summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile2
-rw-r--r--fs/aio.c21
-rw-r--r--fs/btrfs/compression.c33
-rw-r--r--fs/btrfs/compression.h4
-rw-r--r--fs/btrfs/ctree.c14
-rw-r--r--fs/btrfs/locking.c24
-rw-r--r--fs/btrfs/locking.h2
-rw-r--r--fs/btrfs/lzo.c15
-rw-r--r--fs/btrfs/zlib.c20
-rw-r--r--fs/ceph/caps.c2
-rw-r--r--fs/dcache.c1
-rw-r--r--fs/fat/namei_vfat.c20
-rw-r--r--fs/isofs/inode.c42
-rw-r--r--fs/jbd2/journal.c5
-rw-r--r--fs/nfs/blocklayout/blocklayout.c2
-rw-r--r--fs/nfs/blocklayout/rpc_pipefs.c14
-rw-r--r--fs/nfs/delegation.c25
-rw-r--r--fs/nfs/delegation.h1
-rw-r--r--fs/nfs/dir.c1
-rw-r--r--fs/nfs/direct.c1
-rw-r--r--fs/nfs/filelayout/filelayout.c3
-rw-r--r--fs/nfs/inode.c2
-rw-r--r--fs/nfs/netns.h1
-rw-r--r--fs/nfs/nfs4proc.c95
-rw-r--r--fs/nfs/write.c2
-rw-r--r--fs/nfsd/nfs4callback.c8
-rw-r--r--fs/nfsd/nfsd.h9
-rw-r--r--fs/notify/fsnotify.c36
-rw-r--r--fs/notify/fsnotify.h4
-rw-r--r--fs/notify/inode_mark.c8
-rw-r--r--fs/notify/inotify/inotify_user.c9
-rw-r--r--fs/notify/mark.c36
-rw-r--r--fs/notify/vfsmount_mark.c8
-rw-r--r--fs/overlayfs/Kconfig2
-rw-r--r--fs/overlayfs/Makefile4
-rw-r--r--fs/overlayfs/dir.c31
-rw-r--r--fs/overlayfs/inode.c27
-rw-r--r--fs/overlayfs/readdir.c39
-rw-r--r--fs/overlayfs/super.c61
39 files changed, 414 insertions, 220 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 34a1b9dea6dd..da0bbb456d3f 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -104,7 +104,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/
obj-$(CONFIG_AUTOFS4_FS) += autofs4/
obj-$(CONFIG_ADFS_FS) += adfs/
obj-$(CONFIG_FUSE_FS) += fuse/
-obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/
+obj-$(CONFIG_OVERLAY_FS) += overlayfs/
obj-$(CONFIG_UDF_FS) += udf/
obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/
obj-$(CONFIG_OMFS_FS) += omfs/
diff --git a/fs/aio.c b/fs/aio.c
index 84a751005f5b..14b93159ef83 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -165,6 +165,15 @@ static struct vfsmount *aio_mnt;
static const struct file_operations aio_ring_fops;
static const struct address_space_operations aio_ctx_aops;
+/* Backing dev info for aio fs.
+ * -no dirty page accounting or writeback happens
+ */
+static struct backing_dev_info aio_fs_backing_dev_info = {
+ .name = "aiofs",
+ .state = 0,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
+};
+
static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
{
struct qstr this = QSTR_INIT("[aio]", 5);
@@ -176,6 +185,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
inode->i_mapping->a_ops = &aio_ctx_aops;
inode->i_mapping->private_data = ctx;
+ inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
inode->i_size = PAGE_SIZE * nr_pages;
path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -220,6 +230,9 @@ static int __init aio_setup(void)
if (IS_ERR(aio_mnt))
panic("Failed to create aio fs mount.");
+ if (bdi_init(&aio_fs_backing_dev_info))
+ panic("Failed to init aio fs backing dev info.");
+
kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
@@ -281,11 +294,6 @@ static const struct file_operations aio_ring_fops = {
.mmap = aio_ring_mmap,
};
-static int aio_set_page_dirty(struct page *page)
-{
- return 0;
-}
-
#if IS_ENABLED(CONFIG_MIGRATION)
static int aio_migratepage(struct address_space *mapping, struct page *new,
struct page *old, enum migrate_mode mode)
@@ -357,7 +365,7 @@ out:
#endif
static const struct address_space_operations aio_ctx_aops = {
- .set_page_dirty = aio_set_page_dirty,
+ .set_page_dirty = __set_page_dirty_no_writeback,
#if IS_ENABLED(CONFIG_MIGRATION)
.migratepage = aio_migratepage,
#endif
@@ -412,7 +420,6 @@ static int aio_setup_ring(struct kioctx *ctx)
pr_debug("pid(%d) page[%d]->count=%d\n",
current->pid, i, page_count(page));
SetPageUptodate(page);
- SetPageDirty(page);
unlock_page(page);
ctx->ring_pages[i] = page;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d3220d31d3cb..dcd9be32ac57 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1011,8 +1011,6 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(page_out);
memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
- if (*pg_index == (vcnt - 1) && *pg_offset == 0)
- memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
kunmap_atomic(kaddr);
flush_dcache_page(page_out);
@@ -1054,3 +1052,34 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
return 1;
}
+
+/*
+ * When uncompressing data, we need to make sure and zero any parts of
+ * the biovec that were not filled in by the decompression code. pg_index
+ * and pg_offset indicate the last page and the last offset of that page
+ * that have been filled in. This will zero everything remaining in the
+ * biovec.
+ */
+void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
+ unsigned long pg_index,
+ unsigned long pg_offset)
+{
+ while (pg_index < vcnt) {
+ struct page *page = bvec[pg_index].bv_page;
+ unsigned long off = bvec[pg_index].bv_offset;
+ unsigned long len = bvec[pg_index].bv_len;
+
+ if (pg_offset < off)
+ pg_offset = off;
+ if (pg_offset < off + len) {
+ unsigned long bytes = off + len - pg_offset;
+ char *kaddr;
+
+ kaddr = kmap_atomic(page);
+ memset(kaddr + pg_offset, 0, bytes);
+ kunmap_atomic(kaddr);
+ }
+ pg_index++;
+ pg_offset = 0;
+ }
+}
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 0c803b4fbf93..d181f70caae0 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -45,7 +45,9 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long nr_pages);
int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
-
+void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
+ unsigned long pg_index,
+ unsigned long pg_offset);
struct btrfs_compress_op {
struct list_head *(*alloc_workspace)(void);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 19bc6162fb8e..150822ee0a0b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -80,13 +80,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
{
int i;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- /* lockdep really cares that we take all of these spinlocks
- * in the right order. If any of the locks in the path are not
- * currently blocking, it is going to complain. So, make really
- * really sure by forcing the path to blocking before we clear
- * the path blocking.
- */
if (held) {
btrfs_set_lock_blocking_rw(held, held_rw);
if (held_rw == BTRFS_WRITE_LOCK)
@@ -95,7 +88,6 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
held_rw = BTRFS_READ_LOCK_BLOCKING;
}
btrfs_set_path_blocking(p);
-#endif
for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
if (p->nodes[i] && p->locks[i]) {
@@ -107,10 +99,8 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
}
}
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (held)
btrfs_clear_lock_blocking_rw(held, held_rw);
-#endif
}
/* this also releases the path */
@@ -2893,7 +2883,7 @@ cow_done:
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
- err = btrfs_try_tree_read_lock(b);
+ err = btrfs_tree_read_lock_atomic(b);
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
@@ -3025,7 +3015,7 @@ again:
}
level = btrfs_header_level(b);
- err = btrfs_try_tree_read_lock(b);
+ err = btrfs_tree_read_lock_atomic(b);
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 5665d2149249..f8229ef1b46d 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -128,6 +128,26 @@ again:
}
/*
+ * take a spinning read lock.
+ * returns 1 if we get the read lock and 0 if we don't
+ * this won't wait for blocking writers
+ */
+int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
+{
+ if (atomic_read(&eb->blocking_writers))
+ return 0;
+
+ read_lock(&eb->lock);
+ if (atomic_read(&eb->blocking_writers)) {
+ read_unlock(&eb->lock);
+ return 0;
+ }
+ atomic_inc(&eb->read_locks);
+ atomic_inc(&eb->spinning_readers);
+ return 1;
+}
+
+/*
* returns 1 if we get the read lock and 0 if we don't
* this won't wait for blocking writers
*/
@@ -158,9 +178,7 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
atomic_read(&eb->blocking_readers))
return 0;
- if (!write_trylock(&eb->lock))
- return 0;
-
+ write_lock(&eb->lock);
if (atomic_read(&eb->blocking_writers) ||
atomic_read(&eb->blocking_readers)) {
write_unlock(&eb->lock);
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index b81e0e9a4894..c44a9d5f5362 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -35,6 +35,8 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw);
void btrfs_assert_tree_locked(struct extent_buffer *eb);
int btrfs_try_tree_read_lock(struct extent_buffer *eb);
int btrfs_try_tree_write_lock(struct extent_buffer *eb);
+int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
+
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
{
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 78285f30909e..617553cdb7d3 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -373,6 +373,8 @@ cont:
}
done:
kunmap(pages_in[page_in_index]);
+ if (!ret)
+ btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
return ret;
}
@@ -410,10 +412,23 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
goto out;
}
+ /*
+ * the caller is already checking against PAGE_SIZE, but lets
+ * move this check closer to the memcpy/memset
+ */
+ destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
kaddr = kmap_atomic(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
+
+ /*
+ * btrfs_getblock is doing a zero on the tail of the page too,
+ * but this will cover anything missing from the decompressed
+ * data.
+ */
+ if (bytes < destlen)
+ memset(kaddr+bytes, 0, destlen-bytes);
kunmap_atomic(kaddr);
out:
return ret;
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 759fa4e2de8f..fb22fd8d8fb8 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -299,6 +299,8 @@ done:
zlib_inflateEnd(&workspace->strm);
if (data_in)
kunmap(pages_in[page_in_index]);
+ if (!ret)
+ btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
return ret;
}
@@ -310,10 +312,14 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
struct workspace *workspace = list_entry(ws, struct workspace, list);
int ret = 0;
int wbits = MAX_WBITS;
- unsigned long bytes_left = destlen;
+ unsigned long bytes_left;
unsigned long total_out = 0;
+ unsigned long pg_offset = 0;
char *kaddr;
+ destlen = min_t(unsigned long, destlen, PAGE_SIZE);
+ bytes_left = destlen;
+
workspace->strm.next_in = data_in;
workspace->strm.avail_in = srclen;
workspace->strm.total_in = 0;
@@ -341,7 +347,6 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
unsigned long buf_start;
unsigned long buf_offset;
unsigned long bytes;
- unsigned long pg_offset = 0;
ret = zlib_inflate(&workspace->strm, Z_NO_FLUSH);
if (ret != Z_OK && ret != Z_STREAM_END)
@@ -384,6 +389,17 @@ next:
ret = 0;
zlib_inflateEnd(&workspace->strm);
+
+ /*
+ * this should only happen if zlib returned fewer bytes than we
+ * expected. btrfs_get_block is responsible for zeroing from the
+ * end of the inline extent (destlen) to the end of the page
+ */
+ if (pg_offset < destlen) {
+ kaddr = kmap_atomic(dest_page);
+ memset(kaddr + pg_offset, 0, destlen - pg_offset);
+ kunmap_atomic(kaddr);
+ }
return ret;
}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 659f2ea9e6f7..cefca661464b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2638,7 +2638,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
for (i = 0; i < CEPH_CAP_BITS; i++)
if ((dirty & (1 << i)) &&
- flush_tid == ci->i_cap_flush_tid[i])
+ (u16)flush_tid == ci->i_cap_flush_tid[i])
cleaned |= 1 << i;
dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s,"
diff --git a/fs/dcache.c b/fs/dcache.c
index 3ffef7f4e5cd..5bc72b07fde2 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -778,6 +778,7 @@ restart:
struct dentry *parent = lock_parent(dentry);
if (likely(!dentry->d_lockref.count)) {
__dentry_kill(dentry);
+ dput(parent);
goto restart;
}
if (parent)
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 6df8d3d885e5..b8b92c2f9683 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -736,7 +736,12 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
}
alias = d_find_alias(inode);
- if (alias && !vfat_d_anon_disconn(alias)) {
+ /*
+ * Checking "alias->d_parent == dentry->d_parent" to make sure
+ * FS is not corrupted (especially double linked dir).
+ */
+ if (alias && alias->d_parent == dentry->d_parent &&
+ !vfat_d_anon_disconn(alias)) {
/*
* This inode has non anonymous-DCACHE_DISCONNECTED
* dentry. This means, the user did ->lookup() by an
@@ -755,12 +760,9 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
out:
mutex_unlock(&MSDOS_SB(sb)->s_lock);
- dentry->d_time = dentry->d_parent->d_inode->i_version;
- dentry = d_splice_alias(inode, dentry);
- if (dentry)
- dentry->d_time = dentry->d_parent->d_inode->i_version;
- return dentry;
-
+ if (!inode)
+ dentry->d_time = dir->i_version;
+ return d_splice_alias(inode, dentry);
error:
mutex_unlock(&MSDOS_SB(sb)->s_lock);
return ERR_PTR(err);
@@ -793,7 +795,6 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
/* timestamp is already written, so mark_inode_dirty() is unneeded. */
- dentry->d_time = dentry->d_parent->d_inode->i_version;
d_instantiate(dentry, inode);
out:
mutex_unlock(&MSDOS_SB(sb)->s_lock);
@@ -824,6 +825,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
clear_nlink(inode);
inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC;
fat_detach(inode);
+ dentry->d_time = dir->i_version;
out:
mutex_unlock(&MSDOS_SB(sb)->s_lock);
@@ -849,6 +851,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry)
clear_nlink(inode);
inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC;
fat_detach(inode);
+ dentry->d_time = dir->i_version;
out:
mutex_unlock(&MSDOS_SB(sb)->s_lock);
@@ -889,7 +892,6 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inode->i_mtime = inode->i_atime = inode->i_ctime = ts;
/* timestamp is already written, so mark_inode_dirty() is unneeded. */
- dentry->d_time = dentry->d_parent->d_inode->i_version;
d_instantiate(dentry, inode);
mutex_unlock(&MSDOS_SB(sb)->s_lock);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index fe839b915116..d67a16f2a45d 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -174,27 +174,6 @@ struct iso9660_options{
* Compute the hash for the isofs name corresponding to the dentry.
*/
static int
-isofs_hash_common(struct qstr *qstr, int ms)
-{
- const char *name;
- int len;
-
- len = qstr->len;
- name = qstr->name;
- if (ms) {
- while (len && name[len-1] == '.')
- len--;
- }
-
- qstr->hash = full_name_hash(name, len);
-
- return 0;
-}
-
-/*
- * Compute the hash for the isofs name corresponding to the dentry.
- */
-static int
isofs_hashi_common(struct qstr *qstr, int ms)
{
const char *name;
@@ -263,6 +242,27 @@ isofs_dentry_cmpi(const struct dentry *parent, const struct dentry *dentry,
}
#ifdef CONFIG_JOLIET
+/*
+ * Compute the hash for the isofs name corresponding to the dentry.
+ */
+static int
+isofs_hash_common(struct qstr *qstr, int ms)
+{
+ const char *name;
+ int len;
+
+ len = qstr->len;
+ name = qstr->name;
+ if (ms) {
+ while (len && name[len-1] == '.')
+ len--;
+ }
+
+ qstr->hash = full_name_hash(name, len);
+
+ return 0;
+}
+
static int
isofs_hash_ms(const struct dentry *dentry, struct qstr *qstr)
{
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e4dc74713a43..1df94fabe4eb 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1853,13 +1853,12 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
journal->j_chksum_driver = NULL;
return 0;
}
- }
- /* Precompute checksum seed for all metadata */
- if (jbd2_journal_has_csum_v2or3(journal))
+ /* Precompute checksum seed for all metadata */
journal->j_csum_seed = jbd2_chksum(journal, ~0,
sb->s_uuid,
sizeof(sb->s_uuid));
+ }
}
/* If enabling v1 checksums, downgrade superblock */
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 5228f201d3d5..4f46f7a05289 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -378,7 +378,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
loff_t offset = header->args.offset;
size_t count = header->args.count;
struct page **pages = header->args.pages;
- int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
+ int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT;
unsigned int pg_len;
struct blk_plug plug;
int i;
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index e966c023b1b7..acbf9ca4018c 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -65,17 +65,18 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
+ mutex_lock(&nn->bl_mutex);
bl_pipe_msg.bl_wq = &nn->bl_wq;
b->simple.len += 4; /* single volume */
if (b->simple.len > PAGE_SIZE)
- return -EIO;
+ goto out_unlock;
memset(msg, 0, sizeof(*msg));
msg->len = sizeof(*bl_msg) + b->simple.len;
msg->data = kzalloc(msg->len, gfp_mask);
if (!msg->data)
- goto out;
+ goto out_free_data;
bl_msg = msg->data;
bl_msg->type = BL_DEVICE_MOUNT,
@@ -87,7 +88,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
rc = rpc_queue_upcall(nn->bl_device_pipe, msg);
if (rc < 0) {
remove_wait_queue(&nn->bl_wq, &wq);
- goto out;
+ goto out_free_data;
}
set_current_state(TASK_UNINTERRUPTIBLE);
@@ -97,12 +98,14 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b,
if (reply->status != BL_DEVICE_REQUEST_PROC) {
printk(KERN_WARNING "%s failed to decode device: %d\n",
__func__, reply->status);
- goto out;
+ goto out_free_data;
}
dev = MKDEV(reply->major, reply->minor);
-out:
+out_free_data:
kfree(msg->data);
+out_unlock:
+ mutex_unlock(&nn->bl_mutex);
return dev;
}
@@ -232,6 +235,7 @@ static int nfs4blocklayout_net_init(struct net *net)
struct nfs_net *nn = net_generic(net, nfs_net_id);
struct dentry *dentry;
+ mutex_init(&nn->bl_mutex);
init_waitqueue_head(&nn->bl_wq);
nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
if (IS_ERR(nn->bl_device_pipe))
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5853f53db732..7f3f60641344 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -125,6 +125,8 @@ again:
continue;
if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
continue;
+ if (!nfs4_valid_open_stateid(state))
+ continue;
if (!nfs4_stateid_match(&state->stateid, stateid))
continue;
get_nfs_open_context(ctx);
@@ -193,7 +195,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *
{
int res = 0;
- res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+ if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ res = nfs4_proc_delegreturn(inode,
+ delegation->cred,
+ &delegation->stateid,
+ issync);
nfs_free_delegation(delegation);
return res;
}
@@ -380,11 +386,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
{
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
struct nfs_inode *nfsi = NFS_I(inode);
- int err;
+ int err = 0;
if (delegation == NULL)
return 0;
do {
+ if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ break;
err = nfs_delegation_claim_opens(inode, &delegation->stateid);
if (!issync || err != -EAGAIN)
break;
@@ -605,10 +613,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl
rcu_read_unlock();
}
+static void nfs_revoke_delegation(struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+ rcu_read_lock();
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation != NULL) {
+ set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+ nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+ }
+ rcu_read_unlock();
+}
+
void nfs_remove_bad_delegation(struct inode *inode)
{
struct nfs_delegation *delegation;
+ nfs_revoke_delegation(inode);
delegation = nfs_inode_detach_delegation(inode);
if (delegation) {
nfs_inode_find_state_and_recover(inode, &delegation->stateid);
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 5c1cce39297f..e3c20a3ccc93 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@ enum {
NFS_DELEGATION_RETURN_IF_CLOSED,
NFS_DELEGATION_REFERENCED,
NFS_DELEGATION_RETURNING,
+ NFS_DELEGATION_REVOKED,
};
int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 06e8cfcbb670..6e62155abf26 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1527,6 +1527,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
case -ENOENT:
d_drop(dentry);
d_add(dentry, NULL);
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
break;
case -EISDIR:
case -ENOTDIR:
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 20cffc830468..10bf07280f4a 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -266,6 +266,7 @@ static void nfs_direct_req_free(struct kref *kref)
{
struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
+ nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
if (dreq->l_ctx != NULL)
nfs_put_lock_context(dreq->l_ctx);
if (dreq->ctx != NULL)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 46fab1cb455a..7afb52f6a25a 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -145,9 +145,6 @@ static int filelayout_async_handle_error(struct rpc_task *task,
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
- if (state == NULL)
- break;
- nfs_remove_bad_delegation(state->inode);
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 6388a59f2add..00689a8a85e4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -626,7 +626,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
- int err;
+ int err = 0;
trace_nfs_getattr_enter(inode);
/* Flush out writes to the server in order to update c/mtime. */
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index ef221fb8a183..f0e06e4acbef 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -19,6 +19,7 @@ struct nfs_net {
struct rpc_pipe *bl_device_pipe;
struct bl_dev_msg bl_mount_reply;
wait_queue_head_t bl_wq;
+ struct mutex bl_mutex;
struct list_head nfs_client_list;
struct list_head nfs_volume_list;
#if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 405bd95c1f58..69dc20a743f9 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -370,11 +370,6 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
- if (inode != NULL && nfs4_have_delegation(inode, FMODE_READ)) {
- nfs_remove_bad_delegation(inode);
- exception->retry = 1;
- break;
- }
if (state == NULL)
break;
ret = nfs4_schedule_stateid_recovery(server, state);
@@ -1654,7 +1649,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
nfs_inode_find_state_and_recover(state->inode,
stateid);
nfs4_schedule_stateid_recovery(server, state);
- return 0;
+ return -EAGAIN;
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -2109,46 +2104,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
return ret;
}
+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+ nfs_remove_bad_delegation(state->inode);
+ write_seqlock(&state->seqlock);
+ nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+ write_sequnlock(&state->seqlock);
+ clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+ if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+ nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+ /* NFSv4.0 doesn't allow for delegation recovery on open expire */
+ nfs40_clear_delegation_stateid(state);
+ return nfs4_open_expired(sp, state);
+}
+
#if defined(CONFIG_NFS_V4_1)
-static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
+static void nfs41_check_delegation_stateid(struct nfs4_state *state)
{
struct nfs_server *server = NFS_SERVER(state->inode);
- nfs4_stateid *stateid = &state->stateid;
+ nfs4_stateid stateid;
struct nfs_delegation *delegation;
- struct rpc_cred *cred = NULL;
- int status = -NFS4ERR_BAD_STATEID;
-
- /* If a state reset has been done, test_stateid is unneeded */
- if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
- return;
+ struct rpc_cred *cred;
+ int status;
/* Get the delegation credential for use by test/free_stateid */
rcu_read_lock();
delegation = rcu_dereference(NFS_I(state->inode)->delegation);
- if (delegation != NULL &&
- nfs4_stateid_match(&delegation->stateid, stateid)) {
- cred = get_rpccred(delegation->cred);
- rcu_read_unlock();
- status = nfs41_test_stateid(server, stateid, cred);
- trace_nfs4_test_delegation_stateid(state, NULL, status);
- } else
+ if (delegation == NULL) {
rcu_read_unlock();
+ return;
+ }
+
+ nfs4_stateid_copy(&stateid, &delegation->stateid);
+ cred = get_rpccred(delegation->cred);
+ rcu_read_unlock();
+ status = nfs41_test_stateid(server, &stateid, cred);
+ trace_nfs4_test_delegation_stateid(state, NULL, status);
if (status != NFS_OK) {
/* Free the stateid unless the server explicitly
* informs us the stateid is unrecognized. */
if (status != -NFS4ERR_BAD_STATEID)
- nfs41_free_stateid(server, stateid, cred);
- nfs_remove_bad_delegation(state->inode);
-
- write_seqlock(&state->seqlock);
- nfs4_stateid_copy(&state->stateid, &state->open_stateid);
- write_sequnlock(&state->seqlock);
- clear_bit(NFS_DELEGATED_STATE, &state->flags);
+ nfs41_free_stateid(server, &stateid, cred);
+ nfs_finish_clear_delegation_stateid(state);
}
- if (cred != NULL)
- put_rpccred(cred);
+ put_rpccred(cred);
}
/**
@@ -2192,7 +2201,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st
{
int status;
- nfs41_clear_delegation_stateid(state);
+ nfs41_check_delegation_stateid(state);
status = nfs41_check_open_stateid(state);
if (status != NFS_OK)
status = nfs4_open_expired(sp, state);
@@ -2231,19 +2240,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
ret = _nfs4_proc_open(opendata);
- if (ret != 0) {
- if (ret == -ENOENT) {
- dentry = opendata->dentry;
- if (dentry->d_inode)
- d_delete(dentry);
- else if (d_unhashed(dentry))
- d_add(dentry, NULL);
-
- nfs_set_verifier(dentry,
- nfs_save_change_attribute(opendata->dir->d_inode));
- }
+ if (ret != 0)
goto out;
- }
state = nfs4_opendata_to_nfs4_state(opendata);
ret = PTR_ERR(state);
@@ -4841,9 +4839,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
- if (state == NULL)
- break;
- nfs_remove_bad_delegation(state->inode);
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
@@ -8341,7 +8336,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = {
static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
.state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
- .recover_open = nfs4_open_expired,
+ .recover_open = nfs40_open_expired,
.recover_lock = nfs4_lock_expired,
.establish_clid = nfs4_init_clientid,
};
@@ -8408,8 +8403,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
| NFS_CAP_CHANGE_ATTR
| NFS_CAP_POSIX_LOCK
| NFS_CAP_STATEID_NFSV41
- | NFS_CAP_ATOMIC_OPEN_V1
- | NFS_CAP_SEEK,
+ | NFS_CAP_ATOMIC_OPEN_V1,
.init_client = nfs41_init_client,
.shutdown_client = nfs41_shutdown_client,
.match_stateid = nfs41_match_stateid,
@@ -8431,7 +8425,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_CHANGE_ATTR
| NFS_CAP_POSIX_LOCK
| NFS_CAP_STATEID_NFSV41
- | NFS_CAP_ATOMIC_OPEN_V1,
+ | NFS_CAP_ATOMIC_OPEN_V1
+ | NFS_CAP_SEEK,
.init_client = nfs41_init_client,
.shutdown_client = nfs41_shutdown_client,
.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 12493846a2d3..f83b02dc9166 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -715,8 +715,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
nfs_release_request(req);
- else
- WARN_ON_ONCE(1);
}
static void
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index ed2b1151b171..7cbdf1b2e4ab 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -774,8 +774,12 @@ static bool nfsd41_cb_get_slot(struct nfs4_client *clp, struct rpc_task *task)
{
if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
- dprintk("%s slot is busy\n", __func__);
- return false;
+ /* Race breaker */
+ if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+ dprintk("%s slot is busy\n", __func__);
+ return false;
+ }
+ rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
}
return true;
}
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 747f3b95bd11..33a46a8dfaf7 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -335,12 +335,15 @@ void nfsd_lockd_shutdown(void);
(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
- (NFSD4_1_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SECURITY_LABEL)
+#define NFSD4_2_SECURITY_ATTRS FATTR4_WORD2_SECURITY_LABEL
#else
-#define NFSD4_2_SUPPORTED_ATTRS_WORD2 0
+#define NFSD4_2_SECURITY_ATTRS 0
#endif
+#define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
+ (NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
+ NFSD4_2_SECURITY_ATTRS)
+
static inline u32 nfsd_suppattrs0(u32 minorversion)
{
return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 9d3e9c50066a..89326acd4561 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
&fsnotify_mark_srcu);
}
+ /*
+ * We need to merge inode & vfsmount mark lists so that inode mark
+ * ignore masks are properly reflected for mount mark notifications.
+ * That's why this traversal is so complicated...
+ */
while (inode_node || vfsmount_node) {
- inode_group = vfsmount_group = NULL;
+ inode_group = NULL;
+ inode_mark = NULL;
+ vfsmount_group = NULL;
+ vfsmount_mark = NULL;
if (inode_node) {
inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
@@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
vfsmount_group = vfsmount_mark->group;
}
- if (inode_group > vfsmount_group) {
- /* handle inode */
- ret = send_to_group(to_tell, inode_mark, NULL, mask,
- data, data_is, cookie, file_name);
- /* we didn't use the vfsmount_mark */
- vfsmount_group = NULL;
- } else if (vfsmount_group > inode_group) {
- ret = send_to_group(to_tell, NULL, vfsmount_mark, mask,
- data, data_is, cookie, file_name);
- inode_group = NULL;
- } else {
- ret = send_to_group(to_tell, inode_mark, vfsmount_mark,
- mask, data, data_is, cookie,
- file_name);
+ if (inode_group && vfsmount_group) {
+ int cmp = fsnotify_compare_groups(inode_group,
+ vfsmount_group);
+ if (cmp > 0) {
+ inode_group = NULL;
+ inode_mark = NULL;
+ } else if (cmp < 0) {
+ vfsmount_group = NULL;
+ vfsmount_mark = NULL;
+ }
}
+ ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
+ data, data_is, cookie, file_name);
if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
goto out;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 9c0898c4cfe1..3b68b0ae0a97 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
/* protects reads of inode and vfsmount marks list */
extern struct srcu_struct fsnotify_mark_srcu;
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+ struct fsnotify_group *b);
+
extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
__u32 mask);
/* add a mark to an inode */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index e8497144b323..dfbf5447eea4 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
{
struct fsnotify_mark *lmark, *last = NULL;
int ret = 0;
+ int cmp;
mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
@@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
goto out;
}
- if (mark->group->priority < lmark->group->priority)
- continue;
-
- if ((mark->group->priority == lmark->group->priority) &&
- (mark->group < lmark->group))
+ cmp = fsnotify_compare_groups(lmark->group, mark->group);
+ if (cmp < 0)
continue;
hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index daf76652fe58..283aa312d745 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -227,14 +227,13 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
struct fsnotify_event *kevent;
char __user *start;
int ret;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
start = buf;
group = file->private_data;
+ add_wait_queue(&group->notification_waitq, &wait);
while (1) {
- prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
mutex_lock(&group->notification_mutex);
kevent = get_one_event(group, count);
mutex_unlock(&group->notification_mutex);
@@ -264,10 +263,10 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
if (start != buf)
break;
- schedule();
+ wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
+ remove_wait_queue(&group->notification_waitq, &wait);
- finish_wait(&group->notification_waitq, &wait);
if (start != buf && ret != -EFAULT)
ret = buf - start;
return ret;
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d90deaa08e78..34c38fabf514 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -210,6 +210,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
}
/*
+ * Sorting function for lists of fsnotify marks.
+ *
+ * Fanotify supports different notification classes (reflected as priority of
+ * notification group). Events shall be passed to notification groups in
+ * decreasing priority order. To achieve this marks in notification lists for
+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
+ * are descending.
+ *
+ * Furthermore correct handling of the ignore mask requires processing inode
+ * and vfsmount marks of each group together. Using the group address as
+ * further sort criterion provides a unique sorting order and thus we can
+ * merge inode and vfsmount lists of marks in linear time and find groups
+ * present in both lists.
+ *
+ * A return value of 1 signifies that b has priority over a.
+ * A return value of 0 signifies that the two marks have to be handled together.
+ * A return value of -1 signifies that a has priority over b.
+ */
+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
+{
+ if (a == b)
+ return 0;
+ if (!a)
+ return 1;
+ if (!b)
+ return -1;
+ if (a->priority < b->priority)
+ return 1;
+ if (a->priority > b->priority)
+ return -1;
+ if (a < b)
+ return 1;
+ return -1;
+}
+
+/*
* Attach an initialized mark to a given group and fs object.
* These marks may be used for the fsnotify backend to determine which
* event types should be delivered to which group.
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index ac851e8376b1..faefa72a11eb 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
struct mount *m = real_mount(mnt);
struct fsnotify_mark *lmark, *last = NULL;
int ret = 0;
+ int cmp;
mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
@@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
goto out;
}
- if (mark->group->priority < lmark->group->priority)
- continue;
-
- if ((mark->group->priority == lmark->group->priority) &&
- (mark->group < lmark->group))
+ cmp = fsnotify_compare_groups(lmark->group, mark->group);
+ if (cmp < 0)
continue;
hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index e60125976873..34355818a2e0 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -1,4 +1,4 @@
-config OVERLAYFS_FS
+config OVERLAY_FS
tristate "Overlay filesystem support"
help
An overlay filesystem combines two filesystems - an 'upper' filesystem
diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile
index 8f91889480d0..900daed3e91d 100644
--- a/fs/overlayfs/Makefile
+++ b/fs/overlayfs/Makefile
@@ -2,6 +2,6 @@
# Makefile for the overlay filesystem.
#
-obj-$(CONFIG_OVERLAYFS_FS) += overlayfs.o
+obj-$(CONFIG_OVERLAY_FS) += overlay.o
-overlayfs-objs := super.o inode.o dir.o readdir.o copy_up.o
+overlay-objs := super.o inode.o dir.o readdir.o copy_up.o
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 15cd91ad9940..8ffc4b980f1b 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -284,8 +284,7 @@ out:
return ERR_PTR(err);
}
-static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry,
- enum ovl_path_type type)
+static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
{
int err;
struct dentry *ret = NULL;
@@ -294,8 +293,17 @@ static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry,
err = ovl_check_empty_dir(dentry, &list);
if (err)
ret = ERR_PTR(err);
- else if (type == OVL_PATH_MERGE)
- ret = ovl_clear_empty(dentry, &list);
+ else {
+ /*
+ * If no upperdentry then skip clearing whiteouts.
+ *
+ * Can race with copy-up, since we don't hold the upperdir
+ * mutex. Doesn't matter, since copy-up can't create a
+ * non-empty directory from an empty one.
+ */
+ if (ovl_dentry_upper(dentry))
+ ret = ovl_clear_empty(dentry, &list);
+ }
ovl_cache_free(&list);
@@ -487,8 +495,7 @@ out:
return err;
}
-static int ovl_remove_and_whiteout(struct dentry *dentry,
- enum ovl_path_type type, bool is_dir)
+static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
@@ -500,7 +507,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
int err;
if (is_dir) {
- opaquedir = ovl_check_empty_and_clear(dentry, type);
+ opaquedir = ovl_check_empty_and_clear(dentry);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out;
@@ -515,9 +522,10 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
if (IS_ERR(whiteout))
goto out_unlock;
- if (type == OVL_PATH_LOWER) {
+ upper = ovl_dentry_upper(dentry);
+ if (!upper) {
upper = lookup_one_len(dentry->d_name.name, upperdir,
- dentry->d_name.len);
+ dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto kill_whiteout;
@@ -529,7 +537,6 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
} else {
int flags = 0;
- upper = ovl_dentry_upper(dentry);
if (opaquedir)
upper = opaquedir;
err = -ESTALE;
@@ -648,7 +655,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
cap_raise(override_cred->cap_effective, CAP_CHOWN);
old_cred = override_creds(override_cred);
- err = ovl_remove_and_whiteout(dentry, type, is_dir);
+ err = ovl_remove_and_whiteout(dentry, is_dir);
revert_creds(old_cred);
put_cred(override_cred);
@@ -781,7 +788,7 @@ static int ovl_rename2(struct inode *olddir, struct dentry *old,
}
if (overwrite && (new_type == OVL_PATH_LOWER || new_type == OVL_PATH_MERGE) && new_is_dir) {
- opaquedir = ovl_check_empty_and_clear(new, new_type);
+ opaquedir = ovl_check_empty_and_clear(new);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir)) {
opaquedir = NULL;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index af2d18c9fcee..07d74b24913b 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -235,26 +235,36 @@ out:
return err;
}
+static bool ovl_need_xattr_filter(struct dentry *dentry,
+ enum ovl_path_type type)
+{
+ return type == OVL_PATH_UPPER && S_ISDIR(dentry->d_inode->i_mode);
+}
+
ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
void *value, size_t size)
{
- if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE &&
- ovl_is_private_xattr(name))
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+
+ if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
return -ENODATA;
- return vfs_getxattr(ovl_dentry_real(dentry), name, value, size);
+ return vfs_getxattr(realpath.dentry, name, value, size);
}
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
{
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
ssize_t res;
int off;
- res = vfs_listxattr(ovl_dentry_real(dentry), list, size);
+ res = vfs_listxattr(realpath.dentry, list, size);
if (res <= 0 || size == 0)
return res;
- if (ovl_path_type(dentry->d_parent) != OVL_PATH_MERGE)
+ if (!ovl_need_xattr_filter(dentry, type))
return res;
/* filter out private xattrs */
@@ -279,17 +289,16 @@ int ovl_removexattr(struct dentry *dentry, const char *name)
{
int err;
struct path realpath;
- enum ovl_path_type type;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
err = ovl_want_write(dentry);
if (err)
goto out;
- if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE &&
- ovl_is_private_xattr(name))
+ err = -ENODATA;
+ if (ovl_need_xattr_filter(dentry, type) && ovl_is_private_xattr(name))
goto out_drop_write;
- type = ovl_path_real(dentry, &realpath);
if (type == OVL_PATH_LOWER) {
err = vfs_getxattr(realpath.dentry, name, NULL, 0);
if (err < 0)
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 2a7ef4f8e2a6..ab1e3dcbed95 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -274,11 +274,11 @@ static int ovl_dir_mark_whiteouts(struct dentry *dir,
return 0;
}
-static inline int ovl_dir_read_merged(struct path *upperpath,
- struct path *lowerpath,
- struct list_head *list)
+static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list)
{
int err;
+ struct path lowerpath;
+ struct path upperpath;
struct ovl_readdir_data rdd = {
.ctx.actor = ovl_fill_merge,
.list = list,
@@ -286,25 +286,28 @@ static inline int ovl_dir_read_merged(struct path *upperpath,
.is_merge = false,
};
- if (upperpath->dentry) {
- err = ovl_dir_read(upperpath, &rdd);
+ ovl_path_lower(dentry, &lowerpath);
+ ovl_path_upper(dentry, &upperpath);
+
+ if (upperpath.dentry) {
+ err = ovl_dir_read(&upperpath, &rdd);
if (err)
goto out;
- if (lowerpath->dentry) {
- err = ovl_dir_mark_whiteouts(upperpath->dentry, &rdd);
+ if (lowerpath.dentry) {
+ err = ovl_dir_mark_whiteouts(upperpath.dentry, &rdd);
if (err)
goto out;
}
}
- if (lowerpath->dentry) {
+ if (lowerpath.dentry) {
/*
* Insert lowerpath entries before upperpath ones, this allows
* offsets to be reasonably constant
*/
list_add(&rdd.middle, rdd.list);
rdd.is_merge = true;
- err = ovl_dir_read(lowerpath, &rdd);
+ err = ovl_dir_read(&lowerpath, &rdd);
list_del(&rdd.middle);
}
out:
@@ -329,8 +332,6 @@ static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
{
int res;
- struct path lowerpath;
- struct path upperpath;
struct ovl_dir_cache *cache;
cache = ovl_dir_cache(dentry);
@@ -347,10 +348,7 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
cache->refcount = 1;
INIT_LIST_HEAD(&cache->entries);
- ovl_path_lower(dentry, &lowerpath);
- ovl_path_upper(dentry, &upperpath);
-
- res = ovl_dir_read_merged(&upperpath, &lowerpath, &cache->entries);
+ res = ovl_dir_read_merged(dentry, &cache->entries);
if (res) {
ovl_cache_free(&cache->entries);
kfree(cache);
@@ -452,10 +450,10 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
/*
* Need to check if we started out being a lower dir, but got copied up
*/
- if (!od->is_upper && ovl_path_type(dentry) == OVL_PATH_MERGE) {
+ if (!od->is_upper && ovl_path_type(dentry) != OVL_PATH_LOWER) {
struct inode *inode = file_inode(file);
- realfile =lockless_dereference(od->upperfile);
+ realfile = lockless_dereference(od->upperfile);
if (!realfile) {
struct path upperpath;
@@ -538,14 +536,9 @@ const struct file_operations ovl_dir_operations = {
int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
{
int err;
- struct path lowerpath;
- struct path upperpath;
struct ovl_cache_entry *p;
- ovl_path_upper(dentry, &upperpath);
- ovl_path_lower(dentry, &lowerpath);
-
- err = ovl_dir_read_merged(&upperpath, &lowerpath, list);
+ err = ovl_dir_read_merged(dentry, list);
if (err)
return err;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 08b704cebfc4..f16d318b71f8 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -24,7 +24,7 @@ MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Overlay filesystem");
MODULE_LICENSE("GPL");
-#define OVERLAYFS_SUPER_MAGIC 0x794c764f
+#define OVERLAYFS_SUPER_MAGIC 0x794c7630
struct ovl_config {
char *lowerdir;
@@ -84,12 +84,7 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
{
- struct dentry *upperdentry = ACCESS_ONCE(oe->__upperdentry);
- /*
- * Make sure to order reads to upperdentry wrt ovl_dentry_update()
- */
- smp_read_barrier_depends();
- return upperdentry;
+ return lockless_dereference(oe->__upperdentry);
}
void ovl_path_upper(struct dentry *dentry, struct path *path)
@@ -462,11 +457,34 @@ static const match_table_t ovl_tokens = {
{OPT_ERR, NULL}
};
+static char *ovl_next_opt(char **s)
+{
+ char *sbegin = *s;
+ char *p;
+
+ if (sbegin == NULL)
+ return NULL;
+
+ for (p = sbegin; *p; p++) {
+ if (*p == '\\') {
+ p++;
+ if (!*p)
+ break;
+ } else if (*p == ',') {
+ *p = '\0';
+ *s = p + 1;
+ return sbegin;
+ }
+ }
+ *s = NULL;
+ return sbegin;
+}
+
static int ovl_parse_opt(char *opt, struct ovl_config *config)
{
char *p;
- while ((p = strsep(&opt, ",")) != NULL) {
+ while ((p = ovl_next_opt(&opt)) != NULL) {
int token;
substring_t args[MAX_OPT_ARGS];
@@ -554,15 +572,34 @@ out_dput:
goto out_unlock;
}
+static void ovl_unescape(char *s)
+{
+ char *d = s;
+
+ for (;; s++, d++) {
+ if (*s == '\\')
+ s++;
+ *d = *s;
+ if (!*s)
+ break;
+ }
+}
+
static int ovl_mount_dir(const char *name, struct path *path)
{
int err;
+ char *tmp = kstrdup(name, GFP_KERNEL);
+
+ if (!tmp)
+ return -ENOMEM;
- err = kern_path(name, LOOKUP_FOLLOW, path);
+ ovl_unescape(tmp);
+ err = kern_path(tmp, LOOKUP_FOLLOW, path);
if (err) {
- pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+ pr_err("overlayfs: failed to resolve '%s': %i\n", tmp, err);
err = -EINVAL;
}
+ kfree(tmp);
return err;
}
@@ -776,11 +813,11 @@ static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
static struct file_system_type ovl_fs_type = {
.owner = THIS_MODULE,
- .name = "overlayfs",
+ .name = "overlay",
.mount = ovl_mount,
.kill_sb = kill_anon_super,
};
-MODULE_ALIAS_FS("overlayfs");
+MODULE_ALIAS_FS("overlay");
static int __init ovl_init(void)
{