summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/autofs_i.h26
-rw-r--r--fs/autofs4/waitq.c2
-rw-r--r--fs/befs/linuxvfs.c23
-rw-r--r--fs/btrfs/ctree.h10
-rw-r--r--fs/btrfs/extent-tree.c77
-rw-r--r--fs/btrfs/file.c28
-rw-r--r--fs/btrfs/free-space-cache.c16
-rw-r--r--fs/btrfs/inode.c12
-rw-r--r--fs/btrfs/ioctl.c4
-rw-r--r--fs/btrfs/tree-log.c28
-rw-r--r--fs/btrfs/volumes.c51
-rw-r--r--fs/btrfs/volumes.h2
-rw-r--r--fs/cifs/cifs_debug.c2
-rw-r--r--fs/cifs/cifsacl.c28
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h56
-rw-r--r--fs/cifs/connect.c3
-rw-r--r--fs/cifs/dir.c4
-rw-r--r--fs/cifs/transport.c51
-rw-r--r--fs/compat.c5
-rw-r--r--fs/compat_ioctl.c1
-rw-r--r--fs/ecryptfs/Kconfig2
-rw-r--r--fs/ecryptfs/keystore.c2
-rw-r--r--fs/ecryptfs/main.c23
-rw-r--r--fs/ecryptfs/read_write.c18
-rw-r--r--fs/exec.c17
-rw-r--r--fs/ext3/namei.c6
-rw-r--r--fs/ext4/ext4.h1
-rw-r--r--fs/ext4/ext4_jbd2.h4
-rw-r--r--fs/ext4/indirect.c9
-rw-r--r--fs/ext4/inode.c23
-rw-r--r--fs/ext4/namei.c6
-rw-r--r--fs/ext4/page-io.c24
-rw-r--r--fs/ext4/super.c1
-rw-r--r--fs/fat/dir.c2
-rw-r--r--fs/fat/inode.c7
-rw-r--r--fs/fuse/dev.c4
-rw-r--r--fs/fuse/file.c84
-rw-r--r--fs/fuse/fuse_i.h8
-rw-r--r--fs/fuse/inode.c10
-rw-r--r--fs/hugetlbfs/inode.c1
-rw-r--r--fs/inode.c24
-rw-r--r--fs/jfs/jfs_umount.c4
-rw-r--r--fs/nfs/Kconfig16
-rw-r--r--fs/nfs/blocklayout/blocklayout.c1
-rw-r--r--fs/nfs/callback.h2
-rw-r--r--fs/nfs/callback_proc.c25
-rw-r--r--fs/nfs/callback_xdr.c24
-rw-r--r--fs/nfs/objlayout/objio_osd.c28
-rw-r--r--fs/nfs/objlayout/pnfs_osd_xdr_cli.c3
50 files changed, 494 insertions, 316 deletions
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 475f9c5..326dc08 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -39,27 +39,17 @@
/* #define DEBUG */
-#ifdef DEBUG
-#define DPRINTK(fmt, args...) \
-do { \
- printk(KERN_DEBUG "pid %d: %s: " fmt "\n", \
- current->pid, __func__, ##args); \
-} while (0)
-#else
-#define DPRINTK(fmt, args...) do {} while (0)
-#endif
-
-#define AUTOFS_WARN(fmt, args...) \
-do { \
+#define DPRINTK(fmt, ...) \
+ pr_debug("pid %d: %s: " fmt "\n", \
+ current->pid, __func__, ##__VA_ARGS__)
+
+#define AUTOFS_WARN(fmt, ...) \
printk(KERN_WARNING "pid %d: %s: " fmt "\n", \
- current->pid, __func__, ##args); \
-} while (0)
+ current->pid, __func__, ##__VA_ARGS__)
-#define AUTOFS_ERROR(fmt, args...) \
-do { \
+#define AUTOFS_ERROR(fmt, ...) \
printk(KERN_ERR "pid %d: %s: " fmt "\n", \
- current->pid, __func__, ##args); \
-} while (0)
+ current->pid, __func__, ##__VA_ARGS__)
/* Unified info structure. This is pointed to by both the dentry and
inode structures. Each file in the filesystem has an instance of this
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 2543598..e1fbdee 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -104,7 +104,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
size_t pktsz;
DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
- wq->wait_queue_token, wq->name.len, wq->name.name, type);
+ (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type);
memset(&pkt,0,sizeof pkt); /* For security reasons */
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 54b8c28..720d885 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -474,17 +474,22 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd)
befs_data_stream *data = &befs_ino->i_data.ds;
befs_off_t len = data->size;
- befs_debug(sb, "Follow long symlink");
-
- link = kmalloc(len, GFP_NOFS);
- if (!link) {
- link = ERR_PTR(-ENOMEM);
- } else if (befs_read_lsymlink(sb, data, link, len) != len) {
- kfree(link);
- befs_error(sb, "Failed to read entire long symlink");
+ if (len == 0) {
+ befs_error(sb, "Long symlink with illegal length");
link = ERR_PTR(-EIO);
} else {
- link[len - 1] = '\0';
+ befs_debug(sb, "Follow long symlink");
+
+ link = kmalloc(len, GFP_NOFS);
+ if (!link) {
+ link = ERR_PTR(-ENOMEM);
+ } else if (befs_read_lsymlink(sb, data, link, len) != len) {
+ kfree(link);
+ befs_error(sb, "Failed to read entire long symlink");
+ link = ERR_PTR(-EIO);
+ } else {
+ link[len - 1] = '\0';
+ }
}
} else {
link = befs_ino->i_data.symlink;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0469263..03912c5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1415,17 +1415,15 @@ void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val);
#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(struct extent_buffer *eb) \
{ \
- type *p = kmap_atomic(eb->first_page, KM_USER0); \
+ type *p = page_address(eb->first_page); \
u##bits res = le##bits##_to_cpu(p->member); \
- kunmap_atomic(p, KM_USER0); \
return res; \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, \
u##bits val) \
{ \
- type *p = kmap_atomic(eb->first_page, KM_USER0); \
+ type *p = page_address(eb->first_page); \
p->member = cpu_to_le##bits(val); \
- kunmap_atomic(p, KM_USER0); \
}
#define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \
@@ -2367,8 +2365,8 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf);
-int btrfs_drop_snapshot(struct btrfs_root *root,
- struct btrfs_block_rsv *block_rsv, int update_ref);
+void btrfs_drop_snapshot(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv, int update_ref);
int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *node,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 66bac22..f5be06a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1782,6 +1782,9 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
for (i = 0; i < multi->num_stripes; i++, stripe++) {
+ if (!stripe->dev->can_discard)
+ continue;
+
ret = btrfs_issue_discard(stripe->dev->bdev,
stripe->physical,
stripe->length);
@@ -1789,11 +1792,16 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
discarded_bytes += stripe->length;
else if (ret != -EOPNOTSUPP)
break;
+
+ /*
+ * Just in case we get back EOPNOTSUPP for some reason,
+ * just ignore the return value so we don't screw up
+ * people calling discard_extent.
+ */
+ ret = 0;
}
kfree(multi);
}
- if (discarded_bytes && ret == -EOPNOTSUPP)
- ret = 0;
if (actual_bytes)
*actual_bytes = discarded_bytes;
@@ -6269,8 +6277,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
* also make sure backrefs for the shared block and all lower level
* blocks are properly updated.
*/
-int btrfs_drop_snapshot(struct btrfs_root *root,
- struct btrfs_block_rsv *block_rsv, int update_ref)
+void btrfs_drop_snapshot(struct btrfs_root *root,
+ struct btrfs_block_rsv *block_rsv, int update_ref)
{
struct btrfs_path *path;
struct btrfs_trans_handle *trans;
@@ -6283,13 +6291,16 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
int level;
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ err = -ENOMEM;
+ goto out;
+ }
wc = kzalloc(sizeof(*wc), GFP_NOFS);
if (!wc) {
btrfs_free_path(path);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto out;
}
trans = btrfs_start_transaction(tree_root, 0);
@@ -6318,7 +6329,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
path->lowest_level = 0;
if (ret < 0) {
err = ret;
- goto out;
+ goto out_free;
}
WARN_ON(ret > 0);
@@ -6425,11 +6436,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
free_extent_buffer(root->commit_root);
kfree(root);
}
-out:
+out_free:
btrfs_end_transaction_throttle(trans, tree_root);
kfree(wc);
btrfs_free_path(path);
- return err;
+out:
+ if (err)
+ btrfs_std_error(root->fs_info, err);
+ return;
}
/*
@@ -6720,6 +6734,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
struct btrfs_space_info *space_info;
struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
struct btrfs_device *device;
+ u64 min_free;
+ u64 dev_min = 1;
+ u64 dev_nr = 0;
+ int index;
int full = 0;
int ret = 0;
@@ -6729,8 +6747,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
if (!block_group)
return -1;
+ min_free = btrfs_block_group_used(&block_group->item);
+
/* no bytes used, we're good */
- if (!btrfs_block_group_used(&block_group->item))
+ if (!min_free)
goto out;
space_info = block_group->space_info;
@@ -6746,10 +6766,9 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
* all of the extents from this block group. If we can, we're good
*/
if ((space_info->total_bytes != block_group->key.offset) &&
- (space_info->bytes_used + space_info->bytes_reserved +
- space_info->bytes_pinned + space_info->bytes_readonly +
- btrfs_block_group_used(&block_group->item) <
- space_info->total_bytes)) {
+ (space_info->bytes_used + space_info->bytes_reserved +
+ space_info->bytes_pinned + space_info->bytes_readonly +
+ min_free < space_info->total_bytes)) {
spin_unlock(&space_info->lock);
goto out;
}
@@ -6766,9 +6785,31 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
if (full)
goto out;
+ /*
+ * index:
+ * 0: raid10
+ * 1: raid1
+ * 2: dup
+ * 3: raid0
+ * 4: single
+ */
+ index = get_block_group_index(block_group);
+ if (index == 0) {
+ dev_min = 4;
+ /* Divide by 2 */
+ min_free >>= 1;
+ } else if (index == 1) {
+ dev_min = 2;
+ } else if (index == 2) {
+ /* Multiply by 2 */
+ min_free <<= 1;
+ } else if (index == 3) {
+ dev_min = fs_devices->rw_devices;
+ do_div(min_free, dev_min);
+ }
+
mutex_lock(&root->fs_info->chunk_mutex);
list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
- u64 min_free = btrfs_block_group_used(&block_group->item);
u64 dev_offset;
/*
@@ -6779,7 +6820,11 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
ret = find_free_dev_extent(NULL, device, min_free,
&dev_offset, NULL);
if (!ret)
+ dev_nr++;
+
+ if (dev_nr >= dev_min)
break;
+
ret = -1;
}
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 658d669..e7872e4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -150,6 +150,8 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
spin_lock(&root->fs_info->defrag_inodes_lock);
if (!BTRFS_I(inode)->in_defrag)
__btrfs_add_inode_defrag(inode, defrag);
+ else
+ kfree(defrag);
spin_unlock(&root->fs_info->defrag_inodes_lock);
return 0;
}
@@ -1638,11 +1640,15 @@ static long btrfs_fallocate(struct file *file, int mode,
cur_offset = alloc_start;
while (1) {
+ u64 actual_end;
+
em = btrfs_get_extent(inode, NULL, 0, cur_offset,
alloc_end - cur_offset, 0);
BUG_ON(IS_ERR_OR_NULL(em));
last_byte = min(extent_map_end(em), alloc_end);
+ actual_end = min_t(u64, extent_map_end(em), offset + len);
last_byte = (last_byte + mask) & ~mask;
+
if (em->block_start == EXTENT_MAP_HOLE ||
(cur_offset >= inode->i_size &&
!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
@@ -1655,6 +1661,16 @@ static long btrfs_fallocate(struct file *file, int mode,
free_extent_map(em);
break;
}
+ } else if (actual_end > inode->i_size &&
+ !(mode & FALLOC_FL_KEEP_SIZE)) {
+ /*
+ * We didn't need to allocate any more space, but we
+ * still extended the size of the file so we need to
+ * update i_size.
+ */
+ inode->i_ctime = CURRENT_TIME;
+ i_size_write(inode, actual_end);
+ btrfs_ordered_update_i_size(inode, actual_end, NULL);
}
free_extent_map(em);
@@ -1804,10 +1820,14 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
}
}
- if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
- return -EINVAL;
- if (offset > inode->i_sb->s_maxbytes)
- return -EINVAL;
+ if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ if (offset > inode->i_sb->s_maxbytes) {
+ ret = -EINVAL;
+ goto out;
+ }
/* Special lock needed here? */
if (offset != file->f_pos) {
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6377713..6a265b9 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1168,9 +1168,9 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
div64_u64(extent_bytes, (sizeof(struct btrfs_free_space)));
}
-static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
- struct btrfs_free_space *info, u64 offset,
- u64 bytes)
+static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+ struct btrfs_free_space *info,
+ u64 offset, u64 bytes)
{
unsigned long start, count;
@@ -1181,6 +1181,13 @@ static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
bitmap_clear(info->bitmap, start, count);
info->bytes -= bytes;
+}
+
+static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+ struct btrfs_free_space *info, u64 offset,
+ u64 bytes)
+{
+ __bitmap_clear_bits(ctl, info, offset, bytes);
ctl->free_space -= bytes;
}
@@ -1984,7 +1991,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
return 0;
ret = search_start;
- bitmap_clear_bits(ctl, entry, ret, bytes);
+ __bitmap_clear_bits(ctl, entry, ret, bytes);
return ret;
}
@@ -2039,7 +2046,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
continue;
}
} else {
-
ret = entry->offset;
entry->offset += bytes;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 15fceef..0ccc743 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7354,11 +7354,15 @@ static int btrfs_set_page_dirty(struct page *page)
static int btrfs_permission(struct inode *inode, int mask)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
+ umode_t mode = inode->i_mode;
- if (btrfs_root_readonly(root) && (mask & MAY_WRITE))
- return -EROFS;
- if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE))
- return -EACCES;
+ if (mask & MAY_WRITE &&
+ (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
+ if (btrfs_root_readonly(root))
+ return -EROFS;
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
+ return -EACCES;
+ }
return generic_permission(inode, mask);
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7cf0133..970977a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2236,6 +2236,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
btrfs_wait_ordered_range(src, off, len);
}
+ /* truncate page cache pages from target inode range */
+ truncate_inode_pages_range(&inode->i_data, off,
+ ALIGN(off + len, PAGE_CACHE_SIZE) - 1);
+
/* clone data */
key.objectid = btrfs_ino(src);
key.type = BTRFS_EXTENT_DATA_KEY;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index babee65..786639f 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -799,14 +799,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
struct extent_buffer *eb, int slot,
struct btrfs_key *key)
{
- struct inode *dir;
- int ret;
struct btrfs_inode_ref *ref;
+ struct btrfs_dir_item *di;
+ struct inode *dir;
struct inode *inode;
- char *name;
- int namelen;
unsigned long ref_ptr;
unsigned long ref_end;
+ char *name;
+ int namelen;
+ int ret;
int search_done = 0;
/*
@@ -909,6 +910,25 @@ again:
}
btrfs_release_path(path);
+ /* look for a conflicting sequence number */
+ di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir),
+ btrfs_inode_ref_index(eb, ref),
+ name, namelen, 0);
+ if (di && !IS_ERR(di)) {
+ ret = drop_one_dir_item(trans, root, path, dir, di);
+ BUG_ON(ret);
+ }
+ btrfs_release_path(path);
+
+ /* look for a conflicing name */
+ di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir),
+ name, namelen, 0);
+ if (di && !IS_ERR(di)) {
+ ret = drop_one_dir_item(trans, root, path, dir, di);
+ BUG_ON(ret);
+ }
+ btrfs_release_path(path);
+
insert:
/* insert our name */
ret = btrfs_add_link(trans, dir, inode, name, namelen, 0,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 53875ae73..f2a4cc7 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -142,6 +142,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
unsigned long limit;
unsigned long last_waited = 0;
int force_reg = 0;
+ int sync_pending = 0;
struct blk_plug plug;
/*
@@ -229,6 +230,22 @@ loop_lock:
BUG_ON(atomic_read(&cur->bi_cnt) == 0);
+ /*
+ * if we're doing the sync list, record that our
+ * plug has some sync requests on it
+ *
+ * If we're doing the regular list and there are
+ * sync requests sitting around, unplug before
+ * we add more
+ */
+ if (pending_bios == &device->pending_sync_bios) {
+ sync_pending = 1;
+ } else if (sync_pending) {
+ blk_finish_plug(&plug);
+ blk_start_plug(&plug);
+ sync_pending = 0;
+ }
+
submit_bio(cur->bi_rw, cur);
num_run++;
batch_run++;
@@ -500,6 +517,9 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
fs_devices->rw_devices--;
}
+ if (device->can_discard)
+ fs_devices->num_can_discard--;
+
new_device = kmalloc(sizeof(*new_device), GFP_NOFS);
BUG_ON(!new_device);
memcpy(new_device, device, sizeof(*new_device));
@@ -508,6 +528,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
new_device->bdev = NULL;
new_device->writeable = 0;
new_device->in_fs_metadata = 0;
+ new_device->can_discard = 0;
list_replace_rcu(&device->dev_list, &new_device->dev_list);
call_rcu(&device->rcu, free_device);
@@ -547,6 +568,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
fmode_t flags, void *holder)
{
+ struct request_queue *q;
struct block_device *bdev;
struct list_head *head = &fs_devices->devices;
struct btrfs_device *device;
@@ -603,6 +625,12 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
seeding = 0;
}
+ q = bdev_get_queue(bdev);
+ if (blk_queue_discard(q)) {
+ device->can_discard = 1;
+ fs_devices->num_can_discard++;
+ }
+
device->bdev = bdev;
device->in_fs_metadata = 0;
device->mode = flags;
@@ -835,6 +863,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
max_hole_start = search_start;
max_hole_size = 0;
+ hole_size = 0;
if (search_start >= search_end) {
ret = -ENOSPC;
@@ -917,7 +946,14 @@ next:
cond_resched();
}
- hole_size = search_end- search_start;
+ /*
+ * At this point, search_start should be the end of
+ * allocated dev extents, and when shrinking the device,
+ * search_end may be smaller than search_start.
+ */
+ if (search_end > search_start)
+ hole_size = search_end - search_start;
+
if (hole_size > max_hole_size) {
max_hole_start = search_start;
max_hole_size = hole_size;
@@ -1543,6 +1579,7 @@ error:
int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
{
+ struct request_queue *q;
struct btrfs_trans_handle *trans;
struct btrfs_device *device;
struct block_device *bdev;
@@ -1612,6 +1649,9 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
lock_chunks(root);
+ q = bdev_get_queue(bdev);
+ if (blk_queue_discard(q))
+ device->can_discard = 1;
device->writeable = 1;
device->work.func = pending_bios_fn;
generate_random_uuid(device->uuid);
@@ -1647,6 +1687,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
root->fs_info->fs_devices->num_devices++;
root->fs_info->fs_devices->open_devices++;
root->fs_info->fs_devices->rw_devices++;
+ if (device->can_discard)
+ root->fs_info->fs_devices->num_can_discard++;
root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
if (!blk_queue_nonrot(bdev_get_queue(bdev)))
@@ -2413,9 +2455,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
total_avail = device->total_bytes - device->bytes_used;
else
total_avail = 0;
- /* avail is off by max(alloc_start, 1MB), but that is the same
- * for all devices, so it doesn't hurt the sorting later on
- */
+
+ /* If there is no space on this device, skip it. */
+ if (total_avail == 0)
+ continue;
ret = find_free_dev_extent(trans, device,
max_stripe_size * dev_stripes,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7c12d61..6d866db 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -48,6 +48,7 @@ struct btrfs_device {
int writeable;
int in_fs_metadata;
int missing;
+ int can_discard;
spinlock_t io_lock;
@@ -104,6 +105,7 @@ struct btrfs_fs_devices {
u64 rw_devices;
u64 missing_devices;
u64 total_rw_bytes;
+ u64 num_can_discard;
struct block_device *latest_bdev;
/* all of the devices in the FS, protected by a mutex
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 2fe3cf1..6d40656 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -176,7 +176,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
#ifdef CONFIG_CIFS_STATS2
seq_printf(m, " In Send: %d In MaxReq Wait: %d",
- atomic_read(&server->inSend),
+ atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
#endif
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 21de1d6..d0f59fa 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -991,24 +991,6 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
return pntsd;
}
-static int set_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, __u16 fid,
- struct cifs_ntsd *pnntsd, u32 acllen)
-{
- int xid, rc;
- struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-
- if (IS_ERR(tlink))
- return PTR_ERR(tlink);
-
- xid = GetXid();
- rc = CIFSSMBSetCIFSACL(xid, tlink_tcon(tlink), fid, pnntsd, acllen);
- FreeXid(xid);
- cifs_put_tlink(tlink);
-
- cFYI(DBG2, "SetCIFSACL rc = %d", rc);
- return rc;
-}
-
static int set_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, const char *path,
struct cifs_ntsd *pnntsd, u32 acllen)
{
@@ -1047,18 +1029,10 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
struct inode *inode, const char *path)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
- struct cifsFileInfo *open_file;
- int rc;
cFYI(DBG2, "set ACL for %s from mode 0x%x", path, inode->i_mode);
- open_file = find_readable_file(CIFS_I(inode), true);
- if (!open_file)
- return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
-
- rc = set_cifs_acl_by_fid(cifs_sb, open_file->netfid, pnntsd, acllen);
- cifsFileInfo_put(open_file);
- return rc;
+ return set_cifs_acl_by_path(cifs_sb, path, pnntsd, acllen);
}
/* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index cb71dc1..95da802 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -125,5 +125,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "1.74"
+#define CIFS_VERSION "1.75"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 38ce6d4..95dad9d 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -291,7 +291,7 @@ struct TCP_Server_Info {
struct fscache_cookie *fscache; /* client index cache cookie */
#endif
#ifdef CONFIG_CIFS_STATS2
- atomic_t inSend; /* requests trying to send */
+ atomic_t in_send; /* requests trying to send */
atomic_t num_waiters; /* blocked waiting to get in sendrecv */
#endif
};
@@ -672,12 +672,54 @@ struct mid_q_entry {
bool multiEnd:1; /* both received */
};
-struct oplock_q_entry {
- struct list_head qhead;
- struct inode *pinode;
- struct cifs_tcon *tcon;
- __u16 netfid;
-};
+/* Make code in transport.c a little cleaner by moving
+ update of optional stats into function below */
+#ifdef CONFIG_CIFS_STATS2
+
+static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
+{
+ atomic_inc(&server->in_send);
+}
+
+static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
+{
+ atomic_dec(&server->in_send);
+}
+
+static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
+{
+ atomic_inc(&server->num_waiters);
+}
+
+static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
+{
+ atomic_dec(&server->num_waiters);
+}
+
+static inline void cifs_save_when_sent(struct mid_q_entry *mid)
+{
+ mid->when_sent = jiffies;
+}
+#else
+static inline void cifs_in_send_inc(struct TCP_Server_Info *server)
+{
+}
+static inline void cifs_in_send_dec(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_num_waiters_inc(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_num_waiters_dec(struct TCP_Server_Info *server)
+{
+}
+
+static inline void cifs_save_when_sent(struct mid_q_entry *mid)
+{
+}
+#endif
/* for pending dnotify requests */
struct dir_notify_req {
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 80c2e3a..633c246 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2878,7 +2878,8 @@ cleanup_volume_info_contents(struct smb_vol *volume_info)
kfree(volume_info->username);
kzfree(volume_info->password);
kfree(volume_info->UNC);
- kfree(volume_info->UNCip);
+ if (volume_info->UNCip != volume_info->UNC + 2)
+ kfree(volume_info->UNCip);
kfree(volume_info->domainname);
kfree(volume_info->iocharset);
kfree(volume_info->prepath);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ae576fb..72d448b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -105,8 +105,8 @@ cifs_bp_rename_retry:
}
rcu_read_unlock();
if (namelen != dfsplen || read_seqretry(&rename_lock, seq)) {
- cERROR(1, "did not end path lookup where expected namelen is %d",
- namelen);
+ cFYI(1, "did not end path lookup where expected. namelen=%d "
+ "dfsplen=%d", namelen, dfsplen);
/* presumably this is only possible if racing with a rename
of one of the parent directories (we can not lock the dentries
above us to prevent this, but retrying should be harmless) */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index c1b9c4b..10ca6b2 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -266,15 +266,11 @@ static int wait_for_free_request(struct TCP_Server_Info *server,
while (1) {
if (atomic_read(&server->inFlight) >= cifs_max_pending) {
spin_unlock(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&server->num_waiters);
-#endif
+ cifs_num_waiters_inc(server);
wait_event(server->request_q,
atomic_read(&server->inFlight)
< cifs_max_pending);
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&server->num_waiters);
-#endif
+ cifs_num_waiters_dec(server);
spin_lock(&GlobalMid_Lock);
} else {
if (server->tcpStatus == CifsExiting) {
@@ -381,15 +377,13 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov,
mid->callback = callback;
mid->callback_data = cbdata;
mid->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&server->inSend);
-#endif
+
+ cifs_in_send_inc(server);
rc = smb_sendv(server, iov, nvec);
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&server->inSend);
- mid->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(server);
+ cifs_save_when_sent(mid);
mutex_unlock(&server->srv_mutex);
+
if (rc)
goto out_err;
@@ -575,14 +569,10 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
}
midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&ses->server->inSend);
-#endif
+ cifs_in_send_inc(ses->server);
rc = smb_sendv(ses->server, iov, n_vec);
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&ses->server->inSend);
- midQ->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(ses->server);
+ cifs_save_when_sent(midQ);
mutex_unlock(&ses->server->srv_mutex);
@@ -703,14 +693,11 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
}
midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&ses->server->inSend);
-#endif
+
+ cifs_in_send_inc(ses->server);
rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&ses->server->inSend);
- midQ->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(ses->server);
+ cifs_save_when_sent(midQ);
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0)
@@ -843,14 +830,10 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
}
midQ->midState = MID_REQUEST_SUBMITTED;
-#ifdef CONFIG_CIFS_STATS2
- atomic_inc(&ses->server->inSend);
-#endif
+ cifs_in_send_inc(ses->server);
rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
-#ifdef CONFIG_CIFS_STATS2
- atomic_dec(&ses->server->inSend);
- midQ->when_sent = jiffies;
-#endif
+ cifs_in_send_dec(ses->server);
+ cifs_save_when_sent(midQ);
mutex_unlock(&ses->server->srv_mutex);
if (rc < 0) {
diff --git a/fs/compat.c b/fs/compat.c
index 0b48d01..58b1da4 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1675,11 +1675,6 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
}
#endif /* HAVE_SET_RESTORE_SIGMASK */
-long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2)
-{
- return sys_ni_syscall();
-}
-
#ifdef CONFIG_EPOLL
#ifdef HAVE_SET_RESTORE_SIGMASK
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 8be086e..51352de 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1003,6 +1003,7 @@ COMPATIBLE_IOCTL(PPPIOCCONNECT)
COMPATIBLE_IOCTL(PPPIOCDISCONN)
COMPATIBLE_IOCTL(PPPIOCATTCHAN)
COMPATIBLE_IOCTL(PPPIOCGCHAN)
+COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
/* PPPOX */
COMPATIBLE_IOCTL(PPPOEIOCSFWD)
COMPATIBLE_IOCTL(PPPOEIOCDFWD)
diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig
index 1cd6d9d..cc16562 100644
--- a/fs/ecryptfs/Kconfig
+++ b/fs/ecryptfs/Kconfig
@@ -1,6 +1,6 @@
config ECRYPT_FS
tristate "eCrypt filesystem layer support (EXPERIMENTAL)"
- depends on EXPERIMENTAL && KEYS && CRYPTO
+ depends on EXPERIMENTAL && KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
select CRYPTO_ECB
select CRYPTO_CBC
select CRYPTO_MD5
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 08a2b52..ac1ad48 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1973,7 +1973,7 @@ pki_encrypt_session_key(struct key *auth_tok_key,
{
struct ecryptfs_msg_ctx *msg_ctx = NULL;
char *payload = NULL;
- size_t payload_len;
+ size_t payload_len = 0;
struct ecryptfs_message *msg;
int rc;
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 9f1bb74..b4a6bef 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -175,6 +175,7 @@ enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
ecryptfs_opt_encrypted_view, ecryptfs_opt_fnek_sig,
ecryptfs_opt_fn_cipher, ecryptfs_opt_fn_cipher_key_bytes,
ecryptfs_opt_unlink_sigs, ecryptfs_opt_mount_auth_tok_only,
+ ecryptfs_opt_check_dev_ruid,
ecryptfs_opt_err };
static const match_table_t tokens = {
@@ -191,6 +192,7 @@ static const match_table_t tokens = {
{ecryptfs_opt_fn_cipher_key_bytes, "ecryptfs_fn_key_bytes=%u"},
{ecryptfs_opt_unlink_sigs, "ecryptfs_unlink_sigs"},
{ecryptfs_opt_mount_auth_tok_only, "ecryptfs_mount_auth_tok_only"},
+ {ecryptfs_opt_check_dev_ruid, "ecryptfs_check_dev_ruid"},
{ecryptfs_opt_err, NULL}
};
@@ -236,6 +238,7 @@ static void ecryptfs_init_mount_crypt_stat(
* ecryptfs_parse_options
* @sb: The ecryptfs super block
* @options: The options passed to the kernel
+ * @check_ruid: set to 1 if device uid should be checked against the ruid
*
* Parse mount options:
* debug=N - ecryptfs_verbosity level for debug output
@@ -251,7 +254,8 @@ static void ecryptfs_init_mount_crypt_stat(
*
* Returns zero on success; non-zero on error
*/
-static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
+static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options,
+ uid_t *check_ruid)
{
char *p;
int rc = 0;
@@ -276,6 +280,8 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
char *cipher_key_bytes_src;
char *fn_cipher_key_bytes_src;
+ *check_ruid = 0;
+
if (!options) {
rc = -EINVAL;
goto out;
@@ -380,6 +386,9 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options)
mount_crypt_stat->flags |=
ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY;
break;
+ case ecryptfs_opt_check_dev_ruid:
+ *check_ruid = 1;
+ break;
case ecryptfs_opt_err:
default:
printk(KERN_WARNING
@@ -475,6 +484,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
const char *err = "Getting sb failed";
struct inode *inode;
struct path path;
+ uid_t check_ruid;
int rc;
sbi = kmem_cache_zalloc(ecryptfs_sb_info_cache, GFP_KERNEL);
@@ -483,7 +493,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
goto out;
}
- rc = ecryptfs_parse_options(sbi, raw_data);
+ rc = ecryptfs_parse_options(sbi, raw_data, &check_ruid);
if (rc) {
err = "Error parsing options";
goto out;
@@ -521,6 +531,15 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
"known incompatibilities\n");
goto out_free;
}
+
+ if (check_ruid && path.dentry->d_inode->i_uid != current_uid()) {
+ rc = -EPERM;
+ printk(KERN_ERR "Mount of device (uid: %d) not owned by "
+ "requested user (uid: %d)\n",
+ path.dentry->d_inode->i_uid, current_uid());
+ goto out_free;
+ }
+
ecryptfs_set_superblock_lower(s, path.dentry->d_sb);
s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 85d4309..3745f7c 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -39,15 +39,16 @@
int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
loff_t offset, size_t size)
{
- struct ecryptfs_inode_info *inode_info;
+ struct file *lower_file;
mm_segment_t fs_save;
ssize_t rc;
- inode_info = ecryptfs_inode_to_private(ecryptfs_inode);
- BUG_ON(!inode_info->lower_file);
+ lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file;
+ if (!lower_file)
+ return -EIO;
fs_save = get_fs();
set_fs(get_ds());
- rc = vfs_write(inode_info->lower_file, data, size, &offset);
+ rc = vfs_write(lower_file, data, size, &offset);
set_fs(fs_save);
mark_inode_dirty_sync(ecryptfs_inode);
return rc;
@@ -225,15 +226,16 @@ out:
int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
struct inode *ecryptfs_inode)
{
- struct ecryptfs_inode_info *inode_info =
- ecryptfs_inode_to_private(ecryptfs_inode);
+ struct file *lower_file;
mm_segment_t fs_save;
ssize_t rc;
- BUG_ON(!inode_info->lower_file);
+ lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file;
+ if (!lower_file)
+ return -EIO;
fs_save = get_fs();
set_fs(get_ds());
- rc = vfs_read(inode_info->lower_file, data, size, &offset);
+ rc = vfs_read(lower_file, data, size, &offset);
set_fs(fs_save);
return rc;
}
diff --git a/fs/exec.c b/fs/exec.c
index da80612..25dcbe5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1459,6 +1459,23 @@ static int do_execve_common(const char *filename,
struct files_struct *displaced;
bool clear_in_exec;
int retval;
+ const struct cred *cred = current_cred();
+
+ /*
+ * We move the actual failure in case of RLIMIT_NPROC excess from
+ * set*uid() to execve() because too many poorly written programs
+ * don't check setuid() return code. Here we additionally recheck
+ * whether NPROC limit is still exceeded.
+ */
+ if ((current->flags & PF_NPROC_EXCEEDED) &&
+ atomic_read(&cred->user->processes) > rlimit(RLIMIT_NPROC)) {
+ retval = -EAGAIN;
+ goto out_ret;
+ }
+
+ /* We're below the limit (still or again), so we don't want to make
+ * further execve() calls fail. */
+ current->flags &= ~PF_NPROC_EXCEEDED;
retval = unshare_files(&displaced);
if (retval)
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 6e18a0b..5571708 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -2209,9 +2209,11 @@ static int ext3_symlink (struct inode * dir,
/*
* For non-fast symlinks, we just allocate inode and put it on
* orphan list in the first transaction => we need bitmap,
- * group descriptor, sb, inode block, quota blocks.
+ * group descriptor, sb, inode block, quota blocks, and
+ * possibly selinux xattr blocks.
*/
- credits = 4 + EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+ credits = 4 + EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ EXT3_XATTR_TRANS_BLOCKS;
} else {
/*
* Fast symlink. We have to add entry to directory
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e717dfd..b7d7bd0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
+#define EXT4_IO_END_QUEUED 0x0004
struct ext4_io_page {
struct page *p_page;
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index bb85757..5802fa1 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -289,10 +289,10 @@ static inline int ext4_should_order_data(struct inode *inode)
static inline int ext4_should_writeback_data(struct inode *inode)
{
- if (!S_ISREG(inode->i_mode))
- return 0;
if (EXT4_JOURNAL(inode) == NULL)
return 1;
+ if (!S_ISREG(inode->i_mode))
+ return 0;
if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b8602cd..0962642 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -800,12 +800,17 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
}
retry:
- if (rw == READ && ext4_should_dioread_nolock(inode))
+ if (rw == READ && ext4_should_dioread_nolock(inode)) {
+ if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+ mutex_lock(&inode->i_mutex);
+ ext4_flush_completed_IO(inode);
+ mutex_unlock(&inode->i_mutex);
+ }
ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block, NULL, NULL, 0);
- else {
+ } else {
ret = blockdev_direct_IO(rw, iocb, inode, iov,
offset, nr_segs, ext4_get_block);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d47264c..18d2558 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -120,6 +120,9 @@ void ext4_evict_inode(struct inode *inode)
int err;
trace_ext4_evict_inode(inode);
+
+ ext4_ioend_wait(inode);
+
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
@@ -983,6 +986,8 @@ static int ext4_journalled_write_end(struct file *file,
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
+ BUG_ON(!ext4_handle_valid(handle));
+
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
@@ -1283,7 +1288,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
err = ext4_bio_write_page(&io_submit, page,
len, mpd->wbc);
- else
+ else if (buffer_uninit(page_bufs)) {
+ ext4_set_bh_endio(page_bufs, inode);
+ err = block_write_full_page_endio(page,
+ noalloc_get_block_write,
+ mpd->wbc, ext4_end_io_buffer_write);
+ } else
err = block_write_full_page(page,
noalloc_get_block_write, mpd->wbc);
@@ -1699,6 +1709,8 @@ static int __ext4_journalled_writepage(struct page *page,
goto out;
}
+ BUG_ON(!ext4_handle_valid(handle));
+
ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
@@ -2668,8 +2680,15 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
goto out;
}
- io_end->flag = EXT4_IO_END_UNWRITTEN;
+ /*
+ * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+ * but being more careful is always safe for the future change.
+ */
inode = io_end->inode;
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 565a154..f8068c7 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2253,9 +2253,11 @@ static int ext4_symlink(struct inode *dir,
/*
* For non-fast symlinks, we just allocate inode and put it on
* orphan list in the first transaction => we need bitmap,
- * group descriptor, sb, inode block, quota blocks.
+ * group descriptor, sb, inode block, quota blocks, and
+ * possibly selinux xattr blocks.
*/
- credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+ credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ EXT4_XATTR_TRANS_BLOCKS;
} else {
/*
* Fast symlink. We have to add entry to directory
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 430c401..92f38ee 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
unsigned long flags;
int ret;
- mutex_lock(&inode->i_mutex);
+ if (!mutex_trylock(&inode->i_mutex)) {
+ /*
+ * Requeue the work instead of waiting so that the work
+ * items queued after this can be processed.
+ */
+ queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+ /*
+ * To prevent the ext4-dio-unwritten thread from keeping
+ * requeueing end_io requests and occupying cpu for too long,
+ * yield the cpu if it sees an end_io request that has already
+ * been requeued.
+ */
+ if (io->flag & EXT4_IO_END_QUEUED)
+ yield();
+ io->flag |= EXT4_IO_END_QUEUED;
+ return;
+ }
ret = ext4_end_io_nolock(io);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
@@ -334,8 +350,10 @@ submit_and_retry:
if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
- if (buffer_uninit(bh))
- io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4687fea..44d0c8d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -919,7 +919,6 @@ static void ext4_i_callback(struct rcu_head *head)
static void ext4_destroy_inode(struct inode *inode)
{
- ext4_ioend_wait(inode);
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
ext4_msg(inode->i_sb, KERN_ERR,
"Inode %lu (%p): orphan list check failed!",
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 4ad6473..5efbd5d 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -1231,7 +1231,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
struct super_block *sb = dir->i_sb;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */
- struct msdos_dir_entry *de;
+ struct msdos_dir_entry *uninitialized_var(de);
int err, free_slots, i, nr_bhs;
loff_t pos, i_pos;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 5942fec..1726d73 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1188,9 +1188,9 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
out:
/* UTF-8 doesn't provide FAT semantics */
if (!strcmp(opts->iocharset, "utf8")) {
- fat_msg(sb, KERN_ERR, "utf8 is not a recommended IO charset"
+ fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset"
" for FAT filesystems, filesystem will be "
- "case sensitive!\n");
+ "case sensitive!");
}
/* If user doesn't specify allow_utime, it's initialized from dmask. */
@@ -1367,6 +1367,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
sbi->free_clusters = -1; /* Don't know yet */
sbi->free_clus_valid = 0;
sbi->prev_free = FAT_START_ENT;
+ sb->s_maxbytes = 0xffffffff;
if (!sbi->fat_length && b->fat32_length) {
struct fat_boot_fsinfo *fsinfo;
@@ -1377,8 +1378,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
sbi->fat_length = le32_to_cpu(b->fat32_length);
sbi->root_cluster = le32_to_cpu(b->root_cluster);
- sb->s_maxbytes = 0xffffffff;
-
/* MC - if info_sector is 0, don't multiply by 0 */
sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
if (sbi->fsinfo_sector == 0)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 640fc22..168a80f 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1358,6 +1358,10 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
if (outarg.namelen > FUSE_NAME_MAX)
goto err;
+ err = -EINVAL;
+ if (size != sizeof(outarg) + outarg.namelen + 1)
+ goto err;
+
name.name = buf;
name.len = outarg.namelen;
err = fuse_copy_one(cs, buf, outarg.namelen + 1);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index d480d9a..594f07a 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -14,6 +14,7 @@
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/compat.h>
+#include <linux/swap.h>
static const struct file_operations fuse_direct_io_file_operations;
@@ -245,6 +246,12 @@ void fuse_release_common(struct file *file, int opcode)
req = ff->reserved_req;
fuse_prepare_release(ff, file->f_flags, opcode);
+ if (ff->flock) {
+ struct fuse_release_in *inarg = &req->misc.release.in;
+ inarg->release_flags |= FUSE_RELEASE_FLOCK_UNLOCK;
+ inarg->lock_owner = fuse_lock_owner_id(ff->fc,
+ (fl_owner_t) file);
+ }
/* Hold vfsmount and dentry until release is finished */
path_get(&file->f_path);
req->misc.release.path = file->f_path;
@@ -755,18 +762,6 @@ static size_t fuse_send_write(struct fuse_req *req, struct file *file,
return req->misc.write.out.size;
}
-static int fuse_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
-{
- pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-
- *pagep = grab_cache_page_write_begin(mapping, index, flags);
- if (!*pagep)
- return -ENOMEM;
- return 0;
-}
-
void fuse_write_update_size(struct inode *inode, loff_t pos)
{
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -779,62 +774,6 @@ void fuse_write_update_size(struct inode *inode, loff_t pos)
spin_unlock(&fc->lock);
}
-static int fuse_buffered_write(struct file *file, struct inode *inode,
- loff_t pos, unsigned count, struct page *page)
-{
- int err;
- size_t nres;
- struct fuse_conn *fc = get_fuse_conn(inode);
- unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
- struct fuse_req *req;
-
- if (is_bad_inode(inode))
- return -EIO;
-
- /*
- * Make sure writepages on the same page are not mixed up with
- * plain writes.
- */
- fuse_wait_on_page_writeback(inode, page->index);
-
- req = fuse_get_req(fc);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->in.argpages = 1;
- req->num_pages = 1;
- req->pages[0] = page;
- req->page_offset = offset;
- nres = fuse_send_write(req, file, pos, count, NULL);
- err = req->out.h.error;
- fuse_put_request(fc, req);
- if (!err && !nres)
- err = -EIO;
- if (!err) {
- pos += nres;
- fuse_write_update_size(inode, pos);
- if (count == PAGE_CACHE_SIZE)
- SetPageUptodate(page);
- }
- fuse_invalidate_attr(inode);
- return err ? err : nres;
-}
-
-static int fuse_write_end(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
-{
- struct inode *inode = mapping->host;
- int res = 0;
-
- if (copied)
- res = fuse_buffered_write(file, inode, pos, copied, page);
-
- unlock_page(page);
- page_cache_release(page);
- return res;
-}
-
static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file,
struct inode *inode, loff_t pos,
size_t count)
@@ -908,6 +847,8 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
pagefault_enable();
flush_dcache_page(page);
+ mark_page_accessed(page);
+
if (!tmp) {
unlock_page(page);
page_cache_release(page);
@@ -1559,11 +1500,14 @@ static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl)
struct fuse_conn *fc = get_fuse_conn(inode);
int err;
- if (fc->no_lock) {
+ if (fc->no_flock) {
err = flock_lock_file_wait(file, fl);
} else {
+ struct fuse_file *ff = file->private_data;
+
/* emulate flock with POSIX locks */
fl->fl_owner = (fl_owner_t) file;
+ ff->flock = true;
err = fuse_setlk(file, fl, 1);
}
@@ -2201,8 +2145,6 @@ static const struct address_space_operations fuse_file_aops = {
.readpage = fuse_readpage,
.writepage = fuse_writepage,
.launder_page = fuse_launder_page,
- .write_begin = fuse_write_begin,
- .write_end = fuse_write_end,
.readpages = fuse_readpages,
.set_page_dirty = __set_page_dirty_nobuffers,
.bmap = fuse_bmap,
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index c6aa2d4..cf6db0a 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -135,6 +135,9 @@ struct fuse_file {
/** Wait queue head for poll */
wait_queue_head_t poll_wait;
+
+ /** Has flock been performed on this file? */
+ bool flock:1;
};
/** One input argument of a request */
@@ -448,7 +451,7 @@ struct fuse_conn {
/** Is removexattr not implemented by fs? */
unsigned no_removexattr:1;
- /** Are file locking primitives not implemented by fs? */
+ /** Are posix file locking primitives not implemented by fs? */
unsigned no_lock:1;
/** Is access not implemented by fs? */
@@ -472,6 +475,9 @@ struct fuse_conn {
/** Don't apply umask to creation modes */
unsigned dont_mask:1;
+ /** Are BSD file locking primitives not implemented by fs? */
+ unsigned no_flock:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 38f84cd..12b5029 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -71,7 +71,7 @@ struct fuse_mount_data {
unsigned blksize;
};
-struct fuse_forget_link *fuse_alloc_forget()
+struct fuse_forget_link *fuse_alloc_forget(void)
{
return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL);
}
@@ -809,6 +809,10 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
fc->async_read = 1;
if (!(arg->flags & FUSE_POSIX_LOCKS))
fc->no_lock = 1;
+ if (arg->minor >= 17) {
+ if (!(arg->flags & FUSE_FLOCK_LOCKS))
+ fc->no_flock = 1;
+ }
if (arg->flags & FUSE_ATOMIC_O_TRUNC)
fc->atomic_o_trunc = 1;
if (arg->minor >= 9) {
@@ -823,6 +827,7 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
} else {
ra_pages = fc->max_read / PAGE_CACHE_SIZE;
fc->no_lock = 1;
+ fc->no_flock = 1;
}
fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
@@ -843,7 +848,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
arg->minor = FUSE_KERNEL_MINOR_VERSION;
arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
- FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK;
+ FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
+ FUSE_FLOCK_LOCKS;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 87b6e04..ec88953 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -491,6 +491,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
inode->i_op = &page_symlink_inode_operations;
break;
}
+ lockdep_annotate_inode_mutex_key(inode);
}
return inode;
}
diff --git a/fs/inode.c b/fs/inode.c
index 73920d5..ec79246 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -848,16 +848,9 @@ struct inode *new_inode(struct super_block *sb)
}
EXPORT_SYMBOL(new_inode);
-/**
- * unlock_new_inode - clear the I_NEW state and wake up any waiters
- * @inode: new inode to unlock
- *
- * Called when the inode is fully initialised to clear the new state of the
- * inode and wake up anyone waiting for the inode to finish initialisation.
- */
-void unlock_new_inode(struct inode *inode)
-{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void lockdep_annotate_inode_mutex_key(struct inode *inode)
+{
if (S_ISDIR(inode->i_mode)) {
struct file_system_type *type = inode->i_sb->s_type;
@@ -873,7 +866,20 @@ void unlock_new_inode(struct inode *inode)
&type->i_mutex_dir_key);
}
}
+}
+EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key);
#endif
+
+/**
+ * unlock_new_inode - clear the I_NEW state and wake up any waiters
+ * @inode: new inode to unlock
+ *
+ * Called when the inode is fully initialised to clear the new state of the
+ * inode and wake up anyone waiting for the inode to finish initialisation.
+ */
+void unlock_new_inode(struct inode *inode)
+{
+ lockdep_annotate_inode_mutex_key(inode);
spin_lock(&inode->i_lock);
WARN_ON(!(inode->i_state & I_NEW));
inode->i_state &= ~I_NEW;
diff --git a/fs/jfs/jfs_umount.c b/fs/jfs/jfs_umount.c
index adcf92d..7971f37 100644
--- a/fs/jfs/jfs_umount.c
+++ b/fs/jfs/jfs_umount.c
@@ -68,7 +68,7 @@ int jfs_umount(struct super_block *sb)
/*
* Wait for outstanding transactions to be written to log:
*/
- jfs_flush_journal(log, 1);
+ jfs_flush_journal(log, 2);
/*
* close fileset inode allocation map (aka fileset inode)
@@ -146,7 +146,7 @@ int jfs_umount_rw(struct super_block *sb)
*
* remove file system from log active file system list.
*/
- jfs_flush_journal(log, 1);
+ jfs_flush_journal(log, 2);
/*
* Make sure all metadata makes it to disk
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index be02077..dbcd821 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -79,12 +79,9 @@ config NFS_V4_1
depends on NFS_FS && NFS_V4 && EXPERIMENTAL
select SUNRPC_BACKCHANNEL
select PNFS_FILE_LAYOUT
- select PNFS_BLOCK
- select MD
- select BLK_DEV_DM
help
This option enables support for minor version 1 of the NFSv4 protocol
- (RFC 5661 and RFC 5663) in the kernel's NFS client.
+ (RFC 5661) in the kernel's NFS client.
If unsure, say N.
@@ -93,16 +90,13 @@ config PNFS_FILE_LAYOUT
config PNFS_BLOCK
tristate
+ depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM
+ default m
config PNFS_OBJLAYOUT
- tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
+ tristate
depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
- help
- Say M here if you want your pNFS client to support the Objects Layout Driver.
- Requires the SCSI osd initiator library (SCSI_OSD_INITIATOR) and
- upper level driver (SCSI_OSD_ULD).
-
- If unsure, say N.
+ default m
config ROOT_NFS
bool "Root file system on NFS"
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index e56564d..9561c8f 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -36,6 +36,7 @@
#include <linux/namei.h>
#include <linux/bio.h> /* struct bio */
#include <linux/buffer_head.h> /* various write calls */
+#include <linux/prefetch.h>
#include "blocklayout.h"
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index b257383..07df5f1 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -38,6 +38,7 @@ enum nfs4_callback_opnum {
struct cb_process_state {
__be32 drc_status;
struct nfs_client *clp;
+ int slotid;
};
struct cb_compound_hdr_arg {
@@ -166,7 +167,6 @@ extern unsigned nfs4_callback_layoutrecall(
void *dummy, struct cb_process_state *cps);
extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
-extern void nfs4_cb_take_slot(struct nfs_client *clp);
struct cb_devicenotifyitem {
uint32_t cbd_notify_type;
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 74780f9..43926ad 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -348,7 +348,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
/* Normal */
if (likely(args->csa_sequenceid == slot->seq_nr + 1)) {
slot->seq_nr++;
- return htonl(NFS4_OK);
+ goto out_ok;
}
/* Replay */
@@ -367,11 +367,14 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args)
/* Wraparound */
if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) {
slot->seq_nr = 1;
- return htonl(NFS4_OK);
+ goto out_ok;
}
/* Misordered request */
return htonl(NFS4ERR_SEQ_MISORDERED);
+out_ok:
+ tbl->highest_used_slotid = args->csa_slotid;
+ return htonl(NFS4_OK);
}
/*
@@ -433,26 +436,37 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
struct cb_sequenceres *res,
struct cb_process_state *cps)
{
+ struct nfs4_slot_table *tbl;
struct nfs_client *clp;
int i;
__be32 status = htonl(NFS4ERR_BADSESSION);
- cps->clp = NULL;
-
clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
if (clp == NULL)
goto out;
+ tbl = &clp->cl_session->bc_slot_table;
+
+ spin_lock(&tbl->slot_tbl_lock);
/* state manager is resetting the session */
if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) {
- status = NFS4ERR_DELAY;
+ spin_unlock(&tbl->slot_tbl_lock);
+ status = htonl(NFS4ERR_DELAY);
+ /* Return NFS4ERR_BADSESSION if we're draining the session
+ * in order to reset it.
+ */
+ if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
+ status = htonl(NFS4ERR_BADSESSION);
goto out;
}
status = validate_seqid(&clp->cl_session->bc_slot_table, args);
+ spin_unlock(&tbl->slot_tbl_lock);
if (status)
goto out;
+ cps->slotid = args->csa_slotid;
+
/*
* Check for pending referring calls. If a match is found, a
* related callback was received before the response to the original
@@ -469,7 +483,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
res->csr_slotid = args->csa_slotid;
res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
- nfs4_cb_take_slot(clp);
out:
cps->clp = clp; /* put in nfs4_callback_compound */
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index c6c86a7..918ad64 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -754,26 +754,15 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
* Let the state manager know callback processing done.
* A single slot, so highest used slotid is either 0 or -1
*/
- tbl->highest_used_slotid--;
+ tbl->highest_used_slotid = -1;
nfs4_check_drain_bc_complete(session);
spin_unlock(&tbl->slot_tbl_lock);
}
-static void nfs4_cb_free_slot(struct nfs_client *clp)
+static void nfs4_cb_free_slot(struct cb_process_state *cps)
{
- if (clp && clp->cl_session)
- nfs4_callback_free_slot(clp->cl_session);
-}
-
-/* A single slot, so highest used slotid is either 0 or -1 */
-void nfs4_cb_take_slot(struct nfs_client *clp)
-{
- struct nfs4_slot_table *tbl = &clp->cl_session->bc_slot_table;
-
- spin_lock(&tbl->slot_tbl_lock);
- tbl->highest_used_slotid++;
- BUG_ON(tbl->highest_used_slotid != 0);
- spin_unlock(&tbl->slot_tbl_lock);
+ if (cps->slotid != -1)
+ nfs4_callback_free_slot(cps->clp->cl_session);
}
#else /* CONFIG_NFS_V4_1 */
@@ -784,7 +773,7 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
}
-static void nfs4_cb_free_slot(struct nfs_client *clp)
+static void nfs4_cb_free_slot(struct cb_process_state *cps)
{
}
#endif /* CONFIG_NFS_V4_1 */
@@ -866,6 +855,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
struct cb_process_state cps = {
.drc_status = 0,
.clp = NULL,
+ .slotid = -1,
};
unsigned int nops = 0;
@@ -906,7 +896,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
*hdr_res.status = status;
*hdr_res.nops = htonl(nops);
- nfs4_cb_free_slot(cps.clp);
+ nfs4_cb_free_slot(&cps);
nfs_put_client(cps.clp);
dprintk("%s: done, status = %u\n", __func__, ntohl(status));
return rpc_success;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 9383ca7..d0cda12 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -479,7 +479,6 @@ static int _io_check(struct objio_state *ios, bool is_write)
for (i = 0; i < ios->numdevs; i++) {
struct osd_sense_info osi;
struct osd_request *or = ios->per_dev[i].or;
- unsigned dev;
int ret;
if (!or)
@@ -500,9 +499,8 @@ static int _io_check(struct objio_state *ios, bool is_write)
continue; /* we recovered */
}
- dev = ios->per_dev[i].dev;
- objlayout_io_set_result(&ios->ol_state, dev,
- &ios->layout->comps[dev].oc_object_id,
+ objlayout_io_set_result(&ios->ol_state, i,
+ &ios->layout->comps[i].oc_object_id,
osd_pri_2_pnfs_err(osi.osd_err_pri),
ios->per_dev[i].offset,
ios->per_dev[i].length,
@@ -589,22 +587,19 @@ static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
}
static int _add_stripe_unit(struct objio_state *ios, unsigned *cur_pg,
- unsigned pgbase, struct _objio_per_comp *per_dev, int cur_len,
+ unsigned pgbase, struct _objio_per_comp *per_dev, int len,
gfp_t gfp_flags)
{
unsigned pg = *cur_pg;
+ int cur_len = len;
struct request_queue *q =
osd_request_queue(_io_od(ios, per_dev->dev));
- per_dev->length += cur_len;
-
if (per_dev->bio == NULL) {
- unsigned stripes = ios->layout->num_comps /
- ios->layout->mirrors_p1;
- unsigned pages_in_stripe = stripes *
+ unsigned pages_in_stripe = ios->layout->group_width *
(ios->layout->stripe_unit / PAGE_SIZE);
unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
- stripes;
+ ios->layout->group_width;
if (BIO_MAX_PAGES_KMALLOC < bio_size)
bio_size = BIO_MAX_PAGES_KMALLOC;
@@ -632,6 +627,7 @@ static int _add_stripe_unit(struct objio_state *ios, unsigned *cur_pg,
}
BUG_ON(cur_len);
+ per_dev->length += len;
*cur_pg = pg;
return 0;
}
@@ -650,7 +646,7 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
int ret = 0;
while (length) {
- struct _objio_per_comp *per_dev = &ios->per_dev[dev];
+ struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev];
unsigned cur_len, page_off = 0;
if (!per_dev->length) {
@@ -670,8 +666,8 @@ static int _prepare_one_group(struct objio_state *ios, u64 length,
cur_len = stripe_unit;
}
- if (max_comp < dev)
- max_comp = dev;
+ if (max_comp < dev - first_dev)
+ max_comp = dev - first_dev;
} else {
cur_len = stripe_unit;
}
@@ -806,7 +802,7 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
unsigned dev = per_dev->dev;
struct pnfs_osd_object_cred *cred =
- &ios->layout->comps[dev];
+ &ios->layout->comps[cur_comp];
struct osd_obj_id obj = {
.partition = cred->oc_object_id.oid_partition_id,
.id = cred->oc_object_id.oid_object_id,
@@ -904,7 +900,7 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
for (; cur_comp < last_comp; ++cur_comp, ++dev) {
struct osd_request *or = NULL;
struct pnfs_osd_object_cred *cred =
- &ios->layout->comps[dev];
+ &ios->layout->comps[cur_comp];
struct osd_obj_id obj = {
.partition = cred->oc_object_id.oid_partition_id,
.id = cred->oc_object_id.oid_object_id,
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
index 16fc758..b3918f7 100644
--- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
+++ b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
@@ -170,6 +170,9 @@ int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
p = _osd_xdr_decode_data_map(p, &layout->olo_map);
layout->olo_comps_index = be32_to_cpup(p++);
layout->olo_num_comps = be32_to_cpup(p++);
+ dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
+ layout->olo_comps_index, layout->olo_num_comps);
+
iter->total_comps = layout->olo_num_comps;
return 0;
}