info = root->fs_info;
struct inode *inode;
struct page *page;
- char *addr;
pgoff_t index = offset >> PAGE_SHIFT;
pgoff_t last_index;
unsigned pg_offset = offset_in_page(offset);
@@ -4985,10 +4984,8 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
}
}
- addr = kmap(page);
- memcpy(sctx->send_buf + sctx->send_size, addr + pg_offset,
- cur_len);
- kunmap(page);
+ memcpy_from_page(sctx->send_buf + sctx->send_size, page,
+ pg_offset, cur_len);
unlock_page(page);
put_page(page);
index++;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f8435641b912..f7a4ad86adee 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1918,8 +1918,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
btrfs_resize_thread_pool(fs_info,
fs_info->thread_pool_size, old_thread_pool_size);
- if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) !=
- btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+ if ((bool)btrfs_test_opt(fs_info, FREE_SPACE_TREE) !=
+ (bool)btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
(!sb_rdonly(sb) || (*flags & SB_RDONLY))) {
btrfs_warn(fs_info,
"remount supports changing free space tree only from ro to rw");
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 582061c7b547..f4ade821307d 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1453,22 +1453,14 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
return -EUCLEAN;
}
for (; ptr < end; ptr += sizeof(*dref)) {
- u64 root_objectid;
- u64 owner;
u64 offset;
- u64 hash;
+ /*
+ * We cannot check the extent_data_ref hash due to possible
+ * overflow from the leaf due to hash collisions.
+ */
dref = (struct btrfs_extent_data_ref *)ptr;
- root_objectid = btrfs_extent_data_ref_root(leaf, dref);
- owner = btrfs_extent_data_ref_objectid(leaf, dref);
offset = btrfs_extent_data_ref_offset(leaf, dref);
- hash = hash_extent_data_ref(root_objectid, owner, offset);
- if (unlikely(hash != key->offset)) {
- extent_err(leaf, slot,
- "invalid extent data ref hash, item has 0x%016llx key has 0x%016llx",
- hash, key->offset);
- 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",
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d90695c1ab6c..92a368627791 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3169,23 +3169,20 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
mutex_lock(&log_root_tree->log_mutex);
- index2 = log_root_tree->log_transid % 2;
- list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
- root_log_ctx.log_transid = log_root_tree->log_transid;
-
if (btrfs_is_zoned(fs_info)) {
- mutex_lock(&fs_info->tree_root->log_mutex);
if (!log_root_tree->node) {
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
if (ret) {
- mutex_unlock(&fs_info->tree_log_mutex);
mutex_unlock(&log_root_tree->log_mutex);
goto out;
}
}
- mutex_unlock(&fs_info->tree_root->log_mutex);
}
+ index2 = log_root_tree->log_transid % 2;
+ list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
+ root_log_ctx.log_transid = log_root_tree->log_transid;
+
/*
* Now we are safe to update the log_root_tree because we're under the
* log_mutex, and we're a current writer so we're holding the commit
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bc3b33efddc5..1c6810bbaf8b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7448,6 +7448,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device,
int item_size;
int i, ret, slot;
+ if (!device->fs_info->dev_root)
+ return 0;
+
key.objectid = BTRFS_DEV_STATS_OBJECTID;
key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index b025102e435f..8a4514283a4b 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -229,11 +229,33 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name,
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
+ const bool start_trans = (current->journal_info == NULL);
int ret;
- trans = btrfs_start_transaction(root, 2);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ if (start_trans) {
+ /*
+ * 1 unit for inserting/updating/deleting the xattr
+ * 1 unit for the inode item update
+ */
+ trans = btrfs_start_transaction(root, 2);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ } else {
+ /*
+ * This can happen when smack is enabled and a directory is being
+ * created. It happens through d_instantiate_new(), which calls
+ * smack_d_instantiate(), which in turn calls __vfs_setxattr() to
+ * set the transmute xattr (XATTR_NAME_SMACKTRANSMUTE) on the
+ * inode. We have already reserved space for the xattr and inode
+ * update at btrfs_mkdir(), so just use the transaction handle.
+ * We don't join or start a transaction, as that will reset the
+ * block_rsv of the handle and trigger a warning for the start
+ * case.
+ */
+ ASSERT(strncmp(name, XATTR_SECURITY_PREFIX,
+ XATTR_SECURITY_PREFIX_LEN) == 0);
+ trans = current->journal_info;
+ }
ret = btrfs_setxattr(trans, inode, name, value, size, flags);
if (ret)
@@ -244,7 +266,8 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name,
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
BUG_ON(ret);
out:
- btrfs_end_transaction(trans);
+ if (start_trans)
+ btrfs_end_transaction(trans);
return ret;
}
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 05615a1099db..d524acf7b3e5 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -432,9 +432,8 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
PAGE_SIZE - (buf_offset % PAGE_SIZE));
bytes = min(bytes, bytes_left);
- kaddr = kmap_atomic(dest_page);
- memcpy(kaddr + pg_offset, workspace->buf + buf_offset, bytes);
- kunmap_atomic(kaddr);
+ memcpy_to_page(dest_page, pg_offset,
+ workspace->buf + buf_offset, bytes);
pg_offset += bytes;
bytes_left -= bytes;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index d0eb0c8d6269..1f972b75a9ab 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -269,7 +269,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
sector_t sector = 0;
struct blk_zone *zones = NULL;
unsigned int i, nreported = 0, nr_zones;
- unsigned int zone_sectors;
+ sector_t zone_sectors;
char *model, *emulated;
int ret;
@@ -658,7 +658,7 @@ int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
u64 *bytenr_ret)
{
struct blk_zone zones[BTRFS_NR_SB_LOG_ZONES];
- unsigned int zone_sectors;
+ sector_t zone_sectors;
u32 sb_zone;
int ret;
u8 zone_sectors_shift;
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 9a4871636c6c..8e9626d63976 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -688,10 +688,8 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
bytes = min_t(unsigned long, destlen - pg_offset,
workspace->out_buf.size - buf_offset);
- kaddr = kmap_atomic(dest_page);
- memcpy(kaddr + pg_offset, workspace->out_buf.dst + buf_offset,
- bytes);
- kunmap_atomic(kaddr);
+ memcpy_to_page(dest_page, pg_offset,
+ workspace->out_buf.dst + buf_offset, bytes);
pg_offset += bytes;
}
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-22 04:48:03 +0100