summaryrefslogtreecommitdiff
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/ctree.c2
-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.c35
-rw-r--r--fs/btrfs/inode.c55
-rw-r--r--fs/btrfs/qgroup.c12
-rw-r--r--fs/btrfs/reada.c35
-rw-r--r--fs/btrfs/scrub.c2
-rw-r--r--fs/btrfs/tree-log.c8
-rw-r--r--fs/btrfs/volumes.c3
-rw-r--r--fs/btrfs/zoned.c53
13 files changed, 195 insertions, 65 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/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/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 4671c99d468d..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);
@@ -3020,7 +3049,7 @@ readpage_ok:
*/
if (page->index == end_index && i_size <= end) {
u32 zero_start = max(offset_in_page(i_size),
- offset_in_page(end));
+ offset_in_page(start));
zero_user_segment(page, zero_start,
offset_in_page(end) + 1);
@@ -3059,7 +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/inode.c b/fs/btrfs/inode.c
index 35bfa0533f23..a520775949a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3099,11 +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);
@@ -3130,8 +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);
@@ -3184,7 +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;
}
@@ -7910,7 +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)),
@@ -8169,10 +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);
@@ -9008,7 +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;
@@ -9877,6 +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));
@@ -9889,16 +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;
}
@@ -9909,21 +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,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 14ff388fd3bd..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;
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/scrub.c b/fs/btrfs/scrub.c
index c2900ebf767a..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++) {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2f1acc9aea9e..92a368627791 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3169,10 +3169,6 @@ 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)) {
if (!log_root_tree->node) {
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
@@ -3183,6 +3179,10 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
}
}
+ 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/zoned.c b/fs/btrfs/zoned.c
index 1f972b75a9ab..eeb3ebe11d7a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -21,9 +21,30 @@
/* Pseudo write pointer value for conventional zone */
#define WP_CONVENTIONAL ((u64)-2)
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock: 0B (zone 0)
+ * - first copy: 512G (zone starting at that offset)
+ * - second copy: 4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET (0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET (512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET (4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
/* Number of superblock log zones */
#define BTRFS_NR_SB_LOG_ZONES 2
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE SZ_8G
+
static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
{
struct blk_zone *zones = data;
@@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
}
/*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- * - The primary superblock: zones 0 and 1
- * - The first copy: zones 16 and 17
- * - The second copy: zones 1024 or zone at 256GB which is minimum, and
- * the following one
+ * Get the first zone number of the superblock mirror
*/
static inline u32 sb_zone_number(int shift, int mirror)
{
- ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+ u64 zone;
+ ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
switch (mirror) {
- case 0: return 0;
- case 1: return 16;
- case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+ case 0: zone = 0; break;
+ case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+ case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
}
- return 0;
+ ASSERT(zone <= U32_MAX);
+
+ return (u32)zone;
}
/*
@@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
zone_sectors = bdev_zone_sectors(bdev);
}
- nr_sectors = bdev_nr_sectors(bdev);
/* Check if it's power of 2 (see is_power_of_2) */
ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+ /* We reject devices with a zone size larger than 8GB */
+ if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+ btrfs_err_in_rcu(fs_info,
+ "zoned: %s: zone size %llu larger than supported maximum %llu",
+ rcu_str_deref(device->name),
+ zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ nr_sectors = bdev_nr_sectors(bdev);
zone_info->zone_size_shift = ilog2(zone_info->zone_size);
zone_info->max_zone_append_size =
(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
generated by cgit (git 2.34.1) at 2024-05-25 16:13:08 +0000