aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/btrfs_inode.h11
-rw-r--r--fs/btrfs/ctree.h1
-rw-r--r--fs/btrfs/dev-replace.c7
-rw-r--r--fs/btrfs/disk-io.c23
-rw-r--r--fs/btrfs/extent-tree.c8
-rw-r--r--fs/btrfs/extent_io.c44
-rw-r--r--fs/btrfs/inode.c33
-rw-r--r--fs/btrfs/ioctl.c19
-rw-r--r--fs/btrfs/props.c59
-rw-r--r--fs/btrfs/props.h4
-rw-r--r--fs/btrfs/scrub.c26
-rw-r--r--fs/btrfs/sysfs.c3
-rw-r--r--fs/btrfs/tree-log.c54
-rw-r--r--fs/btrfs/volumes.c15
-rw-r--r--fs/btrfs/volumes.h7
-rw-r--r--fs/btrfs/xattr.c11
-rw-r--r--fs/btrfs/zoned.c37
-rw-r--r--fs/btrfs/zoned.h4
18 files changed, 245 insertions, 121 deletions
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 47e72d72f7d0..32131a5d321b 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -384,6 +384,17 @@ static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
return ret;
}
+/*
+ * Check if the inode has flags compatible with compression
+ */
+static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode)
+{
+ if (inode->flags & BTRFS_INODE_NODATACOW ||
+ inode->flags & BTRFS_INODE_NODATASUM)
+ return false;
+ return true;
+}
+
struct btrfs_dio_private {
struct inode *inode;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b7631b88426e..077c95e9baa5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1060,6 +1060,7 @@ struct btrfs_fs_info {
*/
spinlock_t relocation_bg_lock;
u64 data_reloc_bg;
+ struct mutex zoned_data_reloc_io_lock;
u64 nr_global_roots;
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 71fd99b48283..f26202621989 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -734,7 +734,12 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
- /* Commit dev_replace state and reserve 1 item for it. */
+ /*
+ * Commit dev_replace state and reserve 1 item for it.
+ * This is crucial to ensure we won't miss copying extents for new block
+ * groups that are allocated after we started the device replace, and
+ * must be done after setting up the device replace state.
+ */
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 126f244cdf88..84795d831282 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3157,6 +3157,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
mutex_init(&fs_info->zoned_meta_io_lock);
+ mutex_init(&fs_info->zoned_data_reloc_io_lock);
seqlock_init(&fs_info->profiles_lock);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
@@ -3657,6 +3658,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
if (sectorsize < PAGE_SIZE) {
struct btrfs_subpage_info *subpage_info;
+ /*
+ * V1 space cache has some hardcoded PAGE_SIZE usage, and is
+ * going to be deprecated.
+ *
+ * Force to use v2 cache for subpage case.
+ */
+ btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
+ btrfs_set_and_info(fs_info, FREE_SPACE_TREE,
+ "forcing free space tree for sector size %u with page size %lu",
+ sectorsize, PAGE_SIZE);
+
btrfs_warn(fs_info,
"read-write for sector size %u with page size %lu is experimental",
sectorsize, PAGE_SIZE);
@@ -4226,6 +4238,7 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
*/
static void btrfs_end_empty_barrier(struct bio *bio)
{
+ bio_uninit(bio);
complete(bio->bi_private);
}
@@ -4235,7 +4248,7 @@ static void btrfs_end_empty_barrier(struct bio *bio)
*/
static void write_dev_flush(struct btrfs_device *device)
{
- struct bio *bio = device->flush_bio;
+ struct bio *bio = &device->flush_bio;
#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
/*
@@ -4248,12 +4261,12 @@ static void write_dev_flush(struct btrfs_device *device)
* of simplicity, since this is a debug tool and not meant for use in
* non-debug builds.
*/
- struct request_queue *q = bdev_get_queue(device->bdev);
- if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+ if (!bdev_write_cache(device->bdev))
return;
#endif
- bio_reset(bio, device->bdev, REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH);
+ bio_init(bio, device->bdev, NULL, 0,
+ REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH);
bio->bi_end_io = btrfs_end_empty_barrier;
init_completion(&device->flush_wait);
bio->bi_private = &device->flush_wait;
@@ -4267,7 +4280,7 @@ static void write_dev_flush(struct btrfs_device *device)
*/
static blk_status_t wait_dev_flush(struct btrfs_device *device)
{
- struct bio *bio = device->flush_bio;
+ struct bio *bio = &device->flush_bio;
if (!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state))
return BLK_STS_OK;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6aa92f84f465..6260784e74b5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1239,7 +1239,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
if (size) {
ret = blkdev_issue_discard(bdev, start >> 9, size >> 9,
- GFP_NOFS, 0);
+ GFP_NOFS);
if (!ret)
*discarded_bytes += size;
else if (ret != -EOPNOTSUPP)
@@ -1256,7 +1256,7 @@ static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
if (bytes_left) {
ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9,
- GFP_NOFS, 0);
+ GFP_NOFS);
if (!ret)
*discarded_bytes += bytes_left;
}
@@ -1291,7 +1291,7 @@ static int do_discard_extent(struct btrfs_io_stripe *stripe, u64 *bytes)
ret = btrfs_reset_device_zone(dev_replace->tgtdev, phys, len,
&discarded);
discarded += src_disc;
- } else if (blk_queue_discard(bdev_get_queue(stripe->dev->bdev))) {
+ } else if (bdev_max_discard_sectors(stripe->dev->bdev)) {
ret = btrfs_issue_discard(dev->bdev, phys, len, &discarded);
} else {
ret = 0;
@@ -5987,7 +5987,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
*trimmed = 0;
/* Discard not supported = nothing to do. */
- if (!blk_queue_discard(bdev_get_queue(device->bdev)))
+ if (!bdev_max_discard_sectors(device->bdev))
return 0;
/* Not writable = nothing to do. */
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 724e8fe06aa0..33c19f51d79b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2658,6 +2658,7 @@ int btrfs_repair_one_sector(struct inode *inode,
repair_bio = btrfs_bio_alloc(1);
repair_bbio = btrfs_bio(repair_bio);
+ repair_bbio->file_offset = start;
repair_bio->bi_opf = REQ_OP_READ;
repair_bio->bi_end_io = failed_bio->bi_end_io;
repair_bio->bi_iter.bi_sector = failrec->logical >> 9;
@@ -3333,24 +3334,37 @@ static int alloc_new_bio(struct btrfs_inode *inode,
ret = calc_bio_boundaries(bio_ctrl, inode, file_offset);
if (ret < 0)
goto error;
- if (wbc) {
- struct block_device *bdev;
- bdev = fs_info->fs_devices->latest_dev->bdev;
- bio_set_dev(bio, bdev);
- wbc_init_bio(wbc, bio);
- }
- if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
- struct btrfs_device *device;
+ if (wbc) {
+ /*
+ * For Zone append we need the correct block_device that we are
+ * going to write to set in the bio to be able to respect the
+ * hardware limitation. Look it up here:
+ */
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ struct btrfs_device *dev;
+
+ dev = btrfs_zoned_get_device(fs_info, disk_bytenr,
+ fs_info->sectorsize);
+ if (IS_ERR(dev)) {
+ ret = PTR_ERR(dev);
+ goto error;
+ }
- device = btrfs_zoned_get_device(fs_info, disk_bytenr,
- fs_info->sectorsize);
- if (IS_ERR(device)) {
- ret = PTR_ERR(device);
- goto error;
+ bio_set_dev(bio, dev->bdev);
+ } else {
+ /*
+ * Otherwise pick the last added device to support
+ * cgroup writeback. For multi-device file systems this
+ * means blk-cgroup policies have to always be set on the
+ * last added/replaced device. This is a bit odd but has
+ * been like that for a long time.
+ */
+ bio_set_dev(bio, fs_info->fs_devices->latest_dev->bdev);
}
-
- btrfs_bio(bio)->device = device;
+ wbc_init_bio(wbc, bio);
+ } else {
+ ASSERT(bio_op(bio) != REQ_OP_ZONE_APPEND);
}
return 0;
error:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5082b9c70f8c..95c499b8424e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -481,17 +481,6 @@ static noinline int add_async_extent(struct async_chunk *cow,
}
/*
- * Check if the inode has flags compatible with compression
- */
-static inline bool inode_can_compress(struct btrfs_inode *inode)
-{
- if (inode->flags & BTRFS_INODE_NODATACOW ||
- inode->flags & BTRFS_INODE_NODATASUM)
- return false;
- return true;
-}
-
-/*
* Check if the inode needs to be submitted to compression, based on mount
* options, defragmentation, properties or heuristics.
*/
@@ -500,7 +489,7 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start,
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
- if (!inode_can_compress(inode)) {
+ if (!btrfs_inode_can_compress(inode)) {
WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
KERN_ERR "BTRFS: unexpected compression for ino %llu\n",
btrfs_ino(inode));
@@ -2019,7 +2008,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root));
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, nr_written);
- } else if (!inode_can_compress(inode) ||
+ } else if (!btrfs_inode_can_compress(inode) ||
!inode_need_compress(inode, start, end)) {
if (zoned)
ret = run_delalloc_zoned(inode, locked_page, start, end,
@@ -7810,8 +7799,6 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
const bool csum = !(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM);
struct bio_vec bvec;
struct bvec_iter iter;
- const u64 orig_file_offset = dip->file_offset;
- u64 start = orig_file_offset;
u32 bio_offset = 0;
blk_status_t err = BLK_STS_OK;
@@ -7821,6 +7808,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
pgoff = bvec.bv_offset;
for (i = 0; i < nr_sectors; i++) {
+ u64 start = bbio->file_offset + bio_offset;
+
ASSERT(pgoff < PAGE_SIZE);
if (uptodate &&
(!csum || !check_data_csum(inode, bbio,
@@ -7833,17 +7822,13 @@ static blk_status_t btrfs_check_read_dio_bio(struct btrfs_dio_private *dip,
} else {
int ret;
- ASSERT((start - orig_file_offset) < UINT_MAX);
- ret = btrfs_repair_one_sector(inode,
- &bbio->bio,
- start - orig_file_offset,
- bvec.bv_page, pgoff,
+ ret = btrfs_repair_one_sector(inode, &bbio->bio,
+ bio_offset, bvec.bv_page, pgoff,
start, bbio->mirror_num,
submit_dio_repair_bio);
if (ret)
err = errno_to_blk_status(ret);
}
- start += sectorsize;
ASSERT(bio_offset + sectorsize > bio_offset);
bio_offset += sectorsize;
pgoff += sectorsize;
@@ -7870,6 +7855,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode,
static void btrfs_end_dio_bio(struct bio *bio)
{
struct btrfs_dio_private *dip = bio->bi_private;
+ struct btrfs_bio *bbio = btrfs_bio(bio);
blk_status_t err = bio->bi_status;
if (err)
@@ -7880,12 +7866,12 @@ static void btrfs_end_dio_bio(struct bio *bio)
bio->bi_iter.bi_size, err);
if (bio_op(bio) == REQ_OP_READ)
- err = btrfs_check_read_dio_bio(dip, btrfs_bio(bio), !err);
+ err = btrfs_check_read_dio_bio(dip, bbio, !err);
if (err)
dip->dio_bio->bi_status = err;
- btrfs_record_physical_zoned(dip->inode, dip->file_offset, bio);
+ btrfs_record_physical_zoned(dip->inode, bbio->file_offset, bio);
bio_put(bio);
btrfs_dio_private_put(dip);
@@ -8046,6 +8032,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter,
bio = btrfs_bio_clone_partial(dio_bio, clone_offset, clone_len);
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
+ btrfs_bio(bio)->file_offset = file_offset;
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
status = extract_ordered_extent(BTRFS_I(inode), bio,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index be6c24577dbe..b2c692b2fd8d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -468,7 +468,6 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
void __user *arg)
{
struct btrfs_device *device;
- struct request_queue *q;
struct fstrim_range range;
u64 minlen = ULLONG_MAX;
u64 num_devices = 0;
@@ -498,14 +497,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
dev_list) {
- if (!device->bdev)
+ if (!device->bdev || !bdev_max_discard_sectors(device->bdev))
continue;
- q = bdev_get_queue(device->bdev);
- if (blk_queue_discard(q)) {
- num_devices++;
- minlen = min_t(u64, q->limits.discard_granularity,
- minlen);
- }
+ num_devices++;
+ minlen = min_t(u64, bdev_discard_granularity(device->bdev),
+ minlen);
}
rcu_read_unlock();
@@ -2565,7 +2561,12 @@ static noinline int search_ioctl(struct inode *inode,
while (1) {
ret = -EFAULT;
- if (fault_in_writeable(ubuf + sk_offset, *buf_size - sk_offset))
+ /*
+ * Ensure that the whole user buffer is faulted in at sub-page
+ * granularity, otherwise the loop may live-lock.
+ */
+ if (fault_in_subpage_writeable(ubuf + sk_offset,
+ *buf_size - sk_offset))
break;
ret = btrfs_search_forward(root, &key, path, sk->min_transid);
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 1a6d2d5b4b33..1b31481f9e72 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -17,9 +17,11 @@ static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS);
struct prop_handler {
struct hlist_node node;
const char *xattr_name;
- int (*validate)(const char *value, size_t len);
+ int (*validate)(const struct btrfs_inode *inode, const char *value,
+ size_t len);
int (*apply)(struct inode *inode, const char *value, size_t len);
const char *(*extract)(struct inode *inode);
+ bool (*ignore)(const struct btrfs_inode *inode);
int inheritable;
};
@@ -55,7 +57,8 @@ find_prop_handler(const char *name,
return NULL;
}
-int btrfs_validate_prop(const char *name, const char *value, size_t value_len)
+int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name,
+ const char *value, size_t value_len)
{
const struct prop_handler *handler;
@@ -69,7 +72,29 @@ int btrfs_validate_prop(const char *name, const char *value, size_t value_len)
if (value_len == 0)
return 0;
- return handler->validate(value, value_len);
+ return handler->validate(inode, value, value_len);
+}
+
+/*
+ * Check if a property should be ignored (not set) for an inode.
+ *
+ * @inode: The target inode.
+ * @name: The property's name.
+ *
+ * The caller must be sure the given property name is valid, for example by
+ * having previously called btrfs_validate_prop().
+ *
+ * Returns: true if the property should be ignored for the given inode
+ * false if the property must not be ignored for the given inode
+ */
+bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name)
+{
+ const struct prop_handler *handler;
+
+ handler = find_prop_handler(name, NULL);
+ ASSERT(handler != NULL);
+
+ return handler->ignore(inode);
}
int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode,
@@ -252,8 +277,12 @@ int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path)
return ret;
}
-static int prop_compression_validate(const char *value, size_t len)
+static int prop_compression_validate(const struct btrfs_inode *inode,
+ const char *value, size_t len)
{
+ if (!btrfs_inode_can_compress(inode))
+ return -EINVAL;
+
if (!value)
return 0;
@@ -310,6 +339,22 @@ static int prop_compression_apply(struct inode *inode, const char *value,
return 0;
}
+static bool prop_compression_ignore(const struct btrfs_inode *inode)
+{
+ /*
+ * Compression only has effect for regular files, and for directories
+ * we set it just to propagate it to new files created inside them.
+ * Everything else (symlinks, devices, sockets, fifos) is pointless as
+ * it will do nothing, so don't waste metadata space on a compression
+ * xattr for anything that is neither a file nor a directory.
+ */
+ if (!S_ISREG(inode->vfs_inode.i_mode) &&
+ !S_ISDIR(inode->vfs_inode.i_mode))
+ return true;
+
+ return false;
+}
+
static const char *prop_compression_extract(struct inode *inode)
{
switch (BTRFS_I(inode)->prop_compress) {
@@ -330,6 +375,7 @@ static struct prop_handler prop_handlers[] = {
.validate = prop_compression_validate,
.apply = prop_compression_apply,
.extract = prop_compression_extract,
+ .ignore = prop_compression_ignore,
.inheritable = 1
},
};
@@ -356,6 +402,9 @@ static int inherit_props(struct btrfs_trans_handle *trans,
if (!h->inheritable)
continue;
+ if (h->ignore(BTRFS_I(inode)))
+ continue;
+
value = h->extract(parent);
if (!value)
continue;
@@ -364,7 +413,7 @@ static int inherit_props(struct btrfs_trans_handle *trans,
* This is not strictly necessary as the property should be
* valid, but in case it isn't, don't propagate it further.
*/
- ret = h->validate(value, strlen(value));
+ ret = h->validate(BTRFS_I(inode), value, strlen(value));
if (ret)
continue;
diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h
index 40b2c65b518c..59bea741cfcf 100644
--- a/fs/btrfs/props.h
+++ b/fs/btrfs/props.h
@@ -13,7 +13,9 @@ void __init btrfs_props_init(void);
int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode,
const char *name, const char *value, size_t value_len,
int flags);
-int btrfs_validate_prop(const char *name, const char *value, size_t value_len);
+int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name,
+ const char *value, size_t value_len);
+bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name);
int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 11089568b287..8cd713d37ad2 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3699,6 +3699,31 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
if (!cache)
goto skip;
+ ASSERT(cache->start <= chunk_offset);
+ /*
+ * We are using the commit root to search for device extents, so
+ * that means we could have found a device extent item from a
+ * block group that was deleted in the current transaction. The
+ * logical start offset of the deleted block group, stored at
+ * @chunk_offset, might be part of the logical address range of
+ * a new block group (which uses different physical extents).
+ * In this case btrfs_lookup_block_group() has returned the new
+ * block group, and its start address is less than @chunk_offset.
+ *
+ * We skip such new block groups, because it's pointless to
+ * process them, as we won't find their extents because we search
+ * for them using the commit root of the extent tree. For a device
+ * replace it's also fine to skip it, we won't miss copying them
+ * to the target device because we have the write duplication
+ * setup through the regular write path (by btrfs_map_block()),
+ * and we have committed a transaction when we started the device
+ * replace, right after setting up the device replace state.
+ */
+ if (cache->start < chunk_offset) {
+ btrfs_put_block_group(cache);
+ goto skip;
+ }
+
if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) {
spin_lock(&cache->lock);
if (!cache->to_copy) {
@@ -3822,7 +3847,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
dev_replace->item_needs_writeback = 1;
up_write(&dev_replace->rwsem);
- ASSERT(cache->start == chunk_offset);
ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset,
dev_extent_len);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 17389a42a3ab..ba78ca5aabbb 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -922,6 +922,9 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj,
case BTRFS_EXCLOP_BALANCE:
str = "balance\n";
break;
+ case BTRFS_EXCLOP_BALANCE_PAUSED:
+ str = "balance paused\n";
+ break;
case BTRFS_EXCLOP_DEV_ADD:
str = "device add\n";
break;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 571dae8ad65e..e65633686378 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3188,6 +3188,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
if (ret) {
mutex_unlock(&fs_info->tree_root->log_mutex);
+ blk_finish_plug(&plug);
goto out;
}
}
@@ -3720,11 +3721,29 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
key.offset = first_offset;
key.type = BTRFS_DIR_LOG_INDEX_KEY;
ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item));
- if (ret)
+ /*
+ * -EEXIST is fine and can happen sporadically when we are logging a
+ * directory and have concurrent insertions in the subvolume's tree for
+ * items from other inodes and that result in pushing off some dir items
+ * from one leaf to another in order to accommodate for the new items.
+ * This results in logging the same dir index range key.
+ */
+ if (ret && ret != -EEXIST)
return ret;
item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_dir_log_item);
+ if (ret == -EEXIST) {
+ const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item);
+
+ /*
+ * btrfs_del_dir_entries_in_log() might have been called during
+ * an unlink between the initial insertion of this key and the
+ * current update, or we might be logging a single entry deletion
+ * during a rename, so set the new last_offset to the max value.
+ */
+ last_offset = max(last_offset, curr_end);
+ }
btrfs_set_dir_log_end(path->nodes[0], item, last_offset);
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_release_path(path);
@@ -3848,13 +3867,6 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
ret = insert_dir_log_key(trans, log, dst_path,
ino, *last_old_dentry_offset + 1,
key.offset - 1);
- /*
- * -EEXIST should never happen because when we
- * log a directory in full mode (LOG_INODE_ALL)
- * we drop all BTRFS_DIR_LOG_INDEX_KEY keys from
- * the log tree.
- */
- ASSERT(ret != -EEXIST);
if (ret < 0)
return ret;
}
@@ -5804,6 +5816,18 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
}
/*
+ * For symlinks, we must always log their content, which is stored in an
+ * inline extent, otherwise we could end up with an empty symlink after
+ * log replay, which is invalid on linux (symlink(2) returns -ENOENT if
+ * one attempts to create an empty symlink).
+ * We don't need to worry about flushing delalloc, because when we create
+ * the inline extent when the symlink is created (we never have delalloc
+ * for symlinks).
+ */
+ if (S_ISLNK(inode->vfs_inode.i_mode))
+ inode_only = LOG_INODE_ALL;
+
+ /*
* Before logging the inode item, cache the value returned by
* inode_logged(), because after that we have the need to figure out if
* the inode was previously logged in this transaction.
@@ -6181,7 +6205,7 @@ again:
}
ctx->log_new_dentries = false;
- if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
+ if (type == BTRFS_FT_DIR)
log_mode = LOG_INODE_ALL;
ret = btrfs_log_inode(trans, BTRFS_I(di_inode),
log_mode, ctx);
@@ -7018,12 +7042,12 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
/*
* Other concurrent task might be logging the old directory,
* as it can be triggered when logging other inode that had or
- * still has a dentry in the old directory. So take the old
- * directory's log_mutex to prevent getting an -EEXIST when
- * logging a key to record the deletion, or having that other
- * task logging the old directory get an -EEXIST if it attempts
- * to log the same key after we just did it. In both cases that
- * would result in falling back to a transaction commit.
+ * still has a dentry in the old directory. We lock the old
+ * directory's log_mutex to ensure the deletion of the old
+ * name is persisted, because during directory logging we
+ * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of
+ * the old name's dir index item is in the delayed items, so
+ * it could be missed by an in progress directory logging.
*/
mutex_lock(&old_dir->log_mutex);
ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir),
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a8cc736731fd..b6b00338037c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -405,7 +405,6 @@ void btrfs_free_device(struct btrfs_device *device)
WARN_ON(!list_empty(&device->post_commit_list));
rcu_string_free(device->name);
extent_io_tree_release(&device->alloc_state);
- bio_put(device->flush_bio);
btrfs_destroy_dev_zone_info(device);
kfree(device);
}
@@ -643,7 +642,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
set_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
}
- if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+ if (!bdev_nonrot(bdev))
fs_devices->rotating = true;
device->bdev = bdev;
@@ -2706,7 +2705,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
- if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+ if (!bdev_nonrot(bdev))
fs_devices->rotating = true;
orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
@@ -6949,16 +6948,6 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
if (!dev)
return ERR_PTR(-ENOMEM);
- /*
- * Preallocate a bio that's always going to be used for flushing device
- * barriers and matches the device lifespan
- */
- dev->flush_bio = bio_kmalloc(GFP_KERNEL, 0);
- if (!dev->flush_bio) {
- kfree(dev);
- return ERR_PTR(-ENOMEM);
- }
-
INIT_LIST_HEAD(&dev->dev_list);
INIT_LIST_HEAD(&dev->dev_alloc_list);
INIT_LIST_HEAD(&dev->post_commit_list);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index bd297f23d19e..b11c563d2025 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -121,8 +121,8 @@ struct btrfs_device {
/* bytes used on the current transaction */
u64 commit_bytes_used;
- /* for sending down flush barriers */
- struct bio *flush_bio;
+ /* Bio used for flushing device barriers */
+ struct bio flush_bio;
struct completion flush_wait;
/* per-device scrub information */
@@ -328,6 +328,9 @@ struct btrfs_fs_devices {
struct btrfs_bio {
unsigned int mirror_num;
+ /* for direct I/O */
+ u64 file_offset;
+
/* @device is for stripe IO submission. */
struct btrfs_device *device;
u8 *csum;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 99abf41b89b9..85691dc2232f 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -262,7 +262,8 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name,
inode_inc_iversion(inode);
inode->i_ctime = current_time(inode);
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
- BUG_ON(ret);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
out:
if (start_trans)
btrfs_end_transaction(trans);
@@ -403,10 +404,13 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
struct btrfs_root *root = BTRFS_I(inode)->root;
name = xattr_full_name(handler, name);
- ret = btrfs_validate_prop(name, value, size);
+ ret = btrfs_validate_prop(BTRFS_I(inode), name, value, size);
if (ret)
return ret;
+ if (btrfs_ignore_prop(BTRFS_I(inode), name))
+ return 0;
+
trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans))
return PTR_ERR(trans);
@@ -416,7 +420,8 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
inode_inc_iversion(inode);
inode->i_ctime = current_time(inode);
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
- BUG_ON(ret);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
}
btrfs_end_transaction(trans);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1b1b310c3c51..29b54fd9c128 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -350,7 +350,6 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
struct btrfs_fs_info *fs_info = device->fs_info;
struct btrfs_zoned_device_info *zone_info = NULL;
struct block_device *bdev = device->bdev;
- struct request_queue *queue = bdev_get_queue(bdev);
unsigned int max_active_zones;
unsigned int nactive;
sector_t nr_sectors;
@@ -410,7 +409,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
if (!IS_ALIGNED(nr_sectors, zone_sectors))
zone_info->nr_zones++;
- max_active_zones = queue_max_active_zones(queue);
+ max_active_zones = bdev_max_active_zones(bdev);
if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) {
btrfs_err_in_rcu(fs_info,
"zoned: %s: max active zones %u is too small, need at least %u active zones",
@@ -1835,6 +1834,12 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
goto out_unlock;
}
+ /* No space left */
+ if (block_group->alloc_offset == block_group->zone_capacity) {
+ ret = false;
+ goto out_unlock;
+ }
+
for (i = 0; i < map->num_stripes; i++) {
device = map->stripes[i].dev;
physical = map->stripes[i].physical;
@@ -1842,35 +1847,23 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
if (device->zone_info->max_active_zones == 0)
continue;
- /* No space left */
- if (block_group->alloc_offset == block_group->zone_capacity) {
- ret = false;
- goto out_unlock;
- }
-
if (!btrfs_dev_set_active_zone(device, physical)) {
/* Cannot activate the zone */
ret = false;
goto out_unlock;
}
-
- /* Successfully activated all the zones */
- if (i == map->num_stripes - 1)
- block_group->zone_is_active = 1;
-
-
}
+
+ /* Successfully activated all the zones */
+ block_group->zone_is_active = 1;
spin_unlock(&block_group->lock);
- if (block_group->zone_is_active) {
- /* For the active block group list */
- btrfs_get_block_group(block_group);
+ /* For the active block group list */
+ btrfs_get_block_group(block_group);
- spin_lock(&fs_info->zone_active_bgs_lock);
- list_add_tail(&block_group->active_bg_list,
- &fs_info->zone_active_bgs);
- spin_unlock(&fs_info->zone_active_bgs_lock);
- }
+ spin_lock(&fs_info->zone_active_bgs_lock);
+ list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
+ spin_unlock(&fs_info->zone_active_bgs_lock);
return true;
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index cbf016a7bb5d..6dee76248cb4 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -359,7 +359,7 @@ static inline void btrfs_zoned_data_reloc_lock(struct btrfs_inode *inode)
struct btrfs_root *root = inode->root;
if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
- btrfs_inode_lock(&inode->vfs_inode, 0);
+ mutex_lock(&root->fs_info->zoned_data_reloc_io_lock);
}
static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
@@ -367,7 +367,7 @@ static inline void btrfs_zoned_data_reloc_unlock(struct btrfs_inode *inode)
struct btrfs_root *root = inode->root;
if (btrfs_is_data_reloc_root(root) && btrfs_is_zoned(root->fs_info))
- btrfs_inode_unlock(&inode->vfs_inode, 0);
+ mutex_unlock(&root->fs_info->zoned_data_reloc_io_lock);
}
#endif
Powered by cgit, Gruvboxed by Blaster4385.