summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorBenjamin Herrenschmidt <benh@kernel.crashing.org>2009-03-24 13:38:30 +1100
committerBenjamin Herrenschmidt <benh@kernel.crashing.org>2009-03-24 13:38:30 +1100
commit9e41d9597e7825ec20d690013d32bcec5f3fe16a (patch)
treeac6fea59e9a4a1c2183d6bbd6ffa760680673afb /fs
parent77ecfe8d427f554fabbf258e9d789f1d4c3afd63 (diff)
parent8e0ee43bc2c3e19db56a4adaa9a9b04ce885cd84 (diff)
Merge commit 'origin/master' into next
Diffstat (limited to 'fs')
-rw-r--r--fs/aio.c42
-rw-r--r--fs/bio-integrity.c5
-rw-r--r--fs/bio.c6
-rw-r--r--fs/btrfs/ctree.h9
-rw-r--r--fs/btrfs/extent-tree.c45
-rw-r--r--fs/btrfs/volumes.c8
-rw-r--r--fs/buffer.c23
-rw-r--r--fs/devpts/inode.c5
-rw-r--r--fs/ecryptfs/crypto.c51
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h4
-rw-r--r--fs/ecryptfs/inode.c32
-rw-r--r--fs/ecryptfs/keystore.c3
-rw-r--r--fs/ecryptfs/main.c5
-rw-r--r--fs/ext4/extents.c6
-rw-r--r--fs/ext4/ialloc.c4
-rw-r--r--fs/ext4/mballoc.c13
-rw-r--r--fs/fat/inode.c4
-rw-r--r--fs/fs-writeback.c9
-rw-r--r--fs/inode.c7
-rw-r--r--fs/lockd/clntlock.c51
-rw-r--r--fs/minix/inode.c2
-rw-r--r--fs/nfs/client.c73
-rw-r--r--fs/nfs/dir.c8
-rw-r--r--fs/nfs/nfs3acl.c27
-rw-r--r--fs/nfs/nfs3xdr.c34
-rw-r--r--fs/nfs/nfs4namespace.c15
-rw-r--r--fs/nfsd/nfs4xdr.c1
-rw-r--r--fs/ocfs2/alloc.c3
-rw-r--r--fs/ocfs2/aops.c7
-rw-r--r--fs/ocfs2/namei.c3
-rw-r--r--fs/ocfs2/ocfs2_fs.h6
-rw-r--r--fs/ocfs2/xattr.c30
-rw-r--r--fs/pipe.c8
-rw-r--r--fs/proc/base.c16
-rw-r--r--fs/proc/page.c2
-rw-r--r--fs/ramfs/file-nommu.c4
-rw-r--r--fs/squashfs/block.c21
-rw-r--r--fs/super.c5
-rw-r--r--fs/ufs/super.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c12
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.h2
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c10
-rw-r--r--fs/xfs/xfs_iget.c15
-rw-r--r--fs/xfs/xfs_log_recover.c17
44 files changed, 463 insertions, 192 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 8fa77e23394..76da1253795 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -443,7 +443,7 @@ static struct kiocb *__aio_get_req(struct kioctx *ctx)
req->private = NULL;
req->ki_iovec = NULL;
INIT_LIST_HEAD(&req->ki_run_list);
- req->ki_eventfd = ERR_PTR(-EINVAL);
+ req->ki_eventfd = NULL;
/* Check if the completion queue has enough free space to
* accept an event from this io.
@@ -485,8 +485,6 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
{
assert_spin_locked(&ctx->ctx_lock);
- if (!IS_ERR(req->ki_eventfd))
- fput(req->ki_eventfd);
if (req->ki_dtor)
req->ki_dtor(req);
if (req->ki_iovec != &req->ki_inline_vec)
@@ -508,8 +506,11 @@ static void aio_fput_routine(struct work_struct *data)
list_del(&req->ki_list);
spin_unlock_irq(&fput_lock);
- /* Complete the fput */
- __fput(req->ki_filp);
+ /* Complete the fput(s) */
+ if (req->ki_filp != NULL)
+ __fput(req->ki_filp);
+ if (req->ki_eventfd != NULL)
+ __fput(req->ki_eventfd);
/* Link the iocb into the context's free list */
spin_lock_irq(&ctx->ctx_lock);
@@ -527,12 +528,14 @@ static void aio_fput_routine(struct work_struct *data)
*/
static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
{
+ int schedule_putreq = 0;
+
dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
req, atomic_long_read(&req->ki_filp->f_count));
assert_spin_locked(&ctx->ctx_lock);
- req->ki_users --;
+ req->ki_users--;
BUG_ON(req->ki_users < 0);
if (likely(req->ki_users))
return 0;
@@ -540,10 +543,23 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
req->ki_cancel = NULL;
req->ki_retry = NULL;
- /* Must be done under the lock to serialise against cancellation.
- * Call this aio_fput as it duplicates fput via the fput_work.
+ /*
+ * Try to optimize the aio and eventfd file* puts, by avoiding to
+ * schedule work in case it is not __fput() time. In normal cases,
+ * we would not be holding the last reference to the file*, so
+ * this function will be executed w/out any aio kthread wakeup.
*/
- if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
+ if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count)))
+ schedule_putreq++;
+ else
+ req->ki_filp = NULL;
+ if (req->ki_eventfd != NULL) {
+ if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count)))
+ schedule_putreq++;
+ else
+ req->ki_eventfd = NULL;
+ }
+ if (unlikely(schedule_putreq)) {
get_ioctx(ctx);
spin_lock(&fput_lock);
list_add(&req->ki_list, &fput_head);
@@ -571,7 +587,7 @@ int aio_put_req(struct kiocb *req)
static struct kioctx *lookup_ioctx(unsigned long ctx_id)
{
struct mm_struct *mm = current->mm;
- struct kioctx *ctx = NULL;
+ struct kioctx *ctx, *ret = NULL;
struct hlist_node *n;
rcu_read_lock();
@@ -579,12 +595,13 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
if (ctx->user_id == ctx_id && !ctx->dead) {
get_ioctx(ctx);
+ ret = ctx;
break;
}
}
rcu_read_unlock();
- return ctx;
+ return ret;
}
/*
@@ -1009,7 +1026,7 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
* eventfd. The eventfd_signal() function is safe to be called
* from IRQ context.
*/
- if (!IS_ERR(iocb->ki_eventfd))
+ if (iocb->ki_eventfd != NULL)
eventfd_signal(iocb->ki_eventfd, 1);
put_rq:
@@ -1608,6 +1625,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
if (IS_ERR(req->ki_eventfd)) {
ret = PTR_ERR(req->ki_eventfd);
+ req->ki_eventfd = NULL;
goto out_put_req;
}
}
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 549b0144da1..fe2b1aa2464 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -685,19 +685,20 @@ EXPORT_SYMBOL(bio_integrity_split);
* bio_integrity_clone - Callback for cloning bios with integrity metadata
* @bio: New bio
* @bio_src: Original bio
+ * @gfp_mask: Memory allocation mask
* @bs: bio_set to allocate bip from
*
* Description: Called to allocate a bip when cloning a bio
*/
int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
- struct bio_set *bs)
+ gfp_t gfp_mask, struct bio_set *bs)
{
struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
struct bio_integrity_payload *bip;
BUG_ON(bip_src == NULL);
- bip = bio_integrity_alloc_bioset(bio, GFP_NOIO, bip_src->bip_vcnt, bs);
+ bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
if (bip == NULL)
return -EIO;
diff --git a/fs/bio.c b/fs/bio.c
index 124b95c4d58..d4f06327c81 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -463,10 +463,12 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
if (bio_integrity(bio)) {
int ret;
- ret = bio_integrity_clone(b, bio, fs_bio_set);
+ ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
- if (ret < 0)
+ if (ret < 0) {
+ bio_put(b);
return NULL;
+ }
}
return b;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 82491ba8fa4..5e1d4e30e9d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -784,7 +784,14 @@ struct btrfs_fs_info {
struct list_head dirty_cowonly_roots;
struct btrfs_fs_devices *fs_devices;
+
+ /*
+ * the space_info list is almost entirely read only. It only changes
+ * when we add a new raid type to the FS, and that happens
+ * very rarely. RCU is used to protect it.
+ */
struct list_head space_info;
+
spinlock_t delalloc_lock;
spinlock_t new_trans_lock;
u64 delalloc_bytes;
@@ -1797,6 +1804,8 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root);
int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len);
u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
+void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
+
int btrfs_check_metadata_free_space(struct btrfs_root *root);
int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
u64 bytes);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9abf81f71c4..fefe83ad205 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -20,6 +20,7 @@
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/sort.h>
+#include <linux/rcupdate.h>
#include "compat.h"
#include "hash.h"
#include "crc32c.h"
@@ -330,13 +331,33 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
{
struct list_head *head = &info->space_info;
struct btrfs_space_info *found;
- list_for_each_entry(found, head, list) {
- if (found->flags == flags)
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(found, head, list) {
+ if (found->flags == flags) {
+ rcu_read_unlock();
return found;
+ }
}
+ rcu_read_unlock();
return NULL;
}
+/*
+ * after adding space to the filesystem, we need to clear the full flags
+ * on all the space infos.
+ */
+void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
+{
+ struct list_head *head = &info->space_info;
+ struct btrfs_space_info *found;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(found, head, list)
+ found->full = 0;
+ rcu_read_unlock();
+}
+
static u64 div_factor(u64 num, int factor)
{
if (factor == 10)
@@ -1903,7 +1924,6 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
if (!found)
return -ENOMEM;
- list_add(&found->list, &info->space_info);
INIT_LIST_HEAD(&found->block_groups);
init_rwsem(&found->groups_sem);
spin_lock_init(&found->lock);
@@ -1917,6 +1937,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
found->full = 0;
found->force_alloc = 0;
*space_info = found;
+ list_add_rcu(&found->list, &info->space_info);
return 0;
}
@@ -6320,6 +6341,7 @@ out:
int btrfs_free_block_groups(struct btrfs_fs_info *info)
{
struct btrfs_block_group_cache *block_group;
+ struct btrfs_space_info *space_info;
struct rb_node *n;
spin_lock(&info->block_group_cache_lock);
@@ -6341,6 +6363,23 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
spin_lock(&info->block_group_cache_lock);
}
spin_unlock(&info->block_group_cache_lock);
+
+ /* now that all the block groups are freed, go through and
+ * free all the space_info structs. This is only called during
+ * the final stages of unmount, and so we know nobody is
+ * using them. We call synchronize_rcu() once before we start,
+ * just to be on the safe side.
+ */
+ synchronize_rcu();
+
+ while(!list_empty(&info->space_info)) {
+ space_info = list_entry(info->space_info.next,
+ struct btrfs_space_info,
+ list);
+
+ list_del(&space_info->list);
+ kfree(space_info);
+ }
return 0;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1316139bf9e..dd06e18e5aa 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1374,6 +1374,12 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
ret = btrfs_add_device(trans, root, device);
}
+ /*
+ * we've got more storage, clear any full flags on the space
+ * infos
+ */
+ btrfs_clear_space_info_full(root->fs_info);
+
unlock_chunks(root);
btrfs_commit_transaction(trans, root);
@@ -1459,6 +1465,8 @@ static int __btrfs_grow_device(struct btrfs_trans_handle *trans,
device->fs_devices->total_rw_bytes += diff;
device->total_bytes = new_size;
+ btrfs_clear_space_info_full(device->dev_root->fs_info);
+
return btrfs_update_device(trans, device);
}
diff --git a/fs/buffer.c b/fs/buffer.c
index 9f697419ed8..891e1c78e4f 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -760,15 +760,9 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
* If warn is true, then emit a warning if the page is not uptodate and has
* not been truncated.
*/
-static int __set_page_dirty(struct page *page,
+static void __set_page_dirty(struct page *page,
struct address_space *mapping, int warn)
{
- if (unlikely(!mapping))
- return !TestSetPageDirty(page);
-
- if (TestSetPageDirty(page))
- return 0;
-
spin_lock_irq(&mapping->tree_lock);
if (page->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
@@ -785,8 +779,6 @@ static int __set_page_dirty(struct page *page,
}
spin_unlock_irq(&mapping->tree_lock);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-
- return 1;
}
/*
@@ -816,6 +808,7 @@ static int __set_page_dirty(struct page *page,
*/
int __set_page_dirty_buffers(struct page *page)
{
+ int newly_dirty;
struct address_space *mapping = page_mapping(page);
if (unlikely(!mapping))
@@ -831,9 +824,12 @@ int __set_page_dirty_buffers(struct page *page)
bh = bh->b_this_page;
} while (bh != head);
}
+ newly_dirty = !TestSetPageDirty(page);
spin_unlock(&mapping->private_lock);
- return __set_page_dirty(page, mapping, 1);
+ if (newly_dirty)
+ __set_page_dirty(page, mapping, 1);
+ return newly_dirty;
}
EXPORT_SYMBOL(__set_page_dirty_buffers);
@@ -1262,8 +1258,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
return;
}
- if (!test_set_buffer_dirty(bh))
- __set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
+ if (!test_set_buffer_dirty(bh)) {
+ struct page *page = bh->b_page;
+ if (!TestSetPageDirty(page))
+ __set_page_dirty(page, page_mapping(page), 0);
+ }
}
/*
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 5f3231b9633..bff4052b05e 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -198,9 +198,6 @@ static int mknod_ptmx(struct super_block *sb)
fsi->ptmx_dentry = dentry;
rc = 0;
-
- printk(KERN_DEBUG "Created ptmx node in devpts ino %lu\n",
- inode->i_ino);
out:
mutex_unlock(&root->d_inode->i_mutex);
return rc;
@@ -369,8 +366,6 @@ static int new_pts_mount(struct file_system_type *fs_type, int flags,
struct pts_fs_info *fsi;
struct pts_mount_opts *opts;
- printk(KERN_NOTICE "devpts: newinstance mount\n");
-
err = get_sb_nodev(fs_type, flags, data, devpts_fill_super, mnt);
if (err)
return err;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index f6caeb1d110..8b65f289ee0 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -946,6 +946,8 @@ static int ecryptfs_copy_mount_wide_sigs_to_inode_sigs(
list_for_each_entry(global_auth_tok,
&mount_crypt_stat->global_auth_tok_list,
mount_crypt_stat_list) {
+ if (global_auth_tok->flags & ECRYPTFS_AUTH_TOK_FNEK)
+ continue;
rc = ecryptfs_add_keysig(crypt_stat, global_auth_tok->sig);
if (rc) {
printk(KERN_ERR "Error adding keysig; rc = [%d]\n", rc);
@@ -1322,14 +1324,13 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t max,
}
static int
-ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat,
- struct dentry *ecryptfs_dentry,
- char *virt)
+ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry,
+ char *virt, size_t virt_len)
{
int rc;
rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt,
- 0, crypt_stat->num_header_bytes_at_front);
+ 0, virt_len);
if (rc)
printk(KERN_ERR "%s: Error attempting to write header "
"information to lower file; rc = [%d]\n", __func__,
@@ -1339,7 +1340,6 @@ ecryptfs_write_metadata_to_contents(struct ecryptfs_crypt_stat *crypt_stat,
static int
ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry,
- struct ecryptfs_crypt_stat *crypt_stat,
char *page_virt, size_t size)
{
int rc;
@@ -1349,6 +1349,17 @@ ecryptfs_write_metadata_to_xattr(struct dentry *ecryptfs_dentry,
return rc;
}
+static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask,
+ unsigned int order)
+{
+ struct page *page;
+
+ page = alloc_pages(gfp_mask | __GFP_ZERO, order);
+ if (page)
+ return (unsigned long) page_address(page);
+ return 0;
+}
+
/**
* ecryptfs_write_metadata
* @ecryptfs_dentry: The eCryptfs dentry
@@ -1365,7 +1376,9 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
{
struct ecryptfs_crypt_stat *crypt_stat =
&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+ unsigned int order;
char *virt;
+ size_t virt_len;
size_t size = 0;
int rc = 0;
@@ -1381,33 +1394,35 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
rc = -EINVAL;
goto out;
}
+ virt_len = crypt_stat->num_header_bytes_at_front;
+ order = get_order(virt_len);
/* Released in this function */
- virt = (char *)get_zeroed_page(GFP_KERNEL);
+ virt = (char *)ecryptfs_get_zeroed_pages(GFP_KERNEL, order);
if (!virt) {
printk(KERN_ERR "%s: Out of memory\n", __func__);
rc = -ENOMEM;
goto out;
}
- rc = ecryptfs_write_headers_virt(virt, PAGE_CACHE_SIZE, &size,
- crypt_stat, ecryptfs_dentry);
+ rc = ecryptfs_write_headers_virt(virt, virt_len, &size, crypt_stat,
+ ecryptfs_dentry);
if (unlikely(rc)) {
printk(KERN_ERR "%s: Error whilst writing headers; rc = [%d]\n",
__func__, rc);
goto out_free;
}
if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
- rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry,
- crypt_stat, virt, size);
+ rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
+ size);
else
- rc = ecryptfs_write_metadata_to_contents(crypt_stat,
- ecryptfs_dentry, virt);
+ rc = ecryptfs_write_metadata_to_contents(ecryptfs_dentry, virt,
+ virt_len);
if (rc) {
printk(KERN_ERR "%s: Error writing metadata out to lower file; "
"rc = [%d]\n", __func__, rc);
goto out_free;
}
out_free:
- free_page((unsigned long)virt);
+ free_pages((unsigned long)virt, order);
out:
return rc;
}
@@ -2206,17 +2221,19 @@ int ecryptfs_decode_and_decrypt_filename(char **plaintext_name,
struct dentry *ecryptfs_dir_dentry,
const char *name, size_t name_size)
{
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
+ &ecryptfs_superblock_to_private(
+ ecryptfs_dir_dentry->d_sb)->mount_crypt_stat;
char *decoded_name;
size_t decoded_name_size;
size_t packet_size;
int rc = 0;
- if ((name_size > ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)
+ if ((mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
+ && !(mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+ && (name_size > ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE)
&& (strncmp(name, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX,
ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE) == 0)) {
- struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
- &ecryptfs_superblock_to_private(
- ecryptfs_dir_dentry->d_sb)->mount_crypt_stat;
const char *orig_name = name;
size_t orig_name_size = name_size;
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index c11fc95714a..ac749d4d644 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -328,6 +328,7 @@ struct ecryptfs_dentry_info {
*/
struct ecryptfs_global_auth_tok {
#define ECRYPTFS_AUTH_TOK_INVALID 0x00000001
+#define ECRYPTFS_AUTH_TOK_FNEK 0x00000002
u32 flags;
struct list_head mount_crypt_stat_list;
struct key *global_auth_tok_key;
@@ -619,7 +620,6 @@ int ecryptfs_interpose(struct dentry *hidden_dentry,
u32 flags);
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
- struct ecryptfs_crypt_stat *crypt_stat,
struct inode *ecryptfs_dir_inode,
struct nameidata *ecryptfs_nd);
int ecryptfs_decode_and_decrypt_filename(char **decrypted_name,
@@ -696,7 +696,7 @@ ecryptfs_write_header_metadata(char *virt,
int ecryptfs_add_keysig(struct ecryptfs_crypt_stat *crypt_stat, char *sig);
int
ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
- char *sig);
+ char *sig, u32 global_auth_tok_flags);
int ecryptfs_get_global_auth_tok_for_sig(
struct ecryptfs_global_auth_tok **global_auth_tok,
struct ecryptfs_mount_crypt_stat *mount_crypt_stat, char *sig);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 5697899a168..55b3145b807 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -246,7 +246,6 @@ out:
*/
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
- struct ecryptfs_crypt_stat *crypt_stat,
struct inode *ecryptfs_dir_inode,
struct nameidata *ecryptfs_nd)
{
@@ -254,6 +253,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct vfsmount *lower_mnt;
struct inode *lower_inode;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+ struct ecryptfs_crypt_stat *crypt_stat;
char *page_virt = NULL;
u64 file_size;
int rc = 0;
@@ -314,6 +314,11 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
goto out_free_kmem;
}
}
+ crypt_stat = &ecryptfs_inode_to_private(
+ ecryptfs_dentry->d_inode)->crypt_stat;
+ /* TODO: lock for crypt_stat comparison */
+ if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
+ ecryptfs_set_default_sizes(crypt_stat);
rc = ecryptfs_read_and_validate_header_region(page_virt,
ecryptfs_dentry->d_inode);
if (rc) {
@@ -362,9 +367,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
{
char *encrypted_and_encoded_name = NULL;
size_t encrypted_and_encoded_name_size;
- struct ecryptfs_crypt_stat *crypt_stat = NULL;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
- struct ecryptfs_inode_info *inode_info;
struct dentry *lower_dir_dentry, *lower_dentry;
int rc = 0;
@@ -388,26 +391,15 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
}
if (lower_dentry->d_inode)
goto lookup_and_interpose;
- inode_info = ecryptfs_inode_to_private(ecryptfs_dentry->d_inode);
- if (inode_info) {
- crypt_stat = &inode_info->crypt_stat;
- /* TODO: lock for crypt_stat comparison */
- if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
- ecryptfs_set_default_sizes(crypt_stat);
- }
- if (crypt_stat)
- mount_crypt_stat = crypt_stat->mount_crypt_stat;
- else
- mount_crypt_stat = &ecryptfs_superblock_to_private(
- ecryptfs_dentry->d_sb)->mount_crypt_stat;
- if (!(crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCRYPT_FILENAMES))
- && !(mount_crypt_stat && (mount_crypt_stat->flags
- & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)))
+ mount_crypt_stat = &ecryptfs_superblock_to_private(
+ ecryptfs_dentry->d_sb)->mount_crypt_stat;
+ if (!(mount_crypt_stat
+ && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)))
goto lookup_and_interpose;
dput(lower_dentry);
rc = ecryptfs_encrypt_and_encode_filename(
&encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
- crypt_stat, mount_crypt_stat, ecryptfs_dentry->d_name.name,
+ NULL, mount_crypt_stat, ecryptfs_dentry->d_name.name,
ecryptfs_dentry->d_name.len);
if (rc) {
printk(KERN_ERR "%s: Error attempting to encrypt and encode "
@@ -426,7 +418,7 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
}
lookup_and_interpose:
rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry,
- crypt_stat, ecryptfs_dir_inode,
+ ecryptfs_dir_inode,
ecryptfs_nd);
goto out;
out_d_drop:
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index ff539420cc6..e4a6223c314 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -2375,7 +2375,7 @@ struct kmem_cache *ecryptfs_global_auth_tok_cache;
int
ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
- char *sig)
+ char *sig, u32 global_auth_tok_flags)
{
struct ecryptfs_global_auth_tok *new_auth_tok;
int rc = 0;
@@ -2389,6 +2389,7 @@ ecryptfs_add_global_auth_tok(struct ecryptfs_mount_crypt_stat *mount_crypt_stat,
goto out;
}
memcpy(new_auth_tok->sig, sig, ECRYPTFS_SIG_SIZE_HEX);
+ new_auth_tok->flags = global_auth_tok_flags;
new_auth_tok->sig[ECRYPTFS_SIG_SIZE_HEX] = '\0';
mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex);
list_add(&new_auth_tok->mount_crypt_stat_list,
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 789cf2e1be1..aed56c25539 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -319,7 +319,7 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
case ecryptfs_opt_ecryptfs_sig:
sig_src = args[0].from;
rc = ecryptfs_add_global_auth_tok(mount_crypt_stat,
- sig_src);
+ sig_src, 0);
if (rc) {
printk(KERN_ERR "Error attempting to register "
"global sig; rc = [%d]\n", rc);
@@ -370,7 +370,8 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
ECRYPTFS_SIG_SIZE_HEX] = '\0';
rc = ecryptfs_add_global_auth_tok(
mount_crypt_stat,
- mount_crypt_stat->global_default_fnek_sig);
+ mount_crypt_stat->global_default_fnek_sig,
+ ECRYPTFS_AUTH_TOK_FNEK);
if (rc) {
printk(KERN_ERR "Error attempting to register "
"global fnek sig [%s]; rc = [%d]\n",
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e2eab196875..e0aa4fe4f59 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1122,7 +1122,8 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path,
struct ext4_extent_idx *ix;
struct ext4_extent *ex;
ext4_fsblk_t block;
- int depth, ee_len;
+ int depth; /* Note, NOT eh_depth; depth from top of tree */
+ int ee_len;
BUG_ON(path == NULL);
depth = path->p_depth;
@@ -1179,7 +1180,8 @@ got_index:
if (bh == NULL)
return -EIO;
eh = ext_block_hdr(bh);
- if (ext4_ext_check_header(inode, eh, depth)) {
+ /* subtract from p_depth to get proper eh_depth */
+ if (ext4_ext_check_header(inode, eh, path->p_depth - depth)) {
put_bh(bh);
return -EIO;
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 627f8c3337a..2d2b3585ee9 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -698,6 +698,7 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
struct inode *ret;
ext4_group_t i;
int free = 0;
+ static int once = 1;
ext4_group_t flex_group;
/* Cannot create files in a deleted directory */
@@ -719,7 +720,8 @@ struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, int mode)
ret2 = find_group_flex(sb, dir, &group);
if (ret2 == -1) {
ret2 = find_group_other(sb, dir, &group);
- if (ret2 == 0 && printk_ratelimit())
+ if (ret2 == 0 && once)
+ once = 0;
printk(KERN_NOTICE "ext4: find_group_flex "
"failed, fallback succeeded dir %lu\n",
dir->i_ino);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4415beeb0b6..9f61e62f435 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1447,7 +1447,7 @@ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac,
struct ext4_free_extent *gex = &ac->ac_g_ex;
BUG_ON(ex->fe_len <= 0);
- BUG_ON(ex->fe_len >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+ BUG_ON(ex->fe_len > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
BUG_ON(ex->fe_start >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
BUG_ON(ac->ac_status != AC_STATUS_CONTINUE);
@@ -3292,7 +3292,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
}
BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical);
- BUG_ON(size <= 0 || size >= EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
+ BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
@@ -3589,6 +3589,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
struct super_block *sb, struct ext4_prealloc_space *pa)
{
ext4_group_t grp;
+ ext4_fsblk_t grp_blk;
if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
return;
@@ -3603,8 +3604,12 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
pa->pa_deleted = 1;
spin_unlock(&pa->pa_lock);
- /* -1 is to protect from crossing allocation group */
- ext4_get_group_no_and_offset(sb, pa->pa_pstart - 1, &grp, NULL);
+ grp_blk = pa->pa_pstart;
+ /* If linear, pa_pstart may be in the next group when pa is used up */
+ if (pa->pa_linear)
+ grp_blk--;
+
+ ext4_get_group_no_and_offset(sb, grp_blk, &grp, NULL);
/*
* possible race:
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 6b74d09adbe..de0004fe6e0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -202,9 +202,9 @@ static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
sector_t blocknr;
/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
- mutex_lock(&mapping->host->i_mutex);
+ down_read(&mapping->host->i_alloc_sem);
blocknr = generic_block_bmap(mapping, block, fat_get_block);
- mutex_unlock(&mapping->host->i_mutex);
+ up_read(&mapping->host->i_alloc_sem);
return blocknr;
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e5eaa62fd17..e3fe9918faa 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -274,6 +274,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
int ret;
BUG_ON(inode->i_state & I_SYNC);
+ WARN_ON(inode->i_state & I_NEW);
/* Set I_SYNC, reset I_DIRTY */
dirty = inode->i_state & I_DIRTY;
@@ -298,6 +299,7 @@ __sync_single_inode(struct inode *inode, struct writeback_control *wbc)
}
spin_lock(&inode_lock);
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_SYNC;
if (!(inode->i_state & I_FREEING)) {
if (!(inode->i_state & I_DIRTY) &&
@@ -470,6 +472,11 @@ void generic_sync_sb_inodes(struct super_block *sb,
break;
}
+ if (inode->i_state & I_NEW) {
+ requeue_io(inode);
+ continue;
+ }
+
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
if (!sb_is_blkdev_sb(sb))
@@ -531,7 +538,7 @@ void generic_sync_sb_inodes(struct super_block *sb,
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping;
- if (inode->i_state & (I_FREEING|I_WILL_FREE))
+ if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
continue;
mapping = inode->i_mapping;
if (mapping->nrpages == 0)
diff --git a/fs/inode.c b/fs/inode.c
index 913ab2d9a5d..826fb0b9d1c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -359,6 +359,7 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
invalidate_inode_buffers(inode);
if (!atomic_read(&inode->i_count)) {
list_move(&inode->i_list, dispose);
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
count++;
continue;
@@ -460,6 +461,7 @@ static void prune_icache(int nr_to_scan)
continue;
}
list_move(&inode->i_list, &freeable);
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
nr_pruned++;
}
@@ -656,6 +658,7 @@ void unlock_new_inode(struct inode *inode)
* just created it (so there can be no old holders
* that haven't tested I_LOCK).
*/
+ WARN_ON((inode->i_state & (I_LOCK|I_NEW)) != (I_LOCK|I_NEW));
inode->i_state &= ~(I_LOCK|I_NEW);
wake_up_inode(inode);
}
@@ -1145,6 +1148,7 @@ void generic_delete_inode(struct inode *inode)
list_del_init(&inode->i_list);
list_del_init(&inode->i_sb_list);
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
@@ -1186,16 +1190,19 @@ static void generic_forget_inode(struct inode *inode)
spin_unlock(&inode_lock);
return;
}
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_WILL_FREE;
spin_unlock(&inode_lock);
write_inode_now(inode, 1);
spin_lock(&inode_lock);
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state &= ~I_WILL_FREE;
inodes_stat.nr_unused--;
hlist_del_init(&inode->i_hash);
}
list_del_init(&inode->i_list);
list_del_init(&inode->i_sb_list);
+ WARN_ON(inode->i_state & I_NEW);
inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 1f3b0fc0d35..aedc47a264c 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -139,6 +139,55 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
return 0;
}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static const struct in6_addr *nlmclnt_map_v4addr(const struct sockaddr *sap,
+ struct in6_addr *addr_mapped)
+{
+ const struct sockaddr_in *sin = (const struct sockaddr_in *)sap;
+
+ switch (sap->sa_family) {
+ case AF_INET6:
+ return &((const struct sockaddr_in6 *)sap)->sin6_addr;
+ case AF_INET:
+ ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, addr_mapped);
+ return addr_mapped;
+ }
+
+ return NULL;
+}
+
+/*
+ * If lockd is using a PF_INET6 listener, all incoming requests appear
+ * to come from AF_INET6 remotes. The address of AF_INET remotes are
+ * mapped to AF_INET6 automatically by the network layer. In case the
+ * user passed an AF_INET server address at mount time, ensure both
+ * addresses are AF_INET6 before comparing them.
+ */
+static int nlmclnt_cmp_addr(const struct nlm_host *host,
+ const struct sockaddr *sap)
+{
+ const struct in6_addr *addr1;
+ const struct in6_addr *addr2;
+ struct in6_addr addr1_mapped;
+ struct in6_addr addr2_mapped;
+
+ addr1 = nlmclnt_map_v4addr(nlm_addr(host), &addr1_mapped);
+ if (likely(addr1 != NULL)) {
+ addr2 = nlmclnt_map_v4addr(sap, &addr2_mapped);
+ if (likely(addr2 != NULL))
+ return ipv6_addr_equal(addr1, addr2);
+ }
+
+ return 0;
+}
+#else /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+static int nlmclnt_cmp_addr(const struct nlm_host *host,
+ const struct sockaddr *sap)
+{
+ return nlm_cmp_addr(nlm_addr(host), sap);
+}
+#endif /* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+
/*
* The server lockd has called us back to tell us the lock was granted
*/
@@ -166,7 +215,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
*/
if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid)
continue;
- if (!nlm_cmp_addr(nlm_addr(block->b_host), addr))
+ if (!nlmclnt_cmp_addr(block->b_host, addr))
continue;
if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0)
continue;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index d1d1eb84679..618865b3128 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -3,7 +3,7 @@
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
- * Copyright (C) 1996 Gertjan van Wingerde (gertjan@cs.vu.nl)
+ * Copyright (C) 1996 Gertjan van Wingerde
* Minix V2 fs support.
*
* Modified for 680x0 by Andreas Schwab
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9b728f3565a..574158ae239 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -255,6 +255,32 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
}
return 0;
}
+
+/*
+ * Test if two ip6 socket addresses refer to the same socket by
+ * comparing relevant fields. The padding bytes specifically, are not
+ * compared. sin6_flowinfo is not compared because it only affects QoS
+ * and sin6_scope_id is only compared if the address is "link local"
+ * because "link local" addresses need only be unique to a specific
+ * link. Conversely, ordinary unicast addresses might have different
+ * sin6_scope_id.
+ *
+ * The caller should ensure both socket addresses are AF_INET6.
+ */
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
+{
+ const struct sockaddr_in6 *saddr1 = (const struct sockaddr_in6 *)sa1;
+ const struct sockaddr_in6 *saddr2 = (const struct sockaddr_in6 *)sa2;
+
+ if (!ipv6_addr_equal(&saddr1->sin6_addr,
+ &saddr1->sin6_addr))
+ return 0;
+ if (ipv6_addr_scope(&saddr1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL &&
+ saddr1->sin6_scope_id != saddr2->sin6_scope_id)
+ return 0;
+ return saddr1->sin6_port == saddr2->sin6_port;
+}
#else
static int nfs_sockaddr_match_ipaddr4(const struct sockaddr_in *sa1,
const struct sockaddr_in *sa2)
@@ -270,9 +296,52 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
return nfs_sockaddr_match_ipaddr4((const struct sockaddr_in *)sa1,
(const struct sockaddr_in *)sa2);
}
+
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1,
+ const struct sockaddr * sa2)
+{
+ return 0;
+}
#endif
/*
+ * Test if two ip4 socket addresses refer to the same socket, by
+ * comparing relevant fields. The padding bytes specifically, are
+ * not compared.
+ *
+ * The caller should ensure both socket addresses are AF_INET.
+ */
+static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
+{
+ const struct sockaddr_in *saddr1 = (const struct sockaddr_in *)sa1;
+ const struct sockaddr_in *saddr2 = (const struct sockaddr_in *)sa2;
+
+ if (saddr1->sin_addr.s_addr != saddr2->sin_addr.s_addr)
+ return 0;
+ return saddr1->sin_port == saddr2->sin_port;
+}
+
+/*
+ * Test if two socket addresses represent the same actual socket,
+ * by comparing (only) relevant fields.
+ */
+static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
+ const struct sockaddr *sa2)
+{
+ if (sa1->sa_family != sa2->sa_family)
+ return 0;
+
+ switch (sa1->sa_family) {
+ case AF_INET:
+ return nfs_sockaddr_cmp_ip4(sa1, sa2);
+ case AF_INET6:
+ return nfs_sockaddr_cmp_ip6(sa1, sa2);
+ }
+ return 0;
+}
+
+/*
* Find a client by IP address and protocol version
* - returns NULL if no such client
*/
@@ -344,8 +413,10 @@ struct nfs_client *nfs_find_client_next(struct nfs_client *clp)
static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data)
{
struct nfs_client *clp;
+ const struct sockaddr *sap = data->addr;
list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+ const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
/* Don't match clients that failed to initialise properly */
if (clp->cl_cons_state < 0)
continue;
@@ -358,7 +429,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
continue;
/* Match the full socket address */
- if (memcmp(&clp->cl_addr, data->addr, sizeof(clp->cl_addr)) != 0)
+ if (!nfs_sockaddr_cmp(sap, clap))
continue;
atomic_inc(&clp->cl_count);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e35c8199f82..672368f865c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1892,8 +1892,14 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
cache.cred = cred;
cache.jiffies = jiffies;
status = NFS_PROTO(inode)->access(inode, &cache);
- if (status != 0)
+ if (status != 0) {
+ if (status == -ESTALE) {
+ nfs_zap_caches(inode);
+ if (!S_ISDIR(inode->i_mode))
+ set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
+ }
return status;
+ }
nfs_access_add_cache(inode, &cache);
out:
if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index cef62557c87..6bbf0e6daad 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -292,7 +292,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_fattr fattr;
- struct page *pages[NFSACL_MAXPAGES] = { };
+ struct page *pages[NFSACL_MAXPAGES];
struct nfs3_setaclargs args = {
.inode = inode,
.mask = NFS_ACL,
@@ -303,7 +303,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
.rpc_argp = &args,
.rpc_resp = &fattr,
};
- int status, count;
+ int status;
status = -EOPNOTSUPP;
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
@@ -319,6 +319,20 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
if (S_ISDIR(inode->i_mode)) {
args.mask |= NFS_DFACL;
args.acl_default = dfacl;
+ args.len = nfsacl_size(acl, dfacl);
+ } else
+ args.len = nfsacl_size(acl, NULL);
+
+ if (args.len > NFS_ACL_INLINE_BUFSIZE) {
+ unsigned int npages = 1 + ((args.len - 1) >> PAGE_SHIFT);
+
+ status = -ENOMEM;
+ do {
+ args.pages[args.npages] = alloc_page(GFP_KERNEL);
+ if (args.pages[args.npages] == NULL)
+ goto out_freepages;
+ args.npages++;
+ } while (args.npages < npages);
}
dprintk("NFS call setacl\n");
@@ -329,10 +343,6 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
nfs_zap_acl_cache(inode);
dprintk("NFS reply setacl: %d\n", status);
- /* pages may have been allocated at the xdr layer. */
- for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++)
- __free_page(args.pages[count]);
-
switch (status) {
case 0:
status = nfs_refresh_inode(inode, &fattr);
@@ -346,6 +356,11 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
case -ENOTSUPP:
status = -EOPNOTSUPP;
}
+out_freepages:
+ while (args.npages != 0) {
+ args.npages--;
+ __free_page(args.pages[args.npages]);
+ }
out:
return status;
}
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 11cdddec143..6cdeacffde4 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -82,8 +82,10 @@
#define NFS3_commitres_sz (1+NFS3_wcc_data_sz+2)
#define ACL3_getaclargs_sz (NFS3_fh_sz+1)
-#define ACL3_setaclargs_sz (NFS3_fh_sz+1+2*(2+5*3))
-#define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+2*(2+5*3))
+#define ACL3_setaclargs_sz (NFS3_fh_sz+1+ \
+ XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
+#define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+ \
+ XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
#define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz)
/*
@@ -703,28 +705,18 @@ nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p,
struct nfs3_setaclargs *args)
{
struct xdr_buf *buf = &req->rq_snd_buf;
- unsigned int base, len_in_head, len = nfsacl_size(
- (args->mask & NFS_ACL) ? args->acl_access : NULL,
- (args->mask & NFS_DFACL) ? args->acl_default : NULL);
- int count, err;
+ unsigned int base;
+ int err;
p = xdr_encode_fhandle(p, NFS_FH(args->inode));
*p++ = htonl(args->mask);
- base = (char *)p - (char *)buf->head->iov_base;
- /* put as much of the acls into head as possible. */
- len_in_head = min_t(unsigned int, buf->head->iov_len - base, len);
- len -= len_in_head;
- req->rq_slen = xdr_adjust_iovec(req->rq_svec, p + (len_in_head >> 2));
-
- for (count = 0; (count << PAGE_SHIFT) < len; count++) {
- args->pages[count] = alloc_page(GFP_KERNEL);
- if (!args->pages[count]) {
- while (count)
- __free_page(args->pages[--count]);
- return -ENOMEM;
- }
- }
- xdr_encode_pages(buf, args->pages, 0, len);
+ req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+ base = req->rq_slen;
+
+ if (args->npages != 0)
+ xdr_encode_pages(buf, args->pages, 0, args->len);
+ else
+ req->rq_slen += args->len;
err = nfsacl_encode(buf, base, args->inode,
(args->mask & NFS_ACL) ?
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 30befc39b3c..2a2a0a7143a 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -21,7 +21,9 @@
#define NFSDBG_FACILITY NFSDBG_VFS
/*
- * Check if fs_root is valid
+ * Convert the NFSv4 pathname components into a standard posix path.
+ *
+ * Note that the resulting string will be placed at the end of the buffer
*/
static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname,
char *buffer, ssize_t buflen)
@@ -99,21 +101,20 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
{
struct vfsmount *mnt = ERR_PTR(-ENOENT);
char *mnt_path;
- int page2len;
+ unsigned int maxbuflen;
unsigned int s;
mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
if (IS_ERR(mnt_path))
return mnt;
mountdata->mnt_path = mnt_path;
- page2 += strlen(mnt_path) + 1;
- page2len = PAGE_SIZE - strlen(mnt_path) - 1;
+ maxbuflen = mnt_path - 1 - page2;
for (s = 0; s < location->nservers; s++) {
const struct nfs4_string *buf = &location->servers[s];
struct sockaddr_storage addr;
- if (buf->len <= 0 || buf->len >= PAGE_SIZE)
+ if (buf->len <= 0 || buf->len >= maxbuflen)
continue;
mountdata->addr = (struct sockaddr *)&addr;
@@ -126,8 +127,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
continue;
nfs_set_port(mountdata->addr, NFS_PORT);
- strncpy(page2, buf->data, page2len);
- page2[page2len] = '\0';
+ memcpy(page2, buf->data, buf->len);
+ page2[buf->len] = '\0';
mountdata->hostname = page2;
snprintf(page, PAGE_SIZE, "%s:%s",
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index f65953be39c..9250067943d 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2596,6 +2596,7 @@ static nfsd4_enc nfsd4_enc_ops[] = {
[OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop,
[OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop,
[OP_OPEN] = (nfsd4_enc)nfsd4_encode_open,
+ [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop,
[OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm,
[OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade,
[OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 3a9e5deed74..19e3a96aa02 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -176,7 +176,8 @@ static int ocfs2_dinode_insert_check(struct inode *inode,
BUG_ON(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL);
mlog_bug_on_msg(!ocfs2_sparse_alloc(osb) &&
- (OCFS2_I(inode)->ip_clusters != rec->e_cpos),
+ (OCFS2_I(inode)->ip_clusters !=
+ le32_to_cpu(rec->e_cpos)),
"Device %s, asking for sparse allocation: inode %llu, "
"cpos %u, clusters %u\n",
osb->dev_str,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index a067a6cffb0..8e1709a679b 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -227,7 +227,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
size = i_size_read(inode);
if (size > PAGE_CACHE_SIZE ||
- size > ocfs2_max_inline_data(inode->i_sb)) {
+ size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
ocfs2_error(inode->i_sb,
"Inode %llu has with inline data has bad size: %Lu",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1555,6 +1555,7 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
int ret, written = 0;
loff_t end = pos + len;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct ocfs2_dinode *di = NULL;
mlog(0, "Inode %llu, write of %u bytes at off %llu. features: 0x%x\n",
(unsigned long long)oi->ip_blkno, len, (unsigned long long)pos,
@@ -1587,7 +1588,9 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
/*
* Check whether the write can fit.
*/
- if (mmap_page || end > ocfs2_max_inline_data(inode->i_sb))
+ di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
+ if (mmap_page ||
+ end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di))
return 0;
do_inline_write:
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 084aba86c3b..4b11762f249 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -532,7 +532,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL);
- fe->id2.i_data.id_count = cpu_to_le16(ocfs2_max_inline_data(osb->sb));
+ fe->id2.i_data.id_count = cpu_to_le16(
+ ocfs2_max_inline_data_with_xattr(osb->sb, fe));
} else {
fel = &fe->id2.i_list;
fel->l_tree_depth = 0;
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index c7ae45aaa36..2332ef740f4 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -1070,12 +1070,6 @@ static inline int ocfs2_fast_symlink_chars(struct super_block *sb)
offsetof(struct ocfs2_dinode, id2.i_symlink);
}
-static inline int ocfs2_max_inline_data(struct super_block *sb)
-{
- return sb->s_blocksize -
- offsetof(struct ocfs2_dinode, id2.i_data.id_data);
-}
-
static inline int ocfs2_max_inline_data_with_xattr(struct super_block *sb,
struct ocfs2_dinode *di)
{
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 4ddd788add6..2563df89fc2 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -547,8 +547,12 @@ int ocfs2_calc_xattr_init(struct inode *dir,
* when blocksize = 512, may reserve one more cluser for
* xattr bucket, otherwise reserve one metadata block
* for them is ok.
+ * If this is a new directory with inline data,
+ * we choose to reserve the entire inline area for
+ * directory contents and force an external xattr block.
*/
if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE ||
+ (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) ||
(s_size + a_size) > OCFS2_XATTR_FREE_IN_IBODY) {
ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac);
if (ret) {
@@ -4791,19 +4795,33 @@ static int ocfs2_xattr_bucket_set_value_outside(struct inode *inode,
char *val,
int value_len)
{
- int offset;
+ int ret, offset, block_off;
struct ocfs2_xattr_value_root *xv;
struct ocfs2_xattr_entry *xe = xs->here;
+ struct ocfs2_xattr_header *xh = bucket_xh(xs->bucket);
+ void *base;
BUG_ON(!xs->base || !xe || ocfs2_xattr_is_local(xe));
- offset = le16_to_cpu(xe->xe_name_offset) +
- OCFS2_XATTR_SIZE(xe->xe_name_len);
+ ret = ocfs2_xattr_bucket_get_name_value(inode, xh,
+ xe - xh->xh_entries,
+ &block_off,
+ &offset);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
- xv = (struct ocfs2_xattr_value_root *)(xs->base + offset);
+ base = bucket_block(xs->bucket, block_off);
+ xv = (struct ocfs2_xattr_value_root *)(base + offset +
+ OCFS2_XATTR_SIZE(xe->xe_name_len));
- return __ocfs2_xattr_set_value_outside(inode, handle,
- xv, val, value_len);
+ ret = __ocfs2_xattr_set_value_outside(inode, handle,
+ xv, val, value_len);
+ if (ret)
+ mlog_errno(ret);
+out:
+ return ret;
}
static int ocfs2_rm_xattr_cluster(struct inode *inode,
diff --git a/fs/pipe.c b/fs/pipe.c
index 3a48ba5179d..14f502b89cf 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -699,12 +699,12 @@ pipe_rdwr_fasync(int fd, struct file *filp, int on)
int retval;
mutex_lock(&inode->i_mutex);
-
retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
-
- if (retval >= 0)
+ if (retval >= 0) {
retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
-
+ if (retval < 0) /* this can happen only if on == T */
+ fasync_helper(-1, filp, 0, &pipe->fasync_readers);
+ }
mutex_unlock(&inode->i_mutex);
if (retval < 0)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0c9de19a163..beaa0ce3b82 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3066,7 +3066,6 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
int retval = -ENOENT;
ino_t ino;
int tid;
- unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */
struct pid_namespace *ns;
task = get_proc_task(inode);
@@ -3083,18 +3082,18 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
goto out_no_task;
retval = 0;
- switch (pos) {
+ switch ((unsigned long)filp->f_pos) {
case 0:
ino = inode->i_ino;
- if (filldir(dirent, ".", 1, pos, ino, DT_DIR) < 0)
+ if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) < 0)
goto out;
- pos++;
+ filp->f_pos++;
/* fall through */
case 1:
ino = parent_ino(dentry);
- if (filldir(dirent, "..", 2, pos, ino, DT_DIR) < 0)
+ if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) < 0)
goto out;
- pos++;
+ filp->f_pos++;
/* fall through */
}
@@ -3104,9 +3103,9 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
ns = filp->f_dentry->d_sb->s_fs_info;
tid = (int)filp->f_version;
filp->f_version = 0;
- for (task = first_tid(leader, tid, pos - 2, ns);
+ for (task = first_tid(leader, tid, filp->f_pos - 2, ns);
task;
- task = next_tid(task), pos++) {
+ task = next_tid(task), filp->f_pos++) {
tid = task_pid_nr_ns(task, ns);
if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) {
/* returning this tgid failed, save it as the first
@@ -3117,7 +3116,6 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
}
}
out:
- filp->f_pos = pos;
put_task_struct(leader);
out_no_task:
return retval;
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 2d1345112a4..e9983837d08 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -80,7 +80,7 @@ static const struct file_operations proc_kpagecount_operations = {
#define KPF_RECLAIM 9
#define KPF_BUDDY 10
-#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos)
+#define kpf_copy_bit(flags, dstpos, srcpos) (((flags >> srcpos) & 1) << dstpos)
static ssize_t kpageflags_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index b9b567a2837..5d7c7ececa6 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -114,6 +114,9 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
if (!pagevec_add(&lru_pvec, page))
__pagevec_lru_add_file(&lru_pvec);
+ /* prevent the page from being discarded on memory pressure */
+ SetPageDirty(page);
+
unlock_page(page);
}
@@ -126,6 +129,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
return -EFBIG;
add_error:
+ pagevec_lru_add_file(&lru_pvec);
page_cache_release(pages + loop);
for (loop++; loop < npages; loop++)
__free_page(pages + loop);
diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c
index 321728f48f2..2a796031034 100644
--- a/fs/squashfs/block.c
+++ b/fs/squashfs/block.c
@@ -184,15 +184,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
offset = 0;
}
- if (msblk->stream.avail_out == 0) {
- if (page == pages) {
- ERROR("zlib_inflate tried to "
- "decompress too much data, "
- "expected %d bytes. Zlib "
- "data probably corrupt\n",
- srclength);
- goto release_mutex;
- }
+ if (msblk->stream.avail_out == 0 && page < pages) {
msblk->stream.next_out = buffer[page++];
msblk->stream.avail_out = PAGE_CACHE_SIZE;
}
@@ -209,25 +201,20 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index,
zlib_init = 1;
}
- zlib_err = zlib_inflate(&msblk->stream, Z_NO_FLUSH);
+ zlib_err = zlib_inflate(&msblk->stream, Z_SYNC_FLUSH);
if (msblk->stream.avail_in == 0 && k < b)
put_bh(bh[k++]);
} while (zlib_err == Z_OK);
if (zlib_err != Z_STREAM_END) {
- ERROR("zlib_inflate returned unexpected result"
- " 0x%x, srclength %d, avail_in %d,"
- " avail_out %d\n", zlib_err, srclength,
- msblk->stream.avail_in,
- msblk->stream.avail_out);
+ ERROR("zlib_inflate error, data probably corrupt\n");
goto release_mutex;
}
zlib_err = zlib_inflateEnd(&msblk->stream);
if (zlib_err != Z_OK) {
- ERROR("zlib_inflateEnd returned unexpected result 0x%x,"
- " srclength %d\n", zlib_err, srclength);
+ ERROR("zlib_inflate error, data probably corrupt\n");
goto release_mutex;
}
length = msblk->stream.total_out;
diff --git a/fs/super.c b/fs/super.c
index 8349ed6b141..6ce501447ad 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -371,8 +371,10 @@ retry:
continue;
if (!grab_super(old))
goto retry;
- if (s)
+ if (s) {
+ up_write(&s->s_umount);
destroy_super(s);
+ }
return old;
}
}
@@ -387,6 +389,7 @@ retry:
err = set(s, data);
if (err) {
spin_unlock(&sb_lock);
+ up_write(&s->s_umount);
destroy_super(s);
return ERR_PTR(err);
}
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index e65212dfb60..261a1c2f22d 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -41,7 +41,7 @@
* Stefan Reinauer <stepan@home.culture.mipt.ru>
*
* Module usage counts added on 96/04/29 by
- * Gertjan van Wingerde <gertjan@cs.vu.nl>
+ * Gertjan van Wingerde <gwingerde@gmail.com>
*
* Clean swab support on 19970406 by
* Francois-Rene Rideau <fare@tunes.org>
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index cb329edc925..aa1016bb913 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -34,6 +34,12 @@
#include <linux/backing-dev.h>
#include <linux/freezer.h>
+#include "xfs_sb.h"
+#include "xfs_inum.h"
+#include "xfs_ag.h"
+#include "xfs_dmapi.h"
+#include "xfs_mount.h"
+
static kmem_zone_t *xfs_buf_zone;
STATIC int xfsbufd(void *);
STATIC int xfsbufd_wakeup(int, gfp_t);
@@ -1435,10 +1441,12 @@ xfs_unregister_buftarg(
void
xfs_free_buftarg(
- xfs_buftarg_t *btp)
+ struct xfs_mount *mp,
+ struct xfs_buftarg *btp)
{
xfs_flush_buftarg(btp, 1);
- xfs_blkdev_issue_flush(btp);
+ if (mp->m_flags & XFS_MOUNT_BARRIER)
+ xfs_blkdev_issue_flush(btp);
xfs_free_bufhash(btp);
iput(btp->bt_mapping->host);
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 288ae7c4c80..9b4d666ad31 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -413,7 +413,7 @@ static inline int XFS_bwrite(xfs_buf_t *bp)
* Handling of buftargs.
*/
extern xfs_buftarg_t *xfs_alloc_buftarg(struct block_device *, int);
-extern void xfs_free_buftarg(xfs_buftarg_t *);
+extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index c71e226da7f..32ae5028e96 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -734,15 +734,15 @@ xfs_close_devices(
{
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
- xfs_free_buftarg(mp->m_logdev_targp);
+ xfs_free_buftarg(mp, mp->m_logdev_targp);
xfs_blkdev_put(logdev);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
- xfs_free_buftarg(mp->m_rtdev_targp);
+ xfs_free_buftarg(mp, mp->m_rtdev_targp);
xfs_blkdev_put(rtdev);
}
- xfs_free_buftarg(mp->m_ddev_targp);
+ xfs_free_buftarg(mp, mp->m_ddev_targp);
}
/*
@@ -811,9 +811,9 @@ xfs_open_devices(
out_free_rtdev_targ:
if (mp->m_rtdev_targp)
- xfs_free_buftarg(mp->m_rtdev_targp);
+ xfs_free_buftarg(mp, mp->m_rtdev_targp);
out_free_ddev_targ:
- xfs_free_buftarg(mp->m_ddev_targp);
+ xfs_free_buftarg(mp, mp->m_ddev_targp);
out_close_rtdev:
if (rtdev)
xfs_blkdev_put(rtdev);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index e2fb6210d4c..478e587087f 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -246,9 +246,6 @@ xfs_iget_cache_miss(
goto out_destroy;
}
- if (lock_flags)
- xfs_ilock(ip, lock_flags);
-
/*
* Preload the radix tree so we can insert safely under the
* write spinlock. Note that we cannot sleep inside the preload
@@ -256,7 +253,16 @@ xfs_iget_cache_miss(
*/
if (radix_tree_preload(GFP_KERNEL)) {
error = EAGAIN;
- goto out_unlock;
+ goto out_destroy;
+ }
+
+ /*
+ * Because the inode hasn't been added to the radix-tree yet it can't
+ * be found by another thread, so we can do the non-sleeping lock here.
+ */
+ if (lock_flags) {
+ if (!xfs_ilock_nowait(ip, lock_flags))
+ BUG();
}
mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
@@ -284,7 +290,6 @@ xfs_iget_cache_miss(
out_preload_end:
write_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
-out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b1047de2fff..61af610d79b 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1455,10 +1455,19 @@ xlog_recover_add_to_trans(
item = item->ri_prev;
if (item->ri_total == 0) { /* first region to be added */
- item->ri_total = in_f->ilf_size;
- ASSERT(item->ri_total <= XLOG_MAX_REGIONS_IN_ITEM);
- item->ri_buf = kmem_zalloc((item->ri_total *
- sizeof(xfs_log_iovec_t)), KM_SLEEP);
+ if (in_f->ilf_size == 0 ||
+ in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
+ xlog_warn(
+ "XFS: bad number of regions (%d) in inode log format",
+ in_f->ilf_size);
+ ASSERT(0);
+ return XFS_ERROR(EIO);
+ }
+
+ item->ri_total = in_f->ilf_size;
+ item->ri_buf =
+ kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
+ KM_SLEEP);
}
ASSERT(item->ri_total > item->ri_cnt);
/* Description region is ri_buf[0] */