aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/aio.c115
-rw-r--r--fs/btrfs/check-integrity.c32
-rw-r--r--fs/btrfs/check-integrity.h2
-rw-r--r--fs/btrfs/extent-tree.c22
-rw-r--r--fs/btrfs/extent_io.c12
-rw-r--r--fs/btrfs/ioctl.c3
-rw-r--r--fs/btrfs/relocation.c81
-rw-r--r--fs/btrfs/scrub.c33
-rw-r--r--fs/btrfs/send.c4
-rw-r--r--fs/btrfs/super.c5
-rw-r--r--fs/ceph/addr.c8
-rw-r--r--fs/ceph/inode.c136
-rw-r--r--fs/dcache.c2
-rw-r--r--fs/eventpoll.c3
-rw-r--r--fs/hfsplus/wrapper.c17
-rw-r--r--fs/logfs/dev_bdev.c13
-rw-r--r--fs/namei.c7
-rw-r--r--fs/nfs/blocklayout/blocklayout.h1
-rw-r--r--fs/nfs/blocklayout/extents.c2
-rw-r--r--fs/nfs/dns_resolve.c2
-rw-r--r--fs/nfs/inode.c2
-rw-r--r--fs/nfs/internal.h15
-rw-r--r--fs/nfs/nfs4_fs.h8
-rw-r--r--fs/nfs/nfs4proc.c30
-rw-r--r--fs/nfsd/nfscache.c9
-rw-r--r--fs/proc/inode.c14
-rw-r--r--fs/pstore/platform.c7
-rw-r--r--fs/squashfs/file_direct.c5
-rw-r--r--fs/sysfs/file.c8
-rw-r--r--fs/xfs/xfs_bmap.c32
-rw-r--r--fs/xfs/xfs_bmap_util.c14
-rw-r--r--fs/xfs/xfs_buf.c37
-rw-r--r--fs/xfs/xfs_buf.h11
-rw-r--r--fs/xfs/xfs_buf_item.c21
-rw-r--r--fs/xfs/xfs_dir2_node.c26
-rw-r--r--fs/xfs/xfs_discard.c5
-rw-r--r--fs/xfs/xfs_fsops.c6
-rw-r--r--fs/xfs/xfs_ioctl.c3
-rw-r--r--fs/xfs/xfs_ioctl32.c3
-rw-r--r--fs/xfs/xfs_iops.c3
-rw-r--r--fs/xfs/xfs_log_recover.c13
-rw-r--r--fs/xfs/xfs_qm.c80
-rw-r--r--fs/xfs/xfs_trans_buf.c13
43 files changed, 493 insertions, 372 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 08159ed1364..062a5f6a144 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -244,9 +244,14 @@ static void aio_free_ring(struct kioctx *ctx)
int i;
for (i = 0; i < ctx->nr_pages; i++) {
+ struct page *page;
pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
page_count(ctx->ring_pages[i]));
- put_page(ctx->ring_pages[i]);
+ page = ctx->ring_pages[i];
+ if (!page)
+ continue;
+ ctx->ring_pages[i] = NULL;
+ put_page(page);
}
put_aio_ring_file(ctx);
@@ -280,18 +285,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
unsigned long flags;
int rc;
+ rc = 0;
+
+ /* Make sure the old page hasn't already been changed */
+ spin_lock(&mapping->private_lock);
+ ctx = mapping->private_data;
+ if (ctx) {
+ pgoff_t idx;
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ idx = old->index;
+ if (idx < (pgoff_t)ctx->nr_pages) {
+ if (ctx->ring_pages[idx] != old)
+ rc = -EAGAIN;
+ } else
+ rc = -EINVAL;
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else
+ rc = -EINVAL;
+ spin_unlock(&mapping->private_lock);
+
+ if (rc != 0)
+ return rc;
+
/* Writeback must be complete */
BUG_ON(PageWriteback(old));
- put_page(old);
+ get_page(new);
- rc = migrate_page_move_mapping(mapping, new, old, NULL, mode);
+ rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
if (rc != MIGRATEPAGE_SUCCESS) {
- get_page(old);
+ put_page(new);
return rc;
}
- get_page(new);
-
/* We can potentially race against kioctx teardown here. Use the
* address_space's private data lock to protect the mapping's
* private_data.
@@ -303,13 +328,24 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
spin_lock_irqsave(&ctx->completion_lock, flags);
migrate_page_copy(new, old);
idx = old->index;
- if (idx < (pgoff_t)ctx->nr_pages)
- ctx->ring_pages[idx] = new;
+ if (idx < (pgoff_t)ctx->nr_pages) {
+ /* And only do the move if things haven't changed */
+ if (ctx->ring_pages[idx] == old)
+ ctx->ring_pages[idx] = new;
+ else
+ rc = -EAGAIN;
+ } else
+ rc = -EINVAL;
spin_unlock_irqrestore(&ctx->completion_lock, flags);
} else
rc = -EBUSY;
spin_unlock(&mapping->private_lock);
+ if (rc == MIGRATEPAGE_SUCCESS)
+ put_page(old);
+ else
+ put_page(new);
+
return rc;
}
#endif
@@ -326,7 +362,7 @@ static int aio_setup_ring(struct kioctx *ctx)
struct aio_ring *ring;
unsigned nr_events = ctx->max_reqs;
struct mm_struct *mm = current->mm;
- unsigned long size, populate;
+ unsigned long size, unused;
int nr_pages;
int i;
struct file *file;
@@ -347,6 +383,20 @@ static int aio_setup_ring(struct kioctx *ctx)
return -EAGAIN;
}
+ ctx->aio_ring_file = file;
+ nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
+ / sizeof(struct io_event);
+
+ ctx->ring_pages = ctx->internal_pages;
+ if (nr_pages > AIO_RING_PAGES) {
+ ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
+ GFP_KERNEL);
+ if (!ctx->ring_pages) {
+ put_aio_ring_file(ctx);
+ return -ENOMEM;
+ }
+ }
+
for (i = 0; i < nr_pages; i++) {
struct page *page;
page = find_or_create_page(file->f_inode->i_mapping,
@@ -358,17 +408,14 @@ static int aio_setup_ring(struct kioctx *ctx)
SetPageUptodate(page);
SetPageDirty(page);
unlock_page(page);
+
+ ctx->ring_pages[i] = page;
}
- ctx->aio_ring_file = file;
- nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring))
- / sizeof(struct io_event);
+ ctx->nr_pages = i;
- ctx->ring_pages = ctx->internal_pages;
- if (nr_pages > AIO_RING_PAGES) {
- ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *),
- GFP_KERNEL);
- if (!ctx->ring_pages)
- return -ENOMEM;
+ if (unlikely(i != nr_pages)) {
+ aio_free_ring(ctx);
+ return -EAGAIN;
}
ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -377,9 +424,9 @@ static int aio_setup_ring(struct kioctx *ctx)
down_write(&mm->mmap_sem);
ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_POPULATE, 0, &populate);
+ MAP_SHARED, 0, &unused);
+ up_write(&mm->mmap_sem);
if (IS_ERR((void *)ctx->mmap_base)) {
- up_write(&mm->mmap_sem);
ctx->mmap_size = 0;
aio_free_ring(ctx);
return -EAGAIN;
@@ -387,27 +434,6 @@ static int aio_setup_ring(struct kioctx *ctx)
pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
- /* We must do this while still holding mmap_sem for write, as we
- * need to be protected against userspace attempting to mremap()
- * or munmap() the ring buffer.
- */
- ctx->nr_pages = get_user_pages(current, mm, ctx->mmap_base, nr_pages,
- 1, 0, ctx->ring_pages, NULL);
-
- /* Dropping the reference here is safe as the page cache will hold
- * onto the pages for us. It is also required so that page migration
- * can unmap the pages and get the right reference count.
- */
- for (i = 0; i < ctx->nr_pages; i++)
- put_page(ctx->ring_pages[i]);
-
- up_write(&mm->mmap_sem);
-
- if (unlikely(ctx->nr_pages != nr_pages)) {
- aio_free_ring(ctx);
- return -EAGAIN;
- }
-
ctx->user_id = ctx->mmap_base;
ctx->nr_events = nr_events; /* trusted copy */
@@ -645,12 +671,13 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
aio_nr + nr_events < aio_nr) {
spin_unlock(&aio_nr_lock);
err = -EAGAIN;
- goto err;
+ goto err_ctx;
}
aio_nr += ctx->max_reqs;
spin_unlock(&aio_nr_lock);
- percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+ percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */
+ percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */
err = ioctx_add_table(ctx, mm);
if (err)
@@ -662,6 +689,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
err_cleanup:
aio_nr_sub(ctx->max_reqs);
+err_ctx:
+ aio_free_ring(ctx);
err:
free_percpu(ctx->cpu);
free_percpu(ctx->reqs.pcpu_count);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b50764bef14..131d82800b3 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -333,7 +333,6 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx);
static int btrfsic_read_block(struct btrfsic_state *state,
struct btrfsic_block_data_ctx *block_ctx);
static void btrfsic_dump_database(struct btrfsic_state *state);
-static void btrfsic_complete_bio_end_io(struct bio *bio, int err);
static int btrfsic_test_for_metadata(struct btrfsic_state *state,
char **datav, unsigned int num_pages);
static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state,
@@ -1687,7 +1686,6 @@ static int btrfsic_read_block(struct btrfsic_state *state,
for (i = 0; i < num_pages;) {
struct bio *bio;
unsigned int j;
- DECLARE_COMPLETION_ONSTACK(complete);
bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i);
if (!bio) {
@@ -1698,8 +1696,6 @@ static int btrfsic_read_block(struct btrfsic_state *state,
}
bio->bi_bdev = block_ctx->dev->bdev;
bio->bi_sector = dev_bytenr >> 9;
- bio->bi_end_io = btrfsic_complete_bio_end_io;
- bio->bi_private = &complete;
for (j = i; j < num_pages; j++) {
ret = bio_add_page(bio, block_ctx->pagev[j],
@@ -1712,12 +1708,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
"btrfsic: error, failed to add a single page!\n");
return -1;
}
- submit_bio(READ, bio);
-
- /* this will also unplug the queue */
- wait_for_completion(&complete);
-
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ if (submit_bio_wait(READ, bio)) {
printk(KERN_INFO
"btrfsic: read error at logical %llu dev %s!\n",
block_ctx->start, block_ctx->dev->name);
@@ -1740,11 +1731,6 @@ static int btrfsic_read_block(struct btrfsic_state *state,
return block_ctx->len;
}
-static void btrfsic_complete_bio_end_io(struct bio *bio, int err)
-{
- complete((struct completion *)bio->bi_private);
-}
-
static void btrfsic_dump_database(struct btrfsic_state *state)
{
struct list_head *elem_all;
@@ -3008,14 +2994,12 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh)
return submit_bh(rw, bh);
}
-void btrfsic_submit_bio(int rw, struct bio *bio)
+static void __btrfsic_submit_bio(int rw, struct bio *bio)
{
struct btrfsic_dev_state *dev_state;
- if (!btrfsic_is_initialized) {
- submit_bio(rw, bio);
+ if (!btrfsic_is_initialized)
return;
- }
mutex_lock(&btrfsic_mutex);
/* since btrfsic_submit_bio() is also called before
@@ -3106,10 +3090,20 @@ void btrfsic_submit_bio(int rw, struct bio *bio)
}
leave:
mutex_unlock(&btrfsic_mutex);
+}
+void btrfsic_submit_bio(int rw, struct bio *bio)
+{
+ __btrfsic_submit_bio(rw, bio);
submit_bio(rw, bio);
}
+int btrfsic_submit_bio_wait(int rw, struct bio *bio)
+{
+ __btrfsic_submit_bio(rw, bio);
+ return submit_bio_wait(rw, bio);
+}
+
int btrfsic_mount(struct btrfs_root *root,
struct btrfs_fs_devices *fs_devices,
int including_extent_data, u32 print_mask)
diff --git a/fs/btrfs/check-integrity.h b/fs/btrfs/check-integrity.h
index 8b59175cc50..13b8566c97a 100644
--- a/fs/btrfs/check-integrity.h
+++ b/fs/btrfs/check-integrity.h
@@ -22,9 +22,11 @@
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
int btrfsic_submit_bh(int rw, struct buffer_head *bh);
void btrfsic_submit_bio(int rw, struct bio *bio);
+int btrfsic_submit_bio_wait(int rw, struct bio *bio);
#else
#define btrfsic_submit_bh submit_bh
#define btrfsic_submit_bio submit_bio
+#define btrfsic_submit_bio_wait submit_bio_wait
#endif
int btrfsic_mount(struct btrfs_root *root,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 45d98d01028..9c01509dd8a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -767,20 +767,19 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
if (!path)
return -ENOMEM;
- if (metadata) {
- key.objectid = bytenr;
- key.type = BTRFS_METADATA_ITEM_KEY;
- key.offset = offset;
- } else {
- key.objectid = bytenr;
- key.type = BTRFS_EXTENT_ITEM_KEY;
- key.offset = offset;
- }
-
if (!trans) {
path->skip_locking = 1;
path->search_commit_root = 1;
}
+
+search_again:
+ key.objectid = bytenr;
+ key.offset = offset;
+ if (metadata)
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
+
again:
ret = btrfs_search_slot(trans, root->fs_info->extent_root,
&key, path, 0, 0);
@@ -788,7 +787,6 @@ again:
goto out_free;
if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) {
- metadata = 0;
if (path->slots[0]) {
path->slots[0]--;
btrfs_item_key_to_cpu(path->nodes[0], &key,
@@ -855,7 +853,7 @@ again:
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
btrfs_put_delayed_ref(&head->node);
- goto again;
+ goto search_again;
}
if (head->extent_op && head->extent_op->update_flags)
extent_flags |= head->extent_op->flags_to_set;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 8e457fca0a0..ff43802a7c8 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1952,11 +1952,6 @@ static int free_io_failure(struct inode *inode, struct io_failure_record *rec,
return err;
}
-static void repair_io_failure_callback(struct bio *bio, int err)
-{
- complete(bio->bi_private);
-}
-
/*
* this bypasses the standard btrfs submit functions deliberately, as
* the standard behavior is to write all copies in a raid setup. here we only
@@ -1973,7 +1968,6 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
{
struct bio *bio;
struct btrfs_device *dev;
- DECLARE_COMPLETION_ONSTACK(compl);
u64 map_length = 0;
u64 sector;
struct btrfs_bio *bbio = NULL;
@@ -1990,8 +1984,6 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
- bio->bi_private = &compl;
- bio->bi_end_io = repair_io_failure_callback;
bio->bi_size = 0;
map_length = length;
@@ -2012,10 +2004,8 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
}
bio->bi_bdev = dev->bdev;
bio_add_page(bio, page, length, start - page_offset(page));
- btrfsic_submit_bio(WRITE_SYNC, bio);
- wait_for_completion(&compl);
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
/* try to remap that extent elsewhere? */
bio_put(bio);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a111622598b..21da5762b0b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2121,7 +2121,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
if (err == -EINTR)
- goto out;
+ goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -2284,6 +2284,7 @@ out_dput:
dput(dentry);
out_unlock_dir:
mutex_unlock(&dir->i_mutex);
+out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ce459a7cb16..429c73c374b 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -571,7 +571,9 @@ static int is_cowonly_root(u64 root_objectid)
root_objectid == BTRFS_CHUNK_TREE_OBJECTID ||
root_objectid == BTRFS_DEV_TREE_OBJECTID ||
root_objectid == BTRFS_TREE_LOG_OBJECTID ||
- root_objectid == BTRFS_CSUM_TREE_OBJECTID)
+ root_objectid == BTRFS_CSUM_TREE_OBJECTID ||
+ root_objectid == BTRFS_UUID_TREE_OBJECTID ||
+ root_objectid == BTRFS_QUOTA_TREE_OBJECTID)
return 1;
return 0;
}
@@ -1264,10 +1266,10 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
}
/*
- * helper to update/delete the 'address of tree root -> reloc tree'
+ * helper to delete the 'address of tree root -> reloc tree'
* mapping
*/
-static int __update_reloc_root(struct btrfs_root *root, int del)
+static void __del_reloc_root(struct btrfs_root *root)
{
struct rb_node *rb_node;
struct mapping_node *node = NULL;
@@ -1275,7 +1277,7 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
spin_lock(&rc->reloc_root_tree.lock);
rb_node = tree_search(&rc->reloc_root_tree.rb_root,
- root->commit_root->start);
+ root->node->start);
if (rb_node) {
node = rb_entry(rb_node, struct mapping_node, rb_node);
rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
@@ -1283,23 +1285,45 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
spin_unlock(&rc->reloc_root_tree.lock);
if (!node)
- return 0;
+ return;
BUG_ON((struct btrfs_root *)node->data != root);
- if (!del) {
- spin_lock(&rc->reloc_root_tree.lock);
- node->bytenr = root->node->start;
- rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
- node->bytenr, &node->rb_node);
- spin_unlock(&rc->reloc_root_tree.lock);
- if (rb_node)
- backref_tree_panic(rb_node, -EEXIST, node->bytenr);
- } else {
- spin_lock(&root->fs_info->trans_lock);
- list_del_init(&root->root_list);
- spin_unlock(&root->fs_info->trans_lock);
- kfree(node);
+ spin_lock(&root->fs_info->trans_lock);
+ list_del_init(&root->root_list);
+ spin_unlock(&root->fs_info->trans_lock);
+ kfree(node);
+}
+
+/*
+ * helper to update the 'address of tree root -> reloc tree'
+ * mapping
+ */
+static int __update_reloc_root(struct btrfs_root *root, u64 new_bytenr)
+{
+ struct rb_node *rb_node;
+ struct mapping_node *node = NULL;
+ struct reloc_control *rc = root->fs_info->reloc_ctl;
+
+ spin_lock(&rc->reloc_root_tree.lock);
+ rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+ root->node->start);
+ if (rb_node) {
+ node = rb_entry(rb_node, struct mapping_node, rb_node);
+ rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
}
+ spin_unlock(&rc->reloc_root_tree.lock);
+
+ if (!node)
+ return 0;
+ BUG_ON((struct btrfs_root *)node->data != root);
+
+ spin_lock(&rc->reloc_root_tree.lock);
+ node->bytenr = new_bytenr;
+ rb_node = tree_insert(&rc->reloc_root_tree.rb_root,
+ node->bytenr, &node->rb_node);
+ spin_unlock(&rc->reloc_root_tree.lock);
+ if (rb_node)
+ backref_tree_panic(rb_node, -EEXIST, node->bytenr);
return 0;
}
@@ -1420,7 +1444,6 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
{
struct btrfs_root *reloc_root;
struct btrfs_root_item *root_item;
- int del = 0;
int ret;
if (!root->reloc_root)
@@ -1432,11 +1455,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
if (root->fs_info->reloc_ctl->merge_reloc_tree &&
btrfs_root_refs(root_item) == 0) {
root->reloc_root = NULL;
- del = 1;
+ __del_reloc_root(reloc_root);
}
- __update_reloc_root(reloc_root, del);
-
if (reloc_root->commit_root != reloc_root->node) {
btrfs_set_root_node(root_item, reloc_root->node);
free_extent_buffer(reloc_root->commit_root);
@@ -2287,7 +2308,7 @@ void free_reloc_roots(struct list_head *list)
while (!list_empty(list)) {
reloc_root = list_entry(list->next, struct btrfs_root,
root_list);
- __update_reloc_root(reloc_root, 1);
+ __del_reloc_root(reloc_root);
free_extent_buffer(reloc_root->node);
free_extent_buffer(reloc_root->commit_root);
kfree(reloc_root);
@@ -2332,7 +2353,7 @@ again:
ret = merge_reloc_root(rc, root);
if (ret) {
- __update_reloc_root(reloc_root, 1);
+ __del_reloc_root(reloc_root);
free_extent_buffer(reloc_root->node);
free_extent_buffer(reloc_root->commit_root);
kfree(reloc_root);
@@ -2388,6 +2409,13 @@ out:
btrfs_std_error(root->fs_info, ret);
if (!list_empty(&reloc_roots))
free_reloc_roots(&reloc_roots);
+
+ /* new reloc root may be added */
+ mutex_lock(&root->fs_info->reloc_mutex);
+ list_splice_init(&rc->reloc_roots, &reloc_roots);
+ mutex_unlock(&root->fs_info->reloc_mutex);
+ if (!list_empty(&reloc_roots))
+ free_reloc_roots(&reloc_roots);
}
BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
@@ -4522,6 +4550,11 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
BUG_ON(rc->stage == UPDATE_DATA_PTRS &&
root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID);
+ if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
+ if (buf == root->node)
+ __update_reloc_root(root, cow->start);
+ }
+
level = btrfs_header_level(buf);
if (btrfs_header_generation(buf) <=
btrfs_root_last_snapshot(&root->root_item))
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 561e2f16ba3..1fd3f33c330 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -208,7 +208,6 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
int is_metadata, int have_csum,
const u8 *csum, u64 generation,
u16 csum_size);
-static void scrub_complete_bio_end_io(struct bio *bio, int err);
static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good,
int force_write);
@@ -1294,7 +1293,6 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
for (page_num = 0; page_num < sblock->page_count; page_num++) {
struct bio *bio;
struct scrub_page *page = sblock->pagev[page_num];
- DECLARE_COMPLETION_ONSTACK(complete);
if (page->dev->bdev == NULL) {
page->io_error = 1;
@@ -1311,18 +1309,11 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
}
bio->bi_bdev = page->dev->bdev;
bio->bi_sector = page->physical >> 9;
- bio->bi_end_io = scrub_complete_bio_end_io;
- bio->bi_private = &complete;
bio_add_page(bio, page->page, PAGE_SIZE, 0);
- btrfsic_submit_bio(READ, bio);
-
- /* this will also unplug the queue */
- wait_for_completion(&complete);
-
- page->io_error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (btrfsic_submit_bio_wait(READ, bio))
sblock->no_io_error_seen = 0;
+
bio_put(bio);
}
@@ -1391,11 +1382,6 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info,
sblock->checksum_error = 1;
}
-static void scrub_complete_bio_end_io(struct bio *bio, int err)
-{
- complete((struct completion *)bio->bi_private);
-}
-
static int scrub_repair_block_from_good_copy(struct scrub_block *sblock_bad,
struct scrub_block *sblock_good,
int force_write)
@@ -1430,7 +1416,6 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
sblock_bad->checksum_error || page_bad->io_error) {
struct bio *bio;
int ret;
- DECLARE_COMPLETION_ONSTACK(complete);
if (!page_bad->dev->bdev) {
printk_ratelimited(KERN_WARNING
@@ -1443,19 +1428,14 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
return -EIO;
bio->bi_bdev = page_bad->dev->bdev;
bio->bi_sector = page_bad->physical >> 9;
- bio->bi_end_io = scrub_complete_bio_end_io;
- bio->bi_private = &complete;
ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
if (PAGE_SIZE != ret) {
bio_put(bio);
return -EIO;
}
- btrfsic_submit_bio(WRITE, bio);
- /* this will also unplug the queue */
- wait_for_completion(&complete);
- if (!bio_flagged(bio, BIO_UPTODATE)) {
+ if (btrfsic_submit_bio_wait(WRITE, bio)) {
btrfs_dev_stat_inc_and_print(page_bad->dev,
BTRFS_DEV_STAT_WRITE_ERRS);
btrfs_dev_replace_stats_inc(
@@ -3375,7 +3355,6 @@ static int write_page_nocow(struct scrub_ctx *sctx,
struct bio *bio;
struct btrfs_device *dev;
int ret;
- DECLARE_COMPLETION_ONSTACK(compl);
dev = sctx->wr_ctx.tgtdev;
if (!dev)
@@ -3392,8 +3371,6 @@ static int write_page_nocow(struct scrub_ctx *sctx,
spin_unlock(&sctx->stat_lock);
return -ENOMEM;
}
- bio->bi_private = &compl;
- bio->bi_end_io = scrub_complete_bio_end_io;
bio->bi_size = 0;
bio->bi_sector = physical_for_dev_replace >> 9;
bio->bi_bdev = dev->bdev;
@@ -3404,10 +3381,8 @@ leave_with_eio:
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
return -EIO;
}
- btrfsic_submit_bio(WRITE_SYNC, bio);
- wait_for_completion(&compl);
- if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (btrfsic_submit_bio_wait(WRITE_SYNC, bio))
goto leave_with_eio;
bio_put(bio);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 6837fe87f3a..945d1db98f2 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4723,8 +4723,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
}
if (!access_ok(VERIFY_READ, arg->clone_sources,
- sizeof(*arg->clone_sources *
- arg->clone_sources_count))) {
+ sizeof(*arg->clone_sources) *
+ arg->clone_sources_count)) {
ret = -EFAULT;
goto out;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2d8ac1bf0cf..d71a11d13df 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -432,7 +432,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
} else {
printk(KERN_INFO "btrfs: setting nodatacow\n");
}
- info->compress_type = BTRFS_COMPRESS_NONE;
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
btrfs_set_opt(info->mount_opt, NODATACOW);
@@ -461,7 +460,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_set_fs_incompat(info, COMPRESS_LZO);
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
- info->compress_type = BTRFS_COMPRESS_NONE;
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
compress_force = false;
@@ -474,9 +472,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
pr_info("btrfs: force %s compression\n",
compress_type);
- } else
+ } else if (btrfs_test_opt(root, COMPRESS)) {
pr_info("btrfs: use %s compression\n",
compress_type);
+ }
break;
case Opt_ssd:
printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1e561c05953..ec3ba43b9fa 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -210,9 +210,13 @@ static int readpage_nounlock(struct file *filp, struct page *page)
if (err < 0) {
SetPageError(page);
goto out;
- } else if (err < PAGE_CACHE_SIZE) {
+ } else {
+ if (err < PAGE_CACHE_SIZE) {
/* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ } else {
+ flush_dcache_page(page);
+ }
}
SetPageUptodate(page);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9a8e396aed8..278fd289128 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -978,7 +978,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
struct ceph_mds_reply_inode *ininfo;
struct ceph_vino vino;
struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
- int i = 0;
int err = 0;
dout("fill_trace %p is_dentry %d is_target %d\n", req,
@@ -1039,6 +1038,29 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
}
}
+ if (rinfo->head->is_target) {
+ vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+ vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+
+ in = ceph_get_inode(sb, vino);
+ if (IS_ERR(in)) {
+ err = PTR_ERR(in);
+ goto done;
+ }
+ req->r_target_inode = in;
+
+ err = fill_inode(in, &rinfo->targeti, NULL,
+ session, req->r_request_started,
+ (le32_to_cpu(rinfo->head->result) == 0) ?
+ req->r_fmode : -1,
+ &req->r_caps_reservation);
+ if (err < 0) {
+ pr_err("fill_inode badness %p %llx.%llx\n",
+ in, ceph_vinop(in));
+ goto done;
+ }
+ }
+
/*
* ignore null lease/binding on snapdir ENOENT, or else we
* will have trouble splicing in the virtual snapdir later
@@ -1108,7 +1130,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
ceph_dentry(req->r_old_dentry)->offset);
dn = req->r_old_dentry; /* use old_dentry */
- in = dn->d_inode;
}
/* null dentry? */
@@ -1130,44 +1151,28 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
}
/* attach proper inode */
- ininfo = rinfo->targeti.in;
- vino.ino = le64_to_cpu(ininfo->ino);
- vino.snap = le64_to_cpu(ininfo->snapid);
- in = dn->d_inode;
- if (!in) {
- in = ceph_get_inode(sb, vino);
- if (IS_ERR(in)) {
- pr_err("fill_trace bad get_inode "
- "%llx.%llx\n", vino.ino, vino.snap);
- err = PTR_ERR(in);
- d_drop(dn);
- goto done;
- }
+ if (!dn->d_inode) {
+ ihold(in);
dn = splice_dentry(dn, in, &have_lease, true);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
goto done;
}
req->r_dentry = dn; /* may have spliced */
- ihold(in);
- } else if (ceph_ino(in) == vino.ino &&
- ceph_snap(in) == vino.snap) {
- ihold(in);
- } else {
+ } else if (dn->d_inode && dn->d_inode != in) {
dout(" %p links to %p %llx.%llx, not %llx.%llx\n",
- dn, in, ceph_ino(in), ceph_snap(in),
- vino.ino, vino.snap);
+ dn, dn->d_inode, ceph_vinop(dn->d_inode),
+ ceph_vinop(in));
have_lease = false;
- in = NULL;
}
if (have_lease)
update_dentry_lease(dn, rinfo->dlease, session,
req->r_request_started);
dout(" final dn %p\n", dn);
- i++;
- } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
- req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
+ } else if (!req->r_aborted &&
+ (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+ req->r_op == CEPH_MDS_OP_MKSNAP)) {
struct dentry *dn = req->r_dentry;
/* fill out a snapdir LOOKUPSNAP dentry */
@@ -1177,52 +1182,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
ininfo = rinfo->targeti.in;
vino.ino = le64_to_cpu(ininfo->ino);
vino.snap = le64_to_cpu(ininfo->snapid);
- in = ceph_get_inode(sb, vino);
- if (IS_ERR(in)) {
- pr_err("fill_inode get_inode badness %llx.%llx\n",
- vino.ino, vino.snap);
- err = PTR_ERR(in);
- d_delete(dn);
- goto done;
- }
dout(" linking snapped dir %p to dn %p\n", in, dn);
+ ihold(in);
dn = splice_dentry(dn, in, NULL, true);
if (IS_ERR(dn)) {
err = PTR_ERR(dn);
goto done;
}
req->r_dentry = dn; /* may have spliced */
- ihold(in);
- rinfo->head->is_dentry = 1; /* fool notrace handlers */
- }
-
- if (rinfo->head->is_target) {
- vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
- vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
-
- if (in == NULL || ceph_ino(in) != vino.ino ||
- ceph_snap(in) != vino.snap) {
- in = ceph_get_inode(sb, vino);
- if (IS_ERR(in)) {
- err = PTR_ERR(in);
- goto done;
- }
- }
- req->r_target_inode = in;
-
- err = fill_inode(in,
- &rinfo->targeti, NULL,
- session, req->r_request_started,
- (le32_to_cpu(rinfo->head->result) == 0) ?
- req->r_fmode : -1,
- &req->r_caps_reservation);
- if (err < 0) {
- pr_err("fill_inode badness %p %llx.%llx\n",
- in, ceph_vinop(in));
- goto done;
- }
}
-
done:
dout("fill_trace done err=%d\n", err);
return err;
@@ -1272,7 +1240,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
struct qstr dname;
struct dentry *dn;
struct inode *in;
- int err = 0, i;
+ int err = 0, ret, i;
struct inode *snapdir = NULL;
struct ceph_mds_request_head *rhead = req->r_request->front.iov_base;
struct ceph_dentry_info *di;
@@ -1305,6 +1273,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir);
}
+ /* FIXME: release caps/leases if error occurs */
for (i = 0; i < rinfo->dir_nr; i++) {
struct ceph_vino vino;
@@ -1329,9 +1298,10 @@ retry_lookup:
err = -ENOMEM;
goto out;
}
- err = ceph_init_dentry(dn);
- if (err < 0) {
+ ret = ceph_init_dentry(dn);
+ if (ret < 0) {
dput(dn);
+ err = ret;
goto out;
}
} else if (dn->d_inode &&
@@ -1351,9 +1321,6 @@ retry_lookup:
spin_unlock(&parent->d_lock);
}
- di = dn->d_fsdata;
- di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
-
/* inode */
if (dn->d_inode) {
in = dn->d_inode;
@@ -1366,26 +1333,39 @@ retry_lookup:
err = PTR_ERR(in);
goto out;
}
- dn = splice_dentry(dn, in, NULL, false);
- if (IS_ERR(dn))
- dn = NULL;
}
if (fill_inode(in, &rinfo->dir_in[i], NULL, session,
req->r_request_started, -1,
&req->r_caps_reservation) < 0) {
pr_err("fill_inode badness on %p\n", in);
+ if (!dn->d_inode)
+ iput(in);
+ d_drop(dn);
goto next_item;
}
- if (dn)
- update_dentry_lease(dn, rinfo->dir_dlease[i],
- req->r_session,
- req->r_request_started);
+
+ if (!dn->d_inode) {
+ dn = splice_dentry(dn, in, NULL, false);
+ if (IS_ERR(dn)) {
+ err = PTR_ERR(dn);
+ dn = NULL;
+ goto next_item;
+ }
+ }
+
+ di = dn->d_fsdata;
+ di->offset = ceph_make_fpos(frag, i + r_readdir_offset);
+
+ update_dentry_lease(dn, rinfo->dir_dlease[i],
+ req->r_session,
+ req->r_request_started);
next_item:
if (dn)
dput(dn);
}
- req->r_did_prepopulate = true;
+ if (err == 0)
+ req->r_did_prepopulate = true;
out:
if (snapdir) {
diff --git a/fs/dcache.c b/fs/dcache.c
index 4bdb300b16e..6055d61811d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -192,7 +192,7 @@ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char
if (!tcount)
return 0;
}
- mask = ~(~0ul << tcount*8);
+ mask = bytemask_from_count(tcount);
return unlikely(!!((a ^ b) & mask));
}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 79b65c3b9e8..8b5e2584c84 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1852,8 +1852,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
goto error_tgt_fput;
/* Check if EPOLLWAKEUP is allowed */
- if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
- epds.events &= ~EPOLLWAKEUP;
+ ep_take_care_of_epollwakeup(&epds);
/*
* We have to check that the file structure underneath the file descriptor
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index b51a6079108..e9a97a0d431 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -24,13 +24,6 @@ struct hfsplus_wd {
u16 embed_count;
};
-static void hfsplus_end_io_sync(struct bio *bio, int err)
-{
- if (err)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- complete(bio->bi_private);
-}
-
/*
* hfsplus_submit_bio - Perfrom block I/O
* @sb: super block of volume for I/O
@@ -53,7 +46,6 @@ static void hfsplus_end_io_sync(struct bio *bio, int err)
int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
void *buf, void **data, int rw)
{
- DECLARE_COMPLETION_ONSTACK(wait);
struct bio *bio;
int ret = 0;
u64 io_size;
@@ -73,8 +65,6 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_sector = sector;
bio->bi_bdev = sb->s_bdev;
- bio->bi_end_io = hfsplus_end_io_sync;
- bio->bi_private = &wait;
if (!(rw & WRITE) && data)
*data = (u8 *)buf + offset;
@@ -93,12 +83,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
buf = (u8 *)buf + len;
}
- submit_bio(rw, bio);
- wait_for_completion(&wait);
-
- if (!bio_flagged(bio, BIO_UPTODATE))
- ret = -EIO;
-
+ ret = submit_bio_wait(rw, bio);
out:
bio_put(bio);
return ret < 0 ? ret : 0;
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 550475ca6a0..0f95f0d0b31 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -14,16 +14,10 @@
#define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
-static void request_complete(struct bio *bio, int err)
-{
- complete((struct completion *)bio->bi_private);
-}
-
static int sync_request(struct page *page, struct block_device *bdev, int rw)
{
struct bio bio;
struct bio_vec bio_vec;
- struct completion complete;
bio_init(&bio);
bio.bi_max_vecs = 1;
@@ -35,13 +29,8 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw)
bio.bi_size = PAGE_SIZE;
bio.bi_bdev = bdev;
bio.bi_sector = page->index * (PAGE_SIZE >> 9);
- init_completion(&complete);
- bio.bi_private = &complete;
- bio.bi_end_io = request_complete;
- submit_bio(rw, &bio);
- wait_for_completion(&complete);
- return test_bit(BIO_UPTODATE, &bio.bi_flags) ? 0 : -EIO;
+ return submit_bio_wait(rw, &bio);
}
static int bdev_readpage(void *_sb, struct page *page)
diff --git a/fs/namei.c b/fs/namei.c
index c53d3a9547f..3531deebad3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1598,11 +1598,6 @@ static inline int nested_symlink(struct path *path, struct nameidata *nd)
* do a "get_unaligned()" if this helps and is sufficiently
* fast.
*
- * - Little-endian machines (so that we can generate the mask
- * of low bytes efficiently). Again, we *could* do a byte
- * swapping load on big-endian architectures if that is not
- * expensive enough to make the optimization worthless.
- *
* - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
* do not trap on the (extremely unlikely) case of a page
* crossing operation.
@@ -1646,7 +1641,7 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len)
if (!len)
goto done;
}
- mask = ~(~0ul << len*8);
+ mask = bytemask_from_count(len);
hash += mask & a;
done:
return fold_hash(hash);
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 8485978993e..9838fb02047 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -36,6 +36,7 @@
#include <linux/nfs_fs.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
+#include "../nfs4_fs.h"
#include "../pnfs.h"
#include "../netns.h"
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 9c3e117c3ed..4d016144256 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -44,7 +44,7 @@
static inline sector_t normalize(sector_t s, int base)
{
sector_t tmp = s; /* Since do_div modifies its argument */
- return s - do_div(tmp, base);
+ return s - sector_div(tmp, base);
}
static inline sector_t normalize_up(sector_t s, int base)
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index fc0f95ec735..d25f10fb492 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -46,7 +46,9 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/svcauth.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/nfs_fs.h>
+#include "nfs4_fs.h"
#include "dns_resolve.h"
#include "cache_lib.h"
#include "netns.h"
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 18ab2da4eeb..00ad1c2b217 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -312,7 +312,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags)
}
EXPORT_SYMBOL_GPL(nfs4_label_alloc);
#else
-void inline nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
+void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
struct nfs4_label *label)
{
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index bca6a3e3c49..8b5cc04a861 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -269,6 +269,21 @@ extern const u32 nfs41_maxgetdevinfo_overhead;
extern struct rpc_procinfo nfs4_procedures[];
#endif
+#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
+static inline void nfs4_label_free(struct nfs4_label *label)
+{
+ if (label) {
+ kfree(label->label);
+ kfree(label);
+ }
+ return;
+}
+#else
+static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
+static inline void nfs4_label_free(void *label) {}
+#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
+
/* proc.c */
void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 3ce79b04522..5609edc742a 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -9,6 +9,14 @@
#ifndef __LINUX_FS_NFS_NFS4_FS_H
#define __LINUX_FS_NFS_NFS4_FS_H
+#if defined(CONFIG_NFS_V4_2)
+#define NFS4_MAX_MINOR_VERSION 2
+#elif defined(CONFIG_NFS_V4_1)
+#define NFS4_MAX_MINOR_VERSION 1
+#else
+#define NFS4_MAX_MINOR_VERSION 0
+#endif
+
#if IS_ENABLED(CONFIG_NFS_V4)
#define NFS4_MAX_LOOP_ON_RECOVER (10)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 659990c0109..15052b81df4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2518,9 +2518,8 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
calldata->roc_barrier);
nfs_set_open_stateid(state, &calldata->res.stateid, 0);
renew_lease(server, calldata->timestamp);
- nfs4_close_clear_stateid_flags(state,
- calldata->arg.fmode);
break;
+ case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_BAD_STATEID:
@@ -2528,9 +2527,13 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
if (calldata->arg.fmode == 0)
break;
default:
- if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+ if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
rpc_restart_call_prepare(task);
+ goto out_release;
+ }
}
+ nfs4_close_clear_stateid_flags(state, calldata->arg.fmode);
+out_release:
nfs_release_seqid(calldata->arg.seqid);
nfs_refresh_inode(calldata->inode, calldata->res.fattr);
dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
@@ -4802,7 +4805,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
dprintk("%s ERROR %d, Reset session\n", __func__,
task->tk_status);
nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
- goto restart_call;
+ goto wait_on_recovery;
#endif /* CONFIG_NFS_V4_1 */
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
@@ -4987,11 +4990,17 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata)
trace_nfs4_delegreturn_exit(&data->args, &data->res, task->tk_status);
switch (task->tk_status) {
- case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_EXPIRED:
case 0:
renew_lease(data->res.server, data->timestamp);
break;
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_BAD_STATEID:
+ case -NFS4ERR_OLD_STATEID:
+ case -NFS4ERR_STALE_STATEID:
+ case -NFS4ERR_EXPIRED:
+ task->tk_status = 0;
+ break;
default:
if (nfs4_async_handle_error(task, data->res.server, NULL) ==
-EAGAIN) {
@@ -7589,7 +7598,14 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
return;
server = NFS_SERVER(lrp->args.inode);
- if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+ switch (task->tk_status) {
+ default:
+ task->tk_status = 0;
+ case 0:
+ break;
+ case -NFS4ERR_DELAY:
+ if (nfs4_async_handle_error(task, server, NULL) != -EAGAIN)
+ break;
rpc_restart_call_prepare(task);
return;
}
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 9186c7ce0b1..b6af150c96b 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -132,6 +132,13 @@ nfsd_reply_cache_alloc(void)
}
static void
+nfsd_reply_cache_unhash(struct svc_cacherep *rp)
+{
+ hlist_del_init(&rp->c_hash);
+ list_del_init(&rp->c_lru);
+}
+
+static void
nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
{
if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) {
@@ -417,7 +424,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
if (nfsd_cache_entry_expired(rp) ||
num_drc_entries >= max_drc_entries) {
- lru_put_end(rp);
+ nfsd_reply_cache_unhash(rp);
prune_cache_entries();
goto search_cache;
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 28955d4b721..124fc43c709 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -292,16 +292,20 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
{
struct proc_dir_entry *pde = PDE(file_inode(file));
unsigned long rv = -EIO;
- unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
- unsigned long, unsigned long) = NULL;
+
if (use_pde(pde)) {
+ typeof(proc_reg_get_unmapped_area) *get_area;
+
+ get_area = pde->proc_fops->get_unmapped_area;
#ifdef CONFIG_MMU
- get_area = current->mm->get_unmapped_area;
+ if (!get_area)
+ get_area = current->mm->get_unmapped_area;
#endif
- if (pde->proc_fops->get_unmapped_area)
- get_area = pde->proc_fops->get_unmapped_area;
+
if (get_area)
rv = get_area(file, orig_addr, len, pgoff, flags);
+ else
+ rv = orig_addr;
unuse_pde(pde);
}
return rv;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index b8e93a40a5d..78c3c209778 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -443,8 +443,11 @@ int pstore_register(struct pstore_info *psi)
pstore_get_records(0);
kmsg_dump_register(&pstore_dumper);
- pstore_register_console();
- pstore_register_ftrace();
+
+ if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
+ pstore_register_console();
+ pstore_register_ftrace();
+ }
if (pstore_update_ms >= 0) {
pstore_timer.expires = jiffies +
diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c
index 2943b2bfae4..62a0de6632e 100644
--- a/fs/squashfs/file_direct.c
+++ b/fs/squashfs/file_direct.c
@@ -84,6 +84,9 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
*/
res = squashfs_read_cache(target_page, block, bsize, pages,
page);
+ if (res < 0)
+ goto mark_errored;
+
goto out;
}
@@ -119,7 +122,7 @@ mark_errored:
* dealt with by the caller
*/
for (i = 0; i < pages; i++) {
- if (page[i] == target_page)
+ if (page[i] == NULL || page[i] == target_page)
continue;
flush_dcache_page(page[i]);
SetPageError(page[i]);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b94f9368509..35e7d08fe62 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -609,7 +609,7 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
struct sysfs_open_file *of;
- bool has_read, has_write, has_mmap;
+ bool has_read, has_write;
int error = -EACCES;
/* need attr_sd for attr and ops, its parent for kobj */
@@ -621,7 +621,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
has_read = battr->read || battr->mmap;
has_write = battr->write || battr->mmap;
- has_mmap = battr->mmap;
} else {
const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
@@ -633,7 +632,6 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
has_read = ops->show;
has_write = ops->store;
- has_mmap = false;
}
/* check perms and supported operations */
@@ -661,9 +659,9 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
* open file has a separate mutex, it's okay as long as those don't
* happen on the same file. At this point, we can't easily give
* each file a separate locking class. Let's differentiate on
- * whether the file has mmap or not for now.
+ * whether the file is bin or not for now.
*/
- if (has_mmap)
+ if (sysfs_is_bin(attr_sd))
mutex_init(&of->mutex);
else
mutex_init(&of->mutex);
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 3ef11b22e75..3b2c14b6f0f 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1635,7 +1635,7 @@ xfs_bmap_last_extent(
* blocks at the end of the file which do not start at the previous data block,
* we will try to align the new blocks at stripe unit boundaries.
*
- * Returns 0 in bma->aeof if the file (fork) is empty as any new write will be
+ * Returns 1 in bma->aeof if the file (fork) is empty as any new write will be
* at, or past the EOF.
*/
STATIC int
@@ -1650,9 +1650,14 @@ xfs_bmap_isaeof(
bma->aeof = 0;
error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec,
&is_empty);
- if (error || is_empty)
+ if (error)
return error;
+ if (is_empty) {
+ bma->aeof = 1;
+ return 0;
+ }
+
/*
* Check if we are allocation or past the last extent, or at least into
* the last delayed allocated extent.
@@ -3643,10 +3648,19 @@ xfs_bmap_btalloc(
int isaligned;
int tryagain;
int error;
+ int stripe_align;
ASSERT(ap->length);
mp = ap->ip->i_mount;
+
+ /* stripe alignment for allocation is determined by mount parameters */
+ stripe_align = 0;
+ if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
+ stripe_align = mp->m_swidth;
+ else if (mp->m_dalign)
+ stripe_align = mp->m_dalign;
+
align = ap->userdata ? xfs_get_extsz_hint(ap->ip) : 0;
if (unlikely(align)) {
error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
@@ -3655,6 +3669,8 @@ xfs_bmap_btalloc(
ASSERT(!error);
ASSERT(ap->length);
}
+
+
nullfb = *ap->firstblock == NULLFSBLOCK;
fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
if (nullfb) {
@@ -3730,7 +3746,7 @@ xfs_bmap_btalloc(
*/
if (!ap->flist->xbf_low && ap->aeof) {
if (!ap->offset) {
- args.alignment = mp->m_dalign;
+ args.alignment = stripe_align;
atype = args.type;
isaligned = 1;
/*
@@ -3755,13 +3771,13 @@ xfs_bmap_btalloc(
* of minlen+alignment+slop doesn't go up
* between the calls.
*/
- if (blen > mp->m_dalign && blen <= args.maxlen)
- nextminlen = blen - mp->m_dalign;
+ if (blen > stripe_align && blen <= args.maxlen)
+ nextminlen = blen - stripe_align;
else
nextminlen = args.minlen;
- if (nextminlen + mp->m_dalign > args.minlen + 1)
+ if (nextminlen + stripe_align > args.minlen + 1)
args.minalignslop =
- nextminlen + mp->m_dalign -
+ nextminlen + stripe_align -
args.minlen - 1;
else
args.minalignslop = 0;
@@ -3783,7 +3799,7 @@ xfs_bmap_btalloc(
*/
args.type = atype;
args.fsbno = ap->blkno;
- args.alignment = mp->m_dalign;
+ args.alignment = stripe_align;
args.minlen = nextminlen;
args.minalignslop = 0;
isaligned = 1;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5887e41c032..1394106ed22 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1187,7 +1187,12 @@ xfs_zero_remaining_bytes(
XFS_BUF_UNWRITE(bp);
XFS_BUF_READ(bp);
XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
- xfsbdstrat(mp, bp);
+
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ error = XFS_ERROR(EIO);
+ break;
+ }
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
@@ -1200,7 +1205,12 @@ xfs_zero_remaining_bytes(
XFS_BUF_UNDONE(bp);
XFS_BUF_UNREAD(bp);
XFS_BUF_WRITE(bp);
- xfsbdstrat(mp, bp);
+
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ error = XFS_ERROR(EIO);
+ break;
+ }
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index c7f0b77dcb0..afe7645e4b2 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -698,7 +698,11 @@ xfs_buf_read_uncached(
bp->b_flags |= XBF_READ;
bp->b_ops = ops;
- xfsbdstrat(target->bt_mount, bp);
+ if (XFS_FORCED_SHUTDOWN(target->bt_mount)) {
+ xfs_buf_relse(bp);
+ return NULL;
+ }
+ xfs_buf_iorequest(bp);
xfs_buf_iowait(bp);
return bp;
}
@@ -1089,7 +1093,7 @@ xfs_bioerror(
* This is meant for userdata errors; metadata bufs come with
* iodone functions attached, so that we can track down errors.
*/
-STATIC int
+int
xfs_bioerror_relse(
struct xfs_buf *bp)
{
@@ -1152,7 +1156,7 @@ xfs_bwrite(
ASSERT(xfs_buf_islocked(bp));
bp->b_flags |= XBF_WRITE;
- bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
+ bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL);
xfs_bdstrat_cb(bp);
@@ -1164,25 +1168,6 @@ xfs_bwrite(
return error;
}
-/*
- * Wrapper around bdstrat so that we can stop data from going to disk in case
- * we are shutting down the filesystem. Typically user data goes thru this
- * path; one of the exceptions is the superblock.
- */
-void
-xfsbdstrat(
- struct xfs_mount *mp,
- struct xfs_buf *bp)
-{
- if (XFS_FORCED_SHUTDOWN(mp)) {
- trace_xfs_bdstrat_shut(bp, _RET_IP_);
- xfs_bioerror_relse(bp);
- return;
- }
-
- xfs_buf_iorequest(bp);
-}
-
STATIC void
_xfs_buf_ioend(
xfs_buf_t *bp,
@@ -1516,6 +1501,12 @@ xfs_wait_buftarg(
struct xfs_buf *bp;
bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
list_del_init(&bp->b_lru);
+ if (bp->b_flags & XBF_WRITE_FAIL) {
+ xfs_alert(btp->bt_mount,
+"Corruption Alert: Buffer at block 0x%llx had permanent write failures!\n"
+"Please run xfs_repair to determine the extent of the problem.",
+ (long long)bp->b_bn);
+ }
xfs_buf_rele(bp);
}
if (loop++ != 0)
@@ -1799,7 +1790,7 @@ __xfs_buf_delwri_submit(
blk_start_plug(&plug);
list_for_each_entry_safe(bp, n, io_list, b_list) {
- bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+ bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
bp->b_flags |= XBF_WRITE;
if (!wait) {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index e6568336101..1cf21a4a9f2 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -45,6 +45,7 @@ typedef enum {
#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */
+#define XBF_WRITE_FAIL (1 << 24)/* async writes have failed on this buffer */
/* I/O hints for the BIO layer */
#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */
@@ -70,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t;
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
{ XBF_STALE, "STALE" }, \
+ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \
{ XBF_SYNCIO, "SYNCIO" }, \
{ XBF_FUA, "FUA" }, \
{ XBF_FLUSH, "FLUSH" }, \
@@ -80,6 +82,7 @@ typedef unsigned int xfs_buf_flags_t;
{ _XBF_DELWRI_Q, "DELWRI_Q" }, \
{ _XBF_COMPOUND, "COMPOUND" }
+
/*
* Internal state flags.
*/
@@ -269,9 +272,6 @@ extern void xfs_buf_unlock(xfs_buf_t *);
/* Buffer Read and Write Routines */
extern int xfs_bwrite(struct xfs_buf *bp);
-
-extern void xfsbdstrat(struct xfs_mount *, struct xfs_buf *);
-
extern void xfs_buf_ioend(xfs_buf_t *, int);
extern void xfs_buf_ioerror(xfs_buf_t *, int);
extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
@@ -282,6 +282,8 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
#define xfs_buf_zero(bp, off, len) \
xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO)
+extern int xfs_bioerror_relse(struct xfs_buf *);
+
static inline int xfs_buf_geterror(xfs_buf_t *bp)
{
return bp ? bp->b_error : ENOMEM;
@@ -301,7 +303,8 @@ extern void xfs_buf_terminate(void);
#define XFS_BUF_ZEROFLAGS(bp) \
((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
- XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
+ XBF_SYNCIO|XBF_FUA|XBF_FLUSH| \
+ XBF_WRITE_FAIL))
void xfs_buf_stale(struct xfs_buf *bp);
#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a64f67ba25d..2227b9b050b 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -496,6 +496,14 @@ xfs_buf_item_unpin(
}
}
+/*
+ * Buffer IO error rate limiting. Limit it to no more than 10 messages per 30
+ * seconds so as to not spam logs too much on repeated detection of the same
+ * buffer being bad..
+ */
+
+DEFINE_RATELIMIT_STATE(xfs_buf_write_fail_rl_state, 30 * HZ, 10);
+
STATIC uint
xfs_buf_item_push(
struct xfs_log_item *lip,
@@ -524,6 +532,14 @@ xfs_buf_item_push(
trace_xfs_buf_item_push(bip);
+ /* has a previous flush failed due to IO errors? */
+ if ((bp->b_flags & XBF_WRITE_FAIL) &&
+ ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS:")) {
+ xfs_warn(bp->b_target->bt_mount,
+"Detected failing async write on buffer block 0x%llx. Retrying async write.\n",
+ (long long)bp->b_bn);
+ }
+
if (!xfs_buf_delwri_queue(bp, buffer_list))
rval = XFS_ITEM_FLUSHING;
xfs_buf_unlock(bp);
@@ -1096,8 +1112,9 @@ xfs_buf_iodone_callbacks(
xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
- if (!XFS_BUF_ISSTALE(bp)) {
- bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+ if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
+ bp->b_flags |= XBF_WRITE | XBF_ASYNC |
+ XBF_DONE | XBF_WRITE_FAIL;
xfs_buf_iorequest(bp);
} else {
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index 56369d4509d..48c7d18f68c 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -2067,12 +2067,12 @@ xfs_dir2_node_lookup(
*/
int /* error */
xfs_dir2_node_removename(
- xfs_da_args_t *args) /* operation arguments */
+ struct xfs_da_args *args) /* operation arguments */
{
- xfs_da_state_blk_t *blk; /* leaf block */
+ struct xfs_da_state_blk *blk; /* leaf block */
int error; /* error return value */
int rval; /* operation return value */
- xfs_da_state_t *state; /* btree cursor */
+ struct xfs_da_state *state; /* btree cursor */
trace_xfs_dir2_node_removename(args);
@@ -2084,19 +2084,18 @@ xfs_dir2_node_removename(
state->mp = args->dp->i_mount;
state->blocksize = state->mp->m_dirblksize;
state->node_ents = state->mp->m_dir_node_ents;
- /*
- * Look up the entry we're deleting, set up the cursor.
- */
+
+ /* Look up the entry we're deleting, set up the cursor. */
error = xfs_da3_node_lookup_int(state, &rval);
if (error)
- rval = error;
- /*
- * Didn't find it, upper layer screwed up.
- */
+ goto out_free;
+
+ /* Didn't find it, upper layer screwed up. */
if (rval != EEXIST) {
- xfs_da_state_free(state);
- return rval;
+ error = rval;
+ goto out_free;
}
+
blk = &state->path.blk[state->path.active - 1];
ASSERT(blk->magic == XFS_DIR2_LEAFN_MAGIC);
ASSERT(state->extravalid);
@@ -2107,7 +2106,7 @@ xfs_dir2_node_removename(
error = xfs_dir2_leafn_remove(args, blk->bp, blk->index,
&state->extrablk, &rval);
if (error)
- return error;
+ goto out_free;
/*
* Fix the hash values up the btree.
*/
@@ -2122,6 +2121,7 @@ xfs_dir2_node_removename(
*/
if (!error)
error = xfs_dir2_node_to_leaf(state);
+out_free:
xfs_da_state_free(state);
return error;
}
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 8367d6dc18c..4f11ef01113 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -157,7 +157,7 @@ xfs_ioc_trim(
struct xfs_mount *mp,
struct fstrim_range __user *urange)
{
- struct request_queue *q = mp->m_ddev_targp->bt_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(mp->m_ddev_targp->bt_bdev);
unsigned int granularity = q->limits.discard_granularity;
struct fstrim_range range;
xfs_daddr_t start, end, minlen;
@@ -180,7 +180,8 @@ xfs_ioc_trim(
* matter as trimming blocks is an advisory interface.
*/
if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
- range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)))
+ range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp)) ||
+ range.len < mp->m_sb.sb_blocksize)
return -XFS_ERROR(EINVAL);
start = BTOBB(range.start);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a6e54b3319b..02fb943cbf2 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -220,6 +220,8 @@ xfs_growfs_data_private(
*/
nfree = 0;
for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
+ __be32 *agfl_bno;
+
/*
* AG freespace header block
*/
@@ -279,8 +281,10 @@ xfs_growfs_data_private(
agfl->agfl_seqno = cpu_to_be32(agno);
uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_uuid);
}
+
+ agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++)
- agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+ agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 4d613401a5e..33ad9a77791 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -442,7 +442,8 @@ xfs_attrlist_by_handle(
return -XFS_ERROR(EPERM);
if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
return -XFS_ERROR(EFAULT);
- if (al_hreq.buflen > XATTR_LIST_MAX)
+ if (al_hreq.buflen < sizeof(struct attrlist) ||
+ al_hreq.buflen > XATTR_LIST_MAX)
return -XFS_ERROR(EINVAL);
/*
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index e8fb1231db8..a7992f8de9d 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -356,7 +356,8 @@ xfs_compat_attrlist_by_handle(
if (copy_from_user(&al_hreq, arg,
sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
return -XFS_ERROR(EFAULT);
- if (al_hreq.buflen > XATTR_LIST_MAX)
+ if (al_hreq.buflen < sizeof(struct attrlist) ||
+ al_hreq.buflen > XATTR_LIST_MAX)
return -XFS_ERROR(EINVAL);
/*
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 27e0e544e96..104455b8046 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -618,7 +618,8 @@ xfs_setattr_nonsize(
}
if (!gid_eq(igid, gid)) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
- ASSERT(!XFS_IS_PQUOTA_ON(mp));
+ ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
+ !XFS_IS_PQUOTA_ON(mp));
ASSERT(mask & ATTR_GID);
ASSERT(gdqp);
olddquot2 = xfs_qm_vop_chown(tp, ip,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b6b669df40f..eae16920655 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -193,7 +193,10 @@ xlog_bread_noalign(
bp->b_io_length = nbblks;
bp->b_error = 0;
- xfsbdstrat(log->l_mp, bp);
+ if (XFS_FORCED_SHUTDOWN(log->l_mp))
+ return XFS_ERROR(EIO);
+
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error)
xfs_buf_ioerror_alert(bp, __func__);
@@ -4397,7 +4400,13 @@ xlog_do_recover(
XFS_BUF_READ(bp);
XFS_BUF_UNASYNC(bp);
bp->b_ops = &xfs_sb_buf_ops;
- xfsbdstrat(log->l_mp, bp);
+
+ if (XFS_FORCED_SHUTDOWN(log->l_mp)) {
+ xfs_buf_relse(bp);
+ return XFS_ERROR(EIO);
+ }
+
+ xfs_buf_iorequest(bp);
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp, __func__);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 14a4996cfec..dd88f0e27bd 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -134,8 +134,6 @@ xfs_qm_dqpurge(
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
- struct xfs_dquot *gdqp = NULL;
- struct xfs_dquot *pdqp = NULL;
xfs_dqlock(dqp);
if ((dqp->dq_flags & XFS_DQ_FREEING) || dqp->q_nrefs != 0) {
@@ -143,21 +141,6 @@ xfs_qm_dqpurge(
return EAGAIN;
}
- /*
- * If this quota has a hint attached, prepare for releasing it now.
- */
- gdqp = dqp->q_gdquot;
- if (gdqp) {
- xfs_dqlock(gdqp);
- dqp->q_gdquot = NULL;
- }
-
- pdqp = dqp->q_pdquot;
- if (pdqp) {
- xfs_dqlock(pdqp);
- dqp->q_pdquot = NULL;
- }
-
dqp->dq_flags |= XFS_DQ_FREEING;
xfs_dqflock(dqp);
@@ -206,11 +189,47 @@ xfs_qm_dqpurge(
XFS_STATS_DEC(xs_qm_dquot_unused);
xfs_qm_dqdestroy(dqp);
+ return 0;
+}
+
+/*
+ * Release the group or project dquot pointers the user dquots maybe carrying
+ * around as a hint, and proceed to purge the user dquot cache if requested.
+*/
+STATIC int
+xfs_qm_dqpurge_hints(
+ struct xfs_dquot *dqp,
+ void *data)
+{
+ struct xfs_dquot *gdqp = NULL;
+ struct xfs_dquot *pdqp = NULL;
+ uint flags = *((uint *)data);
+
+ xfs_dqlock(dqp);
+ if (dqp->dq_flags & XFS_DQ_FREEING) {
+ xfs_dqunlock(dqp);
+ return EAGAIN;
+ }
+
+ /* If this quota has a hint attached, prepare for releasing it now */
+ gdqp = dqp->q_gdquot;
+ if (gdqp)
+ dqp->q_gdquot = NULL;
+
+ pdqp = dqp->q_pdquot;
+ if (pdqp)
+ dqp->q_pdquot = NULL;
+
+ xfs_dqunlock(dqp);
if (gdqp)
- xfs_qm_dqput(gdqp);
+ xfs_qm_dqrele(gdqp);
if (pdqp)
- xfs_qm_dqput(pdqp);
+ xfs_qm_dqrele(pdqp);
+
+ if (flags & XFS_QMOPT_UQUOTA)
+ return xfs_qm_dqpurge(dqp, NULL);
+
return 0;
}
@@ -222,8 +241,18 @@ xfs_qm_dqpurge_all(
struct xfs_mount *mp,
uint flags)
{
- if (flags & XFS_QMOPT_UQUOTA)
- xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
+ /*
+ * We have to release group/project dquot hint(s) from the user dquot
+ * at first if they are there, otherwise we would run into an infinite
+ * loop while walking through radix tree to purge other type of dquots
+ * since their refcount is not zero if the user dquot refers to them
+ * as hint.
+ *
+ * Call the special xfs_qm_dqpurge_hints() will end up go through the
+ * general xfs_qm_dqpurge() against user dquot cache if requested.
+ */
+ xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags);
+
if (flags & XFS_QMOPT_GQUOTA)
xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_PQUOTA)
@@ -2082,24 +2111,21 @@ xfs_qm_vop_create_dqattach(
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(XFS_IS_QUOTA_RUNNING(mp));
- if (udqp) {
+ if (udqp && XFS_IS_UQUOTA_ON(mp)) {
ASSERT(ip->i_udquot == NULL);
- ASSERT(XFS_IS_UQUOTA_ON(mp));
ASSERT(ip->i_d.di_uid == be32_to_cpu(udqp->q_core.d_id));
ip->i_udquot = xfs_qm_dqhold(udqp);
xfs_trans_mod_dquot(tp, udqp, XFS_TRANS_DQ_ICOUNT, 1);
}
- if (gdqp) {
+ if (gdqp && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(ip->i_gdquot == NULL);
- ASSERT(XFS_IS_GQUOTA_ON(mp));
ASSERT(ip->i_d.di_gid == be32_to_cpu(gdqp->q_core.d_id));
ip->i_gdquot = xfs_qm_dqhold(gdqp);
xfs_trans_mod_dquot(tp, gdqp, XFS_TRANS_DQ_ICOUNT, 1);
}
- if (pdqp) {
+ if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
ASSERT(ip->i_pdquot == NULL);
- ASSERT(XFS_IS_PQUOTA_ON(mp));
ASSERT(xfs_get_projid(ip) == be32_to_cpu(pdqp->q_core.d_id));
ip->i_pdquot = xfs_qm_dqhold(pdqp);
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index c035d11b773..647b6f1d892 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -314,7 +314,18 @@ xfs_trans_read_buf_map(
ASSERT(bp->b_iodone == NULL);
XFS_BUF_READ(bp);
bp->b_ops = ops;
- xfsbdstrat(tp->t_mountp, bp);
+
+ /*
+ * XXX(hch): clean up the error handling here to be less
+ * of a mess..
+ */
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ trace_xfs_bdstrat_shut(bp, _RET_IP_);
+ xfs_bioerror_relse(bp);
+ } else {
+ xfs_buf_iorequest(bp);
+ }
+
error = xfs_buf_iowait(bp);
if (error) {
xfs_buf_ioerror_alert(bp, __func__);