aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/autofs_i.h12
-rw-r--r--fs/autofs4/dev-ioctl.c3
-rw-r--r--fs/autofs4/inode.c4
-rw-r--r--fs/autofs4/waitq.c22
-rw-r--r--fs/btrfs/backref.c27
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/disk-io.c22
-rw-r--r--fs/btrfs/extent-tree.c15
-rw-r--r--fs/btrfs/extent_io.c56
-rw-r--r--fs/btrfs/extent_io.h4
-rw-r--r--fs/btrfs/file.c9
-rw-r--r--fs/btrfs/inode.c54
-rw-r--r--fs/btrfs/ioctl.c5
-rw-r--r--fs/btrfs/reada.c48
-rw-r--r--fs/btrfs/relocation.c4
-rw-r--r--fs/btrfs/scrub.c15
-rw-r--r--fs/btrfs/super.c7
-rw-r--r--fs/btrfs/transaction.c6
-rw-r--r--fs/btrfs/volumes.c13
-rw-r--r--fs/buffer.c1
-rw-r--r--fs/cifs/cifsfs.c12
-rw-r--r--fs/cifs/connect.c12
-rw-r--r--fs/cifs/file.c3
-rw-r--r--fs/dlm/lock.c12
-rw-r--r--fs/eventpoll.c4
-rw-r--r--fs/ext4/super.c2
-rw-r--r--fs/gfs2/lock_dlm.c10
-rw-r--r--fs/hugetlbfs/inode.c1
-rw-r--r--fs/jbd2/commit.c4
-rw-r--r--fs/nfs/blocklayout/blocklayout.c4
-rw-r--r--fs/nfs/client.c5
-rw-r--r--fs/nfs/dir.c4
-rw-r--r--fs/nfs/idmap.c4
-rw-r--r--fs/nfs/internal.h8
-rw-r--r--fs/nfs/namespace.c93
-rw-r--r--fs/nfs/nfs4_fs.h11
-rw-r--r--fs/nfs/nfs4filelayoutdev.c2
-rw-r--r--fs/nfs/nfs4namespace.c86
-rw-r--r--fs/nfs/nfs4proc.c186
-rw-r--r--fs/nfs/nfs4state.c31
-rw-r--r--fs/nfs/nfs4xdr.c53
-rw-r--r--fs/nfs/objlayout/objlayout.c2
-rw-r--r--fs/nfs/pnfs.c2
-rw-r--r--fs/nfs/read.c2
-rw-r--r--fs/nfs/super.c12
-rw-r--r--fs/nfs/write.c5
-rw-r--r--fs/nfsd/nfs4recover.c2
-rw-r--r--fs/pipe.c31
-rw-r--r--fs/proc/task_mmu.c3
49 files changed, 577 insertions, 358 deletions
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index eb1cc92cd67..908e1845541 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -110,7 +110,6 @@ struct autofs_sb_info {
int sub_version;
int min_proto;
int max_proto;
- int compat_daemon;
unsigned long exp_timeout;
unsigned int type;
int reghost_enabled;
@@ -270,6 +269,17 @@ int autofs4_fill_super(struct super_block *, void *, int);
struct autofs_info *autofs4_new_ino(struct autofs_sb_info *);
void autofs4_clean_ino(struct autofs_info *);
+static inline int autofs_prepare_pipe(struct file *pipe)
+{
+ if (!pipe->f_op || !pipe->f_op->write)
+ return -EINVAL;
+ if (!S_ISFIFO(pipe->f_dentry->d_inode->i_mode))
+ return -EINVAL;
+ /* We want a packet pipe */
+ pipe->f_flags |= O_DIRECT;
+ return 0;
+}
+
/* Queue management functions */
int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify);
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 9dacb858670..aa9103f8f01 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -376,7 +376,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
err = -EBADF;
goto out;
}
- if (!pipe->f_op || !pipe->f_op->write) {
+ if (autofs_prepare_pipe(pipe) < 0) {
err = -EPIPE;
fput(pipe);
goto out;
@@ -385,7 +385,6 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
sbi->pipefd = pipefd;
sbi->pipe = pipe;
sbi->catatonic = 0;
- sbi->compat_daemon = is_compat_task();
}
out:
mutex_unlock(&sbi->wq_mutex);
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index d8dc002e9cc..6e488ebe778 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -19,7 +19,6 @@
#include <linux/parser.h>
#include <linux/bitops.h>
#include <linux/magic.h>
-#include <linux/compat.h>
#include "autofs_i.h"
#include <linux/module.h>
@@ -225,7 +224,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
set_autofs_type_indirect(&sbi->type);
sbi->min_proto = 0;
sbi->max_proto = 0;
- sbi->compat_daemon = is_compat_task();
mutex_init(&sbi->wq_mutex);
mutex_init(&sbi->pipe_mutex);
spin_lock_init(&sbi->fs_lock);
@@ -292,7 +290,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
printk("autofs: could not open pipe file descriptor\n");
goto fail_dput;
}
- if (!pipe->f_op || !pipe->f_op->write)
+ if (autofs_prepare_pipe(pipe) < 0)
goto fail_fput;
sbi->pipe = pipe;
sbi->pipefd = pipefd;
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 9c098db4334..da8876d38a7 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -91,24 +91,7 @@ static int autofs4_write(struct autofs_sb_info *sbi,
return (bytes > 0);
}
-
-/*
- * The autofs_v5 packet was misdesigned.
- *
- * The packets are identical on x86-32 and x86-64, but have different
- * alignment. Which means that 'sizeof()' will give different results.
- * Fix it up for the case of running 32-bit user mode on a 64-bit kernel.
- */
-static noinline size_t autofs_v5_packet_size(struct autofs_sb_info *sbi)
-{
- size_t pktsz = sizeof(struct autofs_v5_packet);
-#if defined(CONFIG_X86_64) && defined(CONFIG_COMPAT)
- if (sbi->compat_daemon > 0)
- pktsz -= 4;
-#endif
- return pktsz;
-}
-
+
static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
struct autofs_wait_queue *wq,
int type)
@@ -172,7 +155,8 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
{
struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet;
- pktsz = autofs_v5_packet_size(sbi);
+ pktsz = sizeof(*packet);
+
packet->wait_queue_token = wq->wait_queue_token;
packet->len = wq->name.len;
memcpy(packet->name, wq->name.name, wq->name.len);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index f4e90748940..bcec0675023 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -22,6 +22,7 @@
#include "ulist.h"
#include "transaction.h"
#include "delayed-ref.h"
+#include "locking.h"
/*
* this structure records all encountered refs on the way up to the root
@@ -893,18 +894,22 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
s64 bytes_left = size - 1;
struct extent_buffer *eb = eb_in;
struct btrfs_key found_key;
+ int leave_spinning = path->leave_spinning;
if (bytes_left >= 0)
dest[bytes_left] = '\0';
+ path->leave_spinning = 1;
while (1) {
len = btrfs_inode_ref_name_len(eb, iref);
bytes_left -= len;
if (bytes_left >= 0)
read_extent_buffer(eb, dest + bytes_left,
(unsigned long)(iref + 1), len);
- if (eb != eb_in)
+ if (eb != eb_in) {
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
+ }
ret = inode_ref_info(parent, 0, fs_root, path, &found_key);
if (ret > 0)
ret = -ENOENT;
@@ -919,8 +924,11 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
slot = path->slots[0];
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
- if (eb != eb_in)
+ if (eb != eb_in) {
atomic_inc(&eb->refs);
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ }
btrfs_release_path(path);
iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
@@ -931,6 +939,7 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
}
btrfs_release_path(path);
+ path->leave_spinning = leave_spinning;
if (ret)
return ERR_PTR(ret);
@@ -1247,7 +1256,7 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
struct btrfs_path *path,
iterate_irefs_t *iterate, void *ctx)
{
- int ret;
+ int ret = 0;
int slot;
u32 cur;
u32 len;
@@ -1259,7 +1268,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
struct btrfs_inode_ref *iref;
struct btrfs_key found_key;
- while (1) {
+ while (!ret) {
+ path->leave_spinning = 1;
ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path,
&found_key);
if (ret < 0)
@@ -1275,6 +1285,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
atomic_inc(&eb->refs);
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
btrfs_release_path(path);
item = btrfs_item_nr(eb, slot);
@@ -1288,13 +1300,12 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
(unsigned long long)found_key.objectid,
(unsigned long long)fs_root->objectid);
ret = iterate(parent, iref, eb, ctx);
- if (ret) {
- free_extent_buffer(eb);
+ if (ret)
break;
- }
len = sizeof(*iref) + name_len;
iref = (struct btrfs_inode_ref *)((char *)iref + len);
}
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
}
@@ -1414,6 +1425,8 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
void free_ipath(struct inode_fs_paths *ipath)
{
+ if (!ipath)
+ return;
kfree(ipath->fspath);
kfree(ipath);
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 3f65a812e28..8fd72331d60 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1078,7 +1078,7 @@ struct btrfs_fs_info {
* is required instead of the faster short fsync log commits
*/
u64 last_trans_log_full_commit;
- unsigned long mount_opt:21;
+ unsigned long mount_opt;
unsigned long compress_type:4;
u64 max_inline;
u64 alloc_start;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 20196f41120..d0c969beaad 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -383,17 +383,16 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
break;
- if (!failed_mirror) {
- failed = 1;
- printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror);
- failed_mirror = eb->failed_mirror;
- }
-
num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
eb->start, eb->len);
if (num_copies == 1)
break;
+ if (!failed_mirror) {
+ failed = 1;
+ failed_mirror = eb->read_mirror;
+ }
+
mirror_num++;
if (mirror_num == failed_mirror)
mirror_num++;
@@ -564,7 +563,7 @@ struct extent_buffer *find_eb_for_page(struct extent_io_tree *tree,
}
static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state)
+ struct extent_state *state, int mirror)
{
struct extent_io_tree *tree;
u64 found_start;
@@ -589,6 +588,7 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
if (!reads_done)
goto err;
+ eb->read_mirror = mirror;
if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
ret = -EIO;
goto err;
@@ -652,7 +652,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
eb = (struct extent_buffer *)page->private;
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
- eb->failed_mirror = failed_mirror;
+ eb->read_mirror = failed_mirror;
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
btree_readahead_hook(root, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
@@ -2254,9 +2254,9 @@ int open_ctree(struct super_block *sb,
goto fail_sb_buffer;
}
- if (sectorsize < PAGE_SIZE) {
- printk(KERN_WARNING "btrfs: Incompatible sector size "
- "found on %s\n", sb->s_id);
+ if (sectorsize != PAGE_SIZE) {
+ printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+ "found on %s\n", (unsigned long)sectorsize, sb->s_id);
goto fail_sb_buffer;
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2b35f8d14bb..6fc2e6f5aab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2301,6 +2301,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
if (ret) {
printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret);
+ spin_lock(&delayed_refs->lock);
return ret;
}
@@ -2331,6 +2332,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
if (ret) {
printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret);
+ spin_lock(&delayed_refs->lock);
return ret;
}
@@ -3769,13 +3771,10 @@ again:
*/
if (current->journal_info)
return -EAGAIN;
- ret = wait_event_interruptible(space_info->wait,
- !space_info->flush);
- /* Must have been interrupted, return */
- if (ret) {
- printk(KERN_DEBUG "btrfs: %s returning -EINTR\n", __func__);
+ ret = wait_event_killable(space_info->wait, !space_info->flush);
+ /* Must have been killed, return */
+ if (ret)
return -EINTR;
- }
spin_lock(&space_info->lock);
}
@@ -4215,8 +4214,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
num_bytes = calc_global_metadata_size(fs_info);
- spin_lock(&block_rsv->lock);
spin_lock(&sinfo->lock);
+ spin_lock(&block_rsv->lock);
block_rsv->size = num_bytes;
@@ -4242,8 +4241,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
block_rsv->full = 1;
}
- spin_unlock(&sinfo->lock);
spin_unlock(&block_rsv->lock);
+ spin_unlock(&sinfo->lock);
}
static void init_global_block_rsv(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cd4b5e40022..198c2ba2fa4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -402,20 +402,28 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
return 0;
}
+static struct extent_state *next_state(struct extent_state *state)
+{
+ struct rb_node *next = rb_next(&state->rb_node);
+ if (next)
+ return rb_entry(next, struct extent_state, rb_node);
+ else
+ return NULL;
+}
+
/*
* utility function to clear some bits in an extent state struct.
- * it will optionally wake up any one waiting on this state (wake == 1), or
- * forcibly remove the state from the tree (delete == 1).
+ * it will optionally wake up any one waiting on this state (wake == 1)
*
* If no bits are set on the state struct after clearing things, the
* struct is freed and removed from the tree
*/
-static int clear_state_bit(struct extent_io_tree *tree,
- struct extent_state *state,
- int *bits, int wake)
+static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
+ struct extent_state *state,
+ int *bits, int wake)
{
+ struct extent_state *next;
int bits_to_clear = *bits & ~EXTENT_CTLBITS;
- int ret = state->state & bits_to_clear;
if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) {
u64 range = state->end - state->start + 1;
@@ -427,6 +435,7 @@ static int clear_state_bit(struct extent_io_tree *tree,
if (wake)
wake_up(&state->wq);
if (state->state == 0) {
+ next = next_state(state);
if (state->tree) {
rb_erase(&state->rb_node, &tree->state);
state->tree = NULL;
@@ -436,8 +445,9 @@ static int clear_state_bit(struct extent_io_tree *tree,
}
} else {
merge_state(tree, state);
+ next = next_state(state);
}
- return ret;
+ return next;
}
static struct extent_state *
@@ -476,7 +486,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state *state;
struct extent_state *cached;
struct extent_state *prealloc = NULL;
- struct rb_node *next_node;
struct rb_node *node;
u64 last_end;
int err;
@@ -528,14 +537,11 @@ hit_next:
WARN_ON(state->end < start);
last_end = state->end;
- if (state->end < end && !need_resched())
- next_node = rb_next(&state->rb_node);
- else
- next_node = NULL;
-
/* the state doesn't have the wanted bits, go ahead */
- if (!(state->state & bits))
+ if (!(state->state & bits)) {
+ state = next_state(state);
goto next;
+ }
/*
* | ---- desired range ---- |
@@ -593,16 +599,13 @@ hit_next:
goto out;
}
- clear_state_bit(tree, state, &bits, wake);
+ state = clear_state_bit(tree, state, &bits, wake);
next:
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
- if (start <= end && next_node) {
- state = rb_entry(next_node, struct extent_state,
- rb_node);
+ if (start <= end && state && !need_resched())
goto hit_next;
- }
goto search_again;
out:
@@ -2301,7 +2304,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
u64 start;
u64 end;
int whole_page;
- int failed_mirror;
+ int mirror;
int ret;
if (err)
@@ -2340,20 +2343,18 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
}
spin_unlock(&tree->lock);
+ mirror = (int)(unsigned long)bio->bi_bdev;
if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
ret = tree->ops->readpage_end_io_hook(page, start, end,
- state);
+ state, mirror);
if (ret)
uptodate = 0;
else
clean_io_failure(start, page);
}
- if (!uptodate)
- failed_mirror = (int)(unsigned long)bio->bi_bdev;
-
if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) {
- ret = tree->ops->readpage_io_failed_hook(page, failed_mirror);
+ ret = tree->ops->readpage_io_failed_hook(page, mirror);
if (!ret && !err &&
test_bit(BIO_UPTODATE, &bio->bi_flags))
uptodate = 1;
@@ -2368,8 +2369,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
* can't handle the error it will return -EIO and we
* remain responsible for that page.
*/
- ret = bio_readpage_error(bio, page, start, end,
- failed_mirror, NULL);
+ ret = bio_readpage_error(bio, page, start, end, mirror, NULL);
if (ret == 0) {
uptodate =
test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -4462,7 +4462,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
}
clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
- eb->failed_mirror = 0;
+ eb->read_mirror = 0;
atomic_set(&eb->io_pages, num_reads);
for (i = start_i; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index faf10eb57f7..b516c3b8dec 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -79,7 +79,7 @@ struct extent_io_ops {
u64 start, u64 end,
struct extent_state *state);
int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end,
- struct extent_state *state);
+ struct extent_state *state, int mirror);
int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
struct extent_state *state, int uptodate);
void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
@@ -135,7 +135,7 @@ struct extent_buffer {
spinlock_t refs_lock;
atomic_t refs;
atomic_t io_pages;
- int failed_mirror;
+ int read_mirror;
struct list_head leak_list;
struct rcu_head rcu_head;
pid_t lock_owner;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d83260d7498..53bf2d764bb 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -567,6 +567,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
int extent_type;
int recow;
int ret;
+ int modify_tree = -1;
if (drop_cache)
btrfs_drop_extent_cache(inode, start, end - 1, 0);
@@ -575,10 +576,13 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
if (!path)
return -ENOMEM;
+ if (start >= BTRFS_I(inode)->disk_i_size)
+ modify_tree = 0;
+
while (1) {
recow = 0;
ret = btrfs_lookup_file_extent(trans, root, path, ino,
- search_start, -1);
+ search_start, modify_tree);
if (ret < 0)
break;
if (ret > 0 && path->slots[0] > 0 && search_start == start) {
@@ -634,7 +638,8 @@ next_slot:
}
search_start = max(key.offset, start);
- if (recow) {
+ if (recow || !modify_tree) {
+ modify_tree = -1;
btrfs_release_path(path);
continue;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 115bc05e42b..61b16c641ce 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1947,7 +1947,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
* extent_io.c will try to find good copies for us.
*/
static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state)
+ struct extent_state *state, int mirror)
{
size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT);
struct inode *inode = page->mapping->host;
@@ -4069,7 +4069,7 @@ static struct inode *new_simple_dir(struct super_block *s,
BTRFS_I(inode)->dummy_inode = 1;
inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
- inode->i_op = &simple_dir_inode_operations;
+ inode->i_op = &btrfs_dir_ro_inode_operations;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
@@ -4140,14 +4140,18 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
static int btrfs_dentry_delete(const struct dentry *dentry)
{
struct btrfs_root *root;
+ struct inode *inode = dentry->d_inode;
- if (!dentry->d_inode && !IS_ROOT(dentry))
- dentry = dentry->d_parent;
+ if (!inode && !IS_ROOT(dentry))
+ inode = dentry->d_parent->d_inode;
- if (dentry->d_inode) {
- root = BTRFS_I(dentry->d_inode)->root;
+ if (inode) {
+ root = BTRFS_I(inode)->root;
if (btrfs_root_refs(&root->root_item) == 0)
return 1;
+
+ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+ return 1;
}
return 0;
}
@@ -4188,7 +4192,6 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
struct btrfs_path *path;
struct list_head ins_list;
struct list_head del_list;
- struct qstr q;
int ret;
struct extent_buffer *leaf;
int slot;
@@ -4279,7 +4282,6 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
while (di_cur < di_total) {
struct btrfs_key location;
- struct dentry *tmp;
if (verify_dir_item(root, leaf, di))
break;
@@ -4300,35 +4302,15 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
btrfs_dir_item_key_to_cpu(leaf, di, &location);
- q.name = name_ptr;
- q.len = name_len;
- q.hash = full_name_hash(q.name, q.len);
- tmp = d_lookup(filp->f_dentry, &q);
- if (!tmp) {
- struct btrfs_key *newkey;
-
- newkey = kzalloc(sizeof(struct btrfs_key),
- GFP_NOFS);
- if (!newkey)
- goto no_dentry;
- tmp = d_alloc(filp->f_dentry, &q);
- if (!tmp) {
- kfree(newkey);
- dput(tmp);
- goto no_dentry;
- }
- memcpy(newkey, &location,
- sizeof(struct btrfs_key));
- tmp->d_fsdata = newkey;
- tmp->d_flags |= DCACHE_NEED_LOOKUP;
- d_rehash(tmp);
- dput(tmp);
- } else {
- dput(tmp);
- }
-no_dentry:
+
/* is this a reference to our own snapshot? If so
- * skip it
+ * skip it.
+ *
+ * In contrast to old kernels, we insert the snapshot's
+ * dir item and dir index after it has been created, so
+ * we won't find a reference to our own snapshot. We
+ * still keep the following code for backward
+ * compatibility.
*/
if (location.type == BTRFS_ROOT_ITEM_KEY &&
location.objectid == root->root_key.objectid) {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 18cc23d164a..14f8e1faa46 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2262,7 +2262,10 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
di_args->bytes_used = dev->bytes_used;
di_args->total_bytes = dev->total_bytes;
memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
- strncpy(di_args->path, dev->name, sizeof(di_args->path));
+ if (dev->name)
+ strncpy(di_args->path, dev->name, sizeof(di_args->path));
+ else
+ di_args->path[0] = '\0';
out:
if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index dc5d33146fd..ac5d0108588 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -250,14 +250,12 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
struct btrfs_bio *bbio)
{
int ret;
- int looped = 0;
struct reada_zone *zone;
struct btrfs_block_group_cache *cache = NULL;
u64 start;
u64 end;
int i;
-again:
zone = NULL;
spin_lock(&fs_info->reada_lock);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
@@ -274,9 +272,6 @@ again:
spin_unlock(&fs_info->reada_lock);
}
- if (looped)
- return NULL;
-
cache = btrfs_lookup_block_group(fs_info, logical);
if (!cache)
return NULL;
@@ -307,13 +302,15 @@ again:
ret = radix_tree_insert(&dev->reada_zones,
(unsigned long)(zone->end >> PAGE_CACHE_SHIFT),
zone);
- spin_unlock(&fs_info->reada_lock);
- if (ret) {
+ if (ret == -EEXIST) {
kfree(zone);
- looped = 1;
- goto again;
+ ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
+ logical >> PAGE_CACHE_SHIFT, 1);
+ if (ret == 1)
+ kref_get(&zone->refcnt);
}
+ spin_unlock(&fs_info->reada_lock);
return zone;
}
@@ -323,26 +320,26 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
struct btrfs_key *top, int level)
{
int ret;
- int looped = 0;
struct reada_extent *re = NULL;
+ struct reada_extent *re_exist = NULL;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct btrfs_bio *bbio = NULL;
struct btrfs_device *dev;
+ struct btrfs_device *prev_dev;
u32 blocksize;
u64 length;
int nzones = 0;
int i;
unsigned long index = logical >> PAGE_CACHE_SHIFT;
-again:
spin_lock(&fs_info->reada_lock);
re = radix_tree_lookup(&fs_info->reada_tree, index);
if (re)
kref_get(&re->refcnt);
spin_unlock(&fs_info->reada_lock);
- if (re || looped)
+ if (re)
return re;
re = kzalloc(sizeof(*re), GFP_NOFS);
@@ -398,16 +395,31 @@ again:
/* insert extent in reada_tree + all per-device trees, all or nothing */
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&fs_info->reada_tree, index, re);
+ if (ret == -EEXIST) {
+ re_exist = radix_tree_lookup(&fs_info->reada_tree, index);
+ BUG_ON(!re_exist);
+ kref_get(&re_exist->refcnt);
+ spin_unlock(&fs_info->reada_lock);
+ goto error;
+ }
if (ret) {
spin_unlock(&fs_info->reada_lock);
- if (ret != -ENOMEM) {
- /* someone inserted the extent in the meantime */
- looped = 1;
- }
goto error;
}
+ prev_dev = NULL;
for (i = 0; i < nzones; ++i) {
dev = bbio->stripes[i].dev;
+ if (dev == prev_dev) {
+ /*
+ * in case of DUP, just add the first zone. As both
+ * are on the same device, there's nothing to gain
+ * from adding both.
+ * Also, it wouldn't work, as the tree is per device
+ * and adding would fail with EEXIST
+ */
+ continue;
+ }
+ prev_dev = dev;
ret = radix_tree_insert(&dev->reada_extents, index, re);
if (ret) {
while (--i >= 0) {
@@ -450,9 +462,7 @@ error:
}
kfree(bbio);
kfree(re);
- if (looped)
- goto again;
- return NULL;
+ return re_exist;
}
static void reada_kref_dummy(struct kref *kr)
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 017281dbb2a..646ee21bb03 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1279,7 +1279,9 @@ static int __update_reloc_root(struct btrfs_root *root, int del)
if (rb_node)
backref_tree_panic(rb_node, -EEXIST, node->bytenr);
} else {
+ spin_lock(&root->fs_info->trans_lock);
list_del_init(&root->root_list);
+ spin_unlock(&root->fs_info->trans_lock);
kfree(node);
}
return 0;
@@ -3811,7 +3813,7 @@ restart:
ret = btrfs_block_rsv_check(rc->extent_root, rc->block_rsv, 5);
if (ret < 0) {
- if (ret != -EAGAIN) {
+ if (ret != -ENOSPC) {
err = ret;
WARN_ON(1);
break;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index bc015f77f3e..4f76fc3f8e8 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1257,12 +1257,6 @@ static int scrub_checksum_data(struct scrub_block *sblock)
if (memcmp(csum, on_disk_csum, sdev->csum_size))
fail = 1;
- if (fail) {
- spin_lock(&sdev->stat_lock);
- ++sdev->stat.csum_errors;
- spin_unlock(&sdev->stat_lock);
- }
-
return fail;
}
@@ -1335,15 +1329,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size))
++crc_fail;
- if (crc_fail || fail) {
- spin_lock(&sdev->stat_lock);
- if (crc_fail)
- ++sdev->stat.csum_errors;
- if (fail)
- ++sdev->stat.verify_errors;
- spin_unlock(&sdev->stat_lock);
- }
-
return fail || crc_fail;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8d5d380f7bd..c5f8fca4195 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -815,7 +815,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
return 0;
}
- btrfs_start_delalloc_inodes(root, 0);
btrfs_wait_ordered_extents(root, 0, 0);
trans = btrfs_start_transaction(root, 0);
@@ -1148,13 +1147,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
if (ret)
goto restore;
} else {
- if (fs_info->fs_devices->rw_devices == 0)
+ if (fs_info->fs_devices->rw_devices == 0) {
ret = -EACCES;
goto restore;
+ }
- if (btrfs_super_log_root(fs_info->super_copy) != 0)
+ if (btrfs_super_log_root(fs_info->super_copy) != 0) {
ret = -EINVAL;
goto restore;
+ }
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 11b77a59db6..36422254ef6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -73,8 +73,10 @@ loop:
cur_trans = root->fs_info->running_transaction;
if (cur_trans) {
- if (cur_trans->aborted)
+ if (cur_trans->aborted) {
+ spin_unlock(&root->fs_info->trans_lock);
return cur_trans->aborted;
+ }
atomic_inc(&cur_trans->use_count);
atomic_inc(&cur_trans->num_writers);
cur_trans->num_joined++;
@@ -1400,6 +1402,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
ret = commit_fs_roots(trans, root);
if (ret) {
mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->fs_info->reloc_mutex);
goto cleanup_transaction;
}
@@ -1411,6 +1414,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
ret = commit_cowonly_roots(trans, root);
if (ret) {
mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->fs_info->reloc_mutex);
goto cleanup_transaction;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 759d02486d7..1411b99555a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3324,12 +3324,14 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
stripe_size = devices_info[ndevs-1].max_avail;
num_stripes = ndevs * dev_stripes;
- if (stripe_size * num_stripes > max_chunk_size * ncopies) {
+ if (stripe_size * ndevs > max_chunk_size * ncopies) {
stripe_size = max_chunk_size * ncopies;
- do_div(stripe_size, num_stripes);
+ do_div(stripe_size, ndevs);
}
do_div(stripe_size, dev_stripes);
+
+ /* align to BTRFS_STRIPE_LEN */
do_div(stripe_size, BTRFS_STRIPE_LEN);
stripe_size *= BTRFS_STRIPE_LEN;
@@ -3805,10 +3807,11 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
else if (mirror_num)
stripe_index += mirror_num - 1;
else {
+ int old_stripe_index = stripe_index;
stripe_index = find_live_mirror(map, stripe_index,
map->sub_stripes, stripe_index +
current->pid % map->sub_stripes);
- mirror_num = stripe_index + 1;
+ mirror_num = stripe_index - old_stripe_index + 1;
}
} else {
/*
@@ -4350,8 +4353,10 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
ret = __btrfs_open_devices(fs_devices, FMODE_READ,
root->fs_info->bdev_holder);
- if (ret)
+ if (ret) {
+ free_fs_devices(fs_devices);
goto out;
+ }
if (!fs_devices->seeding) {
__btrfs_close_devices(fs_devices);
diff --git a/fs/buffer.c b/fs/buffer.c
index 36d66653b93..351e18ea2e5 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -985,7 +985,6 @@ grow_dev_page(struct block_device *bdev, sector_t block,
return page;
failed:
- BUG();
unlock_page(page);
page_cache_release(page);
return NULL;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d3421282244..811245b1ff2 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -370,13 +370,13 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
(int)(srcaddr->sa_family));
}
- seq_printf(s, ",uid=%d", cifs_sb->mnt_uid);
+ seq_printf(s, ",uid=%u", cifs_sb->mnt_uid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
seq_printf(s, ",forceuid");
else
seq_printf(s, ",noforceuid");
- seq_printf(s, ",gid=%d", cifs_sb->mnt_gid);
+ seq_printf(s, ",gid=%u", cifs_sb->mnt_gid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
seq_printf(s, ",forcegid");
else
@@ -434,9 +434,13 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_printf(s, ",noperm");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
seq_printf(s, ",strictcache");
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
+ seq_printf(s, ",backupuid=%u", cifs_sb->mnt_backupuid);
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID)
+ seq_printf(s, ",backupgid=%u", cifs_sb->mnt_backupgid);
- seq_printf(s, ",rsize=%d", cifs_sb->rsize);
- seq_printf(s, ",wsize=%d", cifs_sb->wsize);
+ seq_printf(s, ",rsize=%u", cifs_sb->rsize);
+ seq_printf(s, ",wsize=%u", cifs_sb->wsize);
/* convert actimeo and display it in seconds */
seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index f31dc9ac37b..f4d381e331c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3228,10 +3228,6 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
cifs_sb->mnt_uid = pvolume_info->linux_uid;
cifs_sb->mnt_gid = pvolume_info->linux_gid;
- if (pvolume_info->backupuid_specified)
- cifs_sb->mnt_backupuid = pvolume_info->backupuid;
- if (pvolume_info->backupgid_specified)
- cifs_sb->mnt_backupgid = pvolume_info->backupgid;
cifs_sb->mnt_file_mode = pvolume_info->file_mode;
cifs_sb->mnt_dir_mode = pvolume_info->dir_mode;
cFYI(1, "file mode: 0x%hx dir mode: 0x%hx",
@@ -3262,10 +3258,14 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD;
if (pvolume_info->cifs_acl)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL;
- if (pvolume_info->backupuid_specified)
+ if (pvolume_info->backupuid_specified) {
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID;
- if (pvolume_info->backupgid_specified)
+ cifs_sb->mnt_backupuid = pvolume_info->backupuid;
+ }
+ if (pvolume_info->backupgid_specified) {
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID;
+ cifs_sb->mnt_backupgid = pvolume_info->backupgid;
+ }
if (pvolume_info->override_uid)
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID;
if (pvolume_info->override_gid)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index fae765dac93..81725e9286e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2178,7 +2178,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
unsigned long nr_pages, i;
size_t copied, len, cur_len;
ssize_t total_written = 0;
- loff_t offset = *poffset;
+ loff_t offset;
struct iov_iter it;
struct cifsFileInfo *open_file;
struct cifs_tcon *tcon;
@@ -2200,6 +2200,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
open_file = file->private_data;
tcon = tlink_tcon(open_file->tlink);
+ offset = *poffset;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index fa5c07d51dc..4c58d4a3adc 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1737,6 +1737,18 @@ static int _can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now)
return 1;
/*
+ * Even if the convert is compat with all granted locks,
+ * QUECVT forces it behind other locks on the convert queue.
+ */
+
+ if (now && conv && (lkb->lkb_exflags & DLM_LKF_QUECVT)) {
+ if (list_empty(&r->res_convertqueue))
+ return 1;
+ else
+ goto out;
+ }
+
+ /*
* The NOORDER flag is set to avoid the standard vms rules on grant
* order.
*/
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 739b0985b39..c0b3c70ee87 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1663,8 +1663,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
if (op == EPOLL_CTL_ADD) {
if (is_file_epoll(tfile)) {
error = -ELOOP;
- if (ep_loop_check(ep, tfile) != 0)
+ if (ep_loop_check(ep, tfile) != 0) {
+ clear_tfile_check_list();
goto error_tgt_fput;
+ }
} else
list_add(&tfile->f_tfile_llink, &tfile_check_list);
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6da193564e4..e1fb1d5de58 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1597,7 +1597,9 @@ static int parse_options(char *options, struct super_block *sb,
unsigned int *journal_ioprio,
int is_remount)
{
+#ifdef CONFIG_QUOTA
struct ext4_sb_info *sbi = EXT4_SB(sb);
+#endif
char *p;
substring_t args[MAX_OPT_ARGS];
int token;
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index f8411bd1b80..5f5e70e047d 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -200,10 +200,11 @@ static int make_mode(const unsigned int lmstate)
return -1;
}
-static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
+static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags,
const int req)
{
u32 lkf = DLM_LKF_VALBLK;
+ u32 lkid = gl->gl_lksb.sb_lkid;
if (gfs_flags & LM_FLAG_TRY)
lkf |= DLM_LKF_NOQUEUE;
@@ -227,8 +228,11 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
BUG();
}
- if (lkid != 0)
+ if (lkid != 0) {
lkf |= DLM_LKF_CONVERT;
+ if (test_bit(GLF_BLOCKING, &gl->gl_flags))
+ lkf |= DLM_LKF_QUECVT;
+ }
return lkf;
}
@@ -250,7 +254,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
char strname[GDLM_STRNAME_BYTES] = "";
req = make_mode(req_state);
- lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
+ lkf = make_flags(gl, flags, req);
gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
if (gl->gl_lksb.sb_lkid) {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 28cf06e4ec8..001ef01d2fe 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -485,6 +485,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
inode->i_fop = &simple_dir_operations;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
+ lockdep_annotate_inode_mutex_key(inode);
}
return inode;
}
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 806525a7269..840f70f5079 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -723,7 +723,7 @@ start_journal_io:
if (commit_transaction->t_need_data_flush &&
(journal->j_fs_dev != journal->j_dev) &&
(journal->j_flags & JBD2_BARRIER))
- blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);
+ blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL);
/* Done it all: now write the commit record asynchronously. */
if (JBD2_HAS_INCOMPAT_FEATURE(journal,
@@ -859,7 +859,7 @@ wait_for_iobuf:
if (JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) &&
journal->j_flags & JBD2_BARRIER) {
- blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL);
+ blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL);
}
if (err)
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 9c94297bb70..7f6a23f0244 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -38,6 +38,8 @@
#include <linux/buffer_head.h> /* various write calls */
#include <linux/prefetch.h>
+#include "../pnfs.h"
+#include "../internal.h"
#include "blocklayout.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
@@ -868,7 +870,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
* GETDEVICEINFO's maxcount
*/
max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
- max_pages = max_resp_sz >> PAGE_SHIFT;
+ max_pages = nfs_page_array_len(0, max_resp_sz);
dprintk("%s max_resp_sz %u max_pages %d\n",
__func__, max_resp_sz, max_pages);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index da7b5e4ff9e..60f7e4ec842 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1729,7 +1729,8 @@ error:
*/
struct nfs_server *nfs_clone_server(struct nfs_server *source,
struct nfs_fh *fh,
- struct nfs_fattr *fattr)
+ struct nfs_fattr *fattr,
+ rpc_authflavor_t flavor)
{
struct nfs_server *server;
struct nfs_fattr *fattr_fsinfo;
@@ -1758,7 +1759,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
error = nfs_init_server_rpcclient(server,
source->client->cl_timeout,
- source->client->cl_auth->au_flavor);
+ flavor);
if (error < 0)
goto out_free_server;
if (!IS_ERR(source->client_acl))
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 4aaf0316d76..8789210c690 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1429,7 +1429,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
}
open_flags = nd->intent.open.flags;
- attr.ia_valid = 0;
+ attr.ia_valid = ATTR_OPEN;
ctx = create_nfs_open_context(dentry, open_flags);
res = ERR_CAST(ctx);
@@ -1536,7 +1536,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
if (IS_ERR(ctx))
goto out;
- attr.ia_valid = 0;
+ attr.ia_valid = ATTR_OPEN;
if (openflags & O_TRUNC) {
attr.ia_valid |= ATTR_SIZE;
attr.ia_size = 0;
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index b7f348bb618..ba3019f5934 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -554,12 +554,16 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
struct nfs_client *clp;
int error = 0;
+ if (!try_module_get(THIS_MODULE))
+ return 0;
+
while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) {
error = __rpc_pipefs_event(clp, event, sb);
nfs_put_client(clp);
if (error)
break;
}
+ module_put(THIS_MODULE);
return error;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2476dc69365..b777bdaba4c 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -165,7 +165,8 @@ extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
- struct nfs_fattr *);
+ struct nfs_fattr *,
+ rpc_authflavor_t);
extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
extern int nfs4_check_client_ready(struct nfs_client *clp);
extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
@@ -186,10 +187,10 @@ static inline void nfs_fs_proc_exit(void)
/* nfs4namespace.c */
#ifdef CONFIG_NFS_V4
-extern struct vfsmount *nfs_do_refmount(struct dentry *dentry);
+extern struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry);
#else
static inline
-struct vfsmount *nfs_do_refmount(struct dentry *dentry)
+struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
{
return ERR_PTR(-ENOENT);
}
@@ -234,7 +235,6 @@ extern const u32 nfs41_maxwrite_overhead;
/* nfs4proc.c */
#ifdef CONFIG_NFS_V4
extern struct rpc_procinfo nfs4_procedures[];
-void nfs_fixup_secinfo_attributes(struct nfs_fattr *, struct nfs_fh *);
#endif
extern int nfs4_init_ds_session(struct nfs_client *clp);
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 1807866bb3a..d51868e5683 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -148,66 +148,31 @@ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
return pseudoflavor;
}
-static int nfs_negotiate_security(const struct dentry *parent,
- const struct dentry *dentry,
- rpc_authflavor_t *flavor)
+static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
+ struct qstr *name,
+ struct nfs_fh *fh,
+ struct nfs_fattr *fattr)
{
- struct page *page;
- struct nfs4_secinfo_flavors *flavors;
- int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
- int ret = -EPERM;
-
- secinfo = NFS_PROTO(parent->d_inode)->secinfo;
- if (secinfo != NULL) {
- page = alloc_page(GFP_KERNEL);
- if (!page) {
- ret = -ENOMEM;
- goto out;
- }
- flavors = page_address(page);
- ret = secinfo(parent->d_inode, &dentry->d_name, flavors);
- *flavor = nfs_find_best_sec(flavors);
- put_page(page);
- }
-
-out:
- return ret;
-}
-
-static int nfs_lookup_with_sec(struct nfs_server *server, struct dentry *parent,
- struct dentry *dentry, struct path *path,
- struct nfs_fh *fh, struct nfs_fattr *fattr,
- rpc_authflavor_t *flavor)
-{
- struct rpc_clnt *clone;
- struct rpc_auth *auth;
int err;
- err = nfs_negotiate_security(parent, path->dentry, flavor);
- if (err < 0)
- goto out;
- clone = rpc_clone_client(server->client);
- auth = rpcauth_create(*flavor, clone);
- if (!auth) {
- err = -EIO;
- goto out_shutdown;
- }
- err = server->nfs_client->rpc_ops->lookup(clone, parent->d_inode,
- &path->dentry->d_name,
- fh, fattr);
-out_shutdown:
- rpc_shutdown_client(clone);
-out:
- return err;
+ if (NFS_PROTO(dir)->version == 4)
+ return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr);
+
+ err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
+ if (err)
+ return ERR_PTR(err);
+ return rpc_clone_client(NFS_SERVER(dir)->client);
}
#else /* CONFIG_NFS_V4 */
-static inline int nfs_lookup_with_sec(struct nfs_server *server,
- struct dentry *parent, struct dentry *dentry,
- struct path *path, struct nfs_fh *fh,
- struct nfs_fattr *fattr,
- rpc_authflavor_t *flavor)
+static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
+ struct qstr *name,
+ struct nfs_fh *fh,
+ struct nfs_fattr *fattr)
{
- return -EPERM;
+ int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
+ if (err)
+ return ERR_PTR(err);
+ return rpc_clone_client(NFS_SERVER(dir)->client);
}
#endif /* CONFIG_NFS_V4 */
@@ -226,12 +191,10 @@ static inline int nfs_lookup_with_sec(struct nfs_server *server,
struct vfsmount *nfs_d_automount(struct path *path)
{
struct vfsmount *mnt;
- struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
struct dentry *parent;
struct nfs_fh *fh = NULL;
struct nfs_fattr *fattr = NULL;
- int err;
- rpc_authflavor_t flavor = RPC_AUTH_UNIX;
+ struct rpc_clnt *client;
dprintk("--> nfs_d_automount()\n");
@@ -249,21 +212,19 @@ struct vfsmount *nfs_d_automount(struct path *path)
/* Look it up again to get its attributes */
parent = dget_parent(path->dentry);
- err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode,
- &path->dentry->d_name,
- fh, fattr);
- if (err == -EPERM && NFS_PROTO(parent->d_inode)->secinfo != NULL)
- err = nfs_lookup_with_sec(server, parent, path->dentry, path, fh, fattr, &flavor);
+ client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr);
dput(parent);
- if (err != 0) {
- mnt = ERR_PTR(err);
+ if (IS_ERR(client)) {
+ mnt = ERR_CAST(client);
goto out;
}
if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
- mnt = nfs_do_refmount(path->dentry);
+ mnt = nfs_do_refmount(client, path->dentry);
else
- mnt = nfs_do_submount(path->dentry, fh, fattr, flavor);
+ mnt = nfs_do_submount(path->dentry, fh, fattr, client->cl_auth->au_flavor);
+ rpc_shutdown_client(client);
+
if (IS_ERR(mnt))
goto out;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 97ecc863dd7..8d75021020b 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -59,6 +59,7 @@ struct nfs_unique_id {
#define NFS_SEQID_CONFIRMED 1
struct nfs_seqid_counter {
+ ktime_t create_time;
int owner_id;
int flags;
u32 counter;
@@ -204,6 +205,9 @@ struct nfs4_state_maintenance_ops {
extern const struct dentry_operations nfs4_dentry_operations;
extern const struct inode_operations nfs4_dir_inode_operations;
+/* nfs4namespace.c */
+struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *);
+
/* nfs4proc.c */
extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
@@ -212,8 +216,11 @@ extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
-extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
- struct nfs4_fs_locations *fs_locations, struct page *page);
+extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
+ struct nfs4_fs_locations *, struct page *);
+extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *,
+ struct nfs_fh *, struct nfs_fattr *);
+extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
extern int nfs4_release_lockowner(struct nfs4_lock_state *);
extern const struct xattr_handler *nfs4_xattr_handlers[];
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index a866bbd2890..c9cff9adb2d 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -699,7 +699,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla
* GETDEVICEINFO's maxcount
*/
max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
- max_pages = max_resp_sz >> PAGE_SHIFT;
+ max_pages = nfs_page_array_len(0, max_resp_sz);
dprintk("%s inode %p max_resp_sz %u max_pages %d\n",
__func__, inode, max_resp_sz, max_pages);
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 9c8eca315f4..a7f3dedc4ec 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -52,6 +52,30 @@ Elong:
}
/*
+ * return the path component of "<server>:<path>"
+ * nfspath - the "<server>:<path>" string
+ * end - one past the last char that could contain "<server>:"
+ * returns NULL on failure
+ */
+static char *nfs_path_component(const char *nfspath, const char *end)
+{
+ char *p;
+
+ if (*nfspath == '[') {
+ /* parse [] escaped IPv6 addrs */
+ p = strchr(nfspath, ']');
+ if (p != NULL && ++p < end && *p == ':')
+ return p + 1;
+ } else {
+ /* otherwise split on first colon */
+ p = strchr(nfspath, ':');
+ if (p != NULL && p < end)
+ return p + 1;
+ }
+ return NULL;
+}
+
+/*
* Determine the mount path as a string
*/
static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen)
@@ -59,9 +83,9 @@ static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen)
char *limit;
char *path = nfs_path(&limit, dentry, buffer, buflen);
if (!IS_ERR(path)) {
- char *colon = strchr(path, ':');
- if (colon && colon < limit)
- path = colon + 1;
+ char *path_component = nfs_path_component(path, limit);
+ if (path_component)
+ return path_component;
}
return path;
}
@@ -108,6 +132,58 @@ static size_t nfs_parse_server_name(char *string, size_t len,
return ret;
}
+static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name)
+{
+ struct page *page;
+ struct nfs4_secinfo_flavors *flavors;
+ rpc_authflavor_t flavor;
+ int err;
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+ flavors = page_address(page);
+
+ err = nfs4_proc_secinfo(inode, name, flavors);
+ if (err < 0) {
+ flavor = err;
+ goto out;
+ }
+
+ flavor = nfs_find_best_sec(flavors);
+
+out:
+ put_page(page);
+ return flavor;
+}
+
+/*
+ * Please call rpc_shutdown_client() when you are done with this client.
+ */
+struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode,
+ struct qstr *name)
+{
+ struct rpc_clnt *clone;
+ struct rpc_auth *auth;
+ rpc_authflavor_t flavor;
+
+ flavor = nfs4_negotiate_security(inode, name);
+ if (flavor < 0)
+ return ERR_PTR(flavor);
+
+ clone = rpc_clone_client(clnt);
+ if (IS_ERR(clone))
+ return clone;
+
+ auth = rpcauth_create(flavor, clone);
+ if (!auth) {
+ rpc_shutdown_client(clone);
+ clone = ERR_PTR(-EIO);
+ }
+
+ return clone;
+}
+
static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
char *page, char *page2,
const struct nfs4_fs_location *location)
@@ -224,7 +300,7 @@ out:
* @dentry - dentry of referral
*
*/
-struct vfsmount *nfs_do_refmount(struct dentry *dentry)
+struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
{
struct vfsmount *mnt = ERR_PTR(-ENOMEM);
struct dentry *parent;
@@ -250,7 +326,7 @@ struct vfsmount *nfs_do_refmount(struct dentry *dentry)
dprintk("%s: getting locations for %s/%s\n",
__func__, parent->d_name.name, dentry->d_name.name);
- err = nfs4_proc_fs_locations(parent->d_inode, &dentry->d_name, fs_locations, page);
+ err = nfs4_proc_fs_locations(client, parent->d_inode, &dentry->d_name, fs_locations, page);
dput(parent);
if (err != 0 ||
fs_locations->nlocations <= 0 ||
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f82bde005a8..99650aaf893 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -838,7 +838,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
p->o_arg.open_flags = flags;
p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
p->o_arg.clientid = server->nfs_client->cl_clientid;
- p->o_arg.id = sp->so_seqid.owner_id;
+ p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time);
+ p->o_arg.id.uniquifier = sp->so_seqid.owner_id;
p->o_arg.name = &dentry->d_name;
p->o_arg.server = server;
p->o_arg.bitmask = server->attr_bitmask;
@@ -1466,8 +1467,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
goto unlock_no_action;
rcu_read_unlock();
}
- /* Update sequence id. */
- data->o_arg.id = sp->so_seqid.owner_id;
+ /* Update client id. */
data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
@@ -1954,10 +1954,19 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
};
int err;
do {
- err = nfs4_handle_exception(server,
- _nfs4_do_setattr(inode, cred, fattr, sattr, state),
- &exception);
+ err = _nfs4_do_setattr(inode, cred, fattr, sattr, state);
+ switch (err) {
+ case -NFS4ERR_OPENMODE:
+ if (state && !(state->state & FMODE_WRITE)) {
+ err = -EBADF;
+ if (sattr->ia_valid & ATTR_OPEN)
+ err = -EACCES;
+ goto out;
+ }
+ }
+ err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
+out:
return err;
}
@@ -2368,8 +2377,9 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
* Note that we'll actually follow the referral later when
* we detect fsid mismatch in inode revalidation
*/
-static int nfs4_get_referral(struct inode *dir, const struct qstr *name,
- struct nfs_fattr *fattr, struct nfs_fh *fhandle)
+static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir,
+ const struct qstr *name, struct nfs_fattr *fattr,
+ struct nfs_fh *fhandle)
{
int status = -ENOMEM;
struct page *page = NULL;
@@ -2382,7 +2392,7 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name,
if (locations == NULL)
goto out;
- status = nfs4_proc_fs_locations(dir, name, locations, page);
+ status = nfs4_proc_fs_locations(client, dir, name, locations, page);
if (status != 0)
goto out;
/* Make sure server returned a different fsid for the referral */
@@ -2519,39 +2529,84 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir,
return status;
}
-void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr, struct nfs_fh *fh)
+static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr)
{
- memset(fh, 0, sizeof(struct nfs_fh));
- fattr->fsid.major = 1;
fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE |
- NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_FSID | NFS_ATTR_FATTR_MOUNTPOINT;
+ NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_MOUNTPOINT;
fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO;
fattr->nlink = 2;
}
-static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
- struct nfs_fh *fhandle, struct nfs_fattr *fattr)
+static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
+ struct qstr *name, struct nfs_fh *fhandle,
+ struct nfs_fattr *fattr)
{
struct nfs4_exception exception = { };
+ struct rpc_clnt *client = *clnt;
int err;
do {
- int status;
-
- status = _nfs4_proc_lookup(clnt, dir, name, fhandle, fattr);
- switch (status) {
+ err = _nfs4_proc_lookup(client, dir, name, fhandle, fattr);
+ switch (err) {
case -NFS4ERR_BADNAME:
- return -ENOENT;
+ err = -ENOENT;
+ goto out;
case -NFS4ERR_MOVED:
- return nfs4_get_referral(dir, name, fattr, fhandle);
+ err = nfs4_get_referral(client, dir, name, fattr, fhandle);
+ goto out;
case -NFS4ERR_WRONGSEC:
- nfs_fixup_secinfo_attributes(fattr, fhandle);
+ err = -EPERM;
+ if (client != *clnt)
+ goto out;
+
+ client = nfs4_create_sec_client(client, dir, name);
+ if (IS_ERR(client))
+ return PTR_ERR(client);
+
+ exception.retry = 1;
+ break;
+ default:
+ err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception);
}
- err = nfs4_handle_exception(NFS_SERVER(dir),
- status, &exception);
} while (exception.retry);
+
+out:
+ if (err == 0)
+ *clnt = client;
+ else if (client != *clnt)
+ rpc_shutdown_client(client);
+
return err;
}
+static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
+ struct nfs_fh *fhandle, struct nfs_fattr *fattr)
+{
+ int status;
+ struct rpc_clnt *client = NFS_CLIENT(dir);
+
+ status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr);
+ if (client != NFS_CLIENT(dir)) {
+ rpc_shutdown_client(client);
+ nfs_fixup_secinfo_attributes(fattr);
+ }
+ return status;
+}
+
+struct rpc_clnt *
+nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name,
+ struct nfs_fh *fhandle, struct nfs_fattr *fattr)
+{
+ int status;
+ struct rpc_clnt *client = rpc_clone_client(NFS_CLIENT(dir));
+
+ status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr);
+ if (status < 0) {
+ rpc_shutdown_client(client);
+ return ERR_PTR(status);
+ }
+ return client;
+}
+
static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
{
struct nfs_server *server = NFS_SERVER(inode);
@@ -3619,16 +3674,16 @@ out:
return ret;
}
-static void nfs4_write_cached_acl(struct inode *inode, const char *buf, size_t acl_len)
+static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len)
{
struct nfs4_cached_acl *acl;
- if (buf && acl_len <= PAGE_SIZE) {
+ if (pages && acl_len <= PAGE_SIZE) {
acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL);
if (acl == NULL)
goto out;
acl->cached = 1;
- memcpy(acl->data, buf, acl_len);
+ _copy_from_pages(acl->data, pages, pgbase, acl_len);
} else {
acl = kmalloc(sizeof(*acl), GFP_KERNEL);
if (acl == NULL)
@@ -3661,7 +3716,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
struct nfs_getaclres res = {
.acl_len = buflen,
};
- void *resp_buf;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETACL],
.rpc_argp = &args,
@@ -3675,24 +3729,27 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
if (npages == 0)
npages = 1;
+ /* Add an extra page to handle the bitmap returned */
+ npages++;
+
for (i = 0; i < npages; i++) {
pages[i] = alloc_page(GFP_KERNEL);
if (!pages[i])
goto out_free;
}
- if (npages > 1) {
- /* for decoding across pages */
- res.acl_scratch = alloc_page(GFP_KERNEL);
- if (!res.acl_scratch)
- goto out_free;
- }
+
+ /* for decoding across pages */
+ res.acl_scratch = alloc_page(GFP_KERNEL);
+ if (!res.acl_scratch)
+ goto out_free;
+
args.acl_len = npages * PAGE_SIZE;
args.acl_pgbase = 0;
+
/* Let decode_getfacl know not to fail if the ACL data is larger than
* the page we send as a guess */
if (buf == NULL)
res.acl_flags |= NFS4_ACL_LEN_REQUEST;
- resp_buf = page_address(pages[0]);
dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n",
__func__, buf, buflen, npages, args.acl_len);
@@ -3703,9 +3760,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
acl_len = res.acl_len - res.acl_data_offset;
if (acl_len > args.acl_len)
- nfs4_write_cached_acl(inode, NULL, acl_len);
+ nfs4_write_cached_acl(inode, NULL, 0, acl_len);
else
- nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset,
+ nfs4_write_cached_acl(inode, pages, res.acl_data_offset,
acl_len);
if (buf) {
ret = -ERANGE;
@@ -4558,7 +4615,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request)
{
struct nfs_server *server = NFS_SERVER(state->inode);
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .inode = state->inode,
+ };
int err;
do {
@@ -4576,7 +4635,9 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request)
{
struct nfs_server *server = NFS_SERVER(state->inode);
- struct nfs4_exception exception = { };
+ struct nfs4_exception exception = {
+ .inode = state->inode,
+ };
int err;
err = nfs4_set_lock_state(state, request);
@@ -4676,6 +4737,7 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *
{
struct nfs4_exception exception = {
.state = state,
+ .inode = state->inode,
};
int err;
@@ -4721,6 +4783,20 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
if (state == NULL)
return -ENOLCK;
+ /*
+ * Don't rely on the VFS having checked the file open mode,
+ * since it won't do this for flock() locks.
+ */
+ switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) {
+ case F_RDLCK:
+ if (!(filp->f_mode & FMODE_READ))
+ return -EBADF;
+ break;
+ case F_WRLCK:
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+ }
+
do {
status = nfs4_proc_setlk(state, cmd, request);
if ((status != -EAGAIN) || IS_SETLK(cmd))
@@ -4891,8 +4967,10 @@ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr)
fattr->nlink = 2;
}
-int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
- struct nfs4_fs_locations *fs_locations, struct page *page)
+static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
+ const struct qstr *name,
+ struct nfs4_fs_locations *fs_locations,
+ struct page *page)
{
struct nfs_server *server = NFS_SERVER(dir);
u32 bitmask[2] = {
@@ -4926,11 +5004,26 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
nfs_fattr_init(&fs_locations->fattr);
fs_locations->server = server;
fs_locations->nlocations = 0;
- status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
+ status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0);
dprintk("%s: returned status = %d\n", __func__, status);
return status;
}
+int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
+ const struct qstr *name,
+ struct nfs4_fs_locations *fs_locations,
+ struct page *page)
+{
+ struct nfs4_exception exception = { };
+ int err;
+ do {
+ err = nfs4_handle_exception(NFS_SERVER(dir),
+ _nfs4_proc_fs_locations(client, dir, name, fs_locations, page),
+ &exception);
+ } while (exception.retry);
+ return err;
+}
+
static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors)
{
int status;
@@ -4953,8 +5046,8 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct
return status;
}
-static int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
- struct nfs4_secinfo_flavors *flavors)
+int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
+ struct nfs4_secinfo_flavors *flavors)
{
struct nfs4_exception exception = { };
int err;
@@ -5029,10 +5122,9 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
nfs4_construct_boot_verifier(clp, &verifier);
args.id_len = scnprintf(args.id, sizeof(args.id),
- "%s/%s.%s/%u",
+ "%s/%s/%u",
clp->cl_ipaddr,
- init_utsname()->nodename,
- init_utsname()->domainname,
+ clp->cl_rpcclient->cl_nodename,
clp->cl_rpcclient->cl_auth->au_flavor);
res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0f43414eb25..7f0fcfc1fe9 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -393,6 +393,7 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
static void
nfs4_init_seqid_counter(struct nfs_seqid_counter *sc)
{
+ sc->create_time = ktime_get();
sc->flags = 0;
sc->counter = 0;
spin_lock_init(&sc->lock);
@@ -434,13 +435,17 @@ nfs4_alloc_state_owner(struct nfs_server *server,
static void
nfs4_drop_state_owner(struct nfs4_state_owner *sp)
{
- if (!RB_EMPTY_NODE(&sp->so_server_node)) {
+ struct rb_node *rb_node = &sp->so_server_node;
+
+ if (!RB_EMPTY_NODE(rb_node)) {
struct nfs_server *server = sp->so_server;
struct nfs_client *clp = server->nfs_client;
spin_lock(&clp->cl_lock);
- rb_erase(&sp->so_server_node, &server->state_owners);
- RB_CLEAR_NODE(&sp->so_server_node);
+ if (!RB_EMPTY_NODE(rb_node)) {
+ rb_erase(rb_node, &server->state_owners);
+ RB_CLEAR_NODE(rb_node);
+ }
spin_unlock(&clp->cl_lock);
}
}
@@ -516,6 +521,14 @@ out:
/**
* nfs4_put_state_owner - Release a nfs4_state_owner
* @sp: state owner data to release
+ *
+ * Note that we keep released state owners on an LRU
+ * list.
+ * This caches valid state owners so that they can be
+ * reused, to avoid the OPEN_CONFIRM on minor version 0.
+ * It also pins the uniquifier of dropped state owners for
+ * a while, to ensure that those state owner names are
+ * never reused.
*/
void nfs4_put_state_owner(struct nfs4_state_owner *sp)
{
@@ -525,15 +538,9 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp)
if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
return;
- if (!RB_EMPTY_NODE(&sp->so_server_node)) {
- sp->so_expires = jiffies;
- list_add_tail(&sp->so_lru, &server->state_owners_lru);
- spin_unlock(&clp->cl_lock);
- } else {
- nfs4_remove_state_owner_locked(sp);
- spin_unlock(&clp->cl_lock);
- nfs4_free_state_owner(sp);
- }
+ sp->so_expires = jiffies;
+ list_add_tail(&sp->so_lru, &server->state_owners_lru);
+ spin_unlock(&clp->cl_lock);
}
/**
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c74fdb114b4..c54aae364be 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -74,7 +74,7 @@ static int nfs4_stat_to_errno(int);
/* lock,open owner id:
* we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT >> 2)
*/
-#define open_owner_id_maxsz (1 + 1 + 4)
+#define open_owner_id_maxsz (1 + 2 + 1 + 1 + 2)
#define lock_owner_id_maxsz (1 + 1 + 4)
#define decode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ))
#define compound_encode_hdr_maxsz (3 + (NFS4_MAXTAGLEN >> 2))
@@ -1340,12 +1340,13 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
*/
encode_nfs4_seqid(xdr, arg->seqid);
encode_share_access(xdr, arg->fmode);
- p = reserve_space(xdr, 32);
+ p = reserve_space(xdr, 36);
p = xdr_encode_hyper(p, arg->clientid);
- *p++ = cpu_to_be32(20);
+ *p++ = cpu_to_be32(24);
p = xdr_encode_opaque_fixed(p, "open id:", 8);
*p++ = cpu_to_be32(arg->server->s_dev);
- xdr_encode_hyper(p, arg->id);
+ *p++ = cpu_to_be32(arg->id.uniquifier);
+ xdr_encode_hyper(p, arg->id.create_time);
}
static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg)
@@ -4257,8 +4258,6 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
status = decode_attr_error(xdr, bitmap, &err);
if (status < 0)
goto xdr_error;
- if (err == -NFS4ERR_WRONGSEC)
- nfs_fixup_secinfo_attributes(fattr, fh);
status = decode_attr_filehandle(xdr, bitmap, fh);
if (status < 0)
@@ -4901,11 +4900,19 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
bitmap[3] = {0};
struct kvec *iov = req->rq_rcv_buf.head;
int status;
+ size_t page_len = xdr->buf->page_len;
res->acl_len = 0;
if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
goto out;
+
bm_p = xdr->p;
+ res->acl_data_offset = be32_to_cpup(bm_p) + 2;
+ res->acl_data_offset <<= 2;
+ /* Check if the acl data starts beyond the allocated buffer */
+ if (res->acl_data_offset > page_len)
+ return -ERANGE;
+
if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
goto out;
if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
@@ -4915,28 +4922,24 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
return -EIO;
if (likely(bitmap[0] & FATTR4_WORD0_ACL)) {
size_t hdrlen;
- u32 recvd;
/* The bitmap (xdr len + bitmaps) and the attr xdr len words
* are stored with the acl data to handle the problem of
* variable length bitmaps.*/
xdr->p = bm_p;
- res->acl_data_offset = be32_to_cpup(bm_p) + 2;
- res->acl_data_offset <<= 2;
/* We ignore &savep and don't do consistency checks on
* the attr length. Let userspace figure it out.... */
hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base;
attrlen += res->acl_data_offset;
- recvd = req->rq_rcv_buf.len - hdrlen;
- if (attrlen > recvd) {
+ if (attrlen > page_len) {
if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
/* getxattr interface called with a NULL buf */
res->acl_len = attrlen;
goto out;
}
- dprintk("NFS: acl reply: attrlen %u > recvd %u\n",
- attrlen, recvd);
+ dprintk("NFS: acl reply: attrlen %u > page_len %zu\n",
+ attrlen, page_len);
return -EINVAL;
}
xdr_read_pages(xdr, attrlen);
@@ -5089,16 +5092,13 @@ out_err:
return -EINVAL;
}
-static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
+static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
{
struct nfs4_secinfo_flavor *sec_flavor;
int status;
__be32 *p;
int i, num_flavors;
- status = decode_op_hdr(xdr, OP_SECINFO);
- if (status)
- goto out;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
@@ -5124,6 +5124,7 @@ static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
res->flavors->num_flavors++;
}
+ status = 0;
out:
return status;
out_overflow:
@@ -5131,7 +5132,23 @@ out_overflow:
return -EIO;
}
+static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
+{
+ int status = decode_op_hdr(xdr, OP_SECINFO);
+ if (status)
+ return status;
+ return decode_secinfo_common(xdr, res);
+}
+
#if defined(CONFIG_NFS_V4_1)
+static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
+{
+ int status = decode_op_hdr(xdr, OP_SECINFO_NO_NAME);
+ if (status)
+ return status;
+ return decode_secinfo_common(xdr, res);
+}
+
static int decode_exchange_id(struct xdr_stream *xdr,
struct nfs41_exchange_id_res *res)
{
@@ -6816,7 +6833,7 @@ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp,
status = decode_putrootfh(xdr);
if (status)
goto out;
- status = decode_secinfo(xdr, res);
+ status = decode_secinfo_no_name(xdr, res);
out:
return status;
}
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 8d45f1c318c..595c5fc21a1 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -604,7 +604,6 @@ int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
{
struct objlayout_deviceinfo *odi;
struct pnfs_device pd;
- struct super_block *sb;
struct page *page, **pages;
u32 *p;
int err;
@@ -623,7 +622,6 @@ int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
pd.pglen = PAGE_SIZE;
pd.mincount = 0;
- sb = pnfslay->plh_inode->i_sb;
err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd);
dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err);
if (err)
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index b5d45158694..38512bcd2e9 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -587,7 +587,7 @@ send_layoutget(struct pnfs_layout_hdr *lo,
/* allocate pages for xdr post processing */
max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz;
- max_pages = max_resp_sz >> PAGE_SHIFT;
+ max_pages = nfs_page_array_len(0, max_resp_sz);
pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags);
if (!pages)
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 9a0e8ef4a40..0a4be28c2ea 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -322,7 +322,7 @@ out_bad:
while (!list_empty(res)) {
data = list_entry(res->next, struct nfs_read_data, list);
list_del(&data->list);
- nfs_readdata_free(data);
+ nfs_readdata_release(data);
}
nfs_readpage_release(req);
return -ENOMEM;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 37412f706b3..4ac7fca7e4b 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2428,7 +2428,7 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags,
dprintk("--> nfs_xdev_mount()\n");
/* create a new volume representation */
- server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr);
+ server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
if (IS_ERR(server)) {
error = PTR_ERR(server);
goto out_err_noserver;
@@ -2767,11 +2767,15 @@ static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
char *root_devname;
size_t len;
- len = strlen(hostname) + 3;
+ len = strlen(hostname) + 5;
root_devname = kmalloc(len, GFP_KERNEL);
if (root_devname == NULL)
return ERR_PTR(-ENOMEM);
- snprintf(root_devname, len, "%s:/", hostname);
+ /* Does hostname needs to be enclosed in brackets? */
+ if (strchr(hostname, ':'))
+ snprintf(root_devname, len, "[%s]:/", hostname);
+ else
+ snprintf(root_devname, len, "%s:/", hostname);
root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data);
kfree(root_devname);
return root_mnt;
@@ -2951,7 +2955,7 @@ nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
dprintk("--> nfs4_xdev_mount()\n");
/* create a new volume representation */
- server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr);
+ server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
if (IS_ERR(server)) {
error = PTR_ERR(server);
goto out_err_noserver;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 2c68818f68a..c07462320f6 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -682,7 +682,8 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
req->wb_bytes = rqend - req->wb_offset;
out_unlock:
spin_unlock(&inode->i_lock);
- nfs_clear_request_commit(req);
+ if (req)
+ nfs_clear_request_commit(req);
return req;
out_flushme:
spin_unlock(&inode->i_lock);
@@ -1018,7 +1019,7 @@ out_bad:
while (!list_empty(res)) {
data = list_entry(res->next, struct nfs_write_data, list);
list_del(&data->list);
- nfs_writedata_free(data);
+ nfs_writedata_release(data);
}
nfs_redirty_request(req);
return -ENOMEM;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 4767429264a..ed3f9206a0e 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -577,7 +577,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
struct cld_net *cn = nn->cld_net;
if (mlen != sizeof(*cmsg)) {
- dprintk("%s: got %lu bytes, expected %lu\n", __func__, mlen,
+ dprintk("%s: got %zu bytes, expected %zu\n", __func__, mlen,
sizeof(*cmsg));
return -EINVAL;
}
diff --git a/fs/pipe.c b/fs/pipe.c
index 25feaa3faac..fec5e4ad071 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -346,6 +346,16 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
.get = generic_pipe_buf_get,
};
+static const struct pipe_buf_operations packet_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = anon_pipe_buf_release,
+ .steal = generic_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
static ssize_t
pipe_read(struct kiocb *iocb, const struct iovec *_iov,
unsigned long nr_segs, loff_t pos)
@@ -407,6 +417,13 @@ redo:
ret += chars;
buf->offset += chars;
buf->len -= chars;
+
+ /* Was it a packet buffer? Clean up and exit */
+ if (buf->flags & PIPE_BUF_FLAG_PACKET) {
+ total_len = chars;
+ buf->len = 0;
+ }
+
if (!buf->len) {
buf->ops = NULL;
ops->release(pipe, buf);
@@ -459,6 +476,11 @@ redo:
return ret;
}
+static inline int is_packetized(struct file *file)
+{
+ return (file->f_flags & O_DIRECT) != 0;
+}
+
static ssize_t
pipe_write(struct kiocb *iocb, const struct iovec *_iov,
unsigned long nr_segs, loff_t ppos)
@@ -593,6 +615,11 @@ redo2:
buf->ops = &anon_pipe_buf_ops;
buf->offset = 0;
buf->len = chars;
+ buf->flags = 0;
+ if (is_packetized(filp)) {
+ buf->ops = &packet_pipe_buf_ops;
+ buf->flags = PIPE_BUF_FLAG_PACKET;
+ }
pipe->nrbufs = ++bufs;
pipe->tmp_page = NULL;
@@ -1013,7 +1040,7 @@ struct file *create_write_pipe(int flags)
goto err_dentry;
f->f_mapping = inode->i_mapping;
- f->f_flags = O_WRONLY | (flags & O_NONBLOCK);
+ f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
f->f_version = 0;
return f;
@@ -1057,7 +1084,7 @@ int do_pipe_flags(int *fd, int flags)
int error;
int fdw, fdr;
- if (flags & ~(O_CLOEXEC | O_NONBLOCK))
+ if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
return -EINVAL;
fw = create_write_pipe(flags);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 2b9a7607cbd..2d60492d6df 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -597,9 +597,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
if (!page)
continue;
- if (PageReserved(page))
- continue;
-
/* Clear accessed and referenced bits. */
ptep_test_and_clear_young(vma, addr, pte);
ClearPageReferenced(page);