summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/aio.c52
-rw-r--r--fs/btrfs/async-thread.c25
-rw-r--r--fs/btrfs/async-thread.h2
-rw-r--r--fs/btrfs/dev-replace.c5
-rw-r--r--fs/btrfs/disk-io.c9
-rw-r--r--fs/btrfs/disk-io.h13
-rw-r--r--fs/btrfs/extent_io.c22
-rw-r--r--fs/btrfs/inode.c3
-rw-r--r--fs/btrfs/relocation.c2
-rw-r--r--fs/btrfs/root-tree.c8
-rw-r--r--fs/btrfs/transaction.c7
-rw-r--r--fs/btrfs/volumes.c7
-rw-r--r--fs/buffer.c14
-rw-r--r--fs/cifs/cifsfs.c6
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h5
-rw-r--r--fs/cifs/cifspdu.h52
-rw-r--r--fs/cifs/cifssmb.c41
-rw-r--r--fs/cifs/file.c8
-rw-r--r--fs/cifs/fscache.c7
-rw-r--r--fs/cifs/fscache.h13
-rw-r--r--fs/cifs/inode.c45
-rw-r--r--fs/cifs/netmisc.c4
-rw-r--r--fs/cifs/readdir.c3
-rw-r--r--fs/cifs/sess.c88
-rw-r--r--fs/cifs/smb2pdu.c6
-rw-r--r--fs/cifs/smbfsctl.h14
-rw-r--r--fs/cifs/transport.c9
-rw-r--r--fs/dcache.c20
-rw-r--r--fs/ecryptfs/crypto.c2
-rw-r--r--fs/ecryptfs/keystore.c3
-rw-r--r--fs/eventpoll.c4
-rw-r--r--fs/ext3/namei.c5
-rw-r--r--fs/ext4/inode.c2
-rw-r--r--fs/ext4/namei.c5
-rw-r--r--fs/ext4/xattr.c2
-rw-r--r--fs/file_table.c4
-rw-r--r--fs/fuse/dir.c20
-rw-r--r--fs/fuse/file.c23
-rw-r--r--fs/fuse/fuse_i.h2
-rw-r--r--fs/jfs/jfs_inode.c3
-rw-r--r--fs/namei.c3
-rw-r--r--fs/proc/inode.c10
-rw-r--r--fs/proc/task_mmu.c4
-rw-r--r--fs/select.c3
-rw-r--r--fs/seq_file.c2
-rw-r--r--fs/statfs.c2
-rw-r--r--fs/super.c4
-rw-r--r--fs/sysfs/Makefile3
-rw-r--r--fs/sysfs/bin.c502
-rw-r--r--fs/sysfs/dir.c350
-rw-r--r--fs/sysfs/file.c872
-rw-r--r--fs/sysfs/group.c33
-rw-r--r--fs/sysfs/inode.c30
-rw-r--r--fs/sysfs/symlink.c50
-rw-r--r--fs/sysfs/sysfs.h71
-rw-r--r--fs/xfs/xfs_dir2_block.c6
-rw-r--r--fs/xfs/xfs_dir2_format.h51
-rw-r--r--fs/xfs/xfs_dir2_readdir.c4
-rw-r--r--fs/xfs/xfs_dir2_sf.c6
-rw-r--r--fs/xfs/xfs_dquot.c19
-rw-r--r--fs/xfs/xfs_log_recover.c1
62 files changed, 1301 insertions, 1292 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 6b868f0e0c4c..067e3d340c35 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -167,10 +167,25 @@ static int __init aio_setup(void)
}
__initcall(aio_setup);
+static void put_aio_ring_file(struct kioctx *ctx)
+{
+ struct file *aio_ring_file = ctx->aio_ring_file;
+ if (aio_ring_file) {
+ truncate_setsize(aio_ring_file->f_inode, 0);
+
+ /* Prevent further access to the kioctx from migratepages */
+ spin_lock(&aio_ring_file->f_inode->i_mapping->private_lock);
+ aio_ring_file->f_inode->i_mapping->private_data = NULL;
+ ctx->aio_ring_file = NULL;
+ spin_unlock(&aio_ring_file->f_inode->i_mapping->private_lock);
+
+ fput(aio_ring_file);
+ }
+}
+
static void aio_free_ring(struct kioctx *ctx)
{
int i;
- struct file *aio_ring_file = ctx->aio_ring_file;
for (i = 0; i < ctx->nr_pages; i++) {
pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
@@ -178,14 +193,10 @@ static void aio_free_ring(struct kioctx *ctx)
put_page(ctx->ring_pages[i]);
}
+ put_aio_ring_file(ctx);
+
if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
kfree(ctx->ring_pages);
-
- if (aio_ring_file) {
- truncate_setsize(aio_ring_file->f_inode, 0);
- fput(aio_ring_file);
- ctx->aio_ring_file = NULL;
- }
}
static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma)
@@ -207,9 +218,8 @@ static int aio_set_page_dirty(struct page *page)
static int aio_migratepage(struct address_space *mapping, struct page *new,
struct page *old, enum migrate_mode mode)
{
- struct kioctx *ctx = mapping->private_data;
+ struct kioctx *ctx;
unsigned long flags;
- unsigned idx = old->index;
int rc;
/* Writeback must be complete */
@@ -224,10 +234,23 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
get_page(new);
- spin_lock_irqsave(&ctx->completion_lock, flags);
- migrate_page_copy(new, old);
- ctx->ring_pages[idx] = new;
- spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ /* We can potentially race against kioctx teardown here. Use the
+ * address_space's private data lock to protect the mapping's
+ * private_data.
+ */
+ spin_lock(&mapping->private_lock);
+ ctx = mapping->private_data;
+ if (ctx) {
+ pgoff_t idx;
+ 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;
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ } else
+ rc = -EBUSY;
+ spin_unlock(&mapping->private_lock);
return rc;
}
@@ -617,8 +640,7 @@ out_freepcpu:
out_freeref:
free_percpu(ctx->users.pcpu_count);
out_freectx:
- if (ctx->aio_ring_file)
- fput(ctx->aio_ring_file);
+ put_aio_ring_file(ctx);
kmem_cache_free(kioctx_cachep, ctx);
pr_debug("error allocating ioctx %d\n", err);
return ERR_PTR(err);
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 58b7d14b08ee..08cc08f037a6 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -107,7 +107,8 @@ static void check_idle_worker(struct btrfs_worker_thread *worker)
worker->idle = 1;
/* the list may be empty if the worker is just starting */
- if (!list_empty(&worker->worker_list)) {
+ if (!list_empty(&worker->worker_list) &&
+ !worker->workers->stopping) {
list_move(&worker->worker_list,
&worker->workers->idle_list);
}
@@ -127,7 +128,8 @@ static void check_busy_worker(struct btrfs_worker_thread *worker)
spin_lock_irqsave(&worker->workers->lock, flags);
worker->idle = 0;
- if (!list_empty(&worker->worker_list)) {
+ if (!list_empty(&worker->worker_list) &&
+ !worker->workers->stopping) {
list_move_tail(&worker->worker_list,
&worker->workers->worker_list);
}
@@ -412,6 +414,7 @@ void btrfs_stop_workers(struct btrfs_workers *workers)
int can_stop;
spin_lock_irq(&workers->lock);
+ workers->stopping = 1;
list_splice_init(&workers->idle_list, &workers->worker_list);
while (!list_empty(&workers->worker_list)) {
cur = workers->worker_list.next;
@@ -455,6 +458,7 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
workers->ordered = 0;
workers->atomic_start_pending = 0;
workers->atomic_worker_start = async_helper;
+ workers->stopping = 0;
}
/*
@@ -480,15 +484,19 @@ static int __btrfs_start_workers(struct btrfs_workers *workers)
atomic_set(&worker->num_pending, 0);
atomic_set(&worker->refs, 1);
worker->workers = workers;
- worker->task = kthread_run(worker_loop, worker,
- "btrfs-%s-%d", workers->name,
- workers->num_workers + 1);
+ worker->task = kthread_create(worker_loop, worker,
+ "btrfs-%s-%d", workers->name,
+ workers->num_workers + 1);
if (IS_ERR(worker->task)) {
ret = PTR_ERR(worker->task);
- kfree(worker);
goto fail;
}
+
spin_lock_irq(&workers->lock);
+ if (workers->stopping) {
+ spin_unlock_irq(&workers->lock);
+ goto fail_kthread;
+ }
list_add_tail(&worker->worker_list, &workers->idle_list);
worker->idle = 1;
workers->num_workers++;
@@ -496,8 +504,13 @@ static int __btrfs_start_workers(struct btrfs_workers *workers)
WARN_ON(workers->num_workers_starting < 0);
spin_unlock_irq(&workers->lock);
+ wake_up_process(worker->task);
return 0;
+
+fail_kthread:
+ kthread_stop(worker->task);
fail:
+ kfree(worker);
spin_lock_irq(&workers->lock);
workers->num_workers_starting--;
spin_unlock_irq(&workers->lock);
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 063698b90ce2..1f26792683ed 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -107,6 +107,8 @@ struct btrfs_workers {
/* extra name for this worker, used for current->name */
char *name;
+
+ int stopping;
};
void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 70681686e8dc..9efb94e95858 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -535,10 +535,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
btrfs_rm_dev_replace_srcdev(fs_info, src_device);
- if (src_device->bdev) {
- /* zero out the old super */
- btrfs_scratch_superblock(src_device);
- }
+
/*
* this is again a consistent state where no dev_replace procedure
* is running, the target device is part of the filesystem, the
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4ae17ed13b32..62176ad89846 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1561,8 +1561,9 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
return ret;
}
-struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
- struct btrfs_key *location)
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_key *location,
+ bool check_ref)
{
struct btrfs_root *root;
int ret;
@@ -1586,7 +1587,7 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
again:
root = btrfs_lookup_fs_root(fs_info, location->objectid);
if (root) {
- if (btrfs_root_refs(&root->root_item) == 0)
+ if (check_ref && btrfs_root_refs(&root->root_item) == 0)
return ERR_PTR(-ENOENT);
return root;
}
@@ -1595,7 +1596,7 @@ again:
if (IS_ERR(root))
return root;
- if (btrfs_root_refs(&root->root_item) == 0) {
+ if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
ret = -ENOENT;
goto fail;
}
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index b71acd6e1e5b..5ce2a7da8b11 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -68,8 +68,17 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
int btrfs_init_fs_root(struct btrfs_root *root);
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
-struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
- struct btrfs_key *location);
+
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_key *key,
+ bool check_ref);
+static inline struct btrfs_root *
+btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
+ struct btrfs_key *location)
+{
+ return btrfs_get_fs_root(fs_info, location, true);
+}
+
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
void btrfs_btree_balance_dirty(struct btrfs_root *root);
void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c09a40db53db..51731b76900d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -145,8 +145,16 @@ int __init extent_io_init(void)
offsetof(struct btrfs_io_bio, bio));
if (!btrfs_bioset)
goto free_buffer_cache;
+
+ if (bioset_integrity_create(btrfs_bioset, BIO_POOL_SIZE))
+ goto free_bioset;
+
return 0;
+free_bioset:
+ bioset_free(btrfs_bioset);
+ btrfs_bioset = NULL;
+
free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
extent_buffer_cache = NULL;
@@ -1482,10 +1490,8 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
cur_start = state->end + 1;
node = rb_next(node);
total_bytes += state->end - state->start + 1;
- if (total_bytes >= max_bytes) {
- *end = *start + max_bytes - 1;
+ if (total_bytes >= max_bytes)
break;
- }
if (!node)
break;
}
@@ -1614,7 +1620,7 @@ again:
*start = delalloc_start;
*end = delalloc_end;
free_extent_state(cached_state);
- return found;
+ return 0;
}
/*
@@ -1627,10 +1633,9 @@ again:
/*
* make sure to limit the number of pages we try to lock down
- * if we're looping.
*/
- if (delalloc_end + 1 - delalloc_start > max_bytes && loops)
- delalloc_end = delalloc_start + PAGE_CACHE_SIZE - 1;
+ if (delalloc_end + 1 - delalloc_start > max_bytes)
+ delalloc_end = delalloc_start + max_bytes - 1;
/* step two, lock all the pages after the page that has start */
ret = lock_delalloc_pages(inode, locked_page,
@@ -1641,8 +1646,7 @@ again:
*/
free_extent_state(cached_state);
if (!loops) {
- unsigned long offset = (*start) & (PAGE_CACHE_SIZE - 1);
- max_bytes = PAGE_CACHE_SIZE - offset;
+ max_bytes = PAGE_CACHE_SIZE;
loops = 1;
goto again;
} else {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 22ebc13b6c99..51e3afa78354 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6437,6 +6437,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
if (btrfs_extent_readonly(root, disk_bytenr))
goto out;
+ btrfs_release_path(path);
/*
* look for other files referencing this extent, if we
@@ -7986,7 +7987,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
/* check for collisions, even if the name isn't there */
- ret = btrfs_check_dir_item_collision(root, new_dir->i_ino,
+ ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino,
new_dentry->d_name.name,
new_dentry->d_name.len);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a5a26320503f..4a355726151e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -588,7 +588,7 @@ static struct btrfs_root *read_fs_root(struct btrfs_fs_info *fs_info,
else
key.offset = (u64)-1;
- return btrfs_read_fs_root_no_name(fs_info, &key);
+ return btrfs_get_fs_root(fs_info, &key, false);
}
#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 0b1f4ef8db98..ec71ea44d2b4 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -299,11 +299,6 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
continue;
}
- if (btrfs_root_refs(&root->root_item) == 0) {
- btrfs_add_dead_root(root);
- continue;
- }
-
err = btrfs_init_fs_root(root);
if (err) {
btrfs_free_fs_root(root);
@@ -318,6 +313,9 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
btrfs_free_fs_root(root);
break;
}
+
+ if (btrfs_root_refs(&root->root_item) == 0)
+ btrfs_add_dead_root(root);
}
btrfs_free_path(path);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index e7a95356df83..8c81bdc1ef9b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1838,11 +1838,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
assert_qgroups_uptodate(trans);
update_super_roots(root);
- if (!root->fs_info->log_root_recovering) {
- btrfs_set_super_log_root(root->fs_info->super_copy, 0);
- btrfs_set_super_log_root_level(root->fs_info->super_copy, 0);
- }
-
+ btrfs_set_super_log_root(root->fs_info->super_copy, 0);
+ btrfs_set_super_log_root_level(root->fs_info->super_copy, 0);
memcpy(root->fs_info->super_for_commit, root->fs_info->super_copy,
sizeof(*root->fs_info->super_copy));
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a10645830223..043b215769c2 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1716,6 +1716,7 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev)
{
WARN_ON(!mutex_is_locked(&fs_info->fs_devices->device_list_mutex));
+
list_del_rcu(&srcdev->dev_list);
list_del_rcu(&srcdev->dev_alloc_list);
fs_info->fs_devices->num_devices--;
@@ -1725,9 +1726,13 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
}
if (srcdev->can_discard)
fs_info->fs_devices->num_can_discard--;
- if (srcdev->bdev)
+ if (srcdev->bdev) {
fs_info->fs_devices->open_devices--;
+ /* zero out the old super */
+ btrfs_scratch_superblock(srcdev);
+ }
+
call_rcu(&srcdev->rcu, free_device);
}
diff --git a/fs/buffer.c b/fs/buffer.c
index 4d7433534f5c..6024877335ca 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1005,9 +1005,19 @@ grow_dev_page(struct block_device *bdev, sector_t block,
struct buffer_head *bh;
sector_t end_block;
int ret = 0; /* Will call free_more_memory() */
+ gfp_t gfp_mask;
- page = find_or_create_page(inode->i_mapping, index,
- (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
+ gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
+ gfp_mask |= __GFP_MOVABLE;
+ /*
+ * XXX: __getblk_slow() can not really deal with failure and
+ * will endlessly loop on improvised global reclaim. Prefer
+ * looping in the allocator rather than here, at least that
+ * code knows what it's doing.
+ */
+ gfp_mask |= __GFP_NOFAIL;
+
+ page = find_or_create_page(inode->i_mapping, index, gfp_mask);
if (!page)
return ret;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index a16b4e58bcc6..77fc5e181077 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -120,14 +120,16 @@ cifs_read_super(struct super_block *sb)
{
struct inode *inode;
struct cifs_sb_info *cifs_sb;
+ struct cifs_tcon *tcon;
int rc = 0;
cifs_sb = CIFS_SB(sb);
+ tcon = cifs_sb_master_tcon(cifs_sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
sb->s_flags |= MS_POSIXACL;
- if (cifs_sb_master_tcon(cifs_sb)->ses->capabilities & CAP_LARGE_FILES)
+ if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)
sb->s_maxbytes = MAX_LFS_FILESIZE;
else
sb->s_maxbytes = MAX_NON_LFS;
@@ -147,7 +149,7 @@ cifs_read_super(struct super_block *sb)
goto out_no_root;
}
- if (cifs_sb_master_tcon(cifs_sb)->nocase)
+ if (tcon->nocase)
sb->s_d_op = &cifs_ci_dentry_ops;
else
sb->s_d_op = &cifs_dentry_ops;
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index ea723a5e8226..6d0b07217ac9 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -132,5 +132,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.01"
+#define CIFS_VERSION "2.02"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index cfa14c80ef3b..52b6f6c26bfc 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -547,9 +547,6 @@ struct TCP_Server_Info {
unsigned int max_rw; /* maxRw specifies the maximum */
/* message size the server can send or receive for */
/* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */
- unsigned int max_vcs; /* maximum number of smb sessions, at least
- those that can be specified uniquely with
- vcnumbers */
unsigned int capabilities; /* selective disabling of caps by smb sess */
int timeAdj; /* Adjust for difference in server time zone in sec */
__u64 CurrentMid; /* multiplex id - rotating counter */
@@ -715,7 +712,6 @@ struct cifs_ses {
enum statusEnum status;
unsigned overrideSecFlg; /* if non-zero override global sec flags */
__u16 ipc_tid; /* special tid for connection to IPC share */
- __u16 vcnum;
char *serverOS; /* name of operating system underlying server */
char *serverNOS; /* name of network operating system of server */
char *serverDomain; /* security realm of server */
@@ -1272,6 +1268,7 @@ struct dfs_info3_param {
#define CIFS_FATTR_DELETE_PENDING 0x2
#define CIFS_FATTR_NEED_REVAL 0x4
#define CIFS_FATTR_INO_COLLISION 0x8
+#define CIFS_FATTR_UNKNOWN_NLINK 0x10
struct cifs_fattr {
u32 cf_flags;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 948676db8e2e..08f9dfb1a894 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -1491,15 +1491,30 @@ struct file_notify_information {
__u8 FileName[0];
} __attribute__((packed));
-struct reparse_data {
- __u32 ReparseTag;
- __u16 ReparseDataLength;
+/* For IO_REPARSE_TAG_SYMLINK */
+struct reparse_symlink_data {
+ __le32 ReparseTag;
+ __le16 ReparseDataLength;
__u16 Reserved;
- __u16 SubstituteNameOffset;
- __u16 SubstituteNameLength;
- __u16 PrintNameOffset;
- __u16 PrintNameLength;
- __u32 Flags;
+ __le16 SubstituteNameOffset;
+ __le16 SubstituteNameLength;
+ __le16 PrintNameOffset;
+ __le16 PrintNameLength;
+ __le32 Flags;
+ char PathBuffer[0];
+} __attribute__((packed));
+
+/* For IO_REPARSE_TAG_NFS */
+#define NFS_SPECFILE_LNK 0x00000000014B4E4C
+#define NFS_SPECFILE_CHR 0x0000000000524843
+#define NFS_SPECFILE_BLK 0x00000000004B4C42
+#define NFS_SPECFILE_FIFO 0x000000004F464946
+#define NFS_SPECFILE_SOCK 0x000000004B434F53
+struct reparse_posix_data {
+ __le32 ReparseTag;
+ __le16 ReparseDataLength;
+ __u16 Reserved;
+ __le64 InodeType; /* LNK, FIFO, CHR etc. */
char PathBuffer[0];
} __attribute__((packed));
@@ -2652,26 +2667,7 @@ typedef struct file_xattr_info {
} __attribute__((packed)) FILE_XATTR_INFO; /* extended attribute info
level 0x205 */
-
-/* flags for chattr command */
-#define EXT_SECURE_DELETE 0x00000001 /* EXT3_SECRM_FL */
-#define EXT_ENABLE_UNDELETE 0x00000002 /* EXT3_UNRM_FL */
-/* Reserved for compress file 0x4 */
-#define EXT_SYNCHRONOUS 0x00000008 /* EXT3_SYNC_FL */
-#define EXT_IMMUTABLE_FL 0x00000010 /* EXT3_IMMUTABLE_FL */
-#define EXT_OPEN_APPEND_ONLY 0x00000020 /* EXT3_APPEND_FL */
-#define EXT_DO_NOT_BACKUP 0x00000040 /* EXT3_NODUMP_FL */
-#define EXT_NO_UPDATE_ATIME 0x00000080 /* EXT3_NOATIME_FL */
-/* 0x100 through 0x800 reserved for compression flags and are GET-ONLY */
-#define EXT_HASH_TREE_INDEXED_DIR 0x00001000 /* GET-ONLY EXT3_INDEX_FL */
-/* 0x2000 reserved for IMAGIC_FL */
-#define EXT_JOURNAL_THIS_FILE 0x00004000 /* GET-ONLY EXT3_JOURNAL_DATA_FL */
-/* 0x8000 reserved for EXT3_NOTAIL_FL */
-#define EXT_SYNCHRONOUS_DIR 0x00010000 /* EXT3_DIRSYNC_FL */
-#define EXT_TOPDIR 0x00020000 /* EXT3_TOPDIR_FL */
-
-#define EXT_SET_MASK 0x000300FF
-#define EXT_GET_MASK 0x0003DFFF
+/* flags for lsattr and chflags commands removed arein uapi/linux/fs.h */
typedef struct file_chattr_info {
__le64 mask; /* list of all possible attribute bits */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index a3d74fea1623..ccd31ab815d4 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -463,7 +463,6 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr)
cifs_max_pending);
set_credits(server, server->maxReq);
server->maxBuf = le16_to_cpu(rsp->MaxBufSize);
- server->max_vcs = le16_to_cpu(rsp->MaxNumberVcs);
/* even though we do not use raw we might as well set this
accurately, in case we ever find a need for it */
if ((le16_to_cpu(rsp->RawMode) & RAW_ENABLE) == RAW_ENABLE) {
@@ -3089,7 +3088,8 @@ CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
bool is_unicode;
unsigned int sub_len;
char *sub_start;
- struct reparse_data *reparse_buf;
+ struct reparse_symlink_data *reparse_buf;
+ struct reparse_posix_data *posix_buf;
__u32 data_offset, data_count;
char *end_of_smb;
@@ -3138,20 +3138,47 @@ CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
goto qreparse_out;
}
end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount;
- reparse_buf = (struct reparse_data *)
+ reparse_buf = (struct reparse_symlink_data *)
((char *)&pSMBr->hdr.Protocol + data_offset);
if ((char *)reparse_buf >= end_of_smb) {
rc = -EIO;
goto qreparse_out;
}
- if ((reparse_buf->PathBuffer + reparse_buf->PrintNameOffset +
- reparse_buf->PrintNameLength) > end_of_smb) {
+ if (reparse_buf->ReparseTag == cpu_to_le32(IO_REPARSE_TAG_NFS)) {
+ cifs_dbg(FYI, "NFS style reparse tag\n");
+ posix_buf = (struct reparse_posix_data *)reparse_buf;
+
+ if (posix_buf->InodeType != cpu_to_le64(NFS_SPECFILE_LNK)) {
+ cifs_dbg(FYI, "unsupported file type 0x%llx\n",
+ le64_to_cpu(posix_buf->InodeType));
+ rc = -EOPNOTSUPP;
+ goto qreparse_out;
+ }
+ is_unicode = true;
+ sub_len = le16_to_cpu(reparse_buf->ReparseDataLength);
+ if (posix_buf->PathBuffer + sub_len > end_of_smb) {
+ cifs_dbg(FYI, "reparse buf beyond SMB\n");
+ rc = -EIO;
+ goto qreparse_out;
+ }
+ *symlinkinfo = cifs_strndup_from_utf16(posix_buf->PathBuffer,
+ sub_len, is_unicode, nls_codepage);
+ goto qreparse_out;
+ } else if (reparse_buf->ReparseTag !=
+ cpu_to_le32(IO_REPARSE_TAG_SYMLINK)) {
+ rc = -EOPNOTSUPP;
+ goto qreparse_out;
+ }
+
+ /* Reparse tag is NTFS symlink */
+ sub_start = le16_to_cpu(reparse_buf->SubstituteNameOffset) +
+ reparse_buf->PathBuffer;
+ sub_len = le16_to_cpu(reparse_buf->SubstituteNameLength);
+ if (sub_start + sub_len > end_of_smb) {
cifs_dbg(FYI, "reparse buf beyond SMB\n");
rc = -EIO;
goto qreparse_out;
}
- sub_start = reparse_buf->SubstituteNameOffset + reparse_buf->PathBuffer;
- sub_len = reparse_buf->SubstituteNameLength;
if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
is_unicode = true;
else
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index eb955b525e55..7ddddf2e2504 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3254,6 +3254,9 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
/*
* Reads as many pages as possible from fscache. Returns -ENOBUFS
* immediately if the cookie is negative
+ *
+ * After this point, every page in the list might have PG_fscache set,
+ * so we will need to clean that up off of every page we don't use.
*/
rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list,
&num_pages);
@@ -3376,6 +3379,11 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
kref_put(&rdata->refcount, cifs_readdata_release);
}
+ /* Any pages that have been shown to fscache but didn't get added to
+ * the pagecache must be uncached before they get returned to the
+ * allocator.
+ */
+ cifs_fscache_readpages_cancel(mapping->host, page_list);
return rc;
}
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index fe2492d2a8fc..8d4b7bc8ae91 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -223,6 +223,13 @@ void __cifs_readpage_to_fscache(struct inode *inode, struct page *page)
fscache_uncache_page(CIFS_I(inode)->fscache, page);
}
+void __cifs_fscache_readpages_cancel(struct inode *inode, struct list_head *pages)
+{
+ cifs_dbg(FYI, "%s: (fsc: %p, i: %p)\n",
+ __func__, CIFS_I(inode)->fscache, inode);
+ fscache_readpages_cancel(CIFS_I(inode)->fscache, pages);
+}
+
void __cifs_fscache_invalidate_page(struct page *page, struct inode *inode)
{
struct cifsInodeInfo *cifsi = CIFS_I(inode);
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index 63539323e0b9..24794b6cd8ec 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -54,6 +54,7 @@ extern int __cifs_readpages_from_fscache(struct inode *,
struct address_space *,
struct list_head *,
unsigned *);
+extern void __cifs_fscache_readpages_cancel(struct inode *, struct list_head *);
extern void __cifs_readpage_to_fscache(struct inode *, struct page *);
@@ -91,6 +92,13 @@ static inline void cifs_readpage_to_fscache(struct inode *inode,
__cifs_readpage_to_fscache(inode, page);
}
+static inline void cifs_fscache_readpages_cancel(struct inode *inode,
+ struct list_head *pages)
+{
+ if (CIFS_I(inode)->fscache)
+ return __cifs_fscache_readpages_cancel(inode, pages);
+}
+
#else /* CONFIG_CIFS_FSCACHE */
static inline int cifs_fscache_register(void) { return 0; }
static inline void cifs_fscache_unregister(void) {}
@@ -131,6 +139,11 @@ static inline int cifs_readpages_from_fscache(struct inode *inode,
static inline void cifs_readpage_to_fscache(struct inode *inode,
struct page *page) {}
+static inline void cifs_fscache_readpages_cancel(struct inode *inode,
+ struct list_head *pages)
+{
+}
+
#endif /* CONFIG_CIFS_FSCACHE */
#endif /* _CIFS_FSCACHE_H */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index f9ff9c173f78..867b7cdc794a 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -120,6 +120,33 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
cifs_i->invalid_mapping = true;
}
+/*
+ * copy nlink to the inode, unless it wasn't provided. Provide
+ * sane values if we don't have an existing one and none was provided
+ */
+static void
+cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
+{
+ /*
+ * if we're in a situation where we can't trust what we
+ * got from the server (readdir, some non-unix cases)
+ * fake reasonable values
+ */
+ if (fattr->cf_flags & CIFS_FATTR_UNKNOWN_NLINK) {
+ /* only provide fake values on a new inode */
+ if (inode->i_state & I_NEW) {
+ if (fattr->cf_cifsattrs & ATTR_DIRECTORY)
+ set_nlink(inode, 2);
+ else
+ set_nlink(inode, 1);
+ }
+ return;
+ }
+
+ /* we trust the server, so update it */
+ set_nlink(inode, fattr->cf_nlink);
+}
+
/* populate an inode with info from a cifs_fattr struct */
void
cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
@@ -134,7 +161,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
inode->i_mtime = fattr->cf_mtime;
inode->i_ctime = fattr->cf_ctime;
inode->i_rdev = fattr->cf_rdev;
- set_nlink(inode, fattr->cf_nlink);
+ cifs_nlink_fattr_to_inode(inode, fattr);
inode->i_uid = fattr->cf_uid;
inode->i_gid = fattr->cf_gid;
@@ -541,6 +568,7 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
fattr->cf_bytes = le64_to_cpu(info->AllocationSize);
fattr->cf_createtime = le64_to_cpu(info->CreationTime);
+ fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
fattr->cf_mode = S_IFDIR | cifs_sb->mnt_dir_mode;
fattr->cf_dtype = DT_DIR;
@@ -548,7 +576,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
* Server can return wrong NumberOfLinks value for directories
* when Unix extensions are disabled - fake it.
*/
- fattr->cf_nlink = 2;
+ if (!tcon->unix_ext)
+ fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
} else if (fattr->cf_cifsattrs & ATTR_REPARSE) {
fattr->cf_mode = S_IFLNK;
fattr->cf_dtype = DT_LNK;
@@ -561,11 +590,15 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
if (fattr->cf_cifsattrs & ATTR_READONLY)
fattr->cf_mode &= ~(S_IWUGO);
- fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
- if (fattr->cf_nlink < 1) {
- cifs_dbg(1, "replacing bogus file nlink value %u\n",
+ /*
+ * Don't accept zero nlink from non-unix servers unless
+ * delete is pending. Instead mark it as unknown.
+ */
+ if ((fattr->cf_nlink < 1) && !tcon->unix_ext &&
+ !info->DeletePending) {
+ cifs_dbg(1, "bogus file nlink value %u\n",
fattr->cf_nlink);
- fattr->cf_nlink = 1;
+ fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
}
}
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index af847e1cf1c1..651a5279607b 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -780,7 +780,9 @@ static const struct {
ERRDOS, ERRnoaccess, 0xc0000290}, {
ERRDOS, ERRbadfunc, 0xc000029c}, {
ERRDOS, ERRsymlink, NT_STATUS_STOPPED_ON_SYMLINK}, {
- ERRDOS, ERRinvlevel, 0x007c0001}, };
+ ERRDOS, ERRinvlevel, 0x007c0001}, {
+ 0, 0, 0 }
+};
/*****************************************************************************
Print an error message from the status code
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 42ef03be089f..53a75f3d0179 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -180,6 +180,9 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
fattr->cf_dtype = DT_REG;
}
+ /* non-unix readdir doesn't provide nlink */
+ fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
+
if (fattr->cf_cifsattrs & ATTR_READONLY)
fattr->cf_mode &= ~S_IWUGO;
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 5f99b7f19e78..e87387dbf39f 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -32,88 +32,6 @@
#include <linux/slab.h>
#include "cifs_spnego.h"
-/*
- * Checks if this is the first smb session to be reconnected after
- * the socket has been reestablished (so we know whether to use vc 0).
- * Called while holding the cifs_tcp_ses_lock, so do not block
- */
-static bool is_first_ses_reconnect(struct cifs_ses *ses)
-{
- struct list_head *tmp;
- struct cifs_ses *tmp_ses;
-
- list_for_each(tmp, &ses->server->smb_ses_list) {
- tmp_ses = list_entry(tmp, struct cifs_ses,
- smb_ses_list);
- if (tmp_ses->need_reconnect == false)
- return false;
- }
- /* could not find a session that was already connected,
- this must be the first one we are reconnecting */
- return true;
-}
-
-/*
- * vc number 0 is treated specially by some servers, and should be the
- * first one we request. After that we can use vcnumbers up to maxvcs,
- * one for each smb session (some Windows versions set maxvcs incorrectly
- * so maxvc=1 can be ignored). If we have too many vcs, we can reuse
- * any vc but zero (some servers reset the connection on vcnum zero)
- *
- */
-static __le16 get_next_vcnum(struct cifs_ses *ses)
-{
- __u16 vcnum = 0;
- struct list_head *tmp;
- struct cifs_ses *tmp_ses;
- __u16 max_vcs = ses->server->max_vcs;
- __u16 i;
- int free_vc_found = 0;
-
- /* Quoting the MS-SMB specification: "Windows-based SMB servers set this
- field to one but do not enforce this limit, which allows an SMB client
- to establish more virtual circuits than allowed by this value ... but
- other server implementations can enforce this limit." */
- if (max_vcs < 2)
- max_vcs = 0xFFFF;
-
- spin_lock(&cifs_tcp_ses_lock);
- if ((ses->need_reconnect) && is_first_ses_reconnect(ses))
- goto get_vc_num_exit; /* vcnum will be zero */
- for (i = ses->server->srv_count - 1; i < max_vcs; i++) {
- if (i == 0) /* this is the only connection, use vc 0 */
- break;
-
- free_vc_found = 1;
-
- list_for_each(tmp, &ses->server->smb_ses_list) {
- tmp_ses = list_entry(tmp, struct cifs_ses,
- smb_ses_list);
- if (tmp_ses->vcnum == i) {
- free_vc_found = 0;
- break; /* found duplicate, try next vcnum */
- }
- }
- if (free_vc_found)
- break; /* we found a vcnumber that will work - use it */
- }
-
- if (i == 0)
- vcnum = 0; /* for most common case, ie if one smb session, use
- vc zero. Also for case when no free vcnum, zero
- is safest to send (some clients only send zero) */
- else if (free_vc_found == 0)
- vcnum = 1; /* we can not reuse vc=0 safely, since some servers
- reset all uids on that, but 1 is ok. */
- else
- vcnum = i;
- ses->vcnum = vcnum;
-get_vc_num_exit:
- spin_unlock(&cifs_tcp_ses_lock);
-
- return cpu_to_le16(vcnum);
-}
-
static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
{
__u32 capabilities = 0;
@@ -128,7 +46,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4,
USHRT_MAX));
pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq);
- pSMB->req.VcNumber = get_next_vcnum(ses);
+ pSMB->req.VcNumber = __constant_cpu_to_le16(1);
/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
@@ -582,9 +500,9 @@ select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
return NTLMv2;
if (global_secflags & CIFSSEC_MAY_NTLM)
return NTLM;
- /* Fallthrough */
default:
- return Unspecified;
+ /* Fallthrough to attempt LANMAN authentication next */
+ break;
}
case CIFS_NEGFLAVOR_LANMAN:
switch (requested) {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index eba0efde66d7..edccb5252462 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -687,6 +687,10 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
else
return -EIO;
+ /* no need to send SMB logoff if uid already closed due to reconnect */
+ if (ses->need_reconnect)
+ goto smb2_session_already_dead;
+
rc = small_smb2_init(SMB2_LOGOFF, NULL, (void **) &req);
if (rc)
return rc;
@@ -701,6 +705,8 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
* No tcon so can't do
* cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]);
*/
+
+smb2_session_already_dead:
return rc;
}
diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h
index d952ee48f4dc..a4b2391fe66e 100644
--- a/fs/cifs/smbfsctl.h
+++ b/fs/cifs/smbfsctl.h
@@ -97,9 +97,23 @@
#define FSCTL_QUERY_NETWORK_INTERFACE_INFO 0x001401FC /* BB add struct */
#define FSCTL_SRV_READ_HASH 0x001441BB /* BB add struct */
+/* See FSCC 2.1.2.5 */
#define IO_REPARSE_TAG_MOUNT_POINT 0xA0000003
#define IO_REPARSE_TAG_HSM 0xC0000004
#define IO_REPARSE_TAG_SIS 0x80000007
+#define IO_REPARSE_TAG_HSM2 0x80000006
+#define IO_REPARSE_TAG_DRIVER_EXTENDER 0x80000005
+/* Used by the DFS filter. See MS-DFSC */
+#define IO_REPARSE_TAG_DFS 0x8000000A
+/* Used by the DFS filter See MS-DFSC */
+#define IO_REPARSE_TAG_DFSR 0x80000012
+#define IO_REPARSE_TAG_FILTER_MANAGER 0x8000000B
+/* See section MS-FSCC 2.1.2.4 */
+#define IO_REPARSE_TAG_SYMLINK 0xA000000C
+#define IO_REPARSE_TAG_DEDUP 0x80000013
+#define IO_REPARSE_APPXSTREAM 0xC0000014
+/* NFS symlinks, Win 8/SMB3 and later */
+#define IO_REPARSE_TAG_NFS 0x80000014
/* fsctl flags */
/* If Flags is set to this value, the request is an FSCTL not ioctl request */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 6fdcb1b4a106..800b938e4061 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -410,8 +410,13 @@ static int
wait_for_free_request(struct TCP_Server_Info *server, const int timeout,
const int optype)
{
- return wait_for_free_credits(server, timeout,
- server->ops->get_credits_field(server, optype));
+ int *val;
+
+ val = server->ops->get_credits_field(server, optype);
+ /* Since an echo is already inflight, no need to wait to send another */
+ if (*val <= 0 && optype == CIFS_ECHO_OP)
+ return -EAGAIN;
+ return wait_for_free_credits(server, timeout, val);
}
static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf,
diff --git a/fs/dcache.c b/fs/dcache.c
index 41000305d716..ae6ebb88ceff 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -542,7 +542,7 @@ EXPORT_SYMBOL(d_drop);
* If ref is non-zero, then decrement the refcount too.
* Returns dentry requiring refcount drop, or NULL if we're done.
*/
-static inline struct dentry *
+static struct dentry *
dentry_kill(struct dentry *dentry, int unlock_on_failure)
__releases(dentry->d_lock)
{
@@ -630,7 +630,8 @@ repeat:
goto kill_it;
}
- dentry->d_flags |= DCACHE_REFERENCED;
+ if (!(dentry->d_flags & DCACHE_REFERENCED))
+ dentry->d_flags |= DCACHE_REFERENCED;
dentry_lru_add(dentry);
dentry->d_lockref.count--;
@@ -1331,14 +1332,6 @@ rename_retry:
* list is non-empty and continue searching.
*/
-/**
- * have_submounts - check for mounts over a dentry
- * @parent: dentry to check.
- *
- * Return true if the parent or its subdirectories contain
- * a mount point
- */
-
static enum d_walk_ret check_mount(void *data, struct dentry *dentry)
{
int *ret = data;
@@ -1349,6 +1342,13 @@ static enum d_walk_ret check_mount(void *data, struct dentry *dentry)
return D_WALK_CONTINUE;
}
+/**
+ * have_submounts - check for mounts over a dentry
+ * @parent: dentry to check.
+ *
+ * Return true if the parent or its subdirectories contain
+ * a mount point
+ */
int have_submounts(struct dentry *parent)
{
int ret = 0;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index c88e355f7635..000eae2782b6 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -408,7 +408,7 @@ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat,
struct page *page)
{
return ecryptfs_lower_header_size(crypt_stat) +
- (page->index << PAGE_CACHE_SHIFT);
+ ((loff_t)page->index << PAGE_CACHE_SHIFT);
}
/**
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 7d52806c2119..4725a07f003c 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1149,7 +1149,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
struct ecryptfs_msg_ctx *msg_ctx;
struct ecryptfs_message *msg = NULL;
char *auth_tok_sig;
- char *payload;
+ char *payload = NULL;
size_t payload_len = 0;
int rc;
@@ -1203,6 +1203,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
}
out:
kfree(msg);
+ kfree(payload);
return rc;
}
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 473e09da7d02..810c28fb8c3c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,7 +34,6 @@
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <linux/device.h>
-#include <linux/freezer.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/mman.h>
@@ -1605,8 +1604,7 @@ fetch_events:
}
spin_unlock_irqrestore(&ep->lock, flags);
- if (!freezable_schedule_hrtimeout_range(to, slack,
- HRTIMER_MODE_ABS))
+ if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
timed_out = 1;
spin_lock_irqsave(&ep->lock, flags);
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 1194b1f0f839..f8cde46de9cd 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1783,7 +1783,7 @@ retry:
d_tmpfile(dentry, inode);
err = ext3_orphan_add(handle, inode);
if (err)
- goto err_drop_inode;
+ goto err_unlock_inode;
mark_inode_dirty(inode);
unlock_new_inode(inode);
}
@@ -1791,10 +1791,9 @@ retry:
if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
-err_drop_inode:
+err_unlock_inode:
ext3_journal_stop(handle);
unlock_new_inode(inode);
- iput(inode);
return err;
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0d424d7ac02b..e274e9c1171f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2563,7 +2563,7 @@ retry:
break;
}
blk_finish_plug(&plug);
- if (!ret && !cycled) {
+ if (!ret && !cycled && wbc->nr_to_write > 0) {
cycled = 1;
mpd.last_page = writeback_index - 1;
mpd.first_page = 0;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1bec5a5c1e45..5a0408d7b114 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2319,7 +2319,7 @@ retry:
d_tmpfile(dentry, inode);
err = ext4_orphan_add(handle, inode);
if (err)
- goto err_drop_inode;
+ goto err_unlock_inode;
mark_inode_dirty(inode);
unlock_new_inode(inode);
}
@@ -2328,10 +2328,9 @@ retry:
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
-err_drop_inode:
+err_unlock_inode:
ext4_journal_stop(handle);
unlock_new_inode(inode);
- iput(inode);
return err;
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c081e34f717f..03e9bebba198 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1350,6 +1350,8 @@ retry:
s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
+ kfree(is); is = NULL;
+ kfree(bs); bs = NULL;
goto retry;
}
error = -1;
diff --git a/fs/file_table.c b/fs/file_table.c
index abdd15ad13c9..e900ca518635 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -297,7 +297,7 @@ void flush_delayed_fput(void)
delayed_fput(NULL);
}
-static DECLARE_WORK(delayed_fput_work, delayed_fput);
+static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
void fput(struct file *file)
{
@@ -317,7 +317,7 @@ void fput(struct file *file)
}
if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
- schedule_work(&delayed_fput_work);
+ schedule_delayed_work(&delayed_fput_work, 1);
}
}
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 62b43b577bfc..b7989f2ab4c4 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -182,6 +182,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
struct inode *inode;
struct dentry *parent;
struct fuse_conn *fc;
+ struct fuse_inode *fi;
int ret;
inode = ACCESS_ONCE(entry->d_inode);
@@ -228,7 +229,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
if (!err && !outarg.nodeid)
err = -ENOENT;
if (!err) {
- struct fuse_inode *fi = get_fuse_inode(inode);
+ fi = get_fuse_inode(inode);
if (outarg.nodeid != get_node_id(inode)) {
fuse_queue_forget(fc, forget, outarg.nodeid, 1);
goto invalid;
@@ -246,8 +247,11 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
attr_version);
fuse_change_entry_timeout(entry, &outarg);
} else if (inode) {
- fc = get_fuse_conn(inode);
- if (fc->readdirplus_auto) {
+ fi = get_fuse_inode(inode);
+ if (flags & LOOKUP_RCU) {
+ if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state))
+ return -ECHILD;
+ } else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) {
parent = dget_parent(entry);
fuse_advise_use_readdirplus(parent->d_inode);
dput(parent);
@@ -259,7 +263,8 @@ out:
invalid:
ret = 0;
- if (check_submounts_and_drop(entry) != 0)
+
+ if (!(flags & LOOKUP_RCU) && check_submounts_and_drop(entry) != 0)
ret = 1;
goto out;
}
@@ -1063,6 +1068,8 @@ static int fuse_access(struct inode *inode, int mask)
struct fuse_access_in inarg;
int err;
+ BUG_ON(mask & MAY_NOT_BLOCK);
+
if (fc->no_access)
return 0;
@@ -1150,9 +1157,6 @@ static int fuse_permission(struct inode *inode, int mask)
noticed immediately, only after the attribute
timeout has expired */
} else if (mask & (MAY_ACCESS | MAY_CHDIR)) {
- if (mask & MAY_NOT_BLOCK)
- return -ECHILD;
-
err = fuse_access(inode, mask);
} else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
if (!(inode->i_mode & S_IXUGO)) {
@@ -1291,6 +1295,8 @@ static int fuse_direntplus_link(struct file *file,
}
found:
+ if (fc->readdirplus_auto)
+ set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
fuse_change_entry_timeout(dentry, o);
err = 0;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index d409deafc67b..4598345ab87d 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2467,6 +2467,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
{
struct fuse_file *ff = file->private_data;
struct inode *inode = file->f_inode;
+ struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = ff->fc;
struct fuse_req *req;
struct fuse_fallocate_in inarg = {
@@ -2484,10 +2485,20 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
if (lock_inode) {
mutex_lock(&inode->i_mutex);
- if (mode & FALLOC_FL_PUNCH_HOLE)
- fuse_set_nowrite(inode);
+ if (mode & FALLOC_FL_PUNCH_HOLE) {
+ loff_t endbyte = offset + length - 1;
+ err = filemap_write_and_wait_range(inode->i_mapping,
+ offset, endbyte);
+ if (err)
+ goto out;
+
+ fuse_sync_writes(inode);
+ }
}
+ if (!(mode & FALLOC_FL_KEEP_SIZE))
+ set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
req = fuse_get_req_nopages(fc);
if (IS_ERR(req)) {
err = PTR_ERR(req);
@@ -2520,11 +2531,11 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
fuse_invalidate_attr(inode);
out:
- if (lock_inode) {
- if (mode & FALLOC_FL_PUNCH_HOLE)
- fuse_release_nowrite(inode);
+ if (!(mode & FALLOC_FL_KEEP_SIZE))
+ clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
+ if (lock_inode)
mutex_unlock(&inode->i_mutex);
- }
return err;
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 5ced199b50bb..5b9e6f3b6aef 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -115,6 +115,8 @@ struct fuse_inode {
enum {
/** Advise readdirplus */
FUSE_I_ADVISE_RDPLUS,
+ /** Initialized with readdirplus */
+ FUSE_I_INIT_RDPLUS,
/** An operation changing file size is in progress */
FUSE_I_SIZE_UNSTABLE,
};
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index c1a3e603279c..7f464c513ba0 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -95,7 +95,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
if (insert_inode_locked(inode) < 0) {
rc = -EINVAL;
- goto fail_unlock;
+ goto fail_put;
}
inode_init_owner(inode, parent, mode);
@@ -156,7 +156,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
-fail_unlock:
clear_nlink(inode);
unlock_new_inode(inode);
fail_put:
diff --git a/fs/namei.c b/fs/namei.c
index 645268f23eb6..caa28051e197 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2294,10 +2294,11 @@ out:
* path_mountpoint - look up a path to be umounted
* @dfd: directory file descriptor to start walk from
* @name: full pathname to walk
+ * @path: pointer to container for result
* @flags: lookup flags
*
* Look up the given name, but don't attempt to revalidate the last component.
- * Returns 0 and "path" will be valid on success; Retuns error otherwise.
+ * Returns 0 and "path" will be valid on success; Returns error otherwise.
*/
static int
path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 9f8ef9b7674d..8eaa1ba793fc 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -288,10 +288,14 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags)
{
struct proc_dir_entry *pde = PDE(file_inode(file));
- int rv = -EIO;
- unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+ unsigned long rv = -EIO;
+ unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL;
if (use_pde(pde)) {
- get_unmapped_area = pde->proc_fops->get_unmapped_area;
+#ifdef CONFIG_MMU
+ get_unmapped_area = current->mm->get_unmapped_area;
+#endif
+ if (pde->proc_fops->get_unmapped_area)
+ get_unmapped_area = pde->proc_fops->get_unmapped_area;
if (get_unmapped_area)
rv = get_unmapped_area(file, orig_addr, len, pgoff, flags);
unuse_pde(pde);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7366e9d63cee..390bdab01c3c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -941,6 +941,8 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
frame = pte_pfn(pte);
flags = PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
+ if (pte_soft_dirty(pte))
+ flags2 |= __PM_SOFT_DIRTY;
} else if (is_swap_pte(pte)) {
swp_entry_t entry;
if (pte_swp_soft_dirty(pte))
@@ -960,7 +962,7 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
if (page && !PageAnon(page))
flags |= PM_FILE;
- if ((vma->vm_flags & VM_SOFTDIRTY) || pte_soft_dirty(pte))
+ if ((vma->vm_flags & VM_SOFTDIRTY))
flags2 |= __PM_SOFT_DIRTY;
*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
diff --git a/fs/select.c b/fs/select.c
index 35d4adc749d9..dfd5cb18c012 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -238,8 +238,7 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
set_current_state(state);
if (!pwq->triggered)
- rc = freezable_schedule_hrtimeout_range(expires, slack,
- HRTIMER_MODE_ABS);
+ rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
__set_current_state(TASK_RUNNING);
/*
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 3135c2525c76..a290157265ef 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -328,6 +328,8 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence)
m->read_pos = offset;
retval = file->f_pos = offset;
}
+ } else {
+ file->f_pos = offset;
}
}
file->f_version = m->version;
diff --git a/fs/statfs.c b/fs/statfs.c
index c219e733f553..083dc0ac9140 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -94,7 +94,7 @@ retry:
int fd_statfs(int fd, struct kstatfs *st)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_raw(fd);
int error = -EBADF;
if (f.file) {
error = vfs_statfs(&f.file->f_path, st);
diff --git a/fs/super.c b/fs/super.c
index 3a96c9783a8b..0225c20f8770 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -264,6 +264,8 @@ out_free_sb:
*/
static inline void destroy_super(struct super_block *s)
{
+ list_lru_destroy(&s->s_dentry_lru);
+ list_lru_destroy(&s->s_inode_lru);
#ifdef CONFIG_SMP
free_percpu(s->s_files);
#endif
@@ -323,8 +325,6 @@ void deactivate_locked_super(struct super_block *s)
/* caches are now gone, we can safely kill the shrinker now */
unregister_shrinker(&s->s_shrink);
- list_lru_destroy(&s->s_dentry_lru);
- list_lru_destroy(&s->s_inode_lru);
put_filesystem(fs);
put_super(s);
diff --git a/fs/sysfs/Makefile b/fs/sysfs/Makefile
index 7a1ceb946b80..8876ac183373 100644
--- a/fs/sysfs/Makefile
+++ b/fs/sysfs/Makefile
@@ -2,5 +2,4 @@
# Makefile for the sysfs virtual filesystem
#
-obj-y := inode.o file.o dir.o symlink.o mount.o bin.o \
- group.o
+obj-y := inode.o file.o dir.o symlink.o mount.o group.o
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
deleted file mode 100644
index c590cabd57bb..000000000000
--- a/fs/sysfs/bin.c
+++ /dev/null
@@ -1,502 +0,0 @@
-/*
- * fs/sysfs/bin.c - sysfs binary file implementation
- *
- * Copyright (c) 2003 Patrick Mochel
- * Copyright (c) 2003 Matthew Wilcox
- * Copyright (c) 2004 Silicon Graphics, Inc.
- * Copyright (c) 2007 SUSE Linux Products GmbH
- * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
- *
- * This file is released under the GPLv2.
- *
- * Please see Documentation/filesystems/sysfs.txt for more information.
- */
-
-#undef DEBUG
-
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/kobject.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/mm.h>
-#include <linux/uaccess.h>
-
-#include "sysfs.h"
-
-/*
- * There's one bin_buffer for each open file.
- *
- * filp->private_data points to bin_buffer and
- * sysfs_dirent->s_bin_attr.buffers points to a the bin_buffer s
- * sysfs_dirent->s_bin_attr.buffers is protected by sysfs_bin_lock
- */
-static DEFINE_MUTEX(sysfs_bin_lock);
-
-struct bin_buffer {
- struct mutex mutex;
- void *buffer;
- int mmapped;
- const struct vm_operations_struct *vm_ops;
- struct file *file;
- struct hlist_node list;
-};
-
-static int
-fill_read(struct file *file, char *buffer, loff_t off, size_t count)
-{
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
- struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- int rc;
-
- /* need attr_sd for attr, its parent for kobj */
- if (!sysfs_get_active(attr_sd))
- return -ENODEV;
-
- rc = -EIO;
- if (attr->read)
- rc = attr->read(file, kobj, attr, buffer, off, count);
-
- sysfs_put_active(attr_sd);
-
- return rc;
-}
-
-static ssize_t
-read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off)
-{
- struct bin_buffer *bb = file->private_data;
- int size = file_inode(file)->i_size;
- loff_t offs = *off;
- int count = min_t(size_t, bytes, PAGE_SIZE);
- char *temp;
-
- if (!bytes)
- return 0;
-
- if (size) {
- if (offs > size)
- return 0;
- if (offs + count > size)
- count = size - offs;
- }
-
- temp = kmalloc(count, GFP_KERNEL);
- if (!temp)
- return -ENOMEM;
-
- mutex_lock(&bb->mutex);
-
- count = fill_read(file, bb->buffer, offs, count);
- if (count < 0) {
- mutex_unlock(&bb->mutex);
- goto out_free;
- }
-
- memcpy(temp, bb->buffer, count);
-
- mutex_unlock(&bb->mutex);
-
- if (copy_to_user(userbuf, temp, count)) {
- count = -EFAULT;
- goto out_free;
- }
-
- pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
-
- *off = offs + count;
-
- out_free:
- kfree(temp);
- return count;
-}
-
-static int
-flush_write(struct file *file, char *buffer, loff_t offset, size_t count)
-{
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
- struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- int rc;
-
- /* need attr_sd for attr, its parent for kobj */
- if (!sysfs_get_active(attr_sd))
- return -ENODEV;
-
- rc = -EIO;
- if (attr->write)
- rc = attr->write(file, kobj, attr, buffer, offset, count);
-
- sysfs_put_active(attr_sd);
-
- return rc;
-}
-
-static ssize_t write(struct file *file, const char __user *userbuf,
- size_t bytes, loff_t *off)
-{
- struct bin_buffer *bb = file->private_data;
- int size = file_inode(file)->i_size;
- loff_t offs = *off;
- int count = min_t(size_t, bytes, PAGE_SIZE);
- char *temp;
-
- if (!bytes)
- return 0;
-
- if (size) {
- if (offs > size)
- return 0;
- if (offs + count > size)
- count = size - offs;
- }
-
- temp = memdup_user(userbuf, count);
- if (IS_ERR(temp))
- return PTR_ERR(temp);
-
- mutex_lock(&bb->mutex);
-
- memcpy(bb->buffer, temp, count);
-
- count = flush_write(file, bb->buffer, offs, count);
- mutex_unlock(&bb->mutex);
-
- if (count > 0)
- *off = offs + count;
-
- kfree(temp);
- return count;
-}
-
-static void bin_vma_open(struct vm_area_struct *vma)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-
- if (!bb->vm_ops)
- return;
-
- if (!sysfs_get_active(attr_sd))
- return;
-
- if (bb->vm_ops->open)
- bb->vm_ops->open(vma);
-
- sysfs_put_active(attr_sd);
-}
-
-static int bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- int ret;
-
- if (!bb->vm_ops)
- return VM_FAULT_SIGBUS;
-
- if (!sysfs_get_active(attr_sd))
- return VM_FAULT_SIGBUS;
-
- ret = VM_FAULT_SIGBUS;
- if (bb->vm_ops->fault)
- ret = bb->vm_ops->fault(vma, vmf);
-
- sysfs_put_active(attr_sd);
- return ret;
-}
-
-static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- int ret;
-
- if (!bb->vm_ops)
- return VM_FAULT_SIGBUS;
-
- if (!sysfs_get_active(attr_sd))
- return VM_FAULT_SIGBUS;
-
- ret = 0;
- if (bb->vm_ops->page_mkwrite)
- ret = bb->vm_ops->page_mkwrite(vma, vmf);
- else
- file_update_time(file);
-
- sysfs_put_active(attr_sd);
- return ret;
-}
-
-static int bin_access(struct vm_area_struct *vma, unsigned long addr,
- void *buf, int len, int write)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- int ret;
-
- if (!bb->vm_ops)
- return -EINVAL;
-
- if (!sysfs_get_active(attr_sd))
- return -EINVAL;
-
- ret = -EINVAL;
- if (bb->vm_ops->access)
- ret = bb->vm_ops->access(vma, addr, buf, len, write);
-
- sysfs_put_active(attr_sd);
- return ret;
-}
-
-#ifdef CONFIG_NUMA
-static int bin_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- int ret;
-
- if (!bb->vm_ops)
- return 0;
-
- if (!sysfs_get_active(attr_sd))
- return -EINVAL;
-
- ret = 0;
- if (bb->vm_ops->set_policy)
- ret = bb->vm_ops->set_policy(vma, new);
-
- sysfs_put_active(attr_sd);
- return ret;
-}
-
-static struct mempolicy *bin_get_policy(struct vm_area_struct *vma,
- unsigned long addr)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- struct mempolicy *pol;
-
- if (!bb->vm_ops)
- return vma->vm_policy;
-
- if (!sysfs_get_active(attr_sd))
- return vma->vm_policy;
-
- pol = vma->vm_policy;
- if (bb->vm_ops->get_policy)
- pol = bb->vm_ops->get_policy(vma, addr);
-
- sysfs_put_active(attr_sd);
- return pol;
-}
-
-static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from,
- const nodemask_t *to, unsigned long flags)
-{
- struct file *file = vma->vm_file;
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- int ret;
-
- if (!bb->vm_ops)
- return 0;
-
- if (!sysfs_get_active(attr_sd))
- return 0;
-
- ret = 0;
- if (bb->vm_ops->migrate)
- ret = bb->vm_ops->migrate(vma, from, to, flags);
-
- sysfs_put_active(attr_sd);
- return ret;
-}
-#endif
-
-static const struct vm_operations_struct bin_vm_ops = {
- .open = bin_vma_open,
- .fault = bin_fault,
- .page_mkwrite = bin_page_mkwrite,
- .access = bin_access,
-#ifdef CONFIG_NUMA
- .set_policy = bin_set_policy,
- .get_policy = bin_get_policy,
- .migrate = bin_migrate,
-#endif
-};
-
-static int mmap(struct file *file, struct vm_area_struct *vma)
-{
- struct bin_buffer *bb = file->private_data;
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
- struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- int rc;
-
- mutex_lock(&bb->mutex);
-
- /* need attr_sd for attr, its parent for kobj */
- rc = -ENODEV;
- if (!sysfs_get_active(attr_sd))
- goto out_unlock;
-
- rc = -EINVAL;
- if (!attr->mmap)
- goto out_put;
-
- rc = attr->mmap(file, kobj, attr, vma);
- if (rc)
- goto out_put;
-
- /*
- * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
- * to satisfy versions of X which crash if the mmap fails: that
- * substitutes a new vm_file, and we don't then want bin_vm_ops.
- */
- if (vma->vm_file != file)
- goto out_put;
-
- rc = -EINVAL;
- if (bb->mmapped && bb->vm_ops != vma->vm_ops)
- goto out_put;
-
- /*
- * It is not possible to successfully wrap close.
- * So error if someone is trying to use close.
- */
- rc = -EINVAL;
- if (vma->vm_ops && vma->vm_ops->close)
- goto out_put;
-
- rc = 0;
- bb->mmapped = 1;
- bb->vm_ops = vma->vm_ops;
- vma->vm_ops = &bin_vm_ops;
-out_put:
- sysfs_put_active(attr_sd);
-out_unlock:
- mutex_unlock(&bb->mutex);
-
- return rc;
-}
-
-static int open(struct inode *inode, struct file *file)
-{
- struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
- struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
- struct bin_buffer *bb = NULL;
- int error;
-
- /* binary file operations requires both @sd and its parent */
- if (!sysfs_get_active(attr_sd))
- return -ENODEV;
-
- error = -EACCES;
- if ((file->f_mode & FMODE_WRITE) && !(attr->write || attr->mmap))
- goto err_out;
- if ((file->f_mode & FMODE_READ) && !(attr->read || attr->mmap))
- goto err_out;
-
- error = -ENOMEM;
- bb = kzalloc(sizeof(*bb), GFP_KERNEL);
- if (!bb)
- goto err_out;
-
- bb->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!bb->buffer)
- goto err_out;
-
- mutex_init(&bb->mutex);
- bb->file = file;
- file->private_data = bb;
-
- mutex_lock(&sysfs_bin_lock);
- hlist_add_head(&bb->list, &attr_sd->s_bin_attr.buffers);
- mutex_unlock(&sysfs_bin_lock);
-
- /* open succeeded, put active references */
- sysfs_put_active(attr_sd);
- return 0;
-
- err_out:
- sysfs_put_active(attr_sd);
- kfree(bb);
- return error;
-}
-
-static int release(struct inode *inode, struct file *file)
-{
- struct bin_buffer *bb = file->private_data;
-
- mutex_lock(&sysfs_bin_lock);
- hlist_del(&bb->list);
- mutex_unlock(&sysfs_bin_lock);
-
- kfree(bb->buffer);
- kfree(bb);
- return 0;
-}
-
-const struct file_operations bin_fops = {
- .read = read,
- .write = write,
- .mmap = mmap,
- .llseek = generic_file_llseek,
- .open = open,
- .release = release,
-};
-
-
-void unmap_bin_file(struct sysfs_dirent *attr_sd)
-{
- struct bin_buffer *bb;
-
- if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR)
- return;
-
- mutex_lock(&sysfs_bin_lock);
-
- hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) {
- struct inode *inode = file_inode(bb->file);
-
- unmap_mapping_range(inode->i_mapping, 0, 0, 1);
- }
-
- mutex_unlock(&sysfs_bin_lock);
-}
-
-/**
- * sysfs_create_bin_file - create binary file for object.
- * @kobj: object.
- * @attr: attribute descriptor.
- */
-int sysfs_create_bin_file(struct kobject *kobj,
- const struct bin_attribute *attr)
-{
- BUG_ON(!kobj || !kobj->sd || !attr);
-
- return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
-}
-EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
-
-/**
- * sysfs_remove_bin_file - remove binary file for object.
- * @kobj: object.
- * @attr: attribute descriptor.
- */
-void sysfs_remove_bin_file(struct kobject *kobj,
- const struct bin_attribute *attr)
-{
- sysfs_hash_and_remove(kobj->sd, NULL, attr->attr.name);
-}
-EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 4d83cedb9fcb..5e73d6626e50 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -26,21 +26,21 @@
#include "sysfs.h"
DEFINE_MUTEX(sysfs_mutex);
-DEFINE_SPINLOCK(sysfs_assoc_lock);
+DEFINE_SPINLOCK(sysfs_symlink_target_lock);
-#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb);
+#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb)
static DEFINE_SPINLOCK(sysfs_ino_lock);
static DEFINE_IDA(sysfs_ino_ida);
/**
* sysfs_name_hash
- * @ns: Namespace tag to hash
* @name: Null terminated string to hash
+ * @ns: Namespace tag to hash
*
* Returns 31 bit hash of ns + name (so it fits in an off_t )
*/
-static unsigned int sysfs_name_hash(const void *ns, const char *name)
+static unsigned int sysfs_name_hash(const char *name, const void *ns)
{
unsigned long hash = init_name_hash();
unsigned int len = strlen(name);
@@ -56,8 +56,8 @@ static unsigned int sysfs_name_hash(const void *ns, const char *name)
return hash;
}
-static int sysfs_name_compare(unsigned int hash, const void *ns,
- const char *name, const struct sysfs_dirent *sd)
+static int sysfs_name_compare(unsigned int hash, const char *name,
+ const void *ns, const struct sysfs_dirent *sd)
{
if (hash != sd->s_hash)
return hash - sd->s_hash;
@@ -69,7 +69,7 @@ static int sysfs_name_compare(unsigned int hash, const void *ns,
static int sysfs_sd_compare(const struct sysfs_dirent *left,
const struct sysfs_dirent *right)
{
- return sysfs_name_compare(left->s_hash, left->s_ns, left->s_name,
+ return sysfs_name_compare(left->s_hash, left->s_name, left->s_ns,
right);
}
@@ -132,24 +132,6 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children);
}
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-
-/* Test for attributes that want to ignore lockdep for read-locking */
-static bool ignore_lockdep(struct sysfs_dirent *sd)
-{
- return sysfs_type(sd) == SYSFS_KOBJ_ATTR &&
- sd->s_attr.attr->ignore_lockdep;
-}
-
-#else
-
-static inline bool ignore_lockdep(struct sysfs_dirent *sd)
-{
- return true;
-}
-
-#endif
-
/**
* sysfs_get_active - get an active reference to sysfs_dirent
* @sd: sysfs_dirent to get an active reference to
@@ -168,7 +150,7 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
if (!atomic_inc_unless_negative(&sd->s_active))
return NULL;
- if (likely(!ignore_lockdep(sd)))
+ if (likely(!sysfs_ignore_lockdep(sd)))
rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
return sd;
}
@@ -187,7 +169,7 @@ void sysfs_put_active(struct sysfs_dirent *sd)
if (unlikely(!sd))
return;
- if (likely(!ignore_lockdep(sd)))
+ if (likely(!sysfs_ignore_lockdep(sd)))
rwsem_release(&sd->dep_map, 1, _RET_IP_);
v = atomic_dec_return(&sd->s_active);
if (likely(v != SD_DEACTIVATED_BIAS))
@@ -400,22 +382,19 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
/**
* sysfs_addrm_start - prepare for sysfs_dirent add/remove
* @acxt: pointer to sysfs_addrm_cxt to be used
- * @parent_sd: parent sysfs_dirent
*
- * This function is called when the caller is about to add or
- * remove sysfs_dirent under @parent_sd. This function acquires
- * sysfs_mutex. @acxt is used to keep and pass context to
- * other addrm functions.
+ * This function is called when the caller is about to add or remove
+ * sysfs_dirent. This function acquires sysfs_mutex. @acxt is used
+ * to keep and pass context to other addrm functions.
*
* LOCKING:
* Kernel thread context (may sleep). sysfs_mutex is locked on
* return.
*/
-void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
- struct sysfs_dirent *parent_sd)
+void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt)
+ __acquires(sysfs_mutex)
{
memset(acxt, 0, sizeof(*acxt));
- acxt->parent_sd = parent_sd;
mutex_lock(&sysfs_mutex);
}
@@ -424,10 +403,11 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
* __sysfs_add_one - add sysfs_dirent to parent without warning
* @acxt: addrm context to use
* @sd: sysfs_dirent to be added
+ * @parent_sd: the parent sysfs_dirent to add @sd to
*
- * Get @acxt->parent_sd and set sd->s_parent to it and increment
- * nlink of parent inode if @sd is a directory and link into the
- * children list of the parent.
+ * Get @parent_sd and set @sd->s_parent to it and increment nlink of
+ * the parent inode if @sd is a directory and link into the children
+ * list of the parent.
*
* This function should be called between calls to
* sysfs_addrm_start() and sysfs_addrm_finish() and should be
@@ -440,27 +420,28 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
* 0 on success, -EEXIST if entry with the given name already
* exists.
*/
-int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
+ struct sysfs_dirent *parent_sd)
{
struct sysfs_inode_attrs *ps_iattr;
int ret;
- if (!!sysfs_ns_type(acxt->parent_sd) != !!sd->s_ns) {
+ if (!!sysfs_ns_type(parent_sd) != !!sd->s_ns) {
WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
- sysfs_ns_type(acxt->parent_sd) ? "required" : "invalid",
- acxt->parent_sd->s_name, sd->s_name);
+ sysfs_ns_type(parent_sd) ? "required" : "invalid",
+ parent_sd->s_name, sd->s_name);
return -EINVAL;
}
- sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
- sd->s_parent = sysfs_get(acxt->parent_sd);
+ sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns);
+ sd->s_parent = sysfs_get(parent_sd);
ret = sysfs_link_sibling(sd);
if (ret)
return ret;
/* Update timestamps on the parent */
- ps_iattr = acxt->parent_sd->s_iattr;
+ ps_iattr = parent_sd->s_iattr;
if (ps_iattr) {
struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
@@ -490,14 +471,32 @@ static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
return path;
}
+void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name)
+{
+ char *path;
+
+ path = kzalloc(PATH_MAX, GFP_KERNEL);
+ if (path) {
+ sysfs_pathname(parent, path);
+ strlcat(path, "/", PATH_MAX);
+ strlcat(path, name, PATH_MAX);
+ }
+
+ WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n",
+ path ? path : name);
+
+ kfree(path);
+}
+
/**
* sysfs_add_one - add sysfs_dirent to parent
* @acxt: addrm context to use
* @sd: sysfs_dirent to be added
+ * @parent_sd: the parent sysfs_dirent to add @sd to
*
- * Get @acxt->parent_sd and set sd->s_parent to it and increment
- * nlink of parent inode if @sd is a directory and link into the
- * children list of the parent.
+ * Get @parent_sd and set @sd->s_parent to it and increment nlink of
+ * the parent inode if @sd is a directory and link into the children
+ * list of the parent.
*
* This function should be called between calls to
* sysfs_addrm_start() and sysfs_addrm_finish() and should be
@@ -510,23 +509,15 @@ static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
* 0 on success, -EEXIST if entry with the given name already
* exists.
*/
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
+ struct sysfs_dirent *parent_sd)
{
int ret;
- ret = __sysfs_add_one(acxt, sd);
- if (ret == -EEXIST) {
- char *path = kzalloc(PATH_MAX, GFP_KERNEL);
- WARN(1, KERN_WARNING
- "sysfs: cannot create duplicate filename '%s'\n",
- (path == NULL) ? sd->s_name
- : (sysfs_pathname(acxt->parent_sd, path),
- strlcat(path, "/", PATH_MAX),
- strlcat(path, sd->s_name, PATH_MAX),
- path));
- kfree(path);
- }
+ ret = __sysfs_add_one(acxt, sd, parent_sd);
+ if (ret == -EEXIST)
+ sysfs_warn_dup(parent_sd, sd->s_name);
return ret;
}
@@ -545,16 +536,22 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
* LOCKING:
* Determined by sysfs_addrm_start().
*/
-void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+static void sysfs_remove_one(struct sysfs_addrm_cxt *acxt,
+ struct sysfs_dirent *sd)
{
struct sysfs_inode_attrs *ps_iattr;
- BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);
+ /*
+ * Removal can be called multiple times on the same node. Only the
+ * first invocation is effective and puts the base ref.
+ */
+ if (sd->s_flags & SYSFS_FLAG_REMOVED)
+ return;
sysfs_unlink_sibling(sd);
/* Update timestamps on the parent */
- ps_iattr = acxt->parent_sd->s_iattr;
+ ps_iattr = sd->s_parent->s_iattr;
if (ps_iattr) {
struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
@@ -577,6 +574,7 @@ void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
* sysfs_mutex is released.
*/
void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
+ __releases(sysfs_mutex)
{
/* release resources acquired by sysfs_addrm_start() */
mutex_unlock(&sysfs_mutex);
@@ -588,7 +586,7 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
acxt->removed = sd->u.removed_list;
sysfs_deactivate(sd);
- unmap_bin_file(sd);
+ sysfs_unmap_bin_file(sd);
sysfs_put(sd);
}
}
@@ -597,6 +595,7 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
* sysfs_find_dirent - find sysfs_dirent with the given name
* @parent_sd: sysfs_dirent to search under
* @name: name to look for
+ * @ns: the namespace tag to use
*
* Look for sysfs_dirent with name @name under @parent_sd.
*
@@ -607,8 +606,8 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
* Pointer to sysfs_dirent if found, NULL if not.
*/
struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
- const void *ns,
- const unsigned char *name)
+ const unsigned char *name,
+ const void *ns)
{
struct rb_node *node = parent_sd->s_dir.children.rb_node;
unsigned int hash;
@@ -620,13 +619,13 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
return NULL;
}
- hash = sysfs_name_hash(ns, name);
+ hash = sysfs_name_hash(name, ns);
while (node) {
struct sysfs_dirent *sd;
int result;
sd = to_sysfs_dirent(node);
- result = sysfs_name_compare(hash, ns, name, sd);
+ result = sysfs_name_compare(hash, name, ns, sd);
if (result < 0)
node = node->rb_left;
else if (result > 0)
@@ -638,9 +637,10 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
}
/**
- * sysfs_get_dirent - find and get sysfs_dirent with the given name
+ * sysfs_get_dirent_ns - find and get sysfs_dirent with the given name
* @parent_sd: sysfs_dirent to search under
* @name: name to look for
+ * @ns: the namespace tag to use
*
* Look for sysfs_dirent with name @name under @parent_sd and get
* it if found.
@@ -651,24 +651,25 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
* RETURNS:
* Pointer to sysfs_dirent if found, NULL if not.
*/
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
- const void *ns,
- const unsigned char *name)
+struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd,
+ const unsigned char *name,
+ const void *ns)
{
struct sysfs_dirent *sd;
mutex_lock(&sysfs_mutex);
- sd = sysfs_find_dirent(parent_sd, ns, name);
+ sd = sysfs_find_dirent(parent_sd, name, ns);
sysfs_get(sd);
mutex_unlock(&sysfs_mutex);
return sd;
}
-EXPORT_SYMBOL_GPL(sysfs_get_dirent);
+EXPORT_SYMBOL_GPL(sysfs_get_dirent_ns);
static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
- enum kobj_ns_type type, const void *ns, const char *name,
- struct sysfs_dirent **p_sd)
+ enum kobj_ns_type type,
+ const char *name, const void *ns,
+ struct sysfs_dirent **p_sd)
{
umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
struct sysfs_addrm_cxt acxt;
@@ -685,8 +686,8 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
sd->s_dir.kobj = kobj;
/* link in */
- sysfs_addrm_start(&acxt, parent_sd);
- rc = sysfs_add_one(&acxt, sd);
+ sysfs_addrm_start(&acxt);
+ rc = sysfs_add_one(&acxt, sd, parent_sd);
sysfs_addrm_finish(&acxt);
if (rc == 0)
@@ -701,7 +702,7 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name,
struct sysfs_dirent **p_sd)
{
return create_dir(kobj, kobj->sd,
- KOBJ_NS_TYPE_NONE, NULL, name, p_sd);
+ KOBJ_NS_TYPE_NONE, name, NULL, p_sd);
}
/**
@@ -730,14 +731,14 @@ static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
}
/**
- * sysfs_create_dir - create a directory for an object.
- * @kobj: object we're creating directory for.
+ * sysfs_create_dir_ns - create a directory for an object with a namespace tag
+ * @kobj: object we're creating directory for
+ * @ns: the namespace tag to use
*/
-int sysfs_create_dir(struct kobject *kobj)
+int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
{
enum kobj_ns_type type;
struct sysfs_dirent *parent_sd, *sd;
- const void *ns = NULL;
int error = 0;
BUG_ON(!kobj);
@@ -750,11 +751,9 @@ int sysfs_create_dir(struct kobject *kobj)
if (!parent_sd)
return -ENOENT;
- if (sysfs_ns_type(parent_sd))
- ns = kobj->ktype->namespace(kobj);
type = sysfs_read_ns_type(kobj);
- error = create_dir(kobj, parent_sd, type, ns, kobject_name(kobj), &sd);
+ error = create_dir(kobj, parent_sd, type, kobject_name(kobj), ns, &sd);
if (!error)
kobj->sd = sd;
return error;
@@ -776,7 +775,7 @@ static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry,
type = sysfs_ns_type(parent_sd);
ns = sysfs_info(dir->i_sb)->ns[type];
- sd = sysfs_find_dirent(parent_sd, ns, dentry->d_name.name);
+ sd = sysfs_find_dirent(parent_sd, dentry->d_name.name, ns);
/* no such entry */
if (!sd) {
@@ -807,41 +806,128 @@ const struct inode_operations sysfs_dir_inode_operations = {
.setxattr = sysfs_setxattr,
};
-static void remove_dir(struct sysfs_dirent *sd)
+static struct sysfs_dirent *sysfs_leftmost_descendant(struct sysfs_dirent *pos)
{
- struct sysfs_addrm_cxt acxt;
+ struct sysfs_dirent *last;
- sysfs_addrm_start(&acxt, sd->s_parent);
- sysfs_remove_one(&acxt, sd);
- sysfs_addrm_finish(&acxt);
+ while (true) {
+ struct rb_node *rbn;
+
+ last = pos;
+
+ if (sysfs_type(pos) != SYSFS_DIR)
+ break;
+
+ rbn = rb_first(&pos->s_dir.children);
+ if (!rbn)
+ break;
+
+ pos = to_sysfs_dirent(rbn);
+ }
+
+ return last;
}
-void sysfs_remove_subdir(struct sysfs_dirent *sd)
+/**
+ * sysfs_next_descendant_post - find the next descendant for post-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @root: sysfs_dirent whose descendants to walk
+ *
+ * Find the next descendant to visit for post-order traversal of @root's
+ * descendants. @root is included in the iteration and the last node to be
+ * visited.
+ */
+static struct sysfs_dirent *sysfs_next_descendant_post(struct sysfs_dirent *pos,
+ struct sysfs_dirent *root)
{
- remove_dir(sd);
+ struct rb_node *rbn;
+
+ lockdep_assert_held(&sysfs_mutex);
+
+ /* if first iteration, visit leftmost descendant which may be root */
+ if (!pos)
+ return sysfs_leftmost_descendant(root);
+
+ /* if we visited @root, we're done */
+ if (pos == root)
+ return NULL;
+
+ /* if there's an unvisited sibling, visit its leftmost descendant */
+ rbn = rb_next(&pos->s_rb);
+ if (rbn)
+ return sysfs_leftmost_descendant(to_sysfs_dirent(rbn));
+
+ /* no sibling left, visit parent */
+ return pos->s_parent;
}
+static void __sysfs_remove(struct sysfs_addrm_cxt *acxt,
+ struct sysfs_dirent *sd)
+{
+ struct sysfs_dirent *pos, *next;
+
+ if (!sd)
+ return;
-static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
+ pr_debug("sysfs %s: removing\n", sd->s_name);
+
+ next = NULL;
+ do {
+ pos = next;
+ next = sysfs_next_descendant_post(pos, sd);
+ if (pos)
+ sysfs_remove_one(acxt, pos);
+ } while (next);
+}
+
+/**
+ * sysfs_remove - remove a sysfs_dirent recursively
+ * @sd: the sysfs_dirent to remove
+ *
+ * Remove @sd along with all its subdirectories and files.
+ */
+void sysfs_remove(struct sysfs_dirent *sd)
{
struct sysfs_addrm_cxt acxt;
- struct rb_node *pos;
- if (!dir_sd)
- return;
+ sysfs_addrm_start(&acxt);
+ __sysfs_remove(&acxt, sd);
+ sysfs_addrm_finish(&acxt);
+}
- pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
- sysfs_addrm_start(&acxt, dir_sd);
- pos = rb_first(&dir_sd->s_dir.children);
- while (pos) {
- struct sysfs_dirent *sd = to_sysfs_dirent(pos);
- pos = rb_next(pos);
- if (sysfs_type(sd) != SYSFS_DIR)
- sysfs_remove_one(&acxt, sd);
+/**
+ * sysfs_hash_and_remove - find a sysfs_dirent by name and remove it
+ * @dir_sd: parent of the target
+ * @name: name of the sysfs_dirent to remove
+ * @ns: namespace tag of the sysfs_dirent to remove
+ *
+ * Look for the sysfs_dirent with @name and @ns under @dir_sd and remove
+ * it. Returns 0 on success, -ENOENT if such entry doesn't exist.
+ */
+int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name,
+ const void *ns)
+{
+ struct sysfs_addrm_cxt acxt;
+ struct sysfs_dirent *sd;
+
+ if (!dir_sd) {
+ WARN(1, KERN_WARNING "sysfs: can not remove '%s', no directory\n",
+ name);
+ return -ENOENT;
}
+
+ sysfs_addrm_start(&acxt);
+
+ sd = sysfs_find_dirent(dir_sd, name, ns);
+ if (sd)
+ __sysfs_remove(&acxt, sd);
+
sysfs_addrm_finish(&acxt);
- remove_dir(dir_sd);
+ if (sd)
+ return 0;
+ else
+ return -ENOENT;
}
/**
@@ -852,21 +938,34 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
* the directory before we remove the directory, and we've inlined
* what used to be sysfs_rmdir() below, instead of calling separately.
*/
-
void sysfs_remove_dir(struct kobject *kobj)
{
struct sysfs_dirent *sd = kobj->sd;
- spin_lock(&sysfs_assoc_lock);
+ /*
+ * In general, kboject owner is responsible for ensuring removal
+ * doesn't race with other operations and sysfs doesn't provide any
+ * protection; however, when @kobj is used as a symlink target, the
+ * symlinking entity usually doesn't own @kobj and thus has no
+ * control over removal. @kobj->sd may be removed anytime and
+ * symlink code may end up dereferencing an already freed sd.
+ *
+ * sysfs_symlink_target_lock synchronizes @kobj->sd disassociation
+ * against symlink operations so that symlink code can safely
+ * dereference @kobj->sd.
+ */
+ spin_lock(&sysfs_symlink_target_lock);
kobj->sd = NULL;
- spin_unlock(&sysfs_assoc_lock);
+ spin_unlock(&sysfs_symlink_target_lock);
- __sysfs_remove_dir(sd);
+ if (sd) {
+ WARN_ON_ONCE(sysfs_type(sd) != SYSFS_DIR);
+ sysfs_remove(sd);
+ }
}
-int sysfs_rename(struct sysfs_dirent *sd,
- struct sysfs_dirent *new_parent_sd, const void *new_ns,
- const char *new_name)
+int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
+ const char *new_name, const void *new_ns)
{
int error;
@@ -878,7 +977,7 @@ int sysfs_rename(struct sysfs_dirent *sd,
goto out; /* nothing to rename */
error = -EEXIST;
- if (sysfs_find_dirent(new_parent_sd, new_ns, new_name))
+ if (sysfs_find_dirent(new_parent_sd, new_name, new_ns))
goto out;
/* rename sysfs_dirent */
@@ -899,7 +998,7 @@ int sysfs_rename(struct sysfs_dirent *sd,
sysfs_get(new_parent_sd);
sysfs_put(sd->s_parent);
sd->s_ns = new_ns;
- sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
+ sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns);
sd->s_parent = new_parent_sd;
sysfs_link_sibling(sd);
@@ -909,30 +1008,25 @@ int sysfs_rename(struct sysfs_dirent *sd,
return error;
}
-int sysfs_rename_dir(struct kobject *kobj, const char *new_name)
+int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
+ const void *new_ns)
{
struct sysfs_dirent *parent_sd = kobj->sd->s_parent;
- const void *new_ns = NULL;
-
- if (sysfs_ns_type(parent_sd))
- new_ns = kobj->ktype->namespace(kobj);
- return sysfs_rename(kobj->sd, parent_sd, new_ns, new_name);
+ return sysfs_rename(kobj->sd, parent_sd, new_name, new_ns);
}
-int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
+int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
+ const void *new_ns)
{
struct sysfs_dirent *sd = kobj->sd;
struct sysfs_dirent *new_parent_sd;
- const void *new_ns = NULL;
BUG_ON(!sd->s_parent);
- if (sysfs_ns_type(sd->s_parent))
- new_ns = kobj->ktype->namespace(kobj);
new_parent_sd = new_parent_kobj && new_parent_kobj->sd ?
new_parent_kobj->sd : &sysfs_root;
- return sysfs_rename(sd, new_parent_sd, new_ns, sd->s_name);
+ return sysfs_rename(sd, new_parent_sd, sd->s_name, new_ns);
}
/* Relationship between s_mode and the DT_xxx types */
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 15ef5eb13663..79b5da2acbe1 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -21,70 +21,114 @@
#include <linux/mutex.h>
#include <linux/limits.h>
#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/mm.h>
#include "sysfs.h"
/*
- * There's one sysfs_buffer for each open file and one
- * sysfs_open_dirent for each sysfs_dirent with one or more open
- * files.
+ * There's one sysfs_open_file for each open file and one sysfs_open_dirent
+ * for each sysfs_dirent with one or more open files.
*
- * filp->private_data points to sysfs_buffer and
- * sysfs_dirent->s_attr.open points to sysfs_open_dirent. s_attr.open
- * is protected by sysfs_open_dirent_lock.
+ * sysfs_dirent->s_attr.open points to sysfs_open_dirent. s_attr.open is
+ * protected by sysfs_open_dirent_lock.
+ *
+ * filp->private_data points to seq_file whose ->private points to
+ * sysfs_open_file. sysfs_open_files are chained at
+ * sysfs_open_dirent->files, which is protected by sysfs_open_file_mutex.
*/
static DEFINE_SPINLOCK(sysfs_open_dirent_lock);
+static DEFINE_MUTEX(sysfs_open_file_mutex);
struct sysfs_open_dirent {
atomic_t refcnt;
atomic_t event;
wait_queue_head_t poll;
- struct list_head buffers; /* goes through sysfs_buffer.list */
+ struct list_head files; /* goes through sysfs_open_file.list */
};
-struct sysfs_buffer {
- size_t count;
- loff_t pos;
- char *page;
- const struct sysfs_ops *ops;
+struct sysfs_open_file {
+ struct sysfs_dirent *sd;
+ struct file *file;
struct mutex mutex;
- int needs_read_fill;
int event;
struct list_head list;
+
+ bool mmapped;
+ const struct vm_operations_struct *vm_ops;
};
-/**
- * fill_read_buffer - allocate and fill buffer from object.
- * @dentry: dentry pointer.
- * @buffer: data buffer for file.
- *
- * Allocate @buffer->page, if it hasn't been already, then call the
- * kobject's show() method to fill the buffer with this attribute's
- * data.
- * This is called only once, on the file's first read unless an error
- * is returned.
+static bool sysfs_is_bin(struct sysfs_dirent *sd)
+{
+ return sysfs_type(sd) == SYSFS_KOBJ_BIN_ATTR;
+}
+
+static struct sysfs_open_file *sysfs_of(struct file *file)
+{
+ return ((struct seq_file *)file->private_data)->private;
+}
+
+/*
+ * Determine ktype->sysfs_ops for the given sysfs_dirent. This function
+ * must be called while holding an active reference.
*/
-static int fill_read_buffer(struct dentry *dentry, struct sysfs_buffer *buffer)
+static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd)
{
- struct sysfs_dirent *attr_sd = dentry->d_fsdata;
- struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- const struct sysfs_ops *ops = buffer->ops;
- int ret = 0;
+ struct kobject *kobj = sd->s_parent->s_dir.kobj;
+
+ if (!sysfs_ignore_lockdep(sd))
+ lockdep_assert_held(sd);
+ return kobj->ktype ? kobj->ktype->sysfs_ops : NULL;
+}
+
+/*
+ * Reads on sysfs are handled through seq_file, which takes care of hairy
+ * details like buffering and seeking. The following function pipes
+ * sysfs_ops->show() result through seq_file.
+ */
+static int sysfs_seq_show(struct seq_file *sf, void *v)
+{
+ struct sysfs_open_file *of = sf->private;
+ struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
+ const struct sysfs_ops *ops;
+ char *buf;
ssize_t count;
- if (!buffer->page)
- buffer->page = (char *) get_zeroed_page(GFP_KERNEL);
- if (!buffer->page)
- return -ENOMEM;
+ /* acquire buffer and ensure that it's >= PAGE_SIZE */
+ count = seq_get_buf(sf, &buf);
+ if (count < PAGE_SIZE) {
+ seq_commit(sf, -1);
+ return 0;
+ }
- /* need attr_sd for attr and ops, its parent for kobj */
- if (!sysfs_get_active(attr_sd))
+ /*
+ * Need @of->sd for attr and ops, its parent for kobj. @of->mutex
+ * nests outside active ref and is just to ensure that the ops
+ * aren't called concurrently for the same open file.
+ */
+ mutex_lock(&of->mutex);
+ if (!sysfs_get_active(of->sd)) {
+ mutex_unlock(&of->mutex);
return -ENODEV;
+ }
- buffer->event = atomic_read(&attr_sd->s_attr.open->event);
- count = ops->show(kobj, attr_sd->s_attr.attr, buffer->page);
+ of->event = atomic_read(&of->sd->s_attr.open->event);
- sysfs_put_active(attr_sd);
+ /*
+ * Lookup @ops and invoke show(). Control may reach here via seq
+ * file lseek even if @ops->show() isn't implemented.
+ */
+ ops = sysfs_file_ops(of->sd);
+ if (ops->show)
+ count = ops->show(kobj, of->sd->s_attr.attr, buf);
+ else
+ count = 0;
+
+ sysfs_put_active(of->sd);
+ mutex_unlock(&of->mutex);
+
+ if (count < 0)
+ return count;
/*
* The code works fine with PAGE_SIZE return but it's likely to
@@ -96,155 +140,389 @@ static int fill_read_buffer(struct dentry *dentry, struct sysfs_buffer *buffer)
/* Try to struggle along */
count = PAGE_SIZE - 1;
}
- if (count >= 0) {
- buffer->needs_read_fill = 0;
- buffer->count = count;
- } else {
- ret = count;
- }
- return ret;
+ seq_commit(sf, count);
+ return 0;
}
-/**
- * sysfs_read_file - read an attribute.
- * @file: file pointer.
- * @buf: buffer to fill.
- * @count: number of bytes to read.
- * @ppos: starting offset in file.
- *
- * Userspace wants to read an attribute file. The attribute descriptor
- * is in the file's ->d_fsdata. The target object is in the directory's
- * ->d_fsdata.
- *
- * We call fill_read_buffer() to allocate and fill the buffer from the
- * object's show() method exactly once (if the read is happening from
- * the beginning of the file). That should fill the entire buffer with
- * all the data the object has to offer for that attribute.
- * We then call flush_read_buffer() to copy the buffer to userspace
- * in the increments specified.
+/*
+ * Read method for bin files. As reading a bin file can have side-effects,
+ * the exact offset and bytes specified in read(2) call should be passed to
+ * the read callback making it difficult to use seq_file. Implement
+ * simplistic custom buffering for bin files.
*/
-
-static ssize_t
-sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+static ssize_t sysfs_bin_read(struct file *file, char __user *userbuf,
+ size_t bytes, loff_t *off)
{
- struct sysfs_buffer *buffer = file->private_data;
- ssize_t retval = 0;
+ struct sysfs_open_file *of = sysfs_of(file);
+ struct bin_attribute *battr = of->sd->s_attr.bin_attr;
+ struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
+ loff_t size = file_inode(file)->i_size;
+ int count = min_t(size_t, bytes, PAGE_SIZE);
+ loff_t offs = *off;
+ char *buf;
+
+ if (!bytes)
+ return 0;
- mutex_lock(&buffer->mutex);
- if (buffer->needs_read_fill || *ppos == 0) {
- retval = fill_read_buffer(file->f_path.dentry, buffer);
- if (retval)
- goto out;
+ if (size) {
+ if (offs > size)
+ return 0;
+ if (offs + count > size)
+ count = size - offs;
}
- pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n",
- __func__, count, *ppos, buffer->page);
- retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
- buffer->count);
-out:
- mutex_unlock(&buffer->mutex);
- return retval;
-}
-/**
- * fill_write_buffer - copy buffer from userspace.
- * @buffer: data buffer for file.
- * @buf: data from user.
- * @count: number of bytes in @userbuf.
- *
- * Allocate @buffer->page if it hasn't been already, then
- * copy the user-supplied buffer into it.
- */
-static int fill_write_buffer(struct sysfs_buffer *buffer,
- const char __user *buf, size_t count)
-{
- int error;
-
- if (!buffer->page)
- buffer->page = (char *)get_zeroed_page(GFP_KERNEL);
- if (!buffer->page)
+ buf = kmalloc(count, GFP_KERNEL);
+ if (!buf)
return -ENOMEM;
- if (count >= PAGE_SIZE)
- count = PAGE_SIZE - 1;
- error = copy_from_user(buffer->page, buf, count);
- buffer->needs_read_fill = 1;
- /* if buf is assumed to contain a string, terminate it by \0,
- so e.g. sscanf() can scan the string easily */
- buffer->page[count] = 0;
- return error ? -EFAULT : count;
-}
+ /* need of->sd for battr, its parent for kobj */
+ mutex_lock(&of->mutex);
+ if (!sysfs_get_active(of->sd)) {
+ count = -ENODEV;
+ mutex_unlock(&of->mutex);
+ goto out_free;
+ }
+
+ if (battr->read)
+ count = battr->read(file, kobj, battr, buf, offs, count);
+ else
+ count = -EIO;
+ sysfs_put_active(of->sd);
+ mutex_unlock(&of->mutex);
+
+ if (count < 0)
+ goto out_free;
+
+ if (copy_to_user(userbuf, buf, count)) {
+ count = -EFAULT;
+ goto out_free;
+ }
+
+ pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
+
+ *off = offs + count;
+
+ out_free:
+ kfree(buf);
+ return count;
+}
/**
- * flush_write_buffer - push buffer to kobject.
- * @dentry: dentry to the attribute
- * @buffer: data buffer for file.
- * @count: number of bytes
+ * flush_write_buffer - push buffer to kobject
+ * @of: open file
+ * @buf: data buffer for file
+ * @off: file offset to write to
+ * @count: number of bytes
*
- * Get the correct pointers for the kobject and the attribute we're
- * dealing with, then call the store() method for the attribute,
- * passing the buffer that we acquired in fill_write_buffer().
+ * Get the correct pointers for the kobject and the attribute we're dealing
+ * with, then call the store() method for it with @buf.
*/
-static int flush_write_buffer(struct dentry *dentry,
- struct sysfs_buffer *buffer, size_t count)
+static int flush_write_buffer(struct sysfs_open_file *of, char *buf, loff_t off,
+ size_t count)
{
- struct sysfs_dirent *attr_sd = dentry->d_fsdata;
- struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- const struct sysfs_ops *ops = buffer->ops;
- int rc;
+ struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
+ int rc = 0;
- /* need attr_sd for attr and ops, its parent for kobj */
- if (!sysfs_get_active(attr_sd))
+ /*
+ * Need @of->sd for attr and ops, its parent for kobj. @of->mutex
+ * nests outside active ref and is just to ensure that the ops
+ * aren't called concurrently for the same open file.
+ */
+ mutex_lock(&of->mutex);
+ if (!sysfs_get_active(of->sd)) {
+ mutex_unlock(&of->mutex);
return -ENODEV;
+ }
- rc = ops->store(kobj, attr_sd->s_attr.attr, buffer->page, count);
+ if (sysfs_is_bin(of->sd)) {
+ struct bin_attribute *battr = of->sd->s_attr.bin_attr;
- sysfs_put_active(attr_sd);
+ rc = -EIO;
+ if (battr->write)
+ rc = battr->write(of->file, kobj, battr, buf, off,
+ count);
+ } else {
+ const struct sysfs_ops *ops = sysfs_file_ops(of->sd);
+
+ rc = ops->store(kobj, of->sd->s_attr.attr, buf, count);
+ }
+
+ sysfs_put_active(of->sd);
+ mutex_unlock(&of->mutex);
return rc;
}
-
/**
- * sysfs_write_file - write an attribute.
- * @file: file pointer
- * @buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
+ * sysfs_write_file - write an attribute
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ *
+ * Copy data in from userland and pass it to the matching
+ * sysfs_ops->store() by invoking flush_write_buffer().
*
- * Similar to sysfs_read_file(), though working in the opposite direction.
- * We allocate and fill the data from the user in fill_write_buffer(),
- * then push it to the kobject in flush_write_buffer().
- * There is no easy way for us to know if userspace is only doing a partial
- * write, so we don't support them. We expect the entire buffer to come
- * on the first write.
- * Hint: if you're writing a value, first read the file, modify only the
- * the value you're changing, then write entire buffer back.
+ * There is no easy way for us to know if userspace is only doing a partial
+ * write, so we don't support them. We expect the entire buffer to come on
+ * the first write. Hint: if you're writing a value, first read the file,
+ * modify only the the value you're changing, then write entire buffer
+ * back.
*/
-static ssize_t sysfs_write_file(struct file *file, const char __user *buf,
+static ssize_t sysfs_write_file(struct file *file, const char __user *user_buf,
size_t count, loff_t *ppos)
{
- struct sysfs_buffer *buffer = file->private_data;
- ssize_t len;
+ struct sysfs_open_file *of = sysfs_of(file);
+ ssize_t len = min_t(size_t, count, PAGE_SIZE);
+ loff_t size = file_inode(file)->i_size;
+ char *buf;
+
+ if (sysfs_is_bin(of->sd) && size) {
+ if (size <= *ppos)
+ return 0;
+ len = min_t(ssize_t, len, size - *ppos);
+ }
- mutex_lock(&buffer->mutex);
- len = fill_write_buffer(buffer, buf, count);
- if (len > 0)
- len = flush_write_buffer(file->f_path.dentry, buffer, len);
+ if (!len)
+ return 0;
+
+ buf = kmalloc(len + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, user_buf, len)) {
+ len = -EFAULT;
+ goto out_free;
+ }
+ buf[len] = '\0'; /* guarantee string termination */
+
+ len = flush_write_buffer(of, buf, *ppos, len);
if (len > 0)
*ppos += len;
- mutex_unlock(&buffer->mutex);
+out_free:
+ kfree(buf);
return len;
}
+static void sysfs_bin_vma_open(struct vm_area_struct *vma)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+
+ if (!of->vm_ops)
+ return;
+
+ if (!sysfs_get_active(of->sd))
+ return;
+
+ if (of->vm_ops->open)
+ of->vm_ops->open(vma);
+
+ sysfs_put_active(of->sd);
+}
+
+static int sysfs_bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+ int ret;
+
+ if (!of->vm_ops)
+ return VM_FAULT_SIGBUS;
+
+ if (!sysfs_get_active(of->sd))
+ return VM_FAULT_SIGBUS;
+
+ ret = VM_FAULT_SIGBUS;
+ if (of->vm_ops->fault)
+ ret = of->vm_ops->fault(vma, vmf);
+
+ sysfs_put_active(of->sd);
+ return ret;
+}
+
+static int sysfs_bin_page_mkwrite(struct vm_area_struct *vma,
+ struct vm_fault *vmf)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+ int ret;
+
+ if (!of->vm_ops)
+ return VM_FAULT_SIGBUS;
+
+ if (!sysfs_get_active(of->sd))
+ return VM_FAULT_SIGBUS;
+
+ ret = 0;
+ if (of->vm_ops->page_mkwrite)
+ ret = of->vm_ops->page_mkwrite(vma, vmf);
+ else
+ file_update_time(file);
+
+ sysfs_put_active(of->sd);
+ return ret;
+}
+
+static int sysfs_bin_access(struct vm_area_struct *vma, unsigned long addr,
+ void *buf, int len, int write)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+ int ret;
+
+ if (!of->vm_ops)
+ return -EINVAL;
+
+ if (!sysfs_get_active(of->sd))
+ return -EINVAL;
+
+ ret = -EINVAL;
+ if (of->vm_ops->access)
+ ret = of->vm_ops->access(vma, addr, buf, len, write);
+
+ sysfs_put_active(of->sd);
+ return ret;
+}
+
+#ifdef CONFIG_NUMA
+static int sysfs_bin_set_policy(struct vm_area_struct *vma,
+ struct mempolicy *new)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+ int ret;
+
+ if (!of->vm_ops)
+ return 0;
+
+ if (!sysfs_get_active(of->sd))
+ return -EINVAL;
+
+ ret = 0;
+ if (of->vm_ops->set_policy)
+ ret = of->vm_ops->set_policy(vma, new);
+
+ sysfs_put_active(of->sd);
+ return ret;
+}
+
+static struct mempolicy *sysfs_bin_get_policy(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+ struct mempolicy *pol;
+
+ if (!of->vm_ops)
+ return vma->vm_policy;
+
+ if (!sysfs_get_active(of->sd))
+ return vma->vm_policy;
+
+ pol = vma->vm_policy;
+ if (of->vm_ops->get_policy)
+ pol = of->vm_ops->get_policy(vma, addr);
+
+ sysfs_put_active(of->sd);
+ return pol;
+}
+
+static int sysfs_bin_migrate(struct vm_area_struct *vma, const nodemask_t *from,
+ const nodemask_t *to, unsigned long flags)
+{
+ struct file *file = vma->vm_file;
+ struct sysfs_open_file *of = sysfs_of(file);
+ int ret;
+
+ if (!of->vm_ops)
+ return 0;
+
+ if (!sysfs_get_active(of->sd))
+ return 0;
+
+ ret = 0;
+ if (of->vm_ops->migrate)
+ ret = of->vm_ops->migrate(vma, from, to, flags);
+
+ sysfs_put_active(of->sd);
+ return ret;
+}
+#endif
+
+static const struct vm_operations_struct sysfs_bin_vm_ops = {
+ .open = sysfs_bin_vma_open,
+ .fault = sysfs_bin_fault,
+ .page_mkwrite = sysfs_bin_page_mkwrite,
+ .access = sysfs_bin_access,
+#ifdef CONFIG_NUMA
+ .set_policy = sysfs_bin_set_policy,
+ .get_policy = sysfs_bin_get_policy,
+ .migrate = sysfs_bin_migrate,
+#endif
+};
+
+static int sysfs_bin_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct sysfs_open_file *of = sysfs_of(file);
+ struct bin_attribute *battr = of->sd->s_attr.bin_attr;
+ struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
+ int rc;
+
+ mutex_lock(&of->mutex);
+
+ /* need of->sd for battr, its parent for kobj */
+ rc = -ENODEV;
+ if (!sysfs_get_active(of->sd))
+ goto out_unlock;
+
+ if (!battr->mmap)
+ goto out_put;
+
+ rc = battr->mmap(file, kobj, battr, vma);
+ if (rc)
+ goto out_put;
+
+ /*
+ * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
+ * to satisfy versions of X which crash if the mmap fails: that
+ * substitutes a new vm_file, and we don't then want bin_vm_ops.
+ */
+ if (vma->vm_file != file)
+ goto out_put;
+
+ rc = -EINVAL;
+ if (of->mmapped && of->vm_ops != vma->vm_ops)
+ goto out_put;
+
+ /*
+ * It is not possible to successfully wrap close.
+ * So error if someone is trying to use close.
+ */
+ rc = -EINVAL;
+ if (vma->vm_ops && vma->vm_ops->close)
+ goto out_put;
+
+ rc = 0;
+ of->mmapped = 1;
+ of->vm_ops = vma->vm_ops;
+ vma->vm_ops = &sysfs_bin_vm_ops;
+out_put:
+ sysfs_put_active(of->sd);
+out_unlock:
+ mutex_unlock(&of->mutex);
+
+ return rc;
+}
+
/**
* sysfs_get_open_dirent - get or create sysfs_open_dirent
* @sd: target sysfs_dirent
- * @buffer: sysfs_buffer for this instance of open
+ * @of: sysfs_open_file for this instance of open
*
* If @sd->s_attr.open exists, increment its reference count;
- * otherwise, create one. @buffer is chained to the buffers
- * list.
+ * otherwise, create one. @of is chained to the files list.
*
* LOCKING:
* Kernel thread context (may sleep).
@@ -253,11 +531,12 @@ static ssize_t sysfs_write_file(struct file *file, const char __user *buf,
* 0 on success, -errno on failure.
*/
static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
- struct sysfs_buffer *buffer)
+ struct sysfs_open_file *of)
{
struct sysfs_open_dirent *od, *new_od = NULL;
retry:
+ mutex_lock(&sysfs_open_file_mutex);
spin_lock_irq(&sysfs_open_dirent_lock);
if (!sd->s_attr.open && new_od) {
@@ -268,10 +547,11 @@ static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
od = sd->s_attr.open;
if (od) {
atomic_inc(&od->refcnt);
- list_add_tail(&buffer->list, &od->buffers);
+ list_add_tail(&of->list, &od->files);
}
spin_unlock_irq(&sysfs_open_dirent_lock);
+ mutex_unlock(&sysfs_open_file_mutex);
if (od) {
kfree(new_od);
@@ -286,36 +566,40 @@ static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
atomic_set(&new_od->refcnt, 0);
atomic_set(&new_od->event, 1);
init_waitqueue_head(&new_od->poll);
- INIT_LIST_HEAD(&new_od->buffers);
+ INIT_LIST_HEAD(&new_od->files);
goto retry;
}
/**
* sysfs_put_open_dirent - put sysfs_open_dirent
* @sd: target sysfs_dirent
- * @buffer: associated sysfs_buffer
+ * @of: associated sysfs_open_file
*
- * Put @sd->s_attr.open and unlink @buffer from the buffers list.
- * If reference count reaches zero, disassociate and free it.
+ * Put @sd->s_attr.open and unlink @of from the files list. If
+ * reference count reaches zero, disassociate and free it.
*
* LOCKING:
* None.
*/
static void sysfs_put_open_dirent(struct sysfs_dirent *sd,
- struct sysfs_buffer *buffer)
+ struct sysfs_open_file *of)
{
struct sysfs_open_dirent *od = sd->s_attr.open;
unsigned long flags;
+ mutex_lock(&sysfs_open_file_mutex);
spin_lock_irqsave(&sysfs_open_dirent_lock, flags);
- list_del(&buffer->list);
+ if (of)
+ list_del(&of->list);
+
if (atomic_dec_and_test(&od->refcnt))
sd->s_attr.open = NULL;
else
od = NULL;
spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
+ mutex_unlock(&sysfs_open_file_mutex);
kfree(od);
}
@@ -324,67 +608,81 @@ 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_buffer *buffer;
- const struct sysfs_ops *ops;
+ struct sysfs_open_file *of;
+ bool has_read, has_write;
int error = -EACCES;
/* need attr_sd for attr and ops, its parent for kobj */
if (!sysfs_get_active(attr_sd))
return -ENODEV;
- /* every kobject with an attribute needs a ktype assigned */
- if (kobj->ktype && kobj->ktype->sysfs_ops)
- ops = kobj->ktype->sysfs_ops;
- else {
- WARN(1, KERN_ERR
- "missing sysfs attribute operations for kobject: %s\n",
- kobject_name(kobj));
- goto err_out;
- }
+ if (sysfs_is_bin(attr_sd)) {
+ struct bin_attribute *battr = attr_sd->s_attr.bin_attr;
- /* File needs write support.
- * The inode's perms must say it's ok,
- * and we must have a store method.
- */
- if (file->f_mode & FMODE_WRITE) {
- if (!(inode->i_mode & S_IWUGO) || !ops->store)
- goto err_out;
- }
+ has_read = battr->read || battr->mmap;
+ has_write = battr->write || battr->mmap;
+ } else {
+ const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
- /* File needs read support.
- * The inode's perms must say it's ok, and we there
- * must be a show method for it.
- */
- if (file->f_mode & FMODE_READ) {
- if (!(inode->i_mode & S_IRUGO) || !ops->show)
+ /* every kobject with an attribute needs a ktype assigned */
+ if (WARN(!ops, KERN_ERR
+ "missing sysfs attribute operations for kobject: %s\n",
+ kobject_name(kobj)))
goto err_out;
+
+ has_read = ops->show;
+ has_write = ops->store;
}
- /* No error? Great, allocate a buffer for the file, and store it
- * it in file->private_data for easy access.
- */
+ /* check perms and supported operations */
+ if ((file->f_mode & FMODE_WRITE) &&
+ (!(inode->i_mode & S_IWUGO) || !has_write))
+ goto err_out;
+
+ if ((file->f_mode & FMODE_READ) &&
+ (!(inode->i_mode & S_IRUGO) || !has_read))
+ goto err_out;
+
+ /* allocate a sysfs_open_file for the file */
error = -ENOMEM;
- buffer = kzalloc(sizeof(struct sysfs_buffer), GFP_KERNEL);
- if (!buffer)
+ of = kzalloc(sizeof(struct sysfs_open_file), GFP_KERNEL);
+ if (!of)
goto err_out;
- mutex_init(&buffer->mutex);
- buffer->needs_read_fill = 1;
- buffer->ops = ops;
- file->private_data = buffer;
+ mutex_init(&of->mutex);
+ of->sd = attr_sd;
+ of->file = file;
- /* make sure we have open dirent struct */
- error = sysfs_get_open_dirent(attr_sd, buffer);
+ /*
+ * Always instantiate seq_file even if read access doesn't use
+ * seq_file or is not requested. This unifies private data access
+ * and readable regular files are the vast majority anyway.
+ */
+ if (sysfs_is_bin(attr_sd))
+ error = single_open(file, NULL, of);
+ else
+ error = single_open(file, sysfs_seq_show, of);
if (error)
goto err_free;
+ /* seq_file clears PWRITE unconditionally, restore it if WRITE */
+ if (file->f_mode & FMODE_WRITE)
+ file->f_mode |= FMODE_PWRITE;
+
+ /* make sure we have open dirent struct */
+ error = sysfs_get_open_dirent(attr_sd, of);
+ if (error)
+ goto err_close;
+
/* open succeeded, put active references */
sysfs_put_active(attr_sd);
return 0;
- err_free:
- kfree(buffer);
- err_out:
+err_close:
+ single_release(inode, file);
+err_free:
+ kfree(of);
+err_out:
sysfs_put_active(attr_sd);
return error;
}
@@ -392,17 +690,41 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
static int sysfs_release(struct inode *inode, struct file *filp)
{
struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata;
- struct sysfs_buffer *buffer = filp->private_data;
+ struct sysfs_open_file *of = sysfs_of(filp);
- sysfs_put_open_dirent(sd, buffer);
-
- if (buffer->page)
- free_page((unsigned long)buffer->page);
- kfree(buffer);
+ sysfs_put_open_dirent(sd, of);
+ single_release(inode, filp);
+ kfree(of);
return 0;
}
+void sysfs_unmap_bin_file(struct sysfs_dirent *sd)
+{
+ struct sysfs_open_dirent *od;
+ struct sysfs_open_file *of;
+
+ if (!sysfs_is_bin(sd))
+ return;
+
+ spin_lock_irq(&sysfs_open_dirent_lock);
+ od = sd->s_attr.open;
+ if (od)
+ atomic_inc(&od->refcnt);
+ spin_unlock_irq(&sysfs_open_dirent_lock);
+ if (!od)
+ return;
+
+ mutex_lock(&sysfs_open_file_mutex);
+ list_for_each_entry(of, &od->files, list) {
+ struct inode *inode = file_inode(of->file);
+ unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+ }
+ mutex_unlock(&sysfs_open_file_mutex);
+
+ sysfs_put_open_dirent(sd, NULL);
+}
+
/* Sysfs attribute files are pollable. The idea is that you read
* the content and then you use 'poll' or 'select' to wait for
* the content to change. When the content changes (assuming the
@@ -418,7 +740,7 @@ static int sysfs_release(struct inode *inode, struct file *filp)
*/
static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
{
- struct sysfs_buffer *buffer = filp->private_data;
+ struct sysfs_open_file *of = sysfs_of(filp);
struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata;
struct sysfs_open_dirent *od = attr_sd->s_attr.open;
@@ -430,13 +752,12 @@ static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
sysfs_put_active(attr_sd);
- if (buffer->event != atomic_read(&od->event))
+ if (of->event != atomic_read(&od->event))
goto trigger;
return DEFAULT_POLLMASK;
trigger:
- buffer->needs_read_fill = 1;
return DEFAULT_POLLMASK|POLLERR|POLLPRI;
}
@@ -466,9 +787,9 @@ void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
mutex_lock(&sysfs_mutex);
if (sd && dir)
- sd = sysfs_find_dirent(sd, NULL, dir);
+ sd = sysfs_find_dirent(sd, dir, NULL);
if (sd && attr)
- sd = sysfs_find_dirent(sd, NULL, attr);
+ sd = sysfs_find_dirent(sd, attr, NULL);
if (sd)
sysfs_notify_dirent(sd);
@@ -477,7 +798,7 @@ void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
EXPORT_SYMBOL_GPL(sysfs_notify);
const struct file_operations sysfs_file_operations = {
- .read = sysfs_read_file,
+ .read = seq_read,
.write = sysfs_write_file,
.llseek = generic_file_llseek,
.open = sysfs_open_file,
@@ -485,58 +806,25 @@ const struct file_operations sysfs_file_operations = {
.poll = sysfs_poll,
};
-static int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr,
- const void **pns)
-{
- struct sysfs_dirent *dir_sd = kobj->sd;
- const struct sysfs_ops *ops;
- const void *ns = NULL;
- int err;
-
- if (!dir_sd) {
- WARN(1, KERN_ERR "sysfs: kobject %s without dirent\n",
- kobject_name(kobj));
- return -ENOENT;
- }
-
- err = 0;
- if (!sysfs_ns_type(dir_sd))
- goto out;
-
- err = -EINVAL;
- if (!kobj->ktype)
- goto out;
- ops = kobj->ktype->sysfs_ops;
- if (!ops)
- goto out;
- if (!ops->namespace)
- goto out;
-
- err = 0;
- ns = ops->namespace(kobj, attr);
-out:
- if (err) {
- WARN(1, KERN_ERR
- "missing sysfs namespace attribute operation for kobject: %s\n",
- kobject_name(kobj));
- }
- *pns = ns;
- return err;
-}
+const struct file_operations sysfs_bin_operations = {
+ .read = sysfs_bin_read,
+ .write = sysfs_write_file,
+ .llseek = generic_file_llseek,
+ .mmap = sysfs_bin_mmap,
+ .open = sysfs_open_file,
+ .release = sysfs_release,
+ .poll = sysfs_poll,
+};
-int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
- const struct attribute *attr, int type, umode_t amode)
+int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
+ const struct attribute *attr, int type,
+ umode_t amode, const void *ns)
{
umode_t mode = (amode & S_IALLUGO) | S_IFREG;
struct sysfs_addrm_cxt acxt;
struct sysfs_dirent *sd;
- const void *ns;
int rc;
- rc = sysfs_attr_ns(dir_sd->s_dir.kobj, attr, &ns);
- if (rc)
- return rc;
-
sd = sysfs_new_dirent(attr->name, mode, type);
if (!sd)
return -ENOMEM;
@@ -545,8 +833,8 @@ int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
sd->s_attr.attr = (void *)attr;
sysfs_dirent_init_lockdep(sd);
- sysfs_addrm_start(&acxt, dir_sd);
- rc = sysfs_add_one(&acxt, sd);
+ sysfs_addrm_start(&acxt);
+ rc = sysfs_add_one(&acxt, sd, dir_sd);
sysfs_addrm_finish(&acxt);
if (rc)
@@ -559,23 +847,25 @@ int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
int type)
{
- return sysfs_add_file_mode(dir_sd, attr, type, attr->mode);
+ return sysfs_add_file_mode_ns(dir_sd, attr, type, attr->mode, NULL);
}
-
/**
- * sysfs_create_file - create an attribute file for an object.
- * @kobj: object we're creating for.
- * @attr: attribute descriptor.
+ * sysfs_create_file_ns - create an attribute file for an object with custom ns
+ * @kobj: object we're creating for
+ * @attr: attribute descriptor
+ * @ns: namespace the new file should belong to
*/
-int sysfs_create_file(struct kobject *kobj, const struct attribute *attr)
+int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
+ const void *ns)
{
BUG_ON(!kobj || !kobj->sd || !attr);
- return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR);
+ return sysfs_add_file_mode_ns(kobj->sd, attr, SYSFS_KOBJ_ATTR,
+ attr->mode, ns);
}
-EXPORT_SYMBOL_GPL(sysfs_create_file);
+EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
{
@@ -604,7 +894,7 @@ int sysfs_add_file_to_group(struct kobject *kobj,
int error;
if (group)
- dir_sd = sysfs_get_dirent(kobj->sd, NULL, group);
+ dir_sd = sysfs_get_dirent(kobj->sd, group);
else
dir_sd = sysfs_get(kobj->sd);
@@ -630,17 +920,12 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
{
struct sysfs_dirent *sd;
struct iattr newattrs;
- const void *ns;
int rc;
- rc = sysfs_attr_ns(kobj, attr, &ns);
- if (rc)
- return rc;
-
mutex_lock(&sysfs_mutex);
rc = -ENOENT;
- sd = sysfs_find_dirent(kobj->sd, ns, attr->name);
+ sd = sysfs_find_dirent(kobj->sd, attr->name, NULL);
if (!sd)
goto out;
@@ -655,22 +940,21 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
EXPORT_SYMBOL_GPL(sysfs_chmod_file);
/**
- * sysfs_remove_file - remove an object attribute.
- * @kobj: object we're acting for.
- * @attr: attribute descriptor.
+ * sysfs_remove_file_ns - remove an object attribute with a custom ns tag
+ * @kobj: object we're acting for
+ * @attr: attribute descriptor
+ * @ns: namespace tag of the file to remove
*
- * Hash the attribute name and kill the victim.
+ * Hash the attribute name and namespace tag and kill the victim.
*/
-void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr)
+void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
+ const void *ns)
{
- const void *ns;
-
- if (sysfs_attr_ns(kobj, attr, &ns))
- return;
+ struct sysfs_dirent *dir_sd = kobj->sd;
- sysfs_hash_and_remove(kobj->sd, ns, attr->name);
+ sysfs_hash_and_remove(dir_sd, attr->name, ns);
}
-EXPORT_SYMBOL_GPL(sysfs_remove_file);
+EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
{
@@ -692,16 +976,42 @@ void sysfs_remove_file_from_group(struct kobject *kobj,
struct sysfs_dirent *dir_sd;
if (group)
- dir_sd = sysfs_get_dirent(kobj->sd, NULL, group);
+ dir_sd = sysfs_get_dirent(kobj->sd, group);
else
dir_sd = sysfs_get(kobj->sd);
if (dir_sd) {
- sysfs_hash_and_remove(dir_sd, NULL, attr->name);
+ sysfs_hash_and_remove(dir_sd, attr->name, NULL);
sysfs_put(dir_sd);
}
}
EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group);
+/**
+ * sysfs_create_bin_file - create binary file for object.
+ * @kobj: object.
+ * @attr: attribute descriptor.
+ */
+int sysfs_create_bin_file(struct kobject *kobj,
+ const struct bin_attribute *attr)
+{
+ BUG_ON(!kobj || !kobj->sd || !attr);
+
+ return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
+}
+EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
+
+/**
+ * sysfs_remove_bin_file - remove binary file for object.
+ * @kobj: object.
+ * @attr: attribute descriptor.
+ */
+void sysfs_remove_bin_file(struct kobject *kobj,
+ const struct bin_attribute *attr)
+{
+ sysfs_hash_and_remove(kobj->sd, attr->attr.name, NULL);
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
+
struct sysfs_schedule_callback_struct {
struct list_head workq_list;
struct kobject *kobj;
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 5f92cd2f61c1..1898a10e38ce 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -26,7 +26,7 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
if (grp->attrs)
for (attr = grp->attrs; *attr; attr++)
- sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name);
+ sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL);
if (grp->bin_attrs)
for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++)
sysfs_remove_bin_file(kobj, *bin_attr);
@@ -49,16 +49,17 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
* re-adding (if required) the file.
*/
if (update)
- sysfs_hash_and_remove(dir_sd, NULL,
- (*attr)->name);
+ sysfs_hash_and_remove(dir_sd, (*attr)->name,
+ NULL);
if (grp->is_visible) {
mode = grp->is_visible(kobj, *attr, i);
if (!mode)
continue;
}
- error = sysfs_add_file_mode(dir_sd, *attr,
- SYSFS_KOBJ_ATTR,
- (*attr)->mode | mode);
+ error = sysfs_add_file_mode_ns(dir_sd, *attr,
+ SYSFS_KOBJ_ATTR,
+ (*attr)->mode | mode,
+ NULL);
if (unlikely(error))
break;
}
@@ -110,7 +111,7 @@ static int internal_create_group(struct kobject *kobj, int update,
error = create_files(sd, kobj, grp, update);
if (error) {
if (grp->name)
- sysfs_remove_subdir(sd);
+ sysfs_remove(sd);
}
sysfs_put(sd);
return error;
@@ -206,7 +207,7 @@ void sysfs_remove_group(struct kobject *kobj,
struct sysfs_dirent *sd;
if (grp->name) {
- sd = sysfs_get_dirent(dir_sd, NULL, grp->name);
+ sd = sysfs_get_dirent(dir_sd, grp->name);
if (!sd) {
WARN(!sd, KERN_WARNING
"sysfs group %p not found for kobject '%s'\n",
@@ -218,7 +219,7 @@ void sysfs_remove_group(struct kobject *kobj,
remove_files(sd, kobj, grp);
if (grp->name)
- sysfs_remove_subdir(sd);
+ sysfs_remove(sd);
sysfs_put(sd);
}
@@ -261,7 +262,7 @@ int sysfs_merge_group(struct kobject *kobj,
struct attribute *const *attr;
int i;
- dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+ dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
if (!dir_sd)
return -ENOENT;
@@ -269,7 +270,7 @@ int sysfs_merge_group(struct kobject *kobj,
error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR);
if (error) {
while (--i >= 0)
- sysfs_hash_and_remove(dir_sd, NULL, (*--attr)->name);
+ sysfs_hash_and_remove(dir_sd, (*--attr)->name, NULL);
}
sysfs_put(dir_sd);
@@ -288,10 +289,10 @@ void sysfs_unmerge_group(struct kobject *kobj,
struct sysfs_dirent *dir_sd;
struct attribute *const *attr;
- dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+ dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
if (dir_sd) {
for (attr = grp->attrs; *attr; ++attr)
- sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name);
+ sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL);
sysfs_put(dir_sd);
}
}
@@ -310,7 +311,7 @@ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
struct sysfs_dirent *dir_sd;
int error = 0;
- dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+ dir_sd = sysfs_get_dirent(kobj->sd, group_name);
if (!dir_sd)
return -ENOENT;
@@ -332,9 +333,9 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
{
struct sysfs_dirent *dir_sd;
- dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+ dir_sd = sysfs_get_dirent(kobj->sd, group_name);
if (dir_sd) {
- sysfs_hash_and_remove(dir_sd, NULL, link_name);
+ sysfs_hash_and_remove(dir_sd, link_name, NULL);
sysfs_put(dir_sd);
}
}
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 963f910c8034..1750f790af3b 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -258,9 +258,9 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
inode->i_fop = &sysfs_file_operations;
break;
case SYSFS_KOBJ_BIN_ATTR:
- bin_attr = sd->s_bin_attr.bin_attr;
+ bin_attr = sd->s_attr.bin_attr;
inode->i_size = bin_attr->size;
- inode->i_fop = &bin_fops;
+ inode->i_fop = &sysfs_bin_operations;
break;
case SYSFS_KOBJ_LINK:
inode->i_op = &sysfs_symlink_inode_operations;
@@ -314,32 +314,6 @@ void sysfs_evict_inode(struct inode *inode)
sysfs_put(sd);
}
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns,
- const char *name)
-{
- struct sysfs_addrm_cxt acxt;
- struct sysfs_dirent *sd;
-
- if (!dir_sd) {
- WARN(1, KERN_WARNING "sysfs: can not remove '%s', no directory\n",
- name);
- return -ENOENT;
- }
-
- sysfs_addrm_start(&acxt, dir_sd);
-
- sd = sysfs_find_dirent(dir_sd, ns, name);
- if (sd)
- sysfs_remove_one(&acxt, sd);
-
- sysfs_addrm_finish(&acxt);
-
- if (sd)
- return 0;
- else
- return -ENOENT;
-}
-
int sysfs_permission(struct inode *inode, int mask)
{
struct sysfs_dirent *sd;
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 2dd4507d9edd..3ae3f1bf1a09 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -33,13 +33,15 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
BUG_ON(!name || !parent_sd);
- /* target->sd can go away beneath us but is protected with
- * sysfs_assoc_lock. Fetch target_sd from it.
+ /*
+ * We don't own @target and it may be removed at any time.
+ * Synchronize using sysfs_symlink_target_lock. See
+ * sysfs_remove_dir() for details.
*/
- spin_lock(&sysfs_assoc_lock);
+ spin_lock(&sysfs_symlink_target_lock);
if (target->sd)
target_sd = sysfs_get(target->sd);
- spin_unlock(&sysfs_assoc_lock);
+ spin_unlock(&sysfs_symlink_target_lock);
error = -ENOENT;
if (!target_sd)
@@ -52,18 +54,18 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
ns_type = sysfs_ns_type(parent_sd);
if (ns_type)
- sd->s_ns = target->ktype->namespace(target);
+ sd->s_ns = target_sd->s_ns;
sd->s_symlink.target_sd = target_sd;
target_sd = NULL; /* reference is now owned by the symlink */
- sysfs_addrm_start(&acxt, parent_sd);
+ sysfs_addrm_start(&acxt);
/* Symlinks must be between directories with the same ns_type */
if (!ns_type ||
(ns_type == sysfs_ns_type(sd->s_symlink.target_sd->s_parent))) {
if (warn)
- error = sysfs_add_one(&acxt, sd);
+ error = sysfs_add_one(&acxt, sd, parent_sd);
else
- error = __sysfs_add_one(&acxt, sd);
+ error = __sysfs_add_one(&acxt, sd, parent_sd);
} else {
error = -EINVAL;
WARN(1, KERN_WARNING
@@ -155,11 +157,17 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
const char *name)
{
const void *ns = NULL;
- spin_lock(&sysfs_assoc_lock);
+
+ /*
+ * We don't own @target and it may be removed at any time.
+ * Synchronize using sysfs_symlink_target_lock. See
+ * sysfs_remove_dir() for details.
+ */
+ spin_lock(&sysfs_symlink_target_lock);
if (targ->sd && sysfs_ns_type(kobj->sd))
ns = targ->sd->s_ns;
- spin_unlock(&sysfs_assoc_lock);
- sysfs_hash_and_remove(kobj->sd, ns, name);
+ spin_unlock(&sysfs_symlink_target_lock);
+ sysfs_hash_and_remove(kobj->sd, name, ns);
}
/**
@@ -176,24 +184,25 @@ void sysfs_remove_link(struct kobject *kobj, const char *name)
else
parent_sd = kobj->sd;
- sysfs_hash_and_remove(parent_sd, NULL, name);
+ sysfs_hash_and_remove(parent_sd, name, NULL);
}
EXPORT_SYMBOL_GPL(sysfs_remove_link);
/**
- * sysfs_rename_link - rename symlink in object's directory.
+ * sysfs_rename_link_ns - rename symlink in object's directory.
* @kobj: object we're acting for.
* @targ: object we're pointing to.
* @old: previous name of the symlink.
* @new: new name of the symlink.
+ * @new_ns: new namespace of the symlink.
*
* A helper function for the common rename symlink idiom.
*/
-int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
- const char *old, const char *new)
+int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ,
+ const char *old, const char *new, const void *new_ns)
{
struct sysfs_dirent *parent_sd, *sd = NULL;
- const void *old_ns = NULL, *new_ns = NULL;
+ const void *old_ns = NULL;
int result;
if (!kobj)
@@ -205,7 +214,7 @@ int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
old_ns = targ->sd->s_ns;
result = -ENOENT;
- sd = sysfs_get_dirent(parent_sd, old_ns, old);
+ sd = sysfs_get_dirent_ns(parent_sd, old, old_ns);
if (!sd)
goto out;
@@ -215,16 +224,13 @@ int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
if (sd->s_symlink.target_sd->s_dir.kobj != targ)
goto out;
- if (sysfs_ns_type(parent_sd))
- new_ns = targ->ktype->namespace(targ);
-
- result = sysfs_rename(sd, parent_sd, new_ns, new);
+ result = sysfs_rename(sd, parent_sd, new, new_ns);
out:
sysfs_put(sd);
return result;
}
-EXPORT_SYMBOL_GPL(sysfs_rename_link);
+EXPORT_SYMBOL_GPL(sysfs_rename_link_ns);
static int sysfs_get_target_path(struct sysfs_dirent *parent_sd,
struct sysfs_dirent *target_sd, char *path)
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index b6deca3e301d..0af09fbfb3f6 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -29,15 +29,13 @@ struct sysfs_elem_symlink {
};
struct sysfs_elem_attr {
- struct attribute *attr;
+ union {
+ struct attribute *attr;
+ struct bin_attribute *bin_attr;
+ };
struct sysfs_open_dirent *open;
};
-struct sysfs_elem_bin_attr {
- struct bin_attribute *bin_attr;
- struct hlist_head buffers;
-};
-
struct sysfs_inode_attrs {
struct iattr ia_iattr;
void *ia_secdata;
@@ -74,7 +72,6 @@ struct sysfs_dirent {
struct sysfs_elem_dir s_dir;
struct sysfs_elem_symlink s_symlink;
struct sysfs_elem_attr s_attr;
- struct sysfs_elem_bin_attr s_bin_attr;
};
unsigned short s_flags;
@@ -115,6 +112,7 @@ static inline enum kobj_ns_type sysfs_ns_type(struct sysfs_dirent *sd)
}
#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
#define sysfs_dirent_init_lockdep(sd) \
do { \
struct attribute *attr = sd->s_attr.attr; \
@@ -124,15 +122,31 @@ do { \
\
lockdep_init_map(&sd->dep_map, "s_active", key, 0); \
} while (0)
+
+/* Test for attributes that want to ignore lockdep for read-locking */
+static inline bool sysfs_ignore_lockdep(struct sysfs_dirent *sd)
+{
+ int type = sysfs_type(sd);
+
+ return (type == SYSFS_KOBJ_ATTR || type == SYSFS_KOBJ_BIN_ATTR) &&
+ sd->s_attr.attr->ignore_lockdep;
+}
+
#else
+
#define sysfs_dirent_init_lockdep(sd) do {} while (0)
+
+static inline bool sysfs_ignore_lockdep(struct sysfs_dirent *sd)
+{
+ return true;
+}
+
#endif
/*
* Context structure to be used while adding/removing nodes.
*/
struct sysfs_addrm_cxt {
- struct sysfs_dirent *parent_sd;
struct sysfs_dirent *removed;
};
@@ -156,38 +170,37 @@ extern struct kmem_cache *sysfs_dir_cachep;
* dir.c
*/
extern struct mutex sysfs_mutex;
-extern spinlock_t sysfs_assoc_lock;
+extern spinlock_t sysfs_symlink_target_lock;
extern const struct dentry_operations sysfs_dentry_ops;
extern const struct file_operations sysfs_dir_operations;
extern const struct inode_operations sysfs_dir_inode_operations;
-struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd);
struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd);
void sysfs_put_active(struct sysfs_dirent *sd);
-void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
- struct sysfs_dirent *parent_sd);
-int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
-void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
+void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt);
+void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name);
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
+ struct sysfs_dirent *parent_sd);
+int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
+ struct sysfs_dirent *parent_sd);
+void sysfs_remove(struct sysfs_dirent *sd);
+int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name,
+ const void *ns);
void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
- const void *ns,
- const unsigned char *name);
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
- const void *ns,
- const unsigned char *name);
+ const unsigned char *name,
+ const void *ns);
struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type);
void release_sysfs_dirent(struct sysfs_dirent *sd);
int sysfs_create_subdir(struct kobject *kobj, const char *name,
struct sysfs_dirent **p_sd);
-void sysfs_remove_subdir(struct sysfs_dirent *sd);
int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
- const void *ns, const char *new_name);
+ const char *new_name, const void *new_ns);
static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd)
{
@@ -218,25 +231,21 @@ int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags);
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns,
- const char *name);
int sysfs_inode_init(void);
/*
* file.c
*/
extern const struct file_operations sysfs_file_operations;
+extern const struct file_operations sysfs_bin_operations;
int sysfs_add_file(struct sysfs_dirent *dir_sd,
const struct attribute *attr, int type);
-int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
- const struct attribute *attr, int type, umode_t amode);
-/*
- * bin.c
- */
-extern const struct file_operations bin_fops;
-void unmap_bin_file(struct sysfs_dirent *attr_sd);
+int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
+ const struct attribute *attr, int type,
+ umode_t amode, const void *ns);
+void sysfs_unmap_bin_file(struct sysfs_dirent *sd);
/*
* symlink.c
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 0957aa98b6c0..12dad188939d 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -1158,7 +1158,7 @@ xfs_dir2_sf_to_block(
/*
* Create entry for .
*/
- dep = xfs_dir3_data_dot_entry_p(hdr);
+ dep = xfs_dir3_data_dot_entry_p(mp, hdr);
dep->inumber = cpu_to_be64(dp->i_ino);
dep->namelen = 1;
dep->name[0] = '.';
@@ -1172,7 +1172,7 @@ xfs_dir2_sf_to_block(
/*
* Create entry for ..
*/
- dep = xfs_dir3_data_dotdot_entry_p(hdr);
+ dep = xfs_dir3_data_dotdot_entry_p(mp, hdr);
dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
dep->namelen = 2;
dep->name[0] = dep->name[1] = '.';
@@ -1183,7 +1183,7 @@ xfs_dir2_sf_to_block(
blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
(char *)dep - (char *)hdr));
- offset = xfs_dir3_data_first_offset(hdr);
+ offset = xfs_dir3_data_first_offset(mp);
/*
* Loop over existing entries, stuff them in.
*/
diff --git a/fs/xfs/xfs_dir2_format.h b/fs/xfs/xfs_dir2_format.h
index a0961a61ac1a..9cf67381adf6 100644
--- a/fs/xfs/xfs_dir2_format.h
+++ b/fs/xfs/xfs_dir2_format.h
@@ -497,69 +497,58 @@ xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
/*
* Offsets of . and .. in data space (always block 0)
*
- * The macros are used for shortform directories as they have no headers to read
- * the magic number out of. Shortform directories need to know the size of the
- * data block header because the sfe embeds the block offset of the entry into
- * it so that it doesn't change when format conversion occurs. Bad Things Happen
- * if we don't follow this rule.
- *
* XXX: there is scope for significant optimisation of the logic here. Right
* now we are checking for "dir3 format" over and over again. Ideally we should
* only do it once for each operation.
*/
-#define XFS_DIR3_DATA_DOT_OFFSET(mp) \
- xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&(mp)->m_sb))
-#define XFS_DIR3_DATA_DOTDOT_OFFSET(mp) \
- (XFS_DIR3_DATA_DOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 1))
-#define XFS_DIR3_DATA_FIRST_OFFSET(mp) \
- (XFS_DIR3_DATA_DOTDOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 2))
-
static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dot_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dot_offset(struct xfs_mount *mp)
{
- return xfs_dir3_data_entry_offset(hdr);
+ return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
}
static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dotdot_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
{
- bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
- return xfs_dir3_data_dot_offset(hdr) +
- __xfs_dir3_data_entsize(dir3, 1);
+ return xfs_dir3_data_dot_offset(mp) +
+ xfs_dir3_data_entsize(mp, 1);
}
static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_first_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_first_offset(struct xfs_mount *mp)
{
- bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
- hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
- return xfs_dir3_data_dotdot_offset(hdr) +
- __xfs_dir3_data_entsize(dir3, 2);
+ return xfs_dir3_data_dotdot_offset(mp) +
+ xfs_dir3_data_entsize(mp, 2);
}
/*
* location of . and .. in data space (always block 0)
*/
static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dot_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dot_entry_p(
+ struct xfs_mount *mp,
+ struct xfs_dir2_data_hdr *hdr)
{
return (struct xfs_dir2_data_entry *)
- ((char *)hdr + xfs_dir3_data_dot_offset(hdr));
+ ((char *)hdr + xfs_dir3_data_dot_offset(mp));
}
static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dotdot_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dotdot_entry_p(
+ struct xfs_mount *mp,
+ struct xfs_dir2_data_hdr *hdr)
{
return (struct xfs_dir2_data_entry *)
- ((char *)hdr + xfs_dir3_data_dotdot_offset(hdr));
+ ((char *)hdr + xfs_dir3_data_dotdot_offset(mp));
}
static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_first_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_first_entry_p(
+ struct xfs_mount *mp,
+ struct xfs_dir2_data_hdr *hdr)
{
return (struct xfs_dir2_data_entry *)
- ((char *)hdr + xfs_dir3_data_first_offset(hdr));
+ ((char *)hdr + xfs_dir3_data_first_offset(mp));
}
/*
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 8993ec17452c..8f84153e98a8 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -119,9 +119,9 @@ xfs_dir2_sf_getdents(
* mp->m_dirdatablk.
*/
dot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
- XFS_DIR3_DATA_DOT_OFFSET(mp));
+ xfs_dir3_data_dot_offset(mp));
dotdot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
- XFS_DIR3_DATA_DOTDOT_OFFSET(mp));
+ xfs_dir3_data_dotdot_offset(mp));
/*
* Put . entry unless we're starting past it.
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index bb6e2848f473..3ef6d402084c 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -557,7 +557,7 @@ xfs_dir2_sf_addname_hard(
* to insert the new entry.
* If it's going to end up at the end then oldsfep will point there.
*/
- for (offset = XFS_DIR3_DATA_FIRST_OFFSET(mp),
+ for (offset = xfs_dir3_data_first_offset(mp),
oldsfep = xfs_dir2_sf_firstentry(oldsfp),
add_datasize = xfs_dir3_data_entsize(mp, args->namelen),
eof = (char *)oldsfep == &buf[old_isize];
@@ -640,7 +640,7 @@ xfs_dir2_sf_addname_pick(
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
size = xfs_dir3_data_entsize(mp, args->namelen);
- offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+ offset = xfs_dir3_data_first_offset(mp);
sfep = xfs_dir2_sf_firstentry(sfp);
holefit = 0;
/*
@@ -713,7 +713,7 @@ xfs_dir2_sf_check(
mp = dp->i_mount;
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
- offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+ offset = xfs_dir3_data_first_offset(mp);
ino = xfs_dir2_sf_get_parent_ino(sfp);
i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 71520e6e5d65..1ee776d477c3 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -64,7 +64,8 @@ int xfs_dqerror_mod = 33;
struct kmem_zone *xfs_qm_dqtrxzone;
static struct kmem_zone *xfs_qm_dqzone;
-static struct lock_class_key xfs_dquot_other_class;
+static struct lock_class_key xfs_dquot_group_class;
+static struct lock_class_key xfs_dquot_project_class;
/*
* This is called to free all the memory associated with a dquot
@@ -703,8 +704,20 @@ xfs_qm_dqread(
* Make sure group quotas have a different lock class than user
* quotas.
*/
- if (!(type & XFS_DQ_USER))
- lockdep_set_class(&dqp->q_qlock, &xfs_dquot_other_class);
+ switch (type) {
+ case XFS_DQ_USER:
+ /* uses the default lock class */
+ break;
+ case XFS_DQ_GROUP:
+ lockdep_set_class(&dqp->q_qlock, &xfs_dquot_group_class);
+ break;
+ case XFS_DQ_PROJ:
+ lockdep_set_class(&dqp->q_qlock, &xfs_dquot_project_class);
+ break;
+ default:
+ ASSERT(0);
+ break;
+ }
XFS_STATS_INC(xs_qm_dquot);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index cc179878fe41..39797490a1f1 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1585,6 +1585,7 @@ xlog_recover_add_to_trans(
"bad number of regions (%d) in inode log format",
in_f->ilf_size);
ASSERT(0);
+ kmem_free(ptr);
return XFS_ERROR(EIO);
}