summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/vfs_file.c2
-rw-r--r--fs/block_dev.c3
-rw-r--r--fs/cifs/cifssmb.c19
-rw-r--r--fs/ecryptfs/inode.c108
-rw-r--r--fs/ecryptfs/super.c1
-rw-r--r--fs/ext4/ext4.h6
-rw-r--r--fs/ext4/extents.c2
-rw-r--r--fs/ext4/inode.c2
-rw-r--r--fs/fat/namei_vfat.c6
-rw-r--r--fs/nfs/client.c3
-rw-r--r--fs/nfs/dir.c2
-rw-r--r--fs/nfs/nfs4proc.c4
-rw-r--r--fs/nfsd/nfs4xdr.c12
-rw-r--r--fs/ocfs2/acl.c77
-rw-r--r--fs/ocfs2/suballoc.c13
-rw-r--r--fs/proc/base.c5
-rw-r--r--fs/quota/dquot.c12
-rw-r--r--fs/reiserfs/super.c10
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c93
-rw-r--r--fs/xfs/linux-2.6/xfs_sync.c10
-rw-r--r--fs/xfs/xfs_iget.c19
21 files changed, 267 insertions, 142 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 74a0461a9ac0..92f9590429b2 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -114,7 +114,7 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
P9_DPRINTK(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
/* No mandatory locks */
- if (__mandatory_lock(inode))
+ if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
return -ENOLCK;
if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index d11d0289f3d2..8db62b2b6df8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -404,7 +404,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
* NULL first argument is nfsd_sync_dir() and that's not a directory.
*/
-static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
+int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
{
struct block_device *bdev = I_BDEV(filp->f_mapping->host);
int error;
@@ -418,6 +418,7 @@ static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
error = 0;
return error;
}
+EXPORT_SYMBOL(block_fsync);
/*
* pseudo-fs
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 63de4d6a8756..bc3114cb10de 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1430,6 +1430,8 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
__u32 bytes_sent;
__u16 byte_count;
+ *nbytes = 0;
+
/* cFYI(1, ("write at %lld %d bytes", offset, count));*/
if (tcon->ses == NULL)
return -ECONNABORTED;
@@ -1512,11 +1514,18 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
cifs_stats_inc(&tcon->num_writes);
if (rc) {
cFYI(1, ("Send error in write = %d", rc));
- *nbytes = 0;
} else {
*nbytes = le16_to_cpu(pSMBr->CountHigh);
*nbytes = (*nbytes) << 16;
*nbytes += le16_to_cpu(pSMBr->Count);
+
+ /*
+ * Mask off high 16 bits when bytes written as returned by the
+ * server is greater than bytes requested by the client. Some
+ * OS/2 servers are known to set incorrect CountHigh values.
+ */
+ if (*nbytes > count)
+ *nbytes &= 0xFFFF;
}
cifs_buf_release(pSMB);
@@ -1605,6 +1614,14 @@ CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon,
*nbytes = le16_to_cpu(pSMBr->CountHigh);
*nbytes = (*nbytes) << 16;
*nbytes += le16_to_cpu(pSMBr->Count);
+
+ /*
+ * Mask off high 16 bits when bytes written as returned by the
+ * server is greater than bytes requested by the client. OS/2
+ * servers are known to set incorrect CountHigh values.
+ */
+ if (*nbytes > count)
+ *nbytes &= 0xFFFF;
}
/* cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4a430ab4115c..23dc2af56dc6 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -647,38 +647,17 @@ out_lock:
return rc;
}
-static int
-ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+static int ecryptfs_readlink_lower(struct dentry *dentry, char **buf,
+ size_t *bufsiz)
{
+ struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
char *lower_buf;
- size_t lower_bufsiz;
- struct dentry *lower_dentry;
- struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
- char *plaintext_name;
- size_t plaintext_name_size;
+ size_t lower_bufsiz = PATH_MAX;
mm_segment_t old_fs;
int rc;
- lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!lower_dentry->d_inode->i_op->readlink) {
- rc = -EINVAL;
- goto out;
- }
- mount_crypt_stat = &ecryptfs_superblock_to_private(
- dentry->d_sb)->mount_crypt_stat;
- /*
- * If the lower filename is encrypted, it will result in a significantly
- * longer name. If needed, truncate the name after decode and decrypt.
- */
- if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
- lower_bufsiz = PATH_MAX;
- else
- lower_bufsiz = bufsiz;
- /* Released in this function */
lower_buf = kmalloc(lower_bufsiz, GFP_KERNEL);
- if (lower_buf == NULL) {
- printk(KERN_ERR "%s: Out of memory whilst attempting to "
- "kmalloc [%zd] bytes\n", __func__, lower_bufsiz);
+ if (!lower_buf) {
rc = -ENOMEM;
goto out;
}
@@ -688,29 +667,31 @@ ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
(char __user *)lower_buf,
lower_bufsiz);
set_fs(old_fs);
- if (rc >= 0) {
- rc = ecryptfs_decode_and_decrypt_filename(&plaintext_name,
- &plaintext_name_size,
- dentry, lower_buf,
- rc);
- if (rc) {
- printk(KERN_ERR "%s: Error attempting to decode and "
- "decrypt filename; rc = [%d]\n", __func__,
- rc);
- goto out_free_lower_buf;
- }
- /* Check for bufsiz <= 0 done in sys_readlinkat() */
- rc = copy_to_user(buf, plaintext_name,
- min((size_t) bufsiz, plaintext_name_size));
- if (rc)
- rc = -EFAULT;
- else
- rc = plaintext_name_size;
- kfree(plaintext_name);
- fsstack_copy_attr_atime(dentry->d_inode, lower_dentry->d_inode);
- }
-out_free_lower_buf:
+ if (rc < 0)
+ goto out;
+ lower_bufsiz = rc;
+ rc = ecryptfs_decode_and_decrypt_filename(buf, bufsiz, dentry,
+ lower_buf, lower_bufsiz);
+out:
kfree(lower_buf);
+ return rc;
+}
+
+static int
+ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+ char *kbuf;
+ size_t kbufsiz, copied;
+ int rc;
+
+ rc = ecryptfs_readlink_lower(dentry, &kbuf, &kbufsiz);
+ if (rc)
+ goto out;
+ copied = min_t(size_t, bufsiz, kbufsiz);
+ rc = copy_to_user(buf, kbuf, copied) ? -EFAULT : copied;
+ kfree(kbuf);
+ fsstack_copy_attr_atime(dentry->d_inode,
+ ecryptfs_dentry_to_lower(dentry)->d_inode);
out:
return rc;
}
@@ -1015,6 +996,28 @@ out:
return rc;
}
+int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+ int rc = 0;
+
+ mount_crypt_stat = &ecryptfs_superblock_to_private(
+ dentry->d_sb)->mount_crypt_stat;
+ generic_fillattr(dentry->d_inode, stat);
+ if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
+ char *target;
+ size_t targetsiz;
+
+ rc = ecryptfs_readlink_lower(dentry, &target, &targetsiz);
+ if (!rc) {
+ kfree(target);
+ stat->size = targetsiz;
+ }
+ }
+ return rc;
+}
+
int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
@@ -1039,7 +1042,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
lower_dentry = ecryptfs_dentry_to_lower(dentry);
if (!lower_dentry->d_inode->i_op->setxattr) {
- rc = -ENOSYS;
+ rc = -EOPNOTSUPP;
goto out;
}
mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1057,7 +1060,7 @@ ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
int rc = 0;
if (!lower_dentry->d_inode->i_op->getxattr) {
- rc = -ENOSYS;
+ rc = -EOPNOTSUPP;
goto out;
}
mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1084,7 +1087,7 @@ ecryptfs_listxattr(struct dentry *dentry, char *list, size_t size)
lower_dentry = ecryptfs_dentry_to_lower(dentry);
if (!lower_dentry->d_inode->i_op->listxattr) {
- rc = -ENOSYS;
+ rc = -EOPNOTSUPP;
goto out;
}
mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1101,7 +1104,7 @@ static int ecryptfs_removexattr(struct dentry *dentry, const char *name)
lower_dentry = ecryptfs_dentry_to_lower(dentry);
if (!lower_dentry->d_inode->i_op->removexattr) {
- rc = -ENOSYS;
+ rc = -EOPNOTSUPP;
goto out;
}
mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1132,6 +1135,7 @@ const struct inode_operations ecryptfs_symlink_iops = {
.put_link = ecryptfs_put_link,
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
+ .getattr = ecryptfs_getattr_link,
.setxattr = ecryptfs_setxattr,
.getxattr = ecryptfs_getxattr,
.listxattr = ecryptfs_listxattr,
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index b15a43a80ab7..1a037f77aa52 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -85,7 +85,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
if (lower_dentry->d_inode) {
fput(inode_info->lower_file);
inode_info->lower_file = NULL;
- d_drop(lower_dentry);
}
}
ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 874d169a193e..602d5ad6f5e7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -139,8 +139,8 @@ typedef struct ext4_io_end {
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
int error; /* I/O error code */
- ext4_lblk_t offset; /* offset in the file */
- size_t size; /* size of the extent */
+ loff_t offset; /* offset in the file */
+ ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
} ext4_io_end_t;
@@ -1744,7 +1744,7 @@ extern void ext4_ext_release(struct super_block *);
extern long ext4_fallocate(struct inode *inode, int mode, loff_t offset,
loff_t len);
extern int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len);
+ ssize_t len);
extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
sector_t block, unsigned int max_blocks,
struct buffer_head *bh, int flags);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 765a4826b118..c56877972b0e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3603,7 +3603,7 @@ retry:
* Returns 0 on success.
*/
int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
- loff_t len)
+ ssize_t len)
{
handle_t *handle;
ext4_lblk_t block;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 89dbb3874943..c16c3b92d8da 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3551,7 +3551,7 @@ static int ext4_end_aio_dio_nolock(ext4_io_end_t *io)
{
struct inode *inode = io->inode;
loff_t offset = io->offset;
- size_t size = io->size;
+ ssize_t size = io->size;
int ret = 0;
ext4_debug("end_aio_dio_onlock: io 0x%p from inode %lu,list->next 0x%p,"
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index f565f24019b5..72646e2c0f48 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -309,7 +309,7 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
{
struct fat_mount_options *opts = &MSDOS_SB(dir->i_sb)->options;
wchar_t *ip, *ext_start, *end, *name_start;
- unsigned char base[9], ext[4], buf[8], *p;
+ unsigned char base[9], ext[4], buf[5], *p;
unsigned char charbuf[NLS_MAX_CHARSET_SIZE];
int chl, chi;
int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen;
@@ -467,7 +467,7 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
return 0;
}
- i = jiffies & 0xffff;
+ i = jiffies;
sz = (jiffies >> 16) & 0x7;
if (baselen > 2) {
baselen = numtail2_baselen;
@@ -476,7 +476,7 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
name_res[baselen + 4] = '~';
name_res[baselen + 5] = '1' + sz;
while (1) {
- sprintf(buf, "%04X", i);
+ snprintf(buf, sizeof(buf), "%04X", i & 0xffff);
memcpy(&name_res[baselen], buf, 4);
if (vfat_find_form(dir, name_res) < 0)
break;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ee77713ce68b..bd39abc51508 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1293,7 +1293,8 @@ static int nfs4_init_server(struct nfs_server *server,
/* Initialise the client representation from the mount data */
server->flags = data->flags;
- server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
+ server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|
+ NFS_CAP_POSIX_LOCK;
server->options = data->options;
/* Get a client record */
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8b5382efd454..af6948d6faf2 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1025,12 +1025,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
res = NULL;
goto out;
/* This turned out not to be a regular file */
+ case -EISDIR:
case -ENOTDIR:
goto no_open;
case -ELOOP:
if (!(nd->intent.open.flags & O_NOFOLLOW))
goto no_open;
- /* case -EISDIR: */
/* case -EINVAL: */
default:
goto out;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 375f0fae2c6a..ecf660204755 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1520,6 +1520,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
nfs_post_op_update_inode(dir, o_res->dir_attr);
} else
nfs_refresh_inode(dir, o_res->dir_attr);
+ if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
+ server->caps &= ~NFS_CAP_POSIX_LOCK;
if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
status = _nfs4_proc_open_confirm(data);
if (status != 0)
@@ -1660,7 +1662,7 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
status = PTR_ERR(state);
if (IS_ERR(state))
goto err_opendata_put;
- if ((opendata->o_res.rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) != 0)
+ if (server->caps & NFS_CAP_POSIX_LOCK)
set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
nfs4_opendata_put(opendata);
nfs4_put_state_owner(sp);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index a8587e90fd5a..bbf72d8f9fc0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2121,9 +2121,15 @@ out_acl:
* and this is the root of a cross-mounted filesystem.
*/
if (ignore_crossmnt == 0 &&
- exp->ex_path.mnt->mnt_root->d_inode == dentry->d_inode) {
- err = vfs_getattr(exp->ex_path.mnt->mnt_parent,
- exp->ex_path.mnt->mnt_mountpoint, &stat);
+ dentry == exp->ex_path.mnt->mnt_root) {
+ struct path path = exp->ex_path;
+ path_get(&path);
+ while (follow_up(&path)) {
+ if (path.dentry != path.mnt->mnt_root)
+ break;
+ }
+ err = vfs_getattr(path.mnt, path.dentry, &stat);
+ path_put(&path);
if (err)
goto out_nfserr;
}
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 0501974bedd0..8ccf0f8c9cc8 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -30,6 +30,8 @@
#include "alloc.h"
#include "dlmglue.h"
#include "file.h"
+#include "inode.h"
+#include "journal.h"
#include "ocfs2_fs.h"
#include "xattr.h"
@@ -166,6 +168,60 @@ static struct posix_acl *ocfs2_get_acl(struct inode *inode, int type)
}
/*
+ * Helper function to set i_mode in memory and disk. Some call paths
+ * will not have di_bh or a journal handle to pass, in which case it
+ * will create it's own.
+ */
+static int ocfs2_acl_set_mode(struct inode *inode, struct buffer_head *di_bh,
+ handle_t *handle, umode_t new_mode)
+{
+ int ret, commit_handle = 0;
+ struct ocfs2_dinode *di;
+
+ if (di_bh == NULL) {
+ ret = ocfs2_read_inode_block(inode, &di_bh);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ } else
+ get_bh(di_bh);
+
+ if (handle == NULL) {
+ handle = ocfs2_start_trans(OCFS2_SB(inode->i_sb),
+ OCFS2_INODE_UPDATE_CREDITS);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto out_brelse;
+ }
+
+ commit_handle = 1;
+ }
+
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto out_commit;
+ }
+
+ inode->i_mode = new_mode;
+ di->i_mode = cpu_to_le16(inode->i_mode);
+
+ ocfs2_journal_dirty(handle, di_bh);
+
+out_commit:
+ if (commit_handle)
+ ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+out_brelse:
+ brelse(di_bh);
+out:
+ return ret;
+}
+
+/*
* Set the access or default ACL of an inode.
*/
static int ocfs2_set_acl(handle_t *handle,
@@ -193,9 +249,14 @@ static int ocfs2_set_acl(handle_t *handle,
if (ret < 0)
return ret;
else {
- inode->i_mode = mode;
if (ret == 0)
acl = NULL;
+
+ ret = ocfs2_acl_set_mode(inode, di_bh,
+ handle, mode);
+ if (ret)
+ return ret;
+
}
}
break;
@@ -283,6 +344,7 @@ int ocfs2_init_acl(handle_t *handle,
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct posix_acl *acl = NULL;
int ret = 0;
+ mode_t mode;
if (!S_ISLNK(inode->i_mode)) {
if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
@@ -291,12 +353,17 @@ int ocfs2_init_acl(handle_t *handle,
if (IS_ERR(acl))
return PTR_ERR(acl);
}
- if (!acl)
- inode->i_mode &= ~current_umask();
+ if (!acl) {
+ mode = inode->i_mode & ~current_umask();
+ ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
+ if (ret) {
+ mlog_errno(ret);
+ goto cleanup;
+ }
+ }
}
if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
struct posix_acl *clone;
- mode_t mode;
if (S_ISDIR(inode->i_mode)) {
ret = ocfs2_set_acl(handle, inode, di_bh,
@@ -313,7 +380,7 @@ int ocfs2_init_acl(handle_t *handle,
mode = inode->i_mode;
ret = posix_acl_create_masq(clone, &mode);
if (ret >= 0) {
- inode->i_mode = mode;
+ ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode);
if (ret > 0) {
ret = ocfs2_set_acl(handle, inode,
di_bh, ACL_TYPE_ACCESS,
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index c30b644d9572..79b5dacf9312 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -152,7 +152,7 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
#define do_error(fmt, ...) \
do{ \
- if (clean_error) \
+ if (resize) \
mlog(ML_ERROR, fmt "\n", ##__VA_ARGS__); \
else \
ocfs2_error(sb, fmt, ##__VA_ARGS__); \
@@ -160,7 +160,7 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
static int ocfs2_validate_gd_self(struct super_block *sb,
struct buffer_head *bh,
- int clean_error)
+ int resize)
{
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
@@ -211,7 +211,7 @@ static int ocfs2_validate_gd_self(struct super_block *sb,
static int ocfs2_validate_gd_parent(struct super_block *sb,
struct ocfs2_dinode *di,
struct buffer_head *bh,
- int clean_error)
+ int resize)
{
unsigned int max_bits;
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
@@ -233,8 +233,11 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
return -EINVAL;
}
- if (le16_to_cpu(gd->bg_chain) >=
- le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) {
+ /* In resize, we may meet the case bg_chain == cl_next_free_rec. */
+ if ((le16_to_cpu(gd->bg_chain) >
+ le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) ||
+ ((le16_to_cpu(gd->bg_chain) ==
+ le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) && !resize)) {
do_error("Group descriptor #%llu has bad chain %u",
(unsigned long long)bh->b_blocknr,
le16_to_cpu(gd->bg_chain));
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 58324c299165..3cd449d23352 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -442,12 +442,13 @@ static const struct file_operations proc_lstats_operations = {
unsigned long badness(struct task_struct *p, unsigned long uptime);
static int proc_oom_score(struct task_struct *task, char *buffer)
{
- unsigned long points;
+ unsigned long points = 0;
struct timespec uptime;
do_posix_clock_monotonic_gettime(&uptime);
read_lock(&tasklist_lock);
- points = badness(task->group_leader, uptime.tv_sec);
+ if (pid_alive(task))
+ points = badness(task, uptime.tv_sec);
read_unlock(&tasklist_lock);
return sprintf(buffer, "%lu\n", points);
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 6e722c11ce13..6c9da00ddda2 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2321,34 +2321,34 @@ static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
if (di->dqb_valid & QIF_SPACE) {
dm->dqb_curspace = di->dqb_curspace - dm->dqb_rsvspace;
check_blim = 1;
- __set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
+ set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
}
if (di->dqb_valid & QIF_BLIMITS) {
dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
check_blim = 1;
- __set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
+ set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
}
if (di->dqb_valid & QIF_INODES) {
dm->dqb_curinodes = di->dqb_curinodes;
check_ilim = 1;
- __set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
+ set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
}
if (di->dqb_valid & QIF_ILIMITS) {
dm->dqb_isoftlimit = di->dqb_isoftlimit;
dm->dqb_ihardlimit = di->dqb_ihardlimit;
check_ilim = 1;
- __set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
+ set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
}
if (di->dqb_valid & QIF_BTIME) {
dm->dqb_btime = di->dqb_btime;
check_blim = 1;
- __set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
+ set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
}
if (di->dqb_valid & QIF_ITIME) {
dm->dqb_itime = di->dqb_itime;
check_ilim = 1;
- __set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
+ set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
}
if (check_blim) {
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b4a7dd03bdb9..33bc410c6689 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1619,10 +1619,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
save_mount_options(s, data);
sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL);
- if (!sbi) {
- errval = -ENOMEM;
- goto error_alloc;
- }
+ if (!sbi)
+ return -ENOMEM;
s->s_fs_info = sbi;
/* Set default values for options: non-aggressive tails, RO on errors */
REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_SMALLTAIL);
@@ -1879,12 +1877,12 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
return (0);
error:
- reiserfs_write_unlock(s);
-error_alloc:
if (jinit_done) { /* kill the commit thread, free journal ram */
journal_release_error(NULL, s);
}
+ reiserfs_write_unlock(s);
+
reiserfs_free_bitmap_cache(s);
if (SB_BUFFER_WITH_SB(s))
brelse(SB_BUFFER_WITH_SB(s));
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 66abe36c1213..1c65a2b3f4ee 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -163,14 +163,17 @@ xfs_ioend_new_eof(
}
/*
- * Update on-disk file size now that data has been written to disk.
- * The current in-memory file size is i_size. If a write is beyond
- * eof i_new_size will be the intended file size until i_size is
- * updated. If this write does not extend all the way to the valid
- * file size then restrict this update to the end of the write.
+ * Update on-disk file size now that data has been written to disk. The
+ * current in-memory file size is i_size. If a write is beyond eof i_new_size
+ * will be the intended file size until i_size is updated. If this write does
+ * not extend all the way to the valid file size then restrict this update to
+ * the end of the write.
+ *
+ * This function does not block as blocking on the inode lock in IO completion
+ * can lead to IO completion order dependency deadlocks.. If it can't get the
+ * inode ilock it will return EAGAIN. Callers must handle this.
*/
-
-STATIC void
+STATIC int
xfs_setfilesize(
xfs_ioend_t *ioend)
{
@@ -181,9 +184,11 @@ xfs_setfilesize(
ASSERT(ioend->io_type != IOMAP_READ);
if (unlikely(ioend->io_error))
- return;
+ return 0;
+
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL))
+ return EAGAIN;
- xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_ioend_new_eof(ioend);
if (isize) {
ip->i_d.di_size = isize;
@@ -191,6 +196,28 @@ xfs_setfilesize(
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return 0;
+}
+
+/*
+ * Schedule IO completion handling on a xfsdatad if this was
+ * the final hold on this ioend. If we are asked to wait,
+ * flush the workqueue.
+ */
+STATIC void
+xfs_finish_ioend(
+ xfs_ioend_t *ioend,
+ int wait)
+{
+ if (atomic_dec_and_test(&ioend->io_remaining)) {
+ struct workqueue_struct *wq;
+
+ wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
+ xfsconvertd_workqueue : xfsdatad_workqueue;
+ queue_work(wq, &ioend->io_work);
+ if (wait)
+ flush_workqueue(wq);
+ }
}
/*
@@ -198,11 +225,11 @@ xfs_setfilesize(
*/
STATIC void
xfs_end_io(
- struct work_struct *work)
+ struct work_struct *work)
{
- xfs_ioend_t *ioend =
- container_of(work, xfs_ioend_t, io_work);
- struct xfs_inode *ip = XFS_I(ioend->io_inode);
+ xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work);
+ struct xfs_inode *ip = XFS_I(ioend->io_inode);
+ int error;
/*
* For unwritten extents we need to issue transactions to convert a
@@ -210,7 +237,6 @@ xfs_end_io(
*/
if (ioend->io_type == IOMAP_UNWRITTEN &&
likely(!ioend->io_error && !XFS_FORCED_SHUTDOWN(ip->i_mount))) {
- int error;
error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
ioend->io_size);
@@ -222,30 +248,23 @@ xfs_end_io(
* We might have to update the on-disk file size after extending
* writes.
*/
- if (ioend->io_type != IOMAP_READ)
- xfs_setfilesize(ioend);
- xfs_destroy_ioend(ioend);
-}
-
-/*
- * Schedule IO completion handling on a xfsdatad if this was
- * the final hold on this ioend. If we are asked to wait,
- * flush the workqueue.
- */
-STATIC void
-xfs_finish_ioend(
- xfs_ioend_t *ioend,
- int wait)
-{
- if (atomic_dec_and_test(&ioend->io_remaining)) {
- struct workqueue_struct *wq;
-
- wq = (ioend->io_type == IOMAP_UNWRITTEN) ?
- xfsconvertd_workqueue : xfsdatad_workqueue;
- queue_work(wq, &ioend->io_work);
- if (wait)
- flush_workqueue(wq);
+ if (ioend->io_type != IOMAP_READ) {
+ error = xfs_setfilesize(ioend);
+ ASSERT(!error || error == EAGAIN);
}
+
+ /*
+ * If we didn't complete processing of the ioend, requeue it to the
+ * tail of the workqueue for another attempt later. Otherwise destroy
+ * it.
+ */
+ if (error == EAGAIN) {
+ atomic_inc(&ioend->io_remaining);
+ xfs_finish_ioend(ioend, 0);
+ /* ensure we don't spin on blocked ioends */
+ delay(1);
+ } else
+ xfs_destroy_ioend(ioend);
}
/*
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 1f5e4bb5e970..6b6b39416ad3 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -613,7 +613,8 @@ xfssyncd(
set_freezable();
timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
for (;;) {
- timeleft = schedule_timeout_interruptible(timeleft);
+ if (list_empty(&mp->m_sync_list))
+ timeleft = schedule_timeout_interruptible(timeleft);
/* swsusp */
try_to_freeze();
if (kthread_should_stop() && list_empty(&mp->m_sync_list))
@@ -633,8 +634,7 @@ xfssyncd(
list_add_tail(&mp->m_sync_work.w_list,
&mp->m_sync_list);
}
- list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
- list_move(&work->w_list, &tmp);
+ list_splice_init(&mp->m_sync_list, &tmp);
spin_unlock(&mp->m_sync_lock);
list_for_each_entry_safe(work, n, &tmp, w_list) {
@@ -693,12 +693,12 @@ xfs_inode_set_reclaim_tag(
xfs_mount_t *mp = ip->i_mount;
xfs_perag_t *pag = xfs_get_perag(mp, ip->i_ino);
- read_lock(&pag->pag_ici_lock);
+ write_lock(&pag->pag_ici_lock);
spin_lock(&ip->i_flags_lock);
__xfs_inode_set_reclaim_tag(pag, ip);
__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
spin_unlock(&ip->i_flags_lock);
- read_unlock(&pag->pag_ici_lock);
+ write_unlock(&pag->pag_ici_lock);
xfs_put_perag(mp, pag);
}
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 155e798f30a1..fd21160a6238 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -190,13 +190,12 @@ xfs_iget_cache_hit(
trace_xfs_iget_reclaim(ip);
/*
- * We need to set XFS_INEW atomically with clearing the
- * reclaimable tag so that we do have an indicator of the
- * inode still being initialized.
+ * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
+ * from stomping over us while we recycle the inode. We can't
+ * clear the radix tree reclaimable tag yet as it requires
+ * pag_ici_lock to be held exclusive.
*/
- ip->i_flags |= XFS_INEW;
- ip->i_flags &= ~XFS_IRECLAIMABLE;
- __xfs_inode_clear_reclaim_tag(mp, pag, ip);
+ ip->i_flags |= XFS_IRECLAIM;
spin_unlock(&ip->i_flags_lock);
read_unlock(&pag->pag_ici_lock);
@@ -216,7 +215,15 @@ xfs_iget_cache_hit(
trace_xfs_iget_reclaim(ip);
goto out_error;
}
+
+ write_lock(&pag->pag_ici_lock);
+ spin_lock(&ip->i_flags_lock);
+ ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM);
+ ip->i_flags |= XFS_INEW;
+ __xfs_inode_clear_reclaim_tag(mp, pag, ip);
inode->i_state = I_NEW;
+ spin_unlock(&ip->i_flags_lock);
+ write_unlock(&pag->pag_ici_lock);
} else {
/* If the VFS inode is being torn down, pause and try again. */
if (!igrab(inode)) {