list_add_tail(&work->ordered_list, &wq->ordered_list);
spin_unlock_irqrestore(&wq->list_lock, flags);
}
- queue_work(wq->normal_wq, &work->normal_work);
trace_btrfs_work_queued(work);
+ queue_work(wq->normal_wq, &work->normal_work);
}
void btrfs_queue_work(struct btrfs_workqueue *wq,
*/
static void __merge_refs(struct list_head *head, int mode)
{
- struct __prelim_ref *ref1;
+ struct __prelim_ref *pos1;
- list_for_each_entry(ref1, head, list) {
- struct __prelim_ref *ref2 = ref1, *tmp;
+ list_for_each_entry(pos1, head, list) {
+ struct __prelim_ref *pos2 = pos1, *tmp;
- list_for_each_entry_safe_continue(ref2, tmp, head, list) {
- struct __prelim_ref *xchg;
+ list_for_each_entry_safe_continue(pos2, tmp, head, list) {
+ struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2;
struct extent_inode_elem *eie;
if (!ref_for_same_block(ref1, ref2))
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
- struct rw_semaphore delayed_iput_sem;
+ struct mutex cleaner_delayed_iput_mutex;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
int __get_raid_index(u64 flags);
int btrfs_start_write_no_snapshoting(struct btrfs_root *root);
void btrfs_end_write_no_snapshoting(struct btrfs_root *root);
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
void check_system_chunk(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
const u64 type);
em = lookup_extent_mapping(em_tree, start, (u64)-1);
if (!em)
break;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++)
if (srcdev == map->stripes[i].dev)
map->stripes[i].dev = tgtdev;
#include <asm/cpufeature.h>
#endif
+#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\
+ BTRFS_HEADER_FLAG_RELOC |\
+ BTRFS_SUPER_FLAG_ERROR |\
+ BTRFS_SUPER_FLAG_SEEDING |\
+ BTRFS_SUPER_FLAG_METADUMP)
+
static const struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
ret = get_anon_bdev(&root->anon_dev);
if (ret)
goto free_writers;
+
+ mutex_lock(&root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(root,
+ &root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&root->objectid_mutex);
+ goto free_root_dev;
+ }
+
+ ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&root->objectid_mutex);
+
return 0;
+free_root_dev:
+ free_anon_bdev(root->anon_dev);
free_writers:
btrfs_free_subvolume_writers(root->subv_writers);
fail:
int again;
struct btrfs_trans_handle *trans;
- set_freezable();
do {
again = 0;
goto sleep;
}
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(root);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&root->fs_info->cleaner_mutex);
mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
+ mutex_init(&fs_info->cleaner_delayed_iput_mutex);
seqlock_init(&fs_info->profiles_lock);
- init_rwsem(&fs_info->delayed_iput_sem);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
goto fail_alloc;
}
- /*
- * Leafsize and nodesize were always equal, this is only a sanity check.
- */
- if (le32_to_cpu(disk_super->__unused_leafsize) !=
- btrfs_super_nodesize(disk_super)) {
- printk(KERN_ERR "BTRFS: couldn't mount because metadata "
- "blocksizes don't match. node %d leaf %d\n",
- btrfs_super_nodesize(disk_super),
- le32_to_cpu(disk_super->__unused_leafsize));
- err = -EINVAL;
- goto fail_alloc;
- }
- if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
- printk(KERN_ERR "BTRFS: couldn't mount because metadata "
- "blocksize (%d) was too large\n",
- btrfs_super_nodesize(disk_super));
- err = -EINVAL;
- goto fail_alloc;
- }
-
features = btrfs_super_incompat_flags(disk_super);
features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
- if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- printk(KERN_ERR "BTRFS: valid FS not found on %s\n", sb->s_id);
- goto fail_sb_buffer;
- }
-
- if (sectorsize != PAGE_SIZE) {
- printk(KERN_ERR "BTRFS: incompatible sector size (%lu) "
- "found on %s\n", (unsigned long)sectorsize, sb->s_id);
- goto fail_sb_buffer;
- }
-
mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
tree_root->commit_root = btrfs_root_node(tree_root);
btrfs_set_root_refs(&tree_root->root_item, 1);
+ mutex_lock(&tree_root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(tree_root,
+ &tree_root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&tree_root->objectid_mutex);
+ goto recovery_tree_root;
+ }
+
+ ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&tree_root->objectid_mutex);
+
ret = btrfs_read_roots(fs_info, tree_root);
if (ret)
goto recovery_tree_root;
int read_only)
{
struct btrfs_super_block *sb = fs_info->super_copy;
+ u64 nodesize = btrfs_super_nodesize(sb);
+ u64 sectorsize = btrfs_super_sectorsize(sb);
int ret = 0;
+ if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+ printk(KERN_ERR "BTRFS: no valid FS found\n");
+ ret = -EINVAL;
+ }
+ if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)
+ printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n",
+ btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
}
/*
- * The common minimum, we don't know if we can trust the nodesize/sectorsize
- * items yet, they'll be verified later. Issue just a warning.
+ * Check sectorsize and nodesize first, other check will need it.
+ * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
*/
- if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
+ if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+ sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
+ ret = -EINVAL;
+ }
+ /* Only PAGE SIZE is supported yet */
+ if (sectorsize != PAGE_CACHE_SIZE) {
+ printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
+ sectorsize, PAGE_CACHE_SIZE);
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+ nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
+ ret = -EINVAL;
+ }
+ if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+ printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n",
+ le32_to_cpu(sb->__unused_leafsize),
+ nodesize);
+ ret = -EINVAL;
+ }
+
+ /* Root alignment check */
+ if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
btrfs_super_root(sb));
- if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
+ ret = -EINVAL;
+ }
+ if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
btrfs_super_chunk_root(sb));
- if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
- printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
- btrfs_super_log_root(sb));
-
- /*
- * Check the lower bound, the alignment and other constraints are
- * checked later.
- */
- if (btrfs_super_nodesize(sb) < 4096) {
- printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n",
- btrfs_super_nodesize(sb));
ret = -EINVAL;
}
- if (btrfs_super_sectorsize(sb) < 4096) {
- printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n",
- btrfs_super_sectorsize(sb));
+ if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+ printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
+ btrfs_super_log_root(sb));
ret = -EINVAL;
}
!atomic_read(&root->fs_info->open_ioctl_trans)) {
need_commit--;
- if (need_commit > 0)
+ if (need_commit > 0) {
+ btrfs_start_delalloc_roots(fs_info, 0, -1);
btrfs_wait_ordered_roots(fs_info, -1);
+ }
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
if (ret)
return ret;
/*
- * make sure that all running delayed iput are
- * done
+ * The cleaner kthread might still be doing iput
+ * operations. Wait for it to finish so that
+ * more space is released.
*/
- down_write(&root->fs_info->delayed_iput_sem);
- up_write(&root->fs_info->delayed_iput_sem);
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
goto again;
} else {
btrfs_end_transaction(trans, root);
* more device items and remove one chunk item), but this is done at
* btrfs_remove_chunk() through a call to check_system_chunk().
*/
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
num_items = 3 + map->num_stripes;
free_extent_map(em);
disk_super = fs_info->super_copy;
if (!btrfs_super_root(disk_super))
- return 1;
+ return -EINVAL;
features = btrfs_super_incompat_flags(disk_super);
if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
}
return 1;
}
+
+static int wait_snapshoting_atomic_t(atomic_t *a)
+{
+ schedule();
+ return 0;
+}
+
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
+{
+ while (true) {
+ int ret;
+
+ ret = btrfs_start_write_no_snapshoting(root);
+ if (ret)
+ break;
+ wait_on_atomic_t(&root->will_be_snapshoted,
+ wait_snapshoting_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+ }
+}
WARN_ON(extent_map_in_tree(em));
WARN_ON(!list_empty(&em->list));
if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
- kfree(em->bdev);
+ kfree(em->map_lookup);
kmem_cache_free(extent_map_cache, em);
}
}
u64 block_len;
u64 generation;
unsigned long flags;
- struct block_device *bdev;
+ union {
+ struct block_device *bdev;
+
+ /*
+ * used for chunk mappings
+ * flags & EXTENT_FLAG_FS_MAPPING must be set
+ */
+ struct map_lookup *map_lookup;
+ };
atomic_t refs;
unsigned int compress_type;
struct list_head list;
/* simple helper to fault in pages and copy. This should go away
* and be replaced with calls into generic code.
*/
-static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
- size_t write_bytes,
+static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes,
struct page **prepared_pages,
struct iov_iter *i)
{
ret = 0;
}
- copied = btrfs_copy_from_user(pos, num_pages,
- write_bytes, pages, i);
+ copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
/*
* if we have trouble faulting in the pages, fall
#include "locking.h"
#include "free-space-tree.h"
#include "transaction.h"
+#include "sysfs.h"
static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
}
btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+ btrfs_sysfs_feature_update(fs_info,
+ BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE, FEAT_COMPAT_RO);
+
fs_info->creating_free_space_tree = 0;
ret = btrfs_commit_transaction(trans, tree_root);
return PTR_ERR(trans);
btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+ btrfs_sysfs_feature_update(fs_info,
+ BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE, FEAT_COMPAT_RO);
+
fs_info->free_space_root = NULL;
ret = clear_free_space_tree(trans, free_space_root);
return ret;
}
-static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
{
struct btrfs_path *path;
int ret;
int ret;
mutex_lock(&root->objectid_mutex);
- if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
- ret = btrfs_find_highest_objectid(root,
- &root->highest_objectid);
- if (ret)
- goto out;
- }
-
if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
ret = -ENOSPC;
goto out;
struct btrfs_trans_handle *trans);
int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
#endif
{
struct btrfs_fs_info *fs_info = root->fs_info;
- down_read(&fs_info->delayed_iput_sem);
spin_lock(&fs_info->delayed_iput_lock);
while (!list_empty(&fs_info->delayed_iputs)) {
struct btrfs_inode *inode;
spin_lock(&fs_info->delayed_iput_lock);
}
spin_unlock(&fs_info->delayed_iput_lock);
- up_read(&root->fs_info->delayed_iput_sem);
}
/*
return err;
}
-static int wait_snapshoting_atomic_t(atomic_t *a)
-{
- schedule();
- return 0;
-}
-
-static void wait_for_snapshot_creation(struct btrfs_root *root)
-{
- while (true) {
- int ret;
-
- ret = btrfs_start_write_no_snapshoting(root);
- if (ret)
- break;
- wait_on_atomic_t(&root->will_be_snapshoted,
- wait_snapshoting_atomic_t,
- TASK_UNINTERRUPTIBLE);
- }
-}
-
static int btrfs_setsize(struct inode *inode, struct iattr *attr)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
* truncation, it must capture all writes that happened before
* this truncation.
*/
- wait_for_snapshot_creation(root);
+ btrfs_wait_for_snapshot_creation(root);
ret = btrfs_cont_expand(inode, oldsize, newsize);
if (ret) {
btrfs_end_write_no_snapshoting(root);
if (ret)
return ERR_PTR(ret);
- em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
- ins.offset, ins.offset, ins.offset, 0);
- if (IS_ERR(em)) {
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- return em;
- }
-
+ /*
+ * Create the ordered extent before the extent map. This is to avoid
+ * races with the fast fsync path that would lead to it logging file
+ * extent items that point to disk extents that were not yet written to.
+ * The fast fsync path collects ordered extents into a local list and
+ * then collects all the new extent maps, so we must create the ordered
+ * extent first and make sure the fast fsync path collects any new
+ * ordered extents after collecting new extent maps as well.
+ * The fsync path simply can not rely on inode_dio_wait() because it
+ * causes deadlock with AIO.
+ */
ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
ins.offset, ins.offset, 0);
if (ret) {
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- free_extent_map(em);
return ERR_PTR(ret);
}
+ em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
+ ins.offset, ins.offset, ins.offset, 0);
+ if (IS_ERR(em)) {
+ struct btrfs_ordered_extent *oe;
+
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+ oe = btrfs_lookup_ordered_extent(inode, start);
+ ASSERT(oe);
+ if (WARN_ON(!oe))
+ return em;
+ set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
+ set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
+ btrfs_remove_ordered_extent(inode, oe);
+ /* Once for our lookup and once for the ordered extents tree. */
+ btrfs_put_ordered_extent(oe);
+ btrfs_put_ordered_extent(oe);
+ }
return em;
}
goto fail;
}
+ mutex_lock(&new_root->objectid_mutex);
+ new_root->highest_objectid = new_dirid;
+ mutex_unlock(&new_root->objectid_mutex);
+
/*
* insert the directory item
*/
if (range->compress_type == BTRFS_COMPRESS_LZO) {
btrfs_set_fs_incompat(root->fs_info, COMPRESS_LZO);
+ btrfs_sysfs_feature_update(root->fs_info,
+ BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO, FEAT_INCOMPAT);
}
ret = defrag_count;
btrfs_free_path(path);
btrfs_set_fs_incompat(root->fs_info, DEFAULT_SUBVOL);
+ btrfs_sysfs_feature_update(root->fs_info,
+ BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL, FEAT_INCOMPAT);
btrfs_end_transaction(trans, root);
out:
mnt_drop_write_file(file);
return 1;
}
+static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe,
+ int index)
+{
+ return stripe * rbio->stripe_npages + index;
+}
+
+/*
+ * these are just the pages from the rbio array, not from anything
+ * the FS sent down to us
+ */
+static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe,
+ int index)
+{
+ return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)];
+}
+
/*
* helper to index into the pstripe
*/
static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
{
- index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
- return rbio->stripe_pages[index];
+ return rbio_stripe_page(rbio, rbio->nr_data, index);
}
/*
{
if (rbio->nr_data + 1 == rbio->real_stripes)
return NULL;
-
- index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
- PAGE_CACHE_SHIFT;
- return rbio->stripe_pages[index];
+ return rbio_stripe_page(rbio, rbio->nr_data + 1, index);
}
/*
{
struct btrfs_raid_bio *rbio = bio->bi_private;
int err = bio->bi_error;
+ int max_errors;
if (err)
fail_bio_stripe(rbio, bio);
err = 0;
/* OK, we have read all the stripes we need to. */
- if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+ max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
+ 0 : rbio->bbio->max_errors;
+ if (atomic_read(&rbio->error) > max_errors)
err = -EIO;
rbio_orig_end_io(rbio, err);
*/
static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
{
- unsigned long nr = stripe_len * nr_stripes;
- return DIV_ROUND_UP(nr, PAGE_CACHE_SIZE);
+ return DIV_ROUND_UP(stripe_len, PAGE_CACHE_SIZE) * nr_stripes;
}
/*
void *p;
rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
- DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8),
- GFP_NOFS);
+ DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) *
+ sizeof(long), GFP_NOFS);
if (!rbio)
return ERR_PTR(-ENOMEM);
if (!page)
return -ENOMEM;
rbio->stripe_pages[i] = page;
- ClearPageUptodate(page);
}
return 0;
}
-/* allocate pages for just the p/q stripes */
+/* only allocate pages for p/q stripes */
static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
{
int i;
struct page *page;
- i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
+ i = rbio_stripe_page_index(rbio, rbio->nr_data, 0);
for (; i < rbio->nr_pages; i++) {
if (rbio->stripe_pages[i])
}
}
-/*
- * these are just the pages from the rbio array, not from anything
- * the FS sent down to us
- */
-static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, int page)
-{
- int index;
- index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT);
- index += page;
- return rbio->stripe_pages[index];
-}
-
/*
* helper function to walk our bio list and populate the bio_pages array with
* the result. This seems expensive, but it is faster than constantly
{
struct btrfs_bio *bbio = rbio->bbio;
void *pointers[rbio->real_stripes];
- int stripe_len = rbio->stripe_len;
int nr_data = rbio->nr_data;
int stripe;
int pagenr;
int q_stripe = -1;
struct bio_list bio_list;
struct bio *bio;
- int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
int ret;
bio_list_init(&bio_list);
else
clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
- for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *p;
/* first collect one page from each data stripe */
for (stripe = 0; stripe < nr_data; stripe++) {
* everything else.
*/
for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
- for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *page;
if (stripe < rbio->nr_data) {
page = page_in_rbio(rbio, stripe, pagenr, 1);
if (!bbio->tgtdev_map[stripe])
continue;
- for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *page;
if (stripe < rbio->nr_data) {
page = page_in_rbio(rbio, stripe, pagenr, 1);
int bios_to_read = 0;
struct bio_list bio_list;
int ret;
- int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
int pagenr;
int stripe;
struct bio *bio;
* stripe
*/
for (stripe = 0; stripe < rbio->nr_data; stripe++) {
- for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *page;
/*
* we want to find all the pages missing from
int pagenr, stripe;
void **pointers;
int faila = -1, failb = -1;
- int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
struct page *page;
int err;
int i;
index_rbio_pages(rbio);
- for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
/*
* Now we just use bitmap to mark the horizontal stripes in
* which we have data when doing parity scrub.
* other endio functions will fiddle the uptodate bits
*/
if (rbio->operation == BTRFS_RBIO_WRITE) {
- for (i = 0; i < nr_pages; i++) {
+ for (i = 0; i < rbio->stripe_npages; i++) {
if (faila != -1) {
page = rbio_stripe_page(rbio, faila, i);
SetPageUptodate(page);
int bios_to_read = 0;
struct bio_list bio_list;
int ret;
- int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
int pagenr;
int stripe;
struct bio *bio;
continue;
}
- for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *p;
/*
if (!page)
return -ENOMEM;
rbio->stripe_pages[index] = page;
- ClearPageUptodate(page);
}
}
return 0;
}
-/*
- * end io function used by finish_rmw. When we finally
- * get here, we've written a full stripe
- */
-static void raid_write_parity_end_io(struct bio *bio)
-{
- struct btrfs_raid_bio *rbio = bio->bi_private;
- int err = bio->bi_error;
-
- if (bio->bi_error)
- fail_bio_stripe(rbio, bio);
-
- bio_put(bio);
-
- if (!atomic_dec_and_test(&rbio->stripes_pending))
- return;
-
- err = 0;
-
- if (atomic_read(&rbio->error))
- err = -EIO;
-
- rbio_orig_end_io(rbio, err);
-}
-
static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
int need_check)
{
break;
bio->bi_private = rbio;
- bio->bi_end_io = raid_write_parity_end_io;
+ bio->bi_end_io = raid_write_end_io;
submit_bio(WRITE, bio);
}
return;
static inline int scrub_calc_parity_bitmap_len(int nsectors)
{
- return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8);
+ return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * sizeof(long);
}
static void scrub_parity_get(struct scrub_parity *sparity)
return ret;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (em->start != chunk_offset)
goto out;
#include "dev-replace.h"
#include "free-space-cache.h"
#include "backref.h"
+#include "sysfs.h"
#include "tests/btrfs-tests.h"
#include "qgroup.h"
int ret = 0;
char *compress_type;
bool compress_force = false;
+ enum btrfs_compression_type saved_compress_type;
+ bool saved_compress_force;
+ int no_compress = 0;
cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE))
/* Fallthrough */
case Opt_compress:
case Opt_compress_type:
+ saved_compress_type = btrfs_test_opt(root, COMPRESS) ?
+ info->compress_type : BTRFS_COMPRESS_NONE;
+ saved_compress_force =
+ btrfs_test_opt(root, FORCE_COMPRESS);
if (token == Opt_compress ||
token == Opt_compress_force ||
strcmp(args[0].from, "zlib") == 0) {
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
+ no_compress = 0;
} else if (strcmp(args[0].from, "lzo") == 0) {
compress_type = "lzo";
info->compress_type = BTRFS_COMPRESS_LZO;
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
btrfs_set_fs_incompat(info, COMPRESS_LZO);
+ btrfs_sysfs_feature_update(root->fs_info,
+ BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO,
+ FEAT_INCOMPAT);
+ no_compress = 0;
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
compress_force = false;
+ no_compress++;
} else {
ret = -EINVAL;
goto out;
}
if (compress_force) {
- btrfs_set_and_info(root, FORCE_COMPRESS,
- "force %s compression",
- compress_type);
+ btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
} else {
- if (!btrfs_test_opt(root, COMPRESS))
- btrfs_info(root->fs_info,
- "btrfs: use %s compression",
- compress_type);
/*
* If we remount from compress-force=xxx to
* compress=xxx, we need clear FORCE_COMPRESS
*/
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
}
+ if ((btrfs_test_opt(root, COMPRESS) &&
+ (info->compress_type != saved_compress_type ||
+ compress_force != saved_compress_force)) ||
+ (!btrfs_test_opt(root, COMPRESS) &&
+ no_compress == 1)) {
+ btrfs_info(root->fs_info,
+ "%s %s compression",
+ (compress_force) ? "force" : "use",
+ compress_type);
+ }
+ compress_force = false;
break;
case Opt_ssd:
btrfs_set_and_info(root, SSD,
BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
+BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(mixed_backref),
BTRFS_FEAT_ATTR_PTR(raid56),
BTRFS_FEAT_ATTR_PTR(skinny_metadata),
BTRFS_FEAT_ATTR_PTR(no_holes),
+ BTRFS_FEAT_ATTR_PTR(free_space_tree),
NULL
};
return error;
}
+
+/*
+ * Change per-fs features in /sys/fs/btrfs/UUID/features to match current
+ * values in superblock. Call after any changes to incompat/compat_ro flags
+ */
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+ u64 bit, enum btrfs_feature_set set)
+{
+ struct btrfs_fs_devices *fs_devs;
+ struct kobject *fsid_kobj;
+ u64 features;
+ int ret;
+
+ if (!fs_info)
+ return;
+
+ features = get_features(fs_info, set);
+ ASSERT(bit & supported_feature_masks[set]);
+
+ fs_devs = fs_info->fs_devices;
+ fsid_kobj = &fs_devs->fsid_kobj;
+
+ if (!fsid_kobj->state_initialized)
+ return;
+
+ /*
+ * FIXME: this is too heavy to update just one value, ideally we'd like
+ * to use sysfs_update_group but some refactoring is needed first.
+ */
+ sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
+ ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group);
+}
+
static int btrfs_init_debugfs(void)
{
#ifdef CONFIG_DEBUG_FS
#define BTRFS_FEAT_ATTR_COMPAT(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature)
#define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \
- BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature)
+ BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature)
#define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature)
struct kobject *parent);
int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs);
void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+ u64 bit, enum btrfs_feature_set set);
+
#endif /* _BTRFS_SYSFS_H_ */
struct inode *inode,
struct btrfs_path *path,
struct list_head *logged_list,
- struct btrfs_log_ctx *ctx)
+ struct btrfs_log_ctx *ctx,
+ const u64 start,
+ const u64 end)
{
struct extent_map *em, *n;
struct list_head extents;
}
list_sort(NULL, &extents, extent_cmp);
-
+ /*
+ * Collect any new ordered extents within the range. This is to
+ * prevent logging file extent items without waiting for the disk
+ * location they point to being written. We do this only to deal
+ * with races against concurrent lockless direct IO writes.
+ */
+ btrfs_get_logged_extents(inode, logged_list, start, end);
process:
while (!list_empty(&extents)) {
em = list_entry(extents.next, struct extent_map, list);
goto out_unlock;
}
ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
- &logged_list, ctx);
+ &logged_list, ctx, start, end);
if (ret) {
err = ret;
goto out_unlock;
},
};
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
[BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
[BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
+ btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
struct map_lookup *map;
int i;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
u64 end;
free_extent_map(em);
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
lock_chunks(root->fs_info->chunk_root);
check_system_chunk(trans, extent_root, map->type);
unlock_chunks(root->fs_info->chunk_root);
if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
btrfs_warn(fs_info,
- "metatdata profile 0x%llx has lower redundancy than data profile 0x%llx",
+ "metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
bctl->meta.target, bctl->data.target);
}
return;
btrfs_set_fs_incompat(info, RAID56);
+ btrfs_sysfs_feature_update(info, BTRFS_FEATURE_INCOMPAT_RAID56,
+ FEAT_INCOMPAT);
}
#define BTRFS_MAX_DEVS(r) ((BTRFS_LEAF_DATA_SIZE(r) \
goto error;
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
- em->bdev = (struct block_device *)map;
+ em->map_lookup = map;
em->start = start;
em->len = num_bytes;
em->block_start = 0;
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
item_size = btrfs_chunk_item_size(map->num_stripes);
stripe_size = em->orig_block_len;
if (!em)
return 1;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
if (map->stripes[i].dev->missing) {
miss_ndevs++;
return 1;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
ret = map->num_stripes;
else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
BUG_ON(!em);
BUG_ON(em->start > logical || em->start + em->len < logical);
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
len = map->stripe_len * nr_data_stripes(map);
free_extent_map(em);
BUG_ON(!em);
BUG_ON(em->start > logical || em->start + em->len < logical);
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
ret = 1;
free_extent_map(em);
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
offset = logical - em->start;
stripe_len = map->stripe_len;
* target drive.
*/
for (i = 0; i < tmp_num_stripes; i++) {
- if (tmp_bbio->stripes[i].dev->devid == srcdev_devid) {
- /*
- * In case of DUP, in order to keep it
- * simple, only add the mirror with the
- * lowest physical address
- */
- if (found &&
- physical_of_found <=
- tmp_bbio->stripes[i].physical)
- continue;
- index_srcdev = i;
- found = 1;
- physical_of_found =
- tmp_bbio->stripes[i].physical;
- }
+ if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
+ continue;
+
+ /*
+ * In case of DUP, in order to keep it simple, only add
+ * the mirror with the lowest physical address
+ */
+ if (found &&
+ physical_of_found <= tmp_bbio->stripes[i].physical)
+ continue;
+
+ index_srcdev = i;
+ found = 1;
+ physical_of_found = tmp_bbio->stripes[i].physical;
}
- if (found) {
- mirror_num = index_srcdev + 1;
- patch_the_first_stripe_for_dev_replace = 1;
- physical_to_patch_in_first_stripe = physical_of_found;
- } else {
+ btrfs_put_bbio(tmp_bbio);
+
+ if (!found) {
WARN_ON(1);
ret = -EIO;
- btrfs_put_bbio(tmp_bbio);
goto out;
}
- btrfs_put_bbio(tmp_bbio);
+ mirror_num = index_srcdev + 1;
+ patch_the_first_stripe_for_dev_replace = 1;
+ physical_to_patch_in_first_stripe = physical_of_found;
} else if (mirror_num > map->num_stripes) {
mirror_num = 0;
}
free_extent_map(em);
return -EIO;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
length = em->len;
rmap_len = map->stripe_len;
bbio->fs_info = root->fs_info;
atomic_set(&bbio->stripes_pending, bbio->num_stripes);
- if (bbio->raid_map) {
+ if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
+ ((rw & WRITE) || (mirror_num > 1))) {
/* In this case, map_length has been set to the length of
a single stripe; not the whole write */
if (rw & WRITE) {
struct extent_map *em;
u64 logical;
u64 length;
+ u64 stripe_len;
u64 devid;
u8 uuid[BTRFS_UUID_SIZE];
int num_stripes;
logical = key->offset;
length = btrfs_chunk_length(leaf, chunk);
+ stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+ num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+ /* Validation check */
+ if (!num_stripes) {
+ btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
+ num_stripes);
+ return -EIO;
+ }
+ if (!IS_ALIGNED(logical, root->sectorsize)) {
+ btrfs_err(root->fs_info,
+ "invalid chunk logical %llu", logical);
+ return -EIO;
+ }
+ if (!length || !IS_ALIGNED(length, root->sectorsize)) {
+ btrfs_err(root->fs_info,
+ "invalid chunk length %llu", length);
+ return -EIO;
+ }
+ if (!is_power_of_2(stripe_len)) {
+ btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
+ stripe_len);
+ return -EIO;
+ }
+ if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+ btrfs_chunk_type(leaf, chunk)) {
+ btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
+ ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
+ BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+ btrfs_chunk_type(leaf, chunk));
+ return -EIO;
+ }
read_lock(&map_tree->map_tree.lock);
em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
em = alloc_extent_map();
if (!em)
return -ENOMEM;
- num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
if (!map) {
free_extent_map(em);
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
- em->bdev = (struct block_device *)map;
+ em->map_lookup = map;
em->start = logical;
em->len = length;
em->orig_start = 0;
/* In order to kick the device replace finish process */
lock_chunks(root);
list_for_each_entry(em, &transaction->pending_chunks, list) {
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
dev = map->stripes[i].dev;
projects / cascardo / linux.git / commitdiff