* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (96 commits)
no need for list_for_each_entry_safe()/resetting with superblock list
Fix sget() race with failing mount
vfs: don't hold s_umount over close_bdev_exclusive() call
sysv: do not mark superblock dirty on remount
sysv: do not mark superblock dirty on mount
btrfs: remove junk sb_dirt change
BFS: clean up the superblock usage
AFFS: wait for sb synchronization when needed
AFFS: clean up dirty flag usage
cifs: truncate fallout
mbcache: fix shrinker function return value
mbcache: Remove unused features
add f_flags to struct statfs(64)
pass a struct path to vfs_statfs
update VFS documentation for method changes.
All filesystems that need invalidate_inode_buffers() are doing that explicitly
convert remaining ->clear_inode() to ->evict_inode()
Make ->drop_inode() just return whether inode needs to be dropped
fs/inode.c:clear_inode() is gone
fs/inode.c:evict() doesn't care about delete vs. non-delete paths now
...
Fix up trivial conflicts in fs/nilfs2/super.c
}
/*
- * Small addres space operations for POHMELFS.
+ * Small address space operations for POHMELFS.
*/
const struct address_space_operations pohmelfs_aops = {
.readpage = pohmelfs_readpage,
}
/*
- * ->alloc_inode() callback. Allocates inode and initilizes private data.
+ * ->alloc_inode() callback. Allocates inode and initializes private data.
*/
static struct inode *pohmelfs_alloc_inode(struct super_block *sb)
{
goto err_out_exit;
}
- err = inode_setattr(inode, attr);
- if (err) {
- dprintk("%s: ino: %llu, failed to set the attributes.\n", __func__, POHMELFS_I(inode)->ino);
- goto err_out_exit;
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ err = vmtruncate(inode, attr->ia_size);
+ if (err) {
+ dprintk("%s: ino: %llu, failed to set the attributes.\n", __func__, POHMELFS_I(inode)->ino);
+ goto err_out_exit;
+ }
}
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+
dprintk("%s: ino: %llu, mode: %o -> %o, uid: %u -> %u, gid: %u -> %u, size: %llu -> %llu.\n",
__func__, POHMELFS_I(inode)->ino, inode->i_mode, attr->ia_mode,
inode->i_uid, attr->ia_uid, inode->i_gid, attr->ia_gid, inode->i_size, attr->ia_size);
}
}
- static void pohmelfs_drop_inode(struct inode *inode)
+ static int pohmelfs_drop_inode(struct inode *inode)
{
struct pohmelfs_sb *psb = POHMELFS_SB(inode->i_sb);
struct pohmelfs_inode *pi = POHMELFS_I(inode);
list_del_init(&pi->inode_entry);
spin_unlock(&psb->ino_lock);
- generic_drop_inode(inode);
+ return generic_drop_inode(inode);
}
static struct pohmelfs_inode *pohmelfs_get_inode_from_list(struct pohmelfs_sb *psb,
{
struct pohmelfs_sb *psb = POHMELFS_SB(sb);
struct pohmelfs_inode *pi;
- unsigned int count;
+ unsigned int count = 0;
unsigned int in_drop_list = 0;
struct inode *inode, *tmp;
#endif
struct inode *v9fs_get_inode(struct super_block *sb, int mode);
- void v9fs_clear_inode(struct inode *inode);
+ void v9fs_evict_inode(struct inode *inode);
ino_t v9fs_qid2ino(struct p9_qid *qid);
void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
+void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *);
int v9fs_dir_release(struct inode *inode, struct file *filp);
int v9fs_file_open(struct inode *inode, struct file *file);
void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
#include <linux/idr.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/xattr.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include "v9fs_vfs.h"
#include "fid.h"
#include "cache.h"
+#include "xattr.h"
static const struct inode_operations v9fs_dir_inode_operations;
static const struct inode_operations v9fs_dir_inode_operations_dotu;
}
#endif
+/**
+ * v9fs_get_fsgid_for_create - Helper function to get the gid for creating a
+ * new file system object. This checks the S_ISGID to determine the owning
+ * group of the new file system object.
+ */
+
+static gid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
+{
+ BUG_ON(dir_inode == NULL);
+
+ if (dir_inode->i_mode & S_ISGID) {
+ /* set_gid bit is set.*/
+ return dir_inode->i_gid;
+ }
+ return current_fsgid();
+}
+
+/**
+ * v9fs_dentry_from_dir_inode - helper function to get the dentry from
+ * dir inode.
+ *
+ */
+
+static struct dentry *v9fs_dentry_from_dir_inode(struct inode *inode)
+{
+ struct dentry *dentry;
+
+ spin_lock(&dcache_lock);
+ /* Directory should have only one entry. */
+ BUG_ON(S_ISDIR(inode->i_mode) && !list_is_singular(&inode->i_dentry));
+ dentry = list_entry(inode->i_dentry.next, struct dentry, d_alias);
+ spin_unlock(&dcache_lock);
+ return dentry;
+}
+
/**
* v9fs_get_inode - helper function to setup an inode
* @sb: superblock
case S_IFBLK:
case S_IFCHR:
case S_IFSOCK:
- if (!v9fs_proto_dotu(v9ses)) {
+ if (v9fs_proto_dotl(v9ses)) {
+ inode->i_op = &v9fs_file_inode_operations_dotl;
+ inode->i_fop = &v9fs_file_operations_dotl;
+ } else if (v9fs_proto_dotu(v9ses)) {
+ inode->i_op = &v9fs_file_inode_operations;
+ inode->i_fop = &v9fs_file_operations;
+ } else {
P9_DPRINTK(P9_DEBUG_ERROR,
"special files without extended mode\n");
err = -EINVAL;
* @inode: inode to release
*
*/
- void v9fs_clear_inode(struct inode *inode)
+ void v9fs_evict_inode(struct inode *inode)
{
+ truncate_inode_pages(inode->i_mapping, 0);
+ end_writeback(inode);
filemap_fdatawrite(inode->i_mapping);
#ifdef CONFIG_9P_FSCACHE
#endif
}
-/**
- * v9fs_inode_from_fid - populate an inode by issuing a attribute request
- * @v9ses: session information
- * @fid: fid to issue attribute request for
- * @sb: superblock on which to create inode
- *
- */
-
static struct inode *
-v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+v9fs_inode(struct v9fs_session_info *v9ses, struct p9_fid *fid,
struct super_block *sb)
{
int err, umode;
- struct inode *ret;
+ struct inode *ret = NULL;
struct p9_wstat *st;
- ret = NULL;
st = p9_client_stat(fid);
if (IS_ERR(st))
return ERR_CAST(st);
#endif
p9stat_free(st);
kfree(st);
-
return ret;
-
error:
p9stat_free(st);
kfree(st);
return ERR_PTR(err);
}
+static struct inode *
+v9fs_inode_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb)
+{
+ struct inode *ret = NULL;
+ int err;
+ struct p9_stat_dotl *st;
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
+ if (IS_ERR(st))
+ return ERR_CAST(st);
+
+ ret = v9fs_get_inode(sb, st->st_mode);
+ if (IS_ERR(ret)) {
+ err = PTR_ERR(ret);
+ goto error;
+ }
+
+ v9fs_stat2inode_dotl(st, ret);
+ ret->i_ino = v9fs_qid2ino(&st->qid);
+#ifdef CONFIG_9P_FSCACHE
+ v9fs_vcookie_set_qid(ret, &st->qid);
+ v9fs_cache_inode_get_cookie(ret);
+#endif
+ kfree(st);
+ return ret;
+error:
+ kfree(st);
+ return ERR_PTR(err);
+}
+
+/**
+ * v9fs_inode_from_fid - Helper routine to populate an inode by
+ * issuing a attribute request
+ * @v9ses: session information
+ * @fid: fid to issue attribute request for
+ * @sb: superblock on which to create inode
+ *
+ */
+static inline struct inode *
+v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
+ struct super_block *sb)
+{
+ if (v9fs_proto_dotl(v9ses))
+ return v9fs_inode_dotl(v9ses, fid, sb);
+ else
+ return v9fs_inode(v9ses, fid, sb);
+}
+
/**
* v9fs_remove - helper function to remove files and directories
* @dir: directory inode that is being deleted
return ERR_PTR(err);
}
+/**
+ * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol.
+ * @dir: directory inode that is being created
+ * @dentry: dentry that is being deleted
+ * @mode: create permissions
+ * @nd: path information
+ *
+ */
+
+static int
+v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int mode,
+ struct nameidata *nd)
+{
+ int err = 0;
+ char *name = NULL;
+ gid_t gid;
+ int flags;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid = NULL;
+ struct p9_fid *dfid, *ofid;
+ struct file *filp;
+ struct p9_qid qid;
+ struct inode *inode;
+
+ v9ses = v9fs_inode2v9ses(dir);
+ if (nd && nd->flags & LOOKUP_OPEN)
+ flags = nd->intent.open.flags - 1;
+ else
+ flags = O_RDWR;
+
+ name = (char *) dentry->d_name.name;
+ P9_DPRINTK(P9_DEBUG_VFS, "v9fs_vfs_create_dotl: name:%s flags:0x%x "
+ "mode:0x%x\n", name, flags, mode);
+
+ dfid = v9fs_fid_lookup(dentry->d_parent);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ P9_DPRINTK(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ return err;
+ }
+
+ /* clone a fid to use for creation */
+ ofid = p9_client_walk(dfid, 0, NULL, 1);
+ if (IS_ERR(ofid)) {
+ err = PTR_ERR(ofid);
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+ return err;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+ err = p9_client_create_dotl(ofid, name, flags, mode, gid, &qid);
+ if (err < 0) {
+ P9_DPRINTK(P9_DEBUG_VFS,
+ "p9_client_open_dotl failed in creat %d\n",
+ err);
+ goto error;
+ }
+
+ /* No need to populate the inode if we are not opening the file AND
+ * not in cached mode.
+ */
+ if (!v9ses->cache && !(nd && nd->flags & LOOKUP_OPEN)) {
+ /* Not in cached mode. No need to populate inode with stat */
+ dentry->d_op = &v9fs_dentry_operations;
+ p9_client_clunk(ofid);
+ d_instantiate(dentry, NULL);
+ return 0;
+ }
+
+ /* Now walk from the parent so we can get an unopened fid. */
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
+ fid = NULL;
+ goto error;
+ }
+
+ /* instantiate inode and assign the unopened fid to dentry */
+ inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err);
+ goto error;
+ }
+ dentry->d_op = &v9fs_cached_dentry_operations;
+ d_instantiate(dentry, inode);
+ err = v9fs_fid_add(dentry, fid);
+ if (err < 0)
+ goto error;
+
+ /* if we are opening a file, assign the open fid to the file */
+ if (nd && nd->flags & LOOKUP_OPEN) {
+ filp = lookup_instantiate_filp(nd, dentry, v9fs_open_created);
+ if (IS_ERR(filp)) {
+ p9_client_clunk(ofid);
+ return PTR_ERR(filp);
+ }
+ filp->private_data = ofid;
+ } else
+ p9_client_clunk(ofid);
+
+ return 0;
+
+error:
+ if (ofid)
+ p9_client_clunk(ofid);
+ if (fid)
+ p9_client_clunk(fid);
+ return err;
+}
+
/**
* v9fs_vfs_create - VFS hook to create files
* @dir: directory inode that is being created
return err;
}
+
+/**
+ * v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory
+ * @dir: inode that is being unlinked
+ * @dentry: dentry that is being unlinked
+ * @mode: mode for new directory
+ *
+ */
+
+static int v9fs_vfs_mkdir_dotl(struct inode *dir, struct dentry *dentry,
+ int mode)
+{
+ int err;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid = NULL, *dfid = NULL;
+ gid_t gid;
+ char *name;
+ struct inode *inode;
+ struct p9_qid qid;
+ struct dentry *dir_dentry;
+
+ P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+ err = 0;
+ v9ses = v9fs_inode2v9ses(dir);
+
+ mode |= S_IFDIR;
+ dir_dentry = v9fs_dentry_from_dir_inode(dir);
+ dfid = v9fs_fid_lookup(dir_dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ P9_DPRINTK(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ dfid = NULL;
+ goto error;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+ if (gid < 0) {
+ P9_DPRINTK(P9_DEBUG_VFS, "v9fs_get_fsgid_for_create failed\n");
+ goto error;
+ }
+
+ name = (char *) dentry->d_name.name;
+ err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid);
+ if (err < 0)
+ goto error;
+
+ /* instantiate inode and assign the unopened fid to the dentry */
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ fid = NULL;
+ goto error;
+ }
+
+ inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n",
+ err);
+ goto error;
+ }
+ dentry->d_op = &v9fs_cached_dentry_operations;
+ d_instantiate(dentry, inode);
+ err = v9fs_fid_add(dentry, fid);
+ if (err < 0)
+ goto error;
+ fid = NULL;
+ }
+error:
+ if (fid)
+ p9_client_clunk(fid);
+ return err;
+}
+
/**
* v9fs_vfs_lookup - VFS lookup hook to "walk" to a new inode
* @dir: inode that is being walked from
sb = dir->i_sb;
v9ses = v9fs_inode2v9ses(dir);
+ /* We can walk d_parent because we hold the dir->i_mutex */
dfid = v9fs_fid_lookup(dentry->d_parent);
if (IS_ERR(dfid))
return ERR_CAST(dfid);
goto clunk_olddir;
}
+ down_write(&v9ses->rename_sem);
if (v9fs_proto_dotl(v9ses)) {
retval = p9_client_rename(oldfid, newdirfid,
(char *) new_dentry->d_name.name);
if (retval != -ENOSYS)
goto clunk_newdir;
}
+ if (old_dentry->d_parent != new_dentry->d_parent) {
+ /*
+ * 9P .u can only handle file rename in the same directory
+ */
- /* 9P can only handle file rename in the same directory */
- if (memcmp(&olddirfid->qid, &newdirfid->qid, sizeof(newdirfid->qid))) {
P9_DPRINTK(P9_DEBUG_ERROR,
"old dir and new dir are different\n");
retval = -EXDEV;
goto clunk_newdir;
}
-
v9fs_blank_wstat(&wstat);
wstat.muid = v9ses->uname;
wstat.name = (char *) new_dentry->d_name.name;
retval = p9_client_wstat(oldfid, &wstat);
clunk_newdir:
+ if (!retval)
+ /* successful rename */
+ d_move(old_dentry, new_dentry);
+ up_write(&v9ses->rename_sem);
p9_client_clunk(newdirfid);
clunk_olddir:
return 0;
}
+static int
+v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ int err;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid;
+ struct p9_stat_dotl *st;
+
+ P9_DPRINTK(P9_DEBUG_VFS, "dentry: %p\n", dentry);
+ err = -EPERM;
+ v9ses = v9fs_inode2v9ses(dentry->d_inode);
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ return simple_getattr(mnt, dentry, stat);
+
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ /* Ask for all the fields in stat structure. Server will return
+ * whatever it supports
+ */
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_ALL);
+ if (IS_ERR(st))
+ return PTR_ERR(st);
+
+ v9fs_stat2inode_dotl(st, dentry->d_inode);
+ generic_fillattr(dentry->d_inode, stat);
+ /* Change block size to what the server returned */
+ stat->blksize = st->st_blksize;
+
+ kfree(st);
+ return 0;
+}
+
/**
* v9fs_vfs_setattr - set file metadata
* @dentry: file whose metadata to set
}
retval = p9_client_wstat(fid, &wstat);
- if (retval >= 0)
- retval = inode_setattr(dentry->d_inode, iattr);
+ if (retval < 0)
+ return retval;
- return retval;
+ if ((iattr->ia_valid & ATTR_SIZE) &&
+ iattr->ia_size != i_size_read(dentry->d_inode)) {
+ retval = vmtruncate(dentry->d_inode, iattr->ia_size);
+ if (retval)
+ return retval;
+ }
+
+ setattr_copy(dentry->d_inode, iattr);
+ mark_inode_dirty(dentry->d_inode);
+ return 0;
}
+/**
+ * v9fs_vfs_setattr_dotl - set file metadata
+ * @dentry: file whose metadata to set
+ * @iattr: metadata assignment structure
+ *
+ */
+
+static int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr)
+{
+ int retval;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid;
+ struct p9_iattr_dotl p9attr;
+
+ P9_DPRINTK(P9_DEBUG_VFS, "\n");
+
+ retval = inode_change_ok(dentry->d_inode, iattr);
+ if (retval)
+ return retval;
+
+ p9attr.valid = iattr->ia_valid;
+ p9attr.mode = iattr->ia_mode;
+ p9attr.uid = iattr->ia_uid;
+ p9attr.gid = iattr->ia_gid;
+ p9attr.size = iattr->ia_size;
+ p9attr.atime_sec = iattr->ia_atime.tv_sec;
+ p9attr.atime_nsec = iattr->ia_atime.tv_nsec;
+ p9attr.mtime_sec = iattr->ia_mtime.tv_sec;
+ p9attr.mtime_nsec = iattr->ia_mtime.tv_nsec;
+
+ retval = -EPERM;
+ v9ses = v9fs_inode2v9ses(dentry->d_inode);
+ fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ retval = p9_client_setattr(fid, &p9attr);
+ if (retval >= 0)
+ retval = inode_setattr(dentry->d_inode, iattr);
+
+ return retval;
+}
+
/**
* v9fs_stat2inode - populate an inode structure with mistat info
* @stat: Plan 9 metadata (mistat) structure
inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9;
}
+/**
+ * v9fs_stat2inode_dotl - populate an inode structure with stat info
+ * @stat: stat structure
+ * @inode: inode to populate
+ * @sb: superblock of filesystem
+ *
+ */
+
+void
+v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode)
+{
+
+ if ((stat->st_result_mask & P9_STATS_BASIC) == P9_STATS_BASIC) {
+ inode->i_atime.tv_sec = stat->st_atime_sec;
+ inode->i_atime.tv_nsec = stat->st_atime_nsec;
+ inode->i_mtime.tv_sec = stat->st_mtime_sec;
+ inode->i_mtime.tv_nsec = stat->st_mtime_nsec;
+ inode->i_ctime.tv_sec = stat->st_ctime_sec;
+ inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
+ inode->i_uid = stat->st_uid;
+ inode->i_gid = stat->st_gid;
+ inode->i_nlink = stat->st_nlink;
+ inode->i_mode = stat->st_mode;
+ inode->i_rdev = new_decode_dev(stat->st_rdev);
+
+ if ((S_ISBLK(inode->i_mode)) || (S_ISCHR(inode->i_mode)))
+ init_special_inode(inode, inode->i_mode, inode->i_rdev);
+
+ i_size_write(inode, stat->st_size);
+ inode->i_blocks = stat->st_blocks;
+ } else {
+ if (stat->st_result_mask & P9_STATS_ATIME) {
+ inode->i_atime.tv_sec = stat->st_atime_sec;
+ inode->i_atime.tv_nsec = stat->st_atime_nsec;
+ }
+ if (stat->st_result_mask & P9_STATS_MTIME) {
+ inode->i_mtime.tv_sec = stat->st_mtime_sec;
+ inode->i_mtime.tv_nsec = stat->st_mtime_nsec;
+ }
+ if (stat->st_result_mask & P9_STATS_CTIME) {
+ inode->i_ctime.tv_sec = stat->st_ctime_sec;
+ inode->i_ctime.tv_nsec = stat->st_ctime_nsec;
+ }
+ if (stat->st_result_mask & P9_STATS_UID)
+ inode->i_uid = stat->st_uid;
+ if (stat->st_result_mask & P9_STATS_GID)
+ inode->i_gid = stat->st_gid;
+ if (stat->st_result_mask & P9_STATS_NLINK)
+ inode->i_nlink = stat->st_nlink;
+ if (stat->st_result_mask & P9_STATS_MODE) {
+ inode->i_mode = stat->st_mode;
+ if ((S_ISBLK(inode->i_mode)) ||
+ (S_ISCHR(inode->i_mode)))
+ init_special_inode(inode, inode->i_mode,
+ inode->i_rdev);
+ }
+ if (stat->st_result_mask & P9_STATS_RDEV)
+ inode->i_rdev = new_decode_dev(stat->st_rdev);
+ if (stat->st_result_mask & P9_STATS_SIZE)
+ i_size_write(inode, stat->st_size);
+ if (stat->st_result_mask & P9_STATS_BLOCKS)
+ inode->i_blocks = stat->st_blocks;
+ }
+ if (stat->st_result_mask & P9_STATS_GEN)
+ inode->i_generation = stat->st_gen;
+
+ /* Currently we don't support P9_STATS_BTIME and P9_STATS_DATA_VERSION
+ * because the inode structure does not have fields for them.
+ */
+}
+
/**
* v9fs_qid2ino - convert qid into inode number
* @qid: qid to hash
if (IS_ERR(fid))
return PTR_ERR(fid);
- if (!v9fs_proto_dotu(v9ses))
+ if (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses))
return -EBADF;
st = p9_client_stat(fid);
return 0;
}
+/**
+ * v9fs_vfs_symlink_dotl - helper function to create symlinks
+ * @dir: directory inode containing symlink
+ * @dentry: dentry for symlink
+ * @symname: symlink data
+ *
+ * See Also: 9P2000.L RFC for more information
+ *
+ */
+
+static int
+v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
+ const char *symname)
+{
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *dfid;
+ struct p9_fid *fid = NULL;
+ struct inode *inode;
+ struct p9_qid qid;
+ char *name;
+ int err;
+ gid_t gid;
+
+ name = (char *) dentry->d_name.name;
+ P9_DPRINTK(P9_DEBUG_VFS, "v9fs_vfs_symlink_dotl : %lu,%s,%s\n",
+ dir->i_ino, name, symname);
+ v9ses = v9fs_inode2v9ses(dir);
+
+ dfid = v9fs_fid_lookup(dentry->d_parent);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ P9_DPRINTK(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ return err;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+
+ if (gid < 0) {
+ P9_DPRINTK(P9_DEBUG_VFS, "v9fs_get_egid failed %d\n", gid);
+ goto error;
+ }
+
+ /* Server doesn't alter fid on TSYMLINK. Hence no need to clone it. */
+ err = p9_client_symlink(dfid, name, (char *)symname, gid, &qid);
+
+ if (err < 0) {
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_symlink failed %d\n", err);
+ goto error;
+ }
+
+ if (v9ses->cache) {
+ /* Now walk from the parent so we can get an unopened fid. */
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ fid = NULL;
+ goto error;
+ }
+
+ /* instantiate inode and assign the unopened fid to dentry */
+ inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n",
+ err);
+ goto error;
+ }
+ dentry->d_op = &v9fs_cached_dentry_operations;
+ d_instantiate(dentry, inode);
+ err = v9fs_fid_add(dentry, fid);
+ if (err < 0)
+ goto error;
+ fid = NULL;
+ } else {
+ /* Not in cached mode. No need to populate inode with stat */
+ inode = v9fs_get_inode(dir->i_sb, S_IFLNK);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto error;
+ }
+ dentry->d_op = &v9fs_dentry_operations;
+ d_instantiate(dentry, inode);
+ }
+
+error:
+ if (fid)
+ p9_client_clunk(fid);
+
+ return err;
+}
+
/**
* v9fs_vfs_symlink - helper function to create symlinks
* @dir: directory inode containing symlink
return retval;
}
+/**
+ * v9fs_vfs_link_dotl - create a hardlink for dotl
+ * @old_dentry: dentry for file to link to
+ * @dir: inode destination for new link
+ * @dentry: dentry for link
+ *
+ */
+
+static int
+v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *dentry)
+{
+ int err;
+ struct p9_fid *dfid, *oldfid;
+ char *name;
+ struct v9fs_session_info *v9ses;
+ struct dentry *dir_dentry;
+
+ P9_DPRINTK(P9_DEBUG_VFS, "dir ino: %lu, old_name: %s, new_name: %s\n",
+ dir->i_ino, old_dentry->d_name.name,
+ dentry->d_name.name);
+
+ v9ses = v9fs_inode2v9ses(dir);
+ dir_dentry = v9fs_dentry_from_dir_inode(dir);
+ dfid = v9fs_fid_lookup(dir_dentry);
+ if (IS_ERR(dfid))
+ return PTR_ERR(dfid);
+
+ oldfid = v9fs_fid_lookup(old_dentry);
+ if (IS_ERR(oldfid))
+ return PTR_ERR(oldfid);
+
+ name = (char *) dentry->d_name.name;
+
+ err = p9_client_link(dfid, oldfid, (char *)dentry->d_name.name);
+
+ if (err < 0) {
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_link failed %d\n", err);
+ return err;
+ }
+
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ /* Get the latest stat info from server. */
+ struct p9_fid *fid;
+ struct p9_stat_dotl *st;
+
+ fid = v9fs_fid_lookup(old_dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
+ st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
+ if (IS_ERR(st))
+ return PTR_ERR(st);
+
+ v9fs_stat2inode_dotl(st, old_dentry->d_inode);
+
+ kfree(st);
+ } else {
+ /* Caching disabled. No need to get upto date stat info.
+ * This dentry will be released immediately. So, just i_count++
+ */
+ atomic_inc(&old_dentry->d_inode->i_count);
+ }
+
+ dentry->d_op = old_dentry->d_op;
+ d_instantiate(dentry, old_dentry->d_inode);
+
+ return err;
+}
+
/**
* v9fs_vfs_mknod - create a special file
* @dir: inode destination for new link
return retval;
}
+/**
+ * v9fs_vfs_mknod_dotl - create a special file
+ * @dir: inode destination for new link
+ * @dentry: dentry for file
+ * @mode: mode for creation
+ * @rdev: device associated with special file
+ *
+ */
+static int
+v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int mode,
+ dev_t rdev)
+{
+ int err;
+ char *name;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid = NULL, *dfid = NULL;
+ struct inode *inode;
+ gid_t gid;
+ struct p9_qid qid;
+ struct dentry *dir_dentry;
+
+ P9_DPRINTK(P9_DEBUG_VFS,
+ " %lu,%s mode: %x MAJOR: %u MINOR: %u\n", dir->i_ino,
+ dentry->d_name.name, mode, MAJOR(rdev), MINOR(rdev));
+
+ if (!new_valid_dev(rdev))
+ return -EINVAL;
+
+ v9ses = v9fs_inode2v9ses(dir);
+ dir_dentry = v9fs_dentry_from_dir_inode(dir);
+ dfid = v9fs_fid_lookup(dir_dentry);
+ if (IS_ERR(dfid)) {
+ err = PTR_ERR(dfid);
+ P9_DPRINTK(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
+ dfid = NULL;
+ goto error;
+ }
+
+ gid = v9fs_get_fsgid_for_create(dir);
+ if (gid < 0) {
+ P9_DPRINTK(P9_DEBUG_VFS, "v9fs_get_fsgid_for_create failed\n");
+ goto error;
+ }
+
+ name = (char *) dentry->d_name.name;
+
+ err = p9_client_mknod_dotl(dfid, name, mode, rdev, gid, &qid);
+ if (err < 0)
+ goto error;
+
+ /* instantiate inode and assign the unopened fid to the dentry */
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ fid = NULL;
+ goto error;
+ }
+
+ inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n",
+ err);
+ goto error;
+ }
+ dentry->d_op = &v9fs_cached_dentry_operations;
+ d_instantiate(dentry, inode);
+ err = v9fs_fid_add(dentry, fid);
+ if (err < 0)
+ goto error;
+ fid = NULL;
+ } else {
+ /*
+ * Not in cached mode. No need to populate inode with stat.
+ * socket syscall returns a fd, so we need instantiate
+ */
+ inode = v9fs_get_inode(dir->i_sb, mode);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ goto error;
+ }
+ dentry->d_op = &v9fs_dentry_operations;
+ d_instantiate(dentry, inode);
+ }
+
+error:
+ if (fid)
+ p9_client_clunk(fid);
+ return err;
+}
+
static const struct inode_operations v9fs_dir_inode_operations_dotu = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
.unlink = v9fs_vfs_unlink,
.mkdir = v9fs_vfs_mkdir,
.rmdir = v9fs_vfs_rmdir,
- .mknod = v9fs_vfs_mknod,
+ .mknod = v9fs_vfs_mknod_dotl,
.rename = v9fs_vfs_rename,
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};
static const struct inode_operations v9fs_dir_inode_operations_dotl = {
- .create = v9fs_vfs_create,
+ .create = v9fs_vfs_create_dotl,
.lookup = v9fs_vfs_lookup,
- .symlink = v9fs_vfs_symlink,
- .link = v9fs_vfs_link,
+ .link = v9fs_vfs_link_dotl,
+ .symlink = v9fs_vfs_symlink_dotl,
.unlink = v9fs_vfs_unlink,
- .mkdir = v9fs_vfs_mkdir,
+ .mkdir = v9fs_vfs_mkdir_dotl,
.rmdir = v9fs_vfs_rmdir,
- .mknod = v9fs_vfs_mknod,
+ .mknod = v9fs_vfs_mknod_dotl,
.rename = v9fs_vfs_rename,
- .getattr = v9fs_vfs_getattr,
- .setattr = v9fs_vfs_setattr,
+ .getattr = v9fs_vfs_getattr_dotl,
+ .setattr = v9fs_vfs_setattr_dotl,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .removexattr = generic_removexattr,
+ .listxattr = v9fs_listxattr,
+
};
static const struct inode_operations v9fs_dir_inode_operations = {
};
static const struct inode_operations v9fs_file_inode_operations_dotl = {
- .getattr = v9fs_vfs_getattr,
- .setattr = v9fs_vfs_setattr,
+ .getattr = v9fs_vfs_getattr_dotl,
+ .setattr = v9fs_vfs_setattr_dotl,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .removexattr = generic_removexattr,
+ .listxattr = v9fs_listxattr,
};
static const struct inode_operations v9fs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = v9fs_vfs_follow_link,
.put_link = v9fs_vfs_put_link,
- .getattr = v9fs_vfs_getattr,
- .setattr = v9fs_vfs_setattr,
+ .getattr = v9fs_vfs_getattr_dotl,
+ .setattr = v9fs_vfs_setattr_dotl,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .removexattr = generic_removexattr,
+ .listxattr = v9fs_listxattr,
};
#include "v9fs.h"
#include "v9fs_vfs.h"
#include "fid.h"
+#include "xattr.h"
static const struct super_operations v9fs_super_ops, v9fs_super_ops_dotl;
sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
sb->s_blocksize = 1 << sb->s_blocksize_bits;
sb->s_magic = V9FS_MAGIC;
- if (v9fs_proto_dotl(v9ses))
+ if (v9fs_proto_dotl(v9ses)) {
sb->s_op = &v9fs_super_ops_dotl;
- else
+ sb->s_xattr = v9fs_xattr_handlers;
+ } else
sb->s_op = &v9fs_super_ops;
sb->s_bdi = &v9ses->bdi;
struct inode *inode = NULL;
struct dentry *root = NULL;
struct v9fs_session_info *v9ses = NULL;
- struct p9_wstat *st = NULL;
int mode = S_IRWXUGO | S_ISVTX;
struct p9_fid *fid;
int retval = 0;
goto close_session;
}
- st = p9_client_stat(fid);
- if (IS_ERR(st)) {
- retval = PTR_ERR(st);
- goto clunk_fid;
- }
-
sb = sget(fs_type, NULL, v9fs_set_super, v9ses);
if (IS_ERR(sb)) {
retval = PTR_ERR(sb);
- goto free_stat;
+ goto clunk_fid;
}
v9fs_fill_super(sb, v9ses, flags, data);
}
sb->s_root = root;
- root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
- v9fs_stat2inode(st, root->d_inode, sb);
+ if (v9fs_proto_dotl(v9ses)) {
+ struct p9_stat_dotl *st = NULL;
+ st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
+ if (IS_ERR(st)) {
+ retval = PTR_ERR(st);
+ goto clunk_fid;
+ }
+
+ v9fs_stat2inode_dotl(st, root->d_inode);
+ kfree(st);
+ } else {
+ struct p9_wstat *st = NULL;
+ st = p9_client_stat(fid);
+ if (IS_ERR(st)) {
+ retval = PTR_ERR(st);
+ goto clunk_fid;
+ }
+
+ root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+ v9fs_stat2inode(st, root->d_inode, sb);
+
+ p9stat_free(st);
+ kfree(st);
+ }
v9fs_fid_add(root, fid);
- p9stat_free(st);
- kfree(st);
P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
simple_set_mnt(mnt, sb);
return 0;
-free_stat:
- p9stat_free(st);
- kfree(st);
-
clunk_fid:
p9_client_clunk(fid);
return retval;
release_sb:
- p9stat_free(st);
- kfree(st);
deactivate_locked_super(sb);
return retval;
}
.destroy_inode = v9fs_destroy_inode,
#endif
.statfs = simple_statfs,
- .clear_inode = v9fs_clear_inode,
+ .evict_inode = v9fs_evict_inode,
.show_options = generic_show_options,
.umount_begin = v9fs_umount_begin,
};
.destroy_inode = v9fs_destroy_inode,
#endif
.statfs = v9fs_statfs,
- .clear_inode = v9fs_clear_inode,
+ .evict_inode = v9fs_evict_inode,
.show_options = generic_show_options,
.umount_begin = v9fs_umount_begin,
};
.get_sb = v9fs_get_sb,
.kill_sb = v9fs_kill_super,
.owner = THIS_MODULE,
+ .fs_flags = FS_RENAME_DOES_D_MOVE,
};
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- return blockdev_direct_IO_no_locking_newtrunc(rw, iocb, inode,
- I_BDEV(inode), iov, offset, nr_segs,
- blkdev_get_blocks, NULL);
+ return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
+ nr_segs, blkdev_get_blocks, NULL, NULL, 0);
}
int __sync_blockdev(struct block_device *bdev, int wait)
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- *pagep = NULL;
- return block_write_begin_newtrunc(file, mapping, pos, len, flags,
- pagep, fsdata, blkdev_get_block);
+ return block_write_begin(mapping, pos, len, flags, pagep,
+ blkdev_get_block);
}
static int blkdev_write_end(struct file *file, struct address_space *mapping,
inode->i_mapping = &inode->i_data;
}
- static void bdev_clear_inode(struct inode *inode)
+ static void bdev_evict_inode(struct inode *inode)
{
struct block_device *bdev = &BDEV_I(inode)->bdev;
struct list_head *p;
+ truncate_inode_pages(&inode->i_data, 0);
+ invalidate_inode_buffers(inode); /* is it needed here? */
+ end_writeback(inode);
spin_lock(&bdev_lock);
while ( (p = bdev->bd_inodes.next) != &bdev->bd_inodes ) {
__bd_forget(list_entry(p, struct inode, i_devices));
.alloc_inode = bdev_alloc_inode,
.destroy_inode = bdev_destroy_inode,
.drop_inode = generic_delete_inode,
- .clear_inode = bdev_clear_inode,
+ .evict_inode = bdev_evict_inode,
};
static int bd_get_sb(struct file_system_type *fs_type,
if (!bd_may_claim(bdev, whole, holder))
return -EBUSY;
- /* if someone else is claiming, wait for it to finish */
- if (whole->bd_claiming && whole->bd_claiming != holder) {
+ /* if claiming is already in progress, wait for it to finish */
+ if (whole->bd_claiming) {
wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
DEFINE_WAIT(wait);
#include "cifs_fs_sb.h"
#include <linux/mm.h>
#include <linux/key-type.h>
-#include "dns_resolve.h"
#include "cifs_spnego.h"
#include "fscache.h"
#define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */
}
static void
- cifs_clear_inode(struct inode *inode)
+ cifs_evict_inode(struct inode *inode)
{
+ truncate_inode_pages(&inode->i_data, 0);
+ end_writeback(inode);
cifs_fscache_release_inode_cookie(inode);
}
return 0;
}
- void cifs_drop_inode(struct inode *inode)
+ static int cifs_drop_inode(struct inode *inode)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
- return generic_drop_inode(inode);
-
- return generic_delete_inode(inode);
+ /* no serverino => unconditional eviction */
+ return !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) ||
+ generic_drop_inode(inode);
}
static const struct super_operations cifs_super_ops = {
.alloc_inode = cifs_alloc_inode,
.destroy_inode = cifs_destroy_inode,
.drop_inode = cifs_drop_inode,
- .clear_inode = cifs_clear_inode,
+ .evict_inode = cifs_evict_inode,
/* .delete_inode = cifs_delete_inode, */ /* Do not need above
function unless later we add lazy close of inodes or unless the
kernel forgets to call us with the same number of releases (closes)
if (rc)
goto out_unregister_filesystem;
#endif
-#ifdef CONFIG_CIFS_DFS_UPCALL
- rc = cifs_init_dns_resolver();
- if (rc)
- goto out_unregister_key_type;
-#endif
- rc = slow_work_register_user(THIS_MODULE);
- if (rc)
- goto out_unregister_resolver_key;
return 0;
- out_unregister_resolver_key:
-#ifdef CONFIG_CIFS_DFS_UPCALL
- cifs_exit_dns_resolver();
- out_unregister_key_type:
-#endif
#ifdef CONFIG_CIFS_UPCALL
- unregister_key_type(&cifs_spnego_key_type);
out_unregister_filesystem:
-#endif
unregister_filesystem(&cifs_fs_type);
+#endif
out_destroy_request_bufs:
cifs_destroy_request_bufs();
out_destroy_mids:
cifs_fscache_unregister();
#ifdef CONFIG_CIFS_DFS_UPCALL
cifs_dfs_release_automount_timer();
- cifs_exit_dns_resolver();
#endif
#ifdef CONFIG_CIFS_UPCALL
unregister_key_type(&cifs_spnego_key_type);
if ((inode->i_mode & S_IFMT) != (fattr->cf_mode & S_IFMT))
return 0;
- /*
- * uh oh -- it's a directory. We can't use it since hardlinked dirs are
- * verboten. Disable serverino and return it as if it were found, the
- * caller can discard it, generate a uniqueid and retry the find
- */
- if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry)) {
+ /* if it's not a directory or has no dentries, then flag it */
+ if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry))
fattr->cf_flags |= CIFS_FATTR_INO_COLLISION;
- cifs_autodisable_serverino(CIFS_SB(inode->i_sb));
- }
return 1;
}
return 0;
}
+/*
+ * walk dentry list for an inode and report whether it has aliases that
+ * are hashed. We use this to determine if a directory inode can actually
+ * be used.
+ */
+static bool
+inode_has_hashed_dentries(struct inode *inode)
+{
+ struct dentry *dentry;
+
+ spin_lock(&dcache_lock);
+ list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
+ spin_unlock(&dcache_lock);
+ return true;
+ }
+ }
+ spin_unlock(&dcache_lock);
+ return false;
+}
+
/* Given fattrs, get a corresponding inode */
struct inode *
cifs_iget(struct super_block *sb, struct cifs_fattr *fattr)
inode = iget5_locked(sb, hash, cifs_find_inode, cifs_init_inode, fattr);
if (inode) {
- /* was there a problematic inode number collision? */
+ /* was there a potentially problematic inode collision? */
if (fattr->cf_flags & CIFS_FATTR_INO_COLLISION) {
- iput(inode);
- fattr->cf_uniqueid = iunique(sb, ROOT_I);
fattr->cf_flags &= ~CIFS_FATTR_INO_COLLISION;
- goto retry_iget5_locked;
+
+ if (inode_has_hashed_dentries(inode)) {
+ cifs_autodisable_serverino(CIFS_SB(sb));
+ iput(inode);
+ fattr->cf_uniqueid = iunique(sb, ROOT_I);
+ goto retry_iget5_locked;
+ }
}
cifs_fattr_to_inode(inode, fattr);
return rc;
}
- static int cifs_vmtruncate(struct inode *inode, loff_t offset)
+ static void cifs_setsize(struct inode *inode, loff_t offset)
{
loff_t oldsize;
- int err;
spin_lock(&inode->i_lock);
- err = inode_newsize_ok(inode, offset);
- if (err) {
- spin_unlock(&inode->i_lock);
- goto out;
- }
-
oldsize = inode->i_size;
i_size_write(inode, offset);
spin_unlock(&inode->i_lock);
+
truncate_pagecache(inode, oldsize, offset);
- if (inode->i_op->truncate)
- inode->i_op->truncate(inode);
- out:
- return err;
}
static int
if (rc == 0) {
cifsInode->server_eof = attrs->ia_size;
- rc = cifs_vmtruncate(inode, attrs->ia_size);
+ cifs_setsize(inode, attrs->ia_size);
cifs_truncate_page(inode->i_mapping, inode->i_size);
}
xid = GetXid();
- if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) == 0) {
- /* check if we have permission to change attrs */
- rc = inode_change_ok(inode, attrs);
- if (rc < 0)
- goto out;
- else
- rc = 0;
- }
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+ attrs->ia_valid |= ATTR_FORCE;
+
+ rc = inode_change_ok(inode, attrs);
+ if (rc < 0)
+ goto out;
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
CIFS_MOUNT_MAP_SPECIAL_CHR);
}
- if (!rc) {
- rc = inode_setattr(inode, attrs);
+ if (rc)
+ goto out;
- /* force revalidate when any of these times are set since some
- of the fs types (eg ext3, fat) do not have fine enough
- time granularity to match protocol, and we do not have a
- a way (yet) to query the server fs's time granularity (and
- whether it rounds times down).
- */
- if (!rc && (attrs->ia_valid & (ATTR_MTIME | ATTR_CTIME)))
- cifsInode->time = 0;
- }
+ if ((attrs->ia_valid & ATTR_SIZE) &&
+ attrs->ia_size != i_size_read(inode))
+ truncate_setsize(inode, attrs->ia_size);
+
+ setattr_copy(inode, attrs);
+ mark_inode_dirty(inode);
+
+ /* force revalidate when any of these times are set since some
+ of the fs types (eg ext3, fat) do not have fine enough
+ time granularity to match protocol, and we do not have a
+ a way (yet) to query the server fs's time granularity (and
+ whether it rounds times down).
+ */
+ if (attrs->ia_valid & (ATTR_MTIME | ATTR_CTIME))
+ cifsInode->time = 0;
out:
kfree(args);
kfree(full_path);
cFYI(1, "setattr on file %s attrs->iavalid 0x%x",
direntry->d_name.name, attrs->ia_valid);
- if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) == 0) {
- /* check if we have permission to change attrs */
- rc = inode_change_ok(inode, attrs);
- if (rc < 0) {
- FreeXid(xid);
- return rc;
- } else
- rc = 0;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
+ attrs->ia_valid |= ATTR_FORCE;
+
+ rc = inode_change_ok(inode, attrs);
+ if (rc < 0) {
+ FreeXid(xid);
+ return rc;
}
full_path = build_path_from_dentry(direntry);
/* do not need local check to inode_check_ok since the server does
that */
- if (!rc)
- rc = inode_setattr(inode, attrs);
+ if (rc)
+ goto cifs_setattr_exit;
+
+ if ((attrs->ia_valid & ATTR_SIZE) &&
+ attrs->ia_size != i_size_read(inode))
+ truncate_setsize(inode, attrs->ia_size);
+
+ setattr_copy(inode, attrs);
+ mark_inode_dirty(inode);
+ return 0;
+
cifs_setattr_exit:
kfree(full_path);
FreeXid(xid);
* Copyright (C) 1997-2000 Jakub Jelinek (jakub@redhat.com)
* Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be)
* Copyright (C) 2001,2002 Andi Kleen, SuSE Labs
- * Copyright (C) 2003 Pavel Machek (pavel@suse.cz)
+ * Copyright (C) 2003 Pavel Machek (pavel@ucw.cz)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
#include <linux/compat.h>
error = user_path(pathname, &path);
if (!error) {
struct kstatfs tmp;
- error = vfs_statfs(path.dentry, &tmp);
+ error = vfs_statfs(&path, &tmp);
if (!error)
error = put_compat_statfs(buf, &tmp);
path_put(&path);
file = fget(fd);
if (!file)
goto out;
- error = vfs_statfs(file->f_path.dentry, &tmp);
+ error = vfs_statfs(&file->f_path, &tmp);
if (!error)
error = put_compat_statfs(buf, &tmp);
fput(file);
error = user_path(pathname, &path);
if (!error) {
struct kstatfs tmp;
- error = vfs_statfs(path.dentry, &tmp);
+ error = vfs_statfs(&path, &tmp);
if (!error)
error = put_compat_statfs64(buf, &tmp);
path_put(&path);
file = fget(fd);
if (!file)
goto out;
- error = vfs_statfs(file->f_path.dentry, &tmp);
+ error = vfs_statfs(&file->f_path, &tmp);
if (!error)
error = put_compat_statfs64(buf, &tmp);
fput(file);
sb = user_get_super(new_decode_dev(dev));
if (!sb)
return -EINVAL;
- err = vfs_statfs(sb->s_root, &sbuf);
+ err = statfs_by_dentry(sb->s_root, &sbuf);
drop_super(sb);
if (err)
return err;
return retval;
}
-#define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
-
struct compat_old_linux_dirent {
compat_ulong_t d_ino;
compat_ulong_t d_offset;
struct compat_linux_dirent __user * dirent;
struct compat_getdents_callback *buf = __buf;
compat_ulong_t d_ino;
- int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 2, sizeof(compat_long_t));
+ int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
+ namlen + 2, sizeof(compat_long_t));
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
{
struct linux_dirent64 __user *dirent;
struct compat_getdents_callback64 *buf = __buf;
- int jj = NAME_OFFSET(dirent);
- int reclen = ALIGN(jj + namlen + 1, sizeof(u64));
+ int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
+ sizeof(u64));
u64 off;
buf->error = -EINVAL; /* only used if we fail.. */
}
/*
- * Called at the last iput() if i_nlink is zero.
+ * Called at inode eviction from icache
*/
- void ext3_delete_inode (struct inode * inode)
+ void ext3_evict_inode (struct inode *inode)
{
+ struct ext3_block_alloc_info *rsv;
handle_t *handle;
+ int want_delete = 0;
- if (!is_bad_inode(inode))
+ if (!inode->i_nlink && !is_bad_inode(inode)) {
dquot_initialize(inode);
+ want_delete = 1;
+ }
truncate_inode_pages(&inode->i_data, 0);
- if (is_bad_inode(inode))
+ ext3_discard_reservation(inode);
+ rsv = EXT3_I(inode)->i_block_alloc_info;
+ EXT3_I(inode)->i_block_alloc_info = NULL;
+ if (unlikely(rsv))
+ kfree(rsv);
+
+ if (!want_delete)
goto no_delete;
handle = start_transaction(inode);
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
- if (ext3_mark_inode_dirty(handle, inode))
- /* If that failed, just do the required in-core inode clear. */
- clear_inode(inode);
- else
+ if (ext3_mark_inode_dirty(handle, inode)) {
+ /* If that failed, just dquot_drop() and be done with that */
+ dquot_drop(inode);
+ end_writeback(inode);
+ } else {
+ ext3_xattr_delete_inode(handle, inode);
+ dquot_free_inode(inode);
+ dquot_drop(inode);
+ end_writeback(inode);
ext3_free_inode(handle, inode);
+ }
ext3_journal_stop(handle);
return;
no_delete:
- clear_inode(inode); /* We must guarantee clearing of inode... */
+ end_writeback(inode);
+ dquot_drop(inode);
}
typedef struct {
static int do_journal_get_write_access(handle_t *handle,
struct buffer_head *bh)
{
+ int dirty = buffer_dirty(bh);
+ int ret;
+
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
- return ext3_journal_get_write_access(handle, bh);
+ /*
+ * __block_prepare_write() could have dirtied some buffers. Clean
+ * the dirty bit as jbd2_journal_get_write_access() could complain
+ * otherwise about fs integrity issues. Setting of the dirty bit
+ * by __block_prepare_write() isn't a real problem here as we clear
+ * the bit before releasing a page lock and thus writeback cannot
+ * ever write the buffer.
+ */
+ if (dirty)
+ clear_buffer_dirty(bh);
+ ret = ext3_journal_get_write_access(handle, bh);
+ if (!ret && dirty)
+ ret = ext3_journal_dirty_metadata(handle, bh);
+ return ret;
}
/*
ret = PTR_ERR(handle);
goto out;
}
- ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext3_get_block);
+ ret = __block_write_begin(page, pos, len, ext3_get_block);
if (ret)
goto write_begin_failed;
goto out_fail;
}
- if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
- ret = nobh_writepage(page, ext3_get_block, wbc);
- else
- ret = block_write_full_page(page, ext3_get_block, wbc);
+ ret = block_write_full_page(page, ext3_get_block, wbc);
err = ext3_journal_stop(handle);
if (!ret)
ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext3_get_block, NULL);
+ /*
+ * In case of error extending write may have instantiated a few
+ * blocks outside i_size. Trim these off again.
+ */
+ if (unlikely((rw & WRITE) && ret < 0)) {
+ loff_t isize = i_size_read(inode);
+ loff_t end = offset + iov_length(iov, nr_segs);
+
+ if (end > isize)
+ vmtruncate(inode, isize);
+ }
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
goto retry;
length = blocksize - (offset & (blocksize - 1));
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
- /*
- * For "nobh" option, we can only work if we don't need to
- * read-in the page - otherwise we create buffers to do the IO.
- */
- if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
- ext3_should_writeback_data(inode) && PageUptodate(page)) {
- zero_user(page, offset, length);
- set_page_dirty(page);
- goto unlock;
- }
-
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
(__le32*)bh->b_data + addr_per_block,
depth);
- /*
- * We've probably journalled the indirect block several
- * times during the truncate. But it's no longer
- * needed and we now drop it from the transaction via
- * journal_revoke().
- *
- * That's easy if it's exclusively part of this
- * transaction. But if it's part of the committing
- * transaction then journal_forget() will simply
- * brelse() it. That means that if the underlying
- * block is reallocated in ext3_get_block(),
- * unmap_underlying_metadata() will find this block
- * and will try to get rid of it. damn, damn.
- *
- * If this block has already been committed to the
- * journal, a revoke record will be written. And
- * revoke records must be emitted *before* clearing
- * this block's bit in the bitmaps.
- */
- ext3_forget(handle, 1, inode, bh, bh->b_blocknr);
-
/*
* Everything below this this pointer has been
* released. Now let this top-of-subtree go.
truncate_restart_transaction(handle, inode);
}
+ /*
+ * We've probably journalled the indirect block several
+ * times during the truncate. But it's no longer
+ * needed and we now drop it from the transaction via
+ * journal_revoke().
+ *
+ * That's easy if it's exclusively part of this
+ * transaction. But if it's part of the committing
+ * transaction then journal_forget() will simply
+ * brelse() it. That means that if the underlying
+ * block is reallocated in ext3_get_block(),
+ * unmap_underlying_metadata() will find this block
+ * and will try to get rid of it. damn, damn. Thus
+ * we don't allow a block to be reallocated until
+ * a transaction freeing it has fully committed.
+ *
+ * We also have to make sure journal replay after a
+ * crash does not overwrite non-journaled data blocks
+ * with old metadata when the block got reallocated for
+ * data. Thus we have to store a revoke record for a
+ * block in the same transaction in which we free the
+ * block.
+ */
+ ext3_forget(handle, 1, inode, bh, bh->b_blocknr);
+
ext3_free_blocks(handle, inode, nr, 1);
if (parent_bh) {
* If this was a simple ftruncate(), and the file will remain alive
* then we need to clear up the orphan record which we created above.
* However, if this was a real unlink then we were called by
- * ext3_delete_inode(), and we allow that function to clean up the
+ * ext3_evict_inode(), and we allow that function to clean up the
* orphan info for us.
*/
if (inode->i_nlink)
ext3_journal_stop(handle);
}
- rc = inode_setattr(inode, attr);
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ rc = vmtruncate(inode, attr->ia_size);
+ if (rc)
+ goto err_out;
+ }
+
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
- if (!rc && (ia_valid & ATTR_MODE))
+ if (ia_valid & ATTR_MODE)
rc = ext3_acl_chmod(inode);
err_out:
kmem_cache_destroy(ext3_inode_cachep);
}
- static void ext3_clear_inode(struct inode *inode)
- {
- struct ext3_block_alloc_info *rsv = EXT3_I(inode)->i_block_alloc_info;
-
- dquot_drop(inode);
- ext3_discard_reservation(inode);
- EXT3_I(inode)->i_block_alloc_info = NULL;
- if (unlikely(rsv))
- kfree(rsv);
- }
-
static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb)
{
#if defined(CONFIG_QUOTA)
*/
seq_puts(seq, ",barrier=");
seq_puts(seq, test_opt(sb, BARRIER) ? "1" : "0");
- if (test_opt(sb, NOBH))
- seq_puts(seq, ",nobh");
-
seq_printf(seq, ",data=%s", data_mode_string(test_opt(sb, DATA_FLAGS)));
if (test_opt(sb, DATA_ERR_ABORT))
seq_puts(seq, ",data_err=abort");
.destroy_inode = ext3_destroy_inode,
.write_inode = ext3_write_inode,
.dirty_inode = ext3_dirty_inode,
- .delete_inode = ext3_delete_inode,
+ .evict_inode = ext3_evict_inode,
.put_super = ext3_put_super,
.sync_fs = ext3_sync_fs,
.freeze_fs = ext3_freeze,
.unfreeze_fs = ext3_unfreeze,
.statfs = ext3_statfs,
.remount_fs = ext3_remount,
- .clear_inode = ext3_clear_inode,
.show_options = ext3_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext3_quota_read,
*n_blocks_count = option;
break;
case Opt_nobh:
- set_opt(sbi->s_mount_opt, NOBH);
+ ext3_msg(sb, KERN_WARNING,
+ "warning: ignoring deprecated nobh option");
break;
case Opt_bh:
- clear_opt(sbi->s_mount_opt, NOBH);
+ ext3_msg(sb, KERN_WARNING,
+ "warning: ignoring deprecated bh option");
break;
default:
ext3_msg(sb, KERN_ERR,
break;
}
- if (test_opt(sb, NOBH)) {
- if (!(test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)) {
- ext3_msg(sb, KERN_WARNING,
- "warning: ignoring nobh option - "
- "it is supported only with writeback mode");
- clear_opt(sbi->s_mount_opt, NOBH);
- }
- }
/*
* The journal_load will have done any necessary log recovery,
* so we can safely mount the rest of the filesystem now.
#endif
#define EXT4_ERROR_INODE(inode, fmt, a...) \
- ext4_error_inode(__func__, (inode), (fmt), ## a)
+ ext4_error_inode((inode), __func__, __LINE__, 0, (fmt), ## a)
+
+#define EXT4_ERROR_INODE_BLOCK(inode, block, fmt, a...) \
+ ext4_error_inode((inode), __func__, __LINE__, (block), (fmt), ## a)
#define EXT4_ERROR_FILE(file, fmt, a...) \
- ext4_error_file(__func__, (file), (fmt), ## a)
+ ext4_error_file(__func__, __LINE__, (file), (fmt), ## a)
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
};
#define EXT4_IO_UNWRITTEN 0x1
typedef struct ext4_io_end {
- struct list_head list; /* per-file finished AIO list */
+ struct list_head list; /* per-file finished IO list */
struct inode *inode; /* file being written to */
unsigned int flag; /* unwritten or not */
struct page *page; /* page struct for buffer write */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
struct work_struct work; /* data work queue */
+ struct kiocb *iocb; /* iocb struct for AIO */
+ int result; /* error value for AIO */
} ext4_io_end_t;
/*
};
/*
- * Flags used by ext4_get_blocks()
+ * Flags used by ext4_map_blocks()
*/
/* Allocate any needed blocks and/or convert an unitialized
extent to be an initialized ext4 */
#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */
#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */
-#define EXT4_MOUNT_NOBH 0x40000 /* No bufferheads */
#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
__le32 s_last_orphan; /* start of list of inodes to delete */
__le32 s_hash_seed[4]; /* HTREE hash seed */
__u8 s_def_hash_version; /* Default hash version to use */
- __u8 s_reserved_char_pad;
+ __u8 s_jnl_backup_type;
__le16 s_desc_size; /* size of group descriptor */
/*100*/ __le32 s_default_mount_opts;
__le32 s_first_meta_bg; /* First metablock block group */
__le64 s_mmp_block; /* Block for multi-mount protection */
__le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/
__u8 s_log_groups_per_flex; /* FLEX_BG group size */
- __u8 s_reserved_char_pad2;
+ __u8 s_reserved_char_pad;
__le16 s_reserved_pad;
__le64 s_kbytes_written; /* nr of lifetime kilobytes written */
- __u32 s_reserved[160]; /* Padding to the end of the block */
+ __le32 s_snapshot_inum; /* Inode number of active snapshot */
+ __le32 s_snapshot_id; /* sequential ID of active snapshot */
+ __le64 s_snapshot_r_blocks_count; /* reserved blocks for active
+ snapshot's future use */
+ __le32 s_snapshot_list; /* inode number of the head of the
+ on-disk snapshot list */
+#define EXT4_S_ERR_START offsetof(struct ext4_super_block, s_error_count)
+ __le32 s_error_count; /* number of fs errors */
+ __le32 s_first_error_time; /* first time an error happened */
+ __le32 s_first_error_ino; /* inode involved in first error */
+ __le64 s_first_error_block; /* block involved of first error */
+ __u8 s_first_error_func[32]; /* function where the error happened */
+ __le32 s_first_error_line; /* line number where error happened */
+ __le32 s_last_error_time; /* most recent time of an error */
+ __le32 s_last_error_ino; /* inode involved in last error */
+ __le32 s_last_error_line; /* line number where error happened */
+ __le64 s_last_error_block; /* block involved of last error */
+ __u8 s_last_error_func[32]; /* function where the error happened */
+#define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts)
+ __u8 s_mount_opts[64];
+ __le32 s_reserved[112]; /* Padding to the end of the block */
};
+#define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START)
+
#ifdef __KERNEL__
/*
/* workqueue for dio unwritten */
struct workqueue_struct *dio_unwritten_wq;
+
+ /* timer for periodic error stats printing */
+ struct timer_list s_err_report;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
#define EXT4_DEFM_JMODE_DATA 0x0020
#define EXT4_DEFM_JMODE_ORDERED 0x0040
#define EXT4_DEFM_JMODE_WBACK 0x0060
+#define EXT4_DEFM_NOBARRIER 0x0100
+#define EXT4_DEFM_BLOCK_VALIDITY 0x0200
+#define EXT4_DEFM_DISCARD 0x0400
+#define EXT4_DEFM_NODELALLOC 0x0800
/*
* Default journal batch times
~EXT4_DIR_ROUND)
#define EXT4_MAX_REC_LEN ((1<<16)-1)
+/*
+ * If we ever get support for fs block sizes > page_size, we'll need
+ * to remove the #if statements in the next two functions...
+ */
+static inline unsigned int
+ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
+{
+ unsigned len = le16_to_cpu(dlen);
+
+#if (PAGE_CACHE_SIZE >= 65536)
+ if (len == EXT4_MAX_REC_LEN || len == 0)
+ return blocksize;
+ return (len & 65532) | ((len & 3) << 16);
+#else
+ return len;
+#endif
+}
+
+static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
+{
+ if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
+ BUG();
+#if (PAGE_CACHE_SIZE >= 65536)
+ if (len < 65536)
+ return cpu_to_le16(len);
+ if (len == blocksize) {
+ if (blocksize == 65536)
+ return cpu_to_le16(EXT4_MAX_REC_LEN);
+ else
+ return cpu_to_le16(0);
+ }
+ return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
+#else
+ return cpu_to_le16(len);
+#endif
+}
+
/*
* Hash Tree Directory indexing
* (c) Daniel Phillips, 2001
ext4_init_block_bitmap(sb, NULL, group, desc)
/* dir.c */
-extern int ext4_check_dir_entry(const char *, struct inode *,
- struct ext4_dir_entry_2 *,
- struct buffer_head *, unsigned int);
+extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *,
+ struct ext4_dir_entry_2 *,
+ struct buffer_head *, unsigned int);
+#define ext4_check_dir_entry(dir, de, bh, offset) \
+ __ext4_check_dir_entry(__func__, __LINE__, (dir), (de), (bh), (offset))
extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
__u32 minor_hash,
struct ext4_dir_entry_2 *dirent);
extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat);
- extern void ext4_delete_inode(struct inode *);
+ extern void ext4_evict_inode(struct inode *);
+ extern void ext4_clear_inode(struct inode *);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_ext_migrate(struct inode *);
/* namei.c */
-extern unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize);
-extern __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize);
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
ext4_fsblk_t n_blocks_count);
/* super.c */
-extern void __ext4_error(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-#define ext4_error(sb, message...) __ext4_error(sb, __func__, ## message)
-extern void ext4_error_inode(const char *, struct inode *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void ext4_error_file(const char *, struct file *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void __ext4_std_error(struct super_block *, const char *, int);
-extern void ext4_abort(struct super_block *, const char *, const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-extern void __ext4_warning(struct super_block *, const char *,
+extern void __ext4_error(struct super_block *, const char *, unsigned int,
+ const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
+#define ext4_error(sb, message...) __ext4_error(sb, __func__, \
+ __LINE__, ## message)
+extern void ext4_error_inode(struct inode *, const char *, unsigned int,
+ ext4_fsblk_t, const char *, ...)
+ __attribute__ ((format (printf, 5, 6)));
+extern void ext4_error_file(struct file *, const char *, unsigned int,
+ const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
+extern void __ext4_std_error(struct super_block *, const char *,
+ unsigned int, int);
+extern void __ext4_abort(struct super_block *, const char *, unsigned int,
+ const char *, ...)
+ __attribute__ ((format (printf, 4, 5)));
+#define ext4_abort(sb, message...) __ext4_abort(sb, __func__, \
+ __LINE__, ## message)
+extern void __ext4_warning(struct super_block *, const char *, unsigned int,
const char *, ...)
- __attribute__ ((format (printf, 3, 4)));
-#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, ## message)
+ __attribute__ ((format (printf, 4, 5)));
+#define ext4_warning(sb, message...) __ext4_warning(sb, __func__, \
+ __LINE__, ## message)
extern void ext4_msg(struct super_block *, const char *, const char *, ...)
__attribute__ ((format (printf, 3, 4)));
-extern void ext4_grp_locked_error(struct super_block *, ext4_group_t,
- const char *, const char *, ...)
- __attribute__ ((format (printf, 4, 5)));
+extern void __ext4_grp_locked_error(const char *, unsigned int, \
+ struct super_block *, ext4_group_t, \
+ unsigned long, ext4_fsblk_t, \
+ const char *, ...)
+ __attribute__ ((format (printf, 7, 8)));
+#define ext4_grp_locked_error(sb, grp, message...) \
+ __ext4_grp_locked_error(__func__, __LINE__, (sb), (grp), ## message)
extern void ext4_update_dynamic_rev(struct super_block *sb);
extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
__u32 compat);
#define ext4_std_error(sb, errno) \
do { \
if ((errno)) \
- __ext4_std_error((sb), __func__, (errno)); \
+ __ext4_std_error((sb), __func__, __LINE__, (errno)); \
} while (0)
#ifdef CONFIG_SMP
spin_unlock(ext4_group_lock_ptr(sb, group));
}
+static inline void ext4_mark_super_dirty(struct super_block *sb)
+{
+ if (EXT4_SB(sb)->s_journal == NULL)
+ sb->s_dirt =1;
+}
+
/*
* Inodes and files operations
*/
ssize_t len);
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
-extern int ext4_get_blocks(handle_t *handle, struct inode *inode,
- sector_t block, unsigned int max_blocks,
- struct buffer_head *bh, int flags);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
/* move_extent.c */
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
- clear_inode(inode);
+ ext4_clear_inode(inode);
es = EXT4_SB(sb)->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
- sb->s_dirt = 1;
+ ext4_mark_super_dirty(sb);
} else
ext4_error(sb, "bit already cleared for inode %lu", ino);
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
- sb->s_dirt = 1;
+ ext4_mark_super_dirty(sb);
if (sbi->s_log_groups_per_flex) {
flex_group = ext4_flex_group(sbi, group);
/*
* Called at the last iput() if i_nlink is zero.
*/
- void ext4_delete_inode(struct inode *inode)
+ void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
+ if (inode->i_nlink) {
+ truncate_inode_pages(&inode->i_data, 0);
+ goto no_delete;
+ }
+
if (!is_bad_inode(inode))
dquot_initialize(inode);
"couldn't extend journal (err %d)", err);
stop_handle:
ext4_journal_stop(handle);
+ ext4_orphan_del(NULL, inode);
goto no_delete;
}
}
*/
if (ext4_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
- clear_inode(inode);
+ ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
return;
no_delete:
- clear_inode(inode); /* We must guarantee clearing of inode... */
+ ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
typedef struct {
return n;
}
-static int __ext4_check_blockref(const char *function, struct inode *inode,
+static int __ext4_check_blockref(const char *function, unsigned int line,
+ struct inode *inode,
__le32 *p, unsigned int max)
{
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
__le32 *bref = p;
unsigned int blk;
if (blk &&
unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
blk, 1))) {
- ext4_error_inode(function, inode,
- "invalid block reference %u", blk);
+ es->s_last_error_block = cpu_to_le64(blk);
+ ext4_error_inode(inode, function, line, blk,
+ "invalid block");
return -EIO;
}
}
#define ext4_check_indirect_blockref(inode, bh) \
- __ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data, \
+ __ext4_check_blockref(__func__, __LINE__, inode, \
+ (__le32 *)(bh)->b_data, \
EXT4_ADDR_PER_BLOCK((inode)->i_sb))
#define ext4_check_inode_blockref(inode) \
- __ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data, \
+ __ext4_check_blockref(__func__, __LINE__, inode, \
+ EXT4_I(inode)->i_data, \
EXT4_NDIR_BLOCKS)
/**
ext4_discard_preallocations(inode);
}
-static int check_block_validity(struct inode *inode, const char *func,
+static int __check_block_validity(struct inode *inode, const char *func,
+ unsigned int line,
struct ext4_map_blocks *map)
{
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
map->m_len)) {
- ext4_error_inode(func, inode,
- "lblock %lu mapped to illegal pblock %llu "
- "(length %d)", (unsigned long) map->m_lblk,
- map->m_pblk, map->m_len);
+ ext4_error_inode(inode, func, line, map->m_pblk,
+ "lblock %lu mapped to illegal pblock "
+ "(length %d)", (unsigned long) map->m_lblk,
+ map->m_len);
return -EIO;
}
return 0;
}
+#define check_block_validity(inode, map) \
+ __check_block_validity((inode), __func__, __LINE__, (map))
+
/*
* Return the number of contiguous dirty pages in a given inode
* starting at page frame idx.
up_read((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret = check_block_validity(inode, __func__, map);
+ int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret = check_block_validity(inode,
- "ext4_map_blocks_after_alloc",
- map);
+ int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
static int do_journal_get_write_access(handle_t *handle,
struct buffer_head *bh)
{
+ int dirty = buffer_dirty(bh);
+ int ret;
+
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
- return ext4_journal_get_write_access(handle, bh);
+ /*
+ * __block_prepare_write() could have dirtied some buffers. Clean
+ * the dirty bit as jbd2_journal_get_write_access() could complain
+ * otherwise about fs integrity issues. Setting of the dirty bit
+ * by __block_prepare_write() isn't a real problem here as we clear
+ * the bit before releasing a page lock and thus writeback cannot
+ * ever write the buffer.
+ */
+ if (dirty)
+ clear_buffer_dirty(bh);
+ ret = ext4_journal_get_write_access(handle, bh);
+ if (!ret && dirty)
+ ret = ext4_handle_dirty_metadata(handle, NULL, bh);
+ return ret;
}
/*
*pagep = page;
if (ext4_should_dioread_nolock(inode))
- ret = block_write_begin(file, mapping, pos, len, flags, pagep,
- fsdata, ext4_get_block_write);
+ ret = __block_write_begin(page, pos, len, ext4_get_block_write);
else
- ret = block_write_begin(file, mapping, pos, len, flags, pagep,
- fsdata, ext4_get_block);
+ ret = __block_write_begin(page, pos, len, ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
unlock_page(page);
page_cache_release(page);
/*
- * block_write_begin may have instantiated a few blocks
+ * __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold i_mutex.
*
BUG_ON(!handle);
/*
- * Call ext4_get_blocks() to allocate any delayed allocation
+ * Call ext4_map_blocks() to allocate any delayed allocation
* blocks, or to convert an uninitialized extent to be
* initialized (in the case where we have written into
* one or more preallocated blocks).
* indicate that we are on the delayed allocation path. This
* affects functions in many different parts of the allocation
* call path. This flag exists primarily because we don't
- * want to change *many* call functions, so ext4_get_blocks()
+ * want to change *many* call functions, so ext4_map_blocks()
* will set the magic i_delalloc_reserved_flag once the
* inode's allocation semaphore is taken.
*
blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
if (blks < 0) {
+ struct super_block *sb = mpd->inode->i_sb;
+
err = blks;
/*
* If get block returns with error we simply
return 0;
if (err == -ENOSPC &&
- ext4_count_free_blocks(mpd->inode->i_sb)) {
+ ext4_count_free_blocks(sb)) {
mpd->retval = err;
return 0;
}
* writepage and writepages will again try to write
* the same.
*/
- ext4_msg(mpd->inode->i_sb, KERN_CRIT,
- "delayed block allocation failed for inode %lu at "
- "logical offset %llu with max blocks %zd with "
- "error %d", mpd->inode->i_ino,
- (unsigned long long) next,
- mpd->b_size >> mpd->inode->i_blkbits, err);
- printk(KERN_CRIT "This should not happen!! "
- "Data will be lost\n");
- if (err == -ENOSPC) {
- ext4_print_free_blocks(mpd->inode);
+ if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ ext4_msg(sb, KERN_CRIT,
+ "delayed block allocation failed for inode %lu "
+ "at logical offset %llu with max blocks %zd "
+ "with error %d", mpd->inode->i_ino,
+ (unsigned long long) next,
+ mpd->b_size >> mpd->inode->i_blkbits, err);
+ ext4_msg(sb, KERN_CRIT,
+ "This should not happen!! Data will be lost\n");
+ if (err == -ENOSPC)
+ ext4_print_free_blocks(mpd->inode);
}
/* invalidate all the pages */
ext4_da_block_invalidatepages(mpd, next,
* XXX Don't go larger than mballoc is willing to allocate
* This is a stopgap solution. We eventually need to fold
* mpage_da_submit_io() into this function and then call
- * ext4_get_blocks() multiple times in a loop
+ * ext4_map_blocks() multiple times in a loop
*/
if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
goto flush_it;
/*
* This function is used as a standard get_block_t calback function
* when there is no desire to allocate any blocks. It is used as a
- * callback function for block_prepare_write(), nobh_writepage(), and
- * block_write_full_page(). These functions should only try to map a
- * single block at a time.
+ * callback function for block_prepare_write() and block_write_full_page().
+ * These functions should only try to map a single block at a time.
*
* Since this function doesn't do block allocations even if the caller
* requests it by passing in create=1, it is critically important that
* any caller checks to make sure that any buffer heads are returned
* by this function are either all already mapped or marked for
- * delayed allocation before calling nobh_writepage() or
- * block_write_full_page(). Otherwise, b_blocknr could be left
- * unitialized, and the page write functions will be taken by
- * surprise.
+ * delayed allocation before calling block_write_full_page(). Otherwise,
+ * b_blocknr could be left unitialized, and the page write functions will
+ * be taken by surprise.
*/
static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
return __ext4_journalled_writepage(page, len);
}
- if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
- ret = nobh_writepage(page, noalloc_get_block_write, wbc);
- else if (page_bufs && buffer_uninit(page_bufs)) {
+ if (page_bufs && buffer_uninit(page_bufs)) {
ext4_set_bh_endio(page_bufs, inode);
ret = block_write_full_page_endio(page, noalloc_get_block_write,
wbc, ext4_end_io_buffer_write);
int ret, retries = 0;
struct page *page;
pgoff_t index;
- unsigned from, to;
struct inode *inode = mapping->host;
handle_t *handle;
index = pos >> PAGE_CACHE_SHIFT;
- from = pos & (PAGE_CACHE_SIZE - 1);
- to = from + len;
if (ext4_nonda_switch(inode->i_sb)) {
*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
}
*pagep = page;
- ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- ext4_da_get_block_prep);
+ ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
retry:
if (rw == READ && ext4_should_dioread_nolock(inode))
- ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
+ ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
- ext4_get_block, NULL);
- else
+ ext4_get_block, NULL, NULL, 0);
+ else {
ret = blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block, NULL);
+
+ if (unlikely((rw & WRITE) && ret < 0)) {
+ loff_t isize = i_size_read(inode);
+ loff_t end = offset + iov_length(iov, nr_segs);
+
+ if (end > isize)
+ vmtruncate(inode, isize);
+ }
+ }
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
return ret;
}
+ if (io->iocb)
+ aio_complete(io->iocb, io->result, 0);
/* clear the DIO AIO unwritten flag */
io->flag = 0;
return ret;
io->offset = 0;
io->size = 0;
io->page = NULL;
+ io->iocb = NULL;
+ io->result = 0;
INIT_WORK(&io->work, ext4_end_io_work);
INIT_LIST_HEAD(&io->list);
}
if (io_end->flag != EXT4_IO_UNWRITTEN){
ext4_free_io_end(io_end);
iocb->private = NULL;
- goto out;
+out:
+ if (is_async)
+ aio_complete(iocb, ret, 0);
+ return;
}
io_end->offset = offset;
io_end->size = size;
- io_end->flag = EXT4_IO_UNWRITTEN;
+ if (is_async) {
+ io_end->iocb = iocb;
+ io_end->result = ret;
+ }
wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
/* queue the work to convert unwritten extents to written */
list_add_tail(&io_end->list, &ei->i_completed_io_list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
iocb->private = NULL;
-out:
- if (is_async)
- aio_complete(iocb, ret, 0);
}
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
return -ENOMEM;
/*
* we save the io structure for current async
- * direct IO, so that later ext4_get_blocks()
+ * direct IO, so that later ext4_map_blocks()
* could flag the io structure whether there
* is a unwritten extents needs to be converted
* when IO is completed.
length = blocksize - (offset & (blocksize - 1));
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
- /*
- * For "nobh" option, we can only work if we don't need to
- * read-in the page - otherwise we create buffers to do the IO.
- */
- if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
- ext4_should_writeback_data(inode) && PageUptodate(page)) {
- zero_user(page, offset, length);
- set_page_dirty(page);
- goto unlock;
- }
-
if (!page_has_buffers(page))
create_empty_buffers(page, blocksize, 0);
* (should be rare).
*/
if (!bh) {
- EXT4_ERROR_INODE(inode,
- "Read failure block=%llu",
- (unsigned long long) nr);
+ EXT4_ERROR_INODE_BLOCK(inode, nr,
+ "Read failure");
continue;
}
(__le32 *) bh->b_data + addr_per_block,
depth);
- /*
- * We've probably journalled the indirect block several
- * times during the truncate. But it's no longer
- * needed and we now drop it from the transaction via
- * jbd2_journal_revoke().
- *
- * That's easy if it's exclusively part of this
- * transaction. But if it's part of the committing
- * transaction then jbd2_journal_forget() will simply
- * brelse() it. That means that if the underlying
- * block is reallocated in ext4_get_block(),
- * unmap_underlying_metadata() will find this block
- * and will try to get rid of it. damn, damn.
- *
- * If this block has already been committed to the
- * journal, a revoke record will be written. And
- * revoke records must be emitted *before* clearing
- * this block's bit in the bitmaps.
- */
- ext4_forget(handle, 1, inode, bh, bh->b_blocknr);
-
/*
* Everything below this this pointer has been
* released. Now let this top-of-subtree go.
blocks_for_truncate(inode));
}
+ /*
+ * The forget flag here is critical because if
+ * we are journaling (and not doing data
+ * journaling), we have to make sure a revoke
+ * record is written to prevent the journal
+ * replay from overwriting the (former)
+ * indirect block if it gets reallocated as a
+ * data block. This must happen in the same
+ * transaction where the data blocks are
+ * actually freed.
+ */
ext4_free_blocks(handle, inode, 0, nr, 1,
- EXT4_FREE_BLOCKS_METADATA);
+ EXT4_FREE_BLOCKS_METADATA|
+ EXT4_FREE_BLOCKS_FORGET);
if (parent_bh) {
/*
bh = sb_getblk(sb, block);
if (!bh) {
- EXT4_ERROR_INODE(inode, "unable to read inode block - "
- "block %llu", block);
+ EXT4_ERROR_INODE_BLOCK(inode, block,
+ "unable to read itable block");
return -EIO;
}
if (!buffer_uptodate(bh)) {
submit_bh(READ_META, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
- EXT4_ERROR_INODE(inode, "unable to read inode "
- "block %llu", block);
+ EXT4_ERROR_INODE_BLOCK(inode, block,
+ "unable to read itable block");
brelse(bh);
return -EIO;
}
/* we are using combined 48 bit field */
i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 |
le32_to_cpu(raw_inode->i_blocks_lo);
- if (ei->i_flags & EXT4_HUGE_FILE_FL) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) {
/* i_blocks represent file system block size */
return i_blocks << (inode->i_blkbits - 9);
} else {
transaction_t *transaction;
tid_t tid;
- spin_lock(&journal->j_state_lock);
+ read_lock(&journal->j_state_lock);
if (journal->j_running_transaction)
transaction = journal->j_running_transaction;
else
tid = transaction->t_tid;
else
tid = journal->j_commit_sequence;
- spin_unlock(&journal->j_state_lock);
+ read_unlock(&journal->j_state_lock);
ei->i_sync_tid = tid;
ei->i_datasync_tid = tid;
}
ei->i_file_acl);
ret = -EIO;
goto bad_inode;
- } else if (ei->i_flags & EXT4_EXTENTS_FL) {
+ } else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode)))
if (wbc->sync_mode == WB_SYNC_ALL)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
- EXT4_ERROR_INODE(inode,
- "IO error syncing inode (block=%llu)",
- (unsigned long long) iloc.bh->b_blocknr);
+ EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
+ "IO error syncing inode");
err = -EIO;
}
brelse(iloc.bh);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if (attr->ia_size > sbi->s_bitmap_maxbytes) {
- error = -EFBIG;
- goto err_out;
- }
+ if (attr->ia_size > sbi->s_bitmap_maxbytes)
+ return -EFBIG;
}
}
ext4_truncate(inode);
}
- rc = inode_setattr(inode, attr);
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode))
+ rc = vmtruncate(inode, attr->ia_size);
- /* If inode_setattr's call to ext4_truncate failed to get a
- * transaction handle at all, we need to clean up the in-core
- * orphan list manually. */
+ if (!rc) {
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+ }
+
+ /*
+ * If the call to ext4_truncate failed to get a transaction handle at
+ * all, we need to clean up the in-core orphan list manually.
+ */
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
* Calculate the journal credits for a chunk of data modification.
*
* This is called from DIO, fallocate or whoever calling
- * ext4_get_blocks() to map/allocate a chunk of contiguous disk blocks.
+ * ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks.
*
* journal buffers for data blocks are not included here, as DIO
* and fallocate do no need to journal data buffers.
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
- struct ext4_xattr_entry *entry;
if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
return 0;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
- entry = IFIRST(header);
/* No extended attributes present */
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
- vfs_check_frozen(sb, SB_FREEZE_WRITE);
+ vfs_check_frozen(sb, SB_FREEZE_TRANS);
/* Special case here: if the journal has aborted behind our
* backs (eg. EIO in the commit thread), then we still need to
* take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
if (journal) {
if (is_journal_aborted(journal)) {
- ext4_abort(sb, __func__, "Detected aborted journal");
+ ext4_abort(sb, "Detected aborted journal");
return ERR_PTR(-EROFS);
}
return jbd2_journal_start(journal, nblocks);
* that sync() will call the filesystem's write_super callback if
* appropriate.
*/
-int __ext4_journal_stop(const char *where, handle_t *handle)
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
struct super_block *sb;
int err;
if (!err)
err = rc;
if (err)
- __ext4_std_error(sb, where, err);
+ __ext4_std_error(sb, where, line, err);
return err;
}
-void ext4_journal_abort_handle(const char *caller, const char *err_fn,
- struct buffer_head *bh, handle_t *handle, int err)
+void ext4_journal_abort_handle(const char *caller, unsigned int line,
+ const char *err_fn, struct buffer_head *bh,
+ handle_t *handle, int err)
{
char nbuf[16];
const char *errstr = ext4_decode_error(NULL, err, nbuf);
if (is_handle_aborted(handle))
return;
- printk(KERN_ERR "%s: aborting transaction: %s in %s\n",
- caller, errstr, err_fn);
+ printk(KERN_ERR "%s:%d: aborting transaction: %s in %s\n",
+ caller, line, errstr, err_fn);
jbd2_journal_abort_handle(handle);
}
+static void __save_error_info(struct super_block *sb, const char *func,
+ unsigned int line)
+{
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ es->s_last_error_time = cpu_to_le32(get_seconds());
+ strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
+ es->s_last_error_line = cpu_to_le32(line);
+ if (!es->s_first_error_time) {
+ es->s_first_error_time = es->s_last_error_time;
+ strncpy(es->s_first_error_func, func,
+ sizeof(es->s_first_error_func));
+ es->s_first_error_line = cpu_to_le32(line);
+ es->s_first_error_ino = es->s_last_error_ino;
+ es->s_first_error_block = es->s_last_error_block;
+ }
+ /*
+ * Start the daily error reporting function if it hasn't been
+ * started already
+ */
+ if (!es->s_error_count)
+ mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
+ es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
+}
+
+static void save_error_info(struct super_block *sb, const char *func,
+ unsigned int line)
+{
+ __save_error_info(sb, func, line);
+ ext4_commit_super(sb, 1);
+}
+
+
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
static void ext4_handle_error(struct super_block *sb)
{
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
-
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-
if (sb->s_flags & MS_RDONLY)
return;
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
sb->s_flags |= MS_RDONLY;
}
- ext4_commit_super(sb, 1);
if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
void __ext4_error(struct super_block *sb, const char *function,
- const char *fmt, ...)
+ unsigned int line, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: ",
+ sb->s_id, function, line, current->comm);
vprintk(fmt, args);
printk("\n");
va_end(args);
ext4_handle_error(sb);
}
-void ext4_error_inode(const char *function, struct inode *inode,
+void ext4_error_inode(struct inode *inode, const char *function,
+ unsigned int line, ext4_fsblk_t block,
const char *fmt, ...)
{
va_list args;
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+ es->s_last_error_block = cpu_to_le64(block);
+ save_error_info(inode->i_sb, function, line);
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s: inode #%lu: (comm %s) ",
- inode->i_sb->s_id, function, inode->i_ino, current->comm);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: inode #%lu: ",
+ inode->i_sb->s_id, function, line, inode->i_ino);
+ if (block)
+ printk("block %llu: ", block);
+ printk("comm %s: ", current->comm);
vprintk(fmt, args);
printk("\n");
va_end(args);
ext4_handle_error(inode->i_sb);
}
-void ext4_error_file(const char *function, struct file *file,
- const char *fmt, ...)
+void ext4_error_file(struct file *file, const char *function,
+ unsigned int line, const char *fmt, ...)
{
va_list args;
+ struct ext4_super_block *es;
struct inode *inode = file->f_dentry->d_inode;
char pathname[80], *path;
+ es = EXT4_SB(inode->i_sb)->s_es;
+ es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+ save_error_info(inode->i_sb, function, line);
va_start(args, fmt);
path = d_path(&(file->f_path), pathname, sizeof(pathname));
if (!path)
path = "(unknown)";
printk(KERN_CRIT
- "EXT4-fs error (device %s): %s: inode #%lu (comm %s path %s): ",
- inode->i_sb->s_id, function, inode->i_ino, current->comm, path);
+ "EXT4-fs error (device %s): %s:%d: inode #%lu "
+ "(comm %s path %s): ",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, path);
vprintk(fmt, args);
printk("\n");
va_end(args);
/* __ext4_std_error decodes expected errors from journaling functions
* automatically and invokes the appropriate error response. */
-void __ext4_std_error(struct super_block *sb, const char *function, int errno)
+void __ext4_std_error(struct super_block *sb, const char *function,
+ unsigned int line, int errno)
{
char nbuf[16];
const char *errstr;
return;
errstr = ext4_decode_error(sb, errno, nbuf);
- printk(KERN_CRIT "EXT4-fs error (device %s) in %s: %s\n",
- sb->s_id, function, errstr);
+ printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
+ sb->s_id, function, line, errstr);
+ save_error_info(sb, function, line);
ext4_handle_error(sb);
}
* case we take the easy way out and panic immediately.
*/
-void ext4_abort(struct super_block *sb, const char *function,
- const char *fmt, ...)
+void __ext4_abort(struct super_block *sb, const char *function,
+ unsigned int line, const char *fmt, ...)
{
va_list args;
+ save_error_info(sb, function, line);
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id,
+ function, line);
vprintk(fmt, args);
printk("\n");
va_end(args);
+ if ((sb->s_flags & MS_RDONLY) == 0) {
+ ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+ sb->s_flags |= MS_RDONLY;
+ EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ if (EXT4_SB(sb)->s_journal)
+ jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+ save_error_info(sb, function, line);
+ }
if (test_opt(sb, ERRORS_PANIC))
panic("EXT4-fs panic from previous error\n");
-
- if (sb->s_flags & MS_RDONLY)
- return;
-
- ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- sb->s_flags |= MS_RDONLY;
- EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
- if (EXT4_SB(sb)->s_journal)
- jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
}
void ext4_msg (struct super_block * sb, const char *prefix,
}
void __ext4_warning(struct super_block *sb, const char *function,
- const char *fmt, ...)
+ unsigned int line, const char *fmt, ...)
{
va_list args;
va_start(args, fmt);
- printk(KERN_WARNING "EXT4-fs warning (device %s): %s: ",
- sb->s_id, function);
+ printk(KERN_WARNING "EXT4-fs warning (device %s): %s:%d: ",
+ sb->s_id, function, line);
vprintk(fmt, args);
printk("\n");
va_end(args);
}
-void ext4_grp_locked_error(struct super_block *sb, ext4_group_t grp,
- const char *function, const char *fmt, ...)
+void __ext4_grp_locked_error(const char *function, unsigned int line,
+ struct super_block *sb, ext4_group_t grp,
+ unsigned long ino, ext4_fsblk_t block,
+ const char *fmt, ...)
__releases(bitlock)
__acquires(bitlock)
{
va_list args;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ es->s_last_error_ino = cpu_to_le32(ino);
+ es->s_last_error_block = cpu_to_le64(block);
+ __save_error_info(sb, function, line);
va_start(args, fmt);
- printk(KERN_CRIT "EXT4-fs error (device %s): %s: ", sb->s_id, function);
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u",
+ sb->s_id, function, line, grp);
+ if (ino)
+ printk("inode %lu: ", ino);
+ if (block)
+ printk("block %llu:", (unsigned long long) block);
vprintk(fmt, args);
printk("\n");
va_end(args);
if (test_opt(sb, ERRORS_CONT)) {
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
ext4_commit_super(sb, 0);
return;
}
+
ext4_unlock_group(sb, grp);
ext4_handle_error(sb);
/*
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
if (err < 0)
- ext4_abort(sb, __func__,
- "Couldn't clean up the journal");
+ ext4_abort(sb, "Couldn't clean up the journal");
}
ext4_release_system_zone(sb);
kmem_cache_destroy(ext4_inode_cachep);
}
- static void ext4_clear_inode(struct inode *inode)
+ void ext4_clear_inode(struct inode *inode)
{
+ invalidate_inode_buffers(inode);
+ end_writeback(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
if (EXT4_JOURNAL(inode))
seq_puts(seq, ",journal_async_commit");
else if (test_opt(sb, JOURNAL_CHECKSUM))
seq_puts(seq, ",journal_checksum");
- if (test_opt(sb, NOBH))
- seq_puts(seq, ",nobh");
if (test_opt(sb, I_VERSION))
seq_puts(seq, ",i_version");
- if (!test_opt(sb, DELALLOC))
+ if (!test_opt(sb, DELALLOC) &&
+ !(def_mount_opts & EXT4_DEFM_NODELALLOC))
seq_puts(seq, ",nodelalloc");
-
if (sbi->s_stripe)
seq_printf(seq, ",stripe=%lu", sbi->s_stripe);
/*
if (test_opt(sb, NO_AUTO_DA_ALLOC))
seq_puts(seq, ",noauto_da_alloc");
- if (test_opt(sb, DISCARD))
+ if (test_opt(sb, DISCARD) && !(def_mount_opts & EXT4_DEFM_DISCARD))
seq_puts(seq, ",discard");
if (test_opt(sb, NOLOAD))
if (test_opt(sb, DIOREAD_NOLOCK))
seq_puts(seq, ",dioread_nolock");
+ if (test_opt(sb, BLOCK_VALIDITY) &&
+ !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY))
+ seq_puts(seq, ",block_validity");
+
ext4_show_quota_options(seq, sb);
return 0;
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
char *path);
+static int ext4_quota_off(struct super_block *sb, int type);
static int ext4_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
static const struct quotactl_ops ext4_qctl_operations = {
.quota_on = ext4_quota_on,
- .quota_off = dquot_quota_off,
+ .quota_off = ext4_quota_off,
.quota_sync = dquot_quota_sync,
.get_info = dquot_get_dqinfo,
.set_info = dquot_set_dqinfo,
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
- .delete_inode = ext4_delete_inode,
+ .evict_inode = ext4_evict_inode,
.put_super = ext4_put_super,
.sync_fs = ext4_sync_fs,
.freeze_fs = ext4_freeze,
.unfreeze_fs = ext4_unfreeze,
.statfs = ext4_statfs,
.remount_fs = ext4_remount,
- .clear_inode = ext4_clear_inode,
.show_options = ext4_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext4_quota_read,
.destroy_inode = ext4_destroy_inode,
.write_inode = ext4_write_inode,
.dirty_inode = ext4_dirty_inode,
- .delete_inode = ext4_delete_inode,
+ .evict_inode = ext4_evict_inode,
.write_super = ext4_write_super,
.put_super = ext4_put_super,
.statfs = ext4_statfs,
.remount_fs = ext4_remount,
- .clear_inode = ext4_clear_inode,
.show_options = ext4_show_options,
#ifdef CONFIG_QUOTA
.quota_read = ext4_quota_read,
*n_blocks_count = option;
break;
case Opt_nobh:
- set_opt(sbi->s_mount_opt, NOBH);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated nobh option");
break;
case Opt_bh:
- clear_opt(sbi->s_mount_opt, NOBH);
+ ext4_msg(sb, KERN_WARNING,
+ "Ignoring deprecated bh option");
break;
case Opt_i_version:
set_opt(sbi->s_mount_opt, I_VERSION);
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%lu\n",
(part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
sbi->s_sectors_written_start) >> 1);
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
return 1;
}
+/*
+ * This function is called once a day if we have errors logged
+ * on the file system
+ */
+static void print_daily_error_info(unsigned long arg)
+{
+ struct super_block *sb = (struct super_block *) arg;
+ struct ext4_sb_info *sbi;
+ struct ext4_super_block *es;
+
+ sbi = EXT4_SB(sb);
+ es = sbi->s_es;
+
+ if (es->s_error_count)
+ ext4_msg(sb, KERN_NOTICE, "error count: %u",
+ le32_to_cpu(es->s_error_count));
+ if (es->s_first_error_time) {
+ printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+ sb->s_id, le32_to_cpu(es->s_first_error_time),
+ (int) sizeof(es->s_first_error_func),
+ es->s_first_error_func,
+ le32_to_cpu(es->s_first_error_line));
+ if (es->s_first_error_ino)
+ printk(": inode %u",
+ le32_to_cpu(es->s_first_error_ino));
+ if (es->s_first_error_block)
+ printk(": block %llu", (unsigned long long)
+ le64_to_cpu(es->s_first_error_block));
+ printk("\n");
+ }
+ if (es->s_last_error_time) {
+ printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+ sb->s_id, le32_to_cpu(es->s_last_error_time),
+ (int) sizeof(es->s_last_error_func),
+ es->s_last_error_func,
+ le32_to_cpu(es->s_last_error_line));
+ if (es->s_last_error_ino)
+ printk(": inode %u",
+ le32_to_cpu(es->s_last_error_ino));
+ if (es->s_last_error_block)
+ printk(": block %llu", (unsigned long long)
+ le64_to_cpu(es->s_last_error_block));
+ printk("\n");
+ }
+ mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
struct inode *root;
char *cp;
const char *descr;
- int ret = -EINVAL;
+ int ret = -ENOMEM;
int blocksize;
unsigned int db_count;
unsigned int i;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
- return -ENOMEM;
+ goto out_free_orig;
sbi->s_blockgroup_lock =
kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
if (!sbi->s_blockgroup_lock) {
kfree(sbi);
- return -ENOMEM;
+ goto out_free_orig;
}
sb->s_fs_info = sbi;
sbi->s_mount_opt = 0;
sbi->s_resgid = EXT4_DEF_RESGID;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sb_block = sb_block;
- sbi->s_sectors_written_start = part_stat_read(sb->s_bdev->bd_part,
- sectors[1]);
+ if (sb->s_bdev->bd_part)
+ sbi->s_sectors_written_start =
+ part_stat_read(sb->s_bdev->bd_part, sectors[1]);
unlock_kernel();
for (cp = sb->s_id; (cp = strchr(cp, '/'));)
*cp = '!';
+ ret = -EINVAL;
blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
if (!blocksize) {
ext4_msg(sb, KERN_ERR, "unable to set blocksize");
set_opt(sbi->s_mount_opt, ERRORS_CONT);
else
set_opt(sbi->s_mount_opt, ERRORS_RO);
+ if (def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)
+ set_opt(sbi->s_mount_opt, BLOCK_VALIDITY);
+ if (def_mount_opts & EXT4_DEFM_DISCARD)
+ set_opt(sbi->s_mount_opt, DISCARD);
sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
- set_opt(sbi->s_mount_opt, BARRIER);
+ if ((def_mount_opts & EXT4_DEFM_NOBARRIER) == 0)
+ set_opt(sbi->s_mount_opt, BARRIER);
/*
* enable delayed allocation by default
* Use -o nodelalloc to turn it off
*/
- if (!IS_EXT3_SB(sb))
+ if (!IS_EXT3_SB(sb) &&
+ ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sbi->s_mount_opt, DELALLOC);
+ if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
+ &journal_devnum, &journal_ioprio, NULL, 0)) {
+ ext4_msg(sb, KERN_WARNING,
+ "failed to parse options in superblock: %s",
+ sbi->s_es->s_mount_opts);
+ }
if (!parse_options((char *) data, sb, &journal_devnum,
&journal_ioprio, NULL, 0))
goto failed_mount;
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount_wq;
}
- if (test_opt(sb, NOBH)) {
- if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
- ext4_msg(sb, KERN_WARNING, "Ignoring nobh option - "
- "its supported only with writeback mode");
- clear_opt(sbi->s_mount_opt, NOBH);
- }
- if (test_opt(sb, DIOREAD_NOLOCK)) {
- ext4_msg(sb, KERN_WARNING, "dioread_nolock option is "
- "not supported with nobh mode");
- goto failed_mount_wq;
- }
- }
+
EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
if (!EXT4_SB(sb)->dio_unwritten_wq) {
printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
ext4_ext_init(sb);
err = ext4_mb_init(sb, needs_recovery);
if (err) {
- ext4_msg(sb, KERN_ERR, "failed to initalize mballoc (%d)",
+ ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
goto failed_mount4;
}
descr = "out journal";
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
- "Opts: %s", descr, orig_data);
+ "Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
+ *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
+
+ init_timer(&sbi->s_err_report);
+ sbi->s_err_report.function = print_daily_error_info;
+ sbi->s_err_report.data = (unsigned long) sb;
+ if (es->s_error_count)
+ mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
lock_kernel();
kfree(orig_data);
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
lock_kernel();
+out_free_orig:
kfree(orig_data);
return ret;
}
journal->j_min_batch_time = sbi->s_min_batch_time;
journal->j_max_batch_time = sbi->s_max_batch_time;
- spin_lock(&journal->j_state_lock);
+ write_lock(&journal->j_state_lock);
if (test_opt(sb, BARRIER))
journal->j_flags |= JBD2_BARRIER;
else
journal->j_flags |= JBD2_ABORT_ON_SYNCDATA_ERR;
else
journal->j_flags &= ~JBD2_ABORT_ON_SYNCDATA_ERR;
- spin_unlock(&journal->j_state_lock);
+ write_unlock(&journal->j_state_lock);
}
static journal_t *ext4_get_journal(struct super_block *sb,
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER))
err = jbd2_journal_wipe(journal, !really_read_only);
- if (!err)
+ if (!err) {
+ char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
+ if (save)
+ memcpy(save, ((char *) es) +
+ EXT4_S_ERR_START, EXT4_S_ERR_LEN);
err = jbd2_journal_load(journal);
+ if (save)
+ memcpy(((char *) es) + EXT4_S_ERR_START,
+ save, EXT4_S_ERR_LEN);
+ kfree(save);
+ }
if (err) {
ext4_msg(sb, KERN_ERR, "error loading journal");
*/
if (!(sb->s_flags & MS_RDONLY))
es->s_wtime = cpu_to_le32(get_seconds());
- es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+ if (sb->s_bdev->bd_part)
+ es->s_kbytes_written =
+ cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1));
+ else
+ es->s_kbytes_written =
+ cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeblocks_counter));
es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive(
journal = EXT4_SB(sb)->s_journal;
if (journal) {
- vfs_check_frozen(sb, SB_FREEZE_WRITE);
+ vfs_check_frozen(sb, SB_FREEZE_TRANS);
ret = ext4_journal_force_commit(journal);
}
}
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
- ext4_abort(sb, __func__, "Abort forced by user");
+ ext4_abort(sb, "Abort forced by user");
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? MS_POSIXACL : 0);
return err;
}
+static int ext4_quota_off(struct super_block *sb, int type)
+{
+ /* Force all delayed allocation blocks to be allocated */
+ if (test_opt(sb, DELALLOC)) {
+ down_read(&sb->s_umount);
+ sync_filesystem(sb);
+ up_read(&sb->s_umount);
+ }
+
+ return dquot_quota_off(sb, type);
+}
+
/* Read data from quotafile - avoid pagecache and such because we cannot afford
* acquiring the locks... As quota files are never truncated and quota code
* itself serializes the operations (and noone else should touch the files)
ext4_lblk_t blk = off >> EXT4_BLOCK_SIZE_BITS(sb);
int err = 0;
int offset = off & (sb->s_blocksize - 1);
- int journal_quota = EXT4_SB(sb)->s_qf_names[type] != NULL;
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
- if (journal_quota) {
- err = ext4_journal_get_write_access(handle, bh);
- if (err) {
- brelse(bh);
- goto out;
- }
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
+ goto out;
}
lock_buffer(bh);
memcpy(bh->b_data+offset, data, len);
flush_dcache_page(bh->b_page);
unlock_buffer(bh);
- if (journal_quota)
- err = ext4_handle_dirty_metadata(handle, NULL, bh);
- else {
- /* Always do at least ordered writes for quotas */
- err = ext4_jbd2_file_inode(handle, inode);
- mark_buffer_dirty(bh);
- }
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
out:
if (err) {
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
- sb->s_dirt = 1;
- ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_super(handle, sb);
}
}
ea_bdebug(bh, "out of memory");
return;
}
- error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, &hash);
+ error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash);
if (error) {
mb_cache_entry_free(ce);
if (error == -EBUSY) {
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
again:
- ce = mb_cache_entry_find_first(ext4_xattr_cache, 0,
- inode->i_sb->s_bdev, hash);
+ ce = mb_cache_entry_find_first(ext4_xattr_cache, inode->i_sb->s_bdev,
+ hash);
while (ce) {
struct buffer_head *bh;
return bh;
}
brelse(bh);
- ce = mb_cache_entry_find_next(ce, 0, inode->i_sb->s_bdev, hash);
+ ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash);
}
return NULL;
}
int __init
init_ext4_xattr(void)
{
- ext4_xattr_cache = mb_cache_create("ext4_xattr", NULL,
- sizeof(struct mb_cache_entry) +
- sizeof(((struct mb_cache_entry *) 0)->e_indexes[0]), 1, 6);
+ ext4_xattr_cache = mb_cache_create("ext4_xattr", 6);
if (!ext4_xattr_cache)
return -ENOMEM;
return 0;
static int vxfs_remount(struct super_block *, int *, char *);
static const struct super_operations vxfs_super_ops = {
- .clear_inode = vxfs_clear_inode,
+ .evict_inode = vxfs_evict_inode,
.put_super = vxfs_put_super,
.statfs = vxfs_statfs,
.remount_fs = vxfs_remount,
}
/**
- * vxfs_read_super - read superblock into memory and initalize filesystem
+ * vxfs_read_super - read superblock into memory and initialize filesystem
* @sbp: VFS superblock (to fill)
* @dp: fs private mount data
* @silent: do not complain loudly when sth is wrong
spin_lock(&inode_lock);
inode->i_state &= ~I_SYNC;
- if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
+ if (!(inode->i_state & I_FREEING)) {
if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
/*
* More pages get dirtied by a fast dirtier.
if (inode_dirtied_after(inode, wbc->wb_start))
return 1;
- BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
+ BUG_ON(inode->i_state & I_FREEING);
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
{
int ret = 0;
- wbc->wb_start = jiffies; /* livelock avoidance */
+ if (!wbc->wb_start)
+ wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&wb->b_io))
queue_io(wb, wbc->older_than_this);
{
WARN_ON(!rwsem_is_locked(&sb->s_umount));
- wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&wb->b_io))
queue_io(wb, wbc->older_than_this);
wbc.range_end = LLONG_MAX;
}
+ wbc.wb_start = jiffies; /* livelock avoidance */
for (;;) {
/*
* Stop writeback when nr_pages has been consumed
if (hlist_unhashed(&inode->i_hash))
goto out;
}
- if (inode->i_state & (I_FREEING|I_CLEAR))
+ if (inode->i_state & I_FREEING)
goto out;
/*
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping;
- if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+ if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
continue;
mapping = inode->i_mapping;
if (mapping->nrpages == 0)
exist. So if permissions are revoked this won't be
noticed immediately, only after the attribute
timeout has expired */
- } else if (mask & MAY_ACCESS) {
+ } else if (mask & (MAY_ACCESS | MAY_CHDIR)) {
err = fuse_access(inode, mask);
} else if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
if (!(inode->i_mode & S_IXUGO)) {
if (!fuse_allow_task(fc, current))
return -EACCES;
- if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
- err = inode_change_ok(inode, attr);
- if (err)
- return err;
- }
+ if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
+ attr->ia_valid |= ATTR_FORCE;
+
+ err = inode_change_ok(inode, attr);
+ if (err)
+ return err;
if ((attr->ia_valid & ATTR_OPEN) && fc->atomic_o_trunc)
return 0;
- if (attr->ia_valid & ATTR_SIZE) {
- err = inode_newsize_ok(inode, attr->ia_size);
- if (err)
- return err;
+ if (attr->ia_valid & ATTR_SIZE)
is_truncate = true;
- }
req = fuse_get_req(fc);
if (IS_ERR(req))
if (ret <= 0)
return ret;
- ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc);
- if (ret == -EAGAIN)
- ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
- return ret;
+ return nobh_writepage(page, gfs2_get_block_noalloc, wbc);
}
/**
}
}
- error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
- if (error)
- goto out_unlock;
+ alloc_required = gfs2_write_alloc_required(ip, pos, len);
if (alloc_required || gfs2_is_jdata(ip))
gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
page_cache_release(page);
/*
- * XXX(hch): the call below should probably be replaced with
+ * XXX(truncate): the call below should probably be replaced with
* a call to the gfs2-specific truncate blocks helper to actually
* release disk blocks..
*/
if (pos + len > ip->i_inode.i_size)
- simple_setsize(&ip->i_inode, ip->i_inode.i_size);
+ truncate_setsize(&ip->i_inode, ip->i_inode.i_size);
out_endtrans:
gfs2_trans_end(sdp);
out_trans_fail:
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
- rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
- iov, offset, nr_segs,
- gfs2_get_block_direct, NULL);
+ rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ offset, nr_segs, gfs2_get_block_direct,
+ NULL, NULL, 0);
out:
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
- int ar;
- int error;
if (ip->i_disksize < (8 << 20) || ip->i_disksize > (1 << 30) ||
(ip->i_disksize & (sdp->sd_sb.sb_bsize - 1))) {
}
jd->jd_blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
- error = gfs2_write_alloc_required(ip, 0, ip->i_disksize, &ar);
- if (!error && ar) {
+ if (gfs2_write_alloc_required(ip, 0, ip->i_disksize)) {
gfs2_consist_inode(ip);
- error = -EIO;
+ return -EIO;
}
- return error;
+ return 0;
}
/**
* node for later deallocation.
*/
- static void gfs2_drop_inode(struct inode *inode)
+ static int gfs2_drop_inode(struct inode *inode)
{
struct gfs2_inode *ip = GFS2_I(inode);
if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
clear_nlink(inode);
}
- generic_drop_inode(inode);
- }
-
- /**
- * gfs2_clear_inode - Deallocate an inode when VFS is done with it
- * @inode: The VFS inode
- *
- */
-
- static void gfs2_clear_inode(struct inode *inode)
- {
- struct gfs2_inode *ip = GFS2_I(inode);
-
- ip->i_gl->gl_object = NULL;
- gfs2_glock_put(ip->i_gl);
- ip->i_gl = NULL;
- if (ip->i_iopen_gh.gh_gl) {
- ip->i_iopen_gh.gh_gl->gl_object = NULL;
- gfs2_glock_dq_uninit(&ip->i_iopen_gh);
- }
+ return generic_drop_inode(inode);
}
static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
* is safe, just less efficient.
*/
- static void gfs2_delete_inode(struct inode *inode)
+ static void gfs2_evict_inode(struct inode *inode)
{
struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
+ if (inode->i_nlink)
+ goto out;
+
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (unlikely(error)) {
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
gfs2_holder_uninit(&ip->i_iopen_gh);
gfs2_glock_dq_uninit(&gh);
if (error && error != GLR_TRYFAILED && error != -EROFS)
- fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
+ fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
out:
truncate_inode_pages(&inode->i_data, 0);
- clear_inode(inode);
+ end_writeback(inode);
+
+ ip->i_gl->gl_object = NULL;
+ gfs2_glock_put(ip->i_gl);
+ ip->i_gl = NULL;
+ if (ip->i_iopen_gh.gh_gl) {
+ ip->i_iopen_gh.gh_gl->gl_object = NULL;
+ gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+ }
}
static struct inode *gfs2_alloc_inode(struct super_block *sb)
.alloc_inode = gfs2_alloc_inode,
.destroy_inode = gfs2_destroy_inode,
.write_inode = gfs2_write_inode,
- .delete_inode = gfs2_delete_inode,
+ .evict_inode = gfs2_evict_inode,
.put_super = gfs2_put_super,
.sync_fs = gfs2_sync_fs,
.freeze_fs = gfs2_freeze,
.unfreeze_fs = gfs2_unfreeze,
.statfs = gfs2_statfs,
.remount_fs = gfs2_remount_fs,
- .clear_inode = gfs2_clear_inode,
.drop_inode = gfs2_drop_inode,
.show_options = gfs2_show_options,
};
#define NCP_DEFAULT_TIME_OUT 10
#define NCP_DEFAULT_RETRY_COUNT 20
- static void ncp_delete_inode(struct inode *);
+ static void ncp_evict_inode(struct inode *);
static void ncp_put_super(struct super_block *);
static int ncp_statfs(struct dentry *, struct kstatfs *);
static int ncp_show_options(struct seq_file *, struct vfsmount *);
.alloc_inode = ncp_alloc_inode,
.destroy_inode = ncp_destroy_inode,
.drop_inode = generic_delete_inode,
- .delete_inode = ncp_delete_inode,
+ .evict_inode = ncp_evict_inode,
.put_super = ncp_put_super,
.statfs = ncp_statfs,
.remount_fs = ncp_remount,
}
static void
- ncp_delete_inode(struct inode *inode)
+ ncp_evict_inode(struct inode *inode)
{
truncate_inode_pages(&inode->i_data, 0);
+ end_writeback(inode);
if (S_ISDIR(inode->i_mode)) {
- DDPRINTK("ncp_delete_inode: put directory %ld\n", inode->i_ino);
+ DDPRINTK("ncp_evict_inode: put directory %ld\n", inode->i_ino);
}
if (ncp_make_closed(inode) != 0) {
/* We can't do anything but complain. */
- printk(KERN_ERR "ncp_delete_inode: could not close\n");
+ printk(KERN_ERR "ncp_evict_inode: could not close\n");
}
- clear_inode(inode);
}
static void ncp_stop_tasks(struct ncp_server *server) {
out_bdi:
/* 23/12/1998 Marcin Dalecki <dalecki@cs.net.pl>:
*
- * The previously used put_filp(ncp_filp); was bogous, since
- * it doesn't proper unlocking.
+ * The previously used put_filp(ncp_filp); was bogus, since
+ * it doesn't perform proper unlocking.
*/
fput(ncp_filp);
out:
tmpattr.ia_valid = ATTR_MODE;
tmpattr.ia_mode = attr->ia_mode;
- result = inode_setattr(inode, &tmpattr);
- if (result)
- goto out;
+ setattr_copy(inode, &tmpattr);
+ mark_inode_dirty(inode);
}
}
#endif
result = ncp_make_closed(inode);
if (result)
goto out;
- {
- struct iattr tmpattr;
-
- tmpattr.ia_valid = ATTR_SIZE;
- tmpattr.ia_size = attr->ia_size;
-
- result = inode_setattr(inode, &tmpattr);
+
+ if (attr->ia_size != i_size_read(inode)) {
+ result = vmtruncate(inode, attr->ia_size);
if (result)
goto out;
+ mark_inode_dirty(inode);
}
}
if ((attr->ia_valid & ATTR_CTIME) != 0) {
NCP_FINFO(inode)->nwattr = info.attributes;
#endif
}
- if (!result)
- result = inode_setattr(inode, attr);
+ if (result)
+ goto out;
+
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+
out:
unlock_kernel();
return result;
return ino;
}
- void nfs_clear_inode(struct inode *inode)
+ static void nfs_clear_inode(struct inode *inode)
{
/*
* The following should never happen...
nfs_fscache_release_inode_cookie(inode);
}
+ void nfs_evict_inode(struct inode *inode)
+ {
+ truncate_inode_pages(&inode->i_data, 0);
+ end_writeback(inode);
+ nfs_clear_inode(inode);
+ }
+
/**
* nfs_sync_mapping - helper to flush all mmapped dirty data to disk
*/
return 0;
/* Write all dirty data */
- if (S_ISREG(inode->i_mode)) {
- filemap_write_and_wait(inode->i_mapping);
+ if (S_ISREG(inode->i_mode))
nfs_wb_all(inode);
- }
fattr = nfs_alloc_fattr();
if (fattr == NULL)
return err;
}
+static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
+{
+ atomic_set(&l_ctx->count, 1);
+ l_ctx->lockowner = current->files;
+ l_ctx->pid = current->tgid;
+ INIT_LIST_HEAD(&l_ctx->list);
+}
+
+static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
+{
+ struct nfs_lock_context *pos;
+
+ list_for_each_entry(pos, &ctx->lock_context.list, list) {
+ if (pos->lockowner != current->files)
+ continue;
+ if (pos->pid != current->tgid)
+ continue;
+ atomic_inc(&pos->count);
+ return pos;
+ }
+ return NULL;
+}
+
+struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
+{
+ struct nfs_lock_context *res, *new = NULL;
+ struct inode *inode = ctx->path.dentry->d_inode;
+
+ spin_lock(&inode->i_lock);
+ res = __nfs_find_lock_context(ctx);
+ if (res == NULL) {
+ spin_unlock(&inode->i_lock);
+ new = kmalloc(sizeof(*new), GFP_KERNEL);
+ if (new == NULL)
+ return NULL;
+ nfs_init_lock_context(new);
+ spin_lock(&inode->i_lock);
+ res = __nfs_find_lock_context(ctx);
+ if (res == NULL) {
+ list_add_tail(&new->list, &ctx->lock_context.list);
+ new->open_context = ctx;
+ res = new;
+ new = NULL;
+ }
+ }
+ spin_unlock(&inode->i_lock);
+ kfree(new);
+ return res;
+}
+
+void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
+{
+ struct nfs_open_context *ctx = l_ctx->open_context;
+ struct inode *inode = ctx->path.dentry->d_inode;
+
+ if (!atomic_dec_and_lock(&l_ctx->count, &inode->i_lock))
+ return;
+ list_del(&l_ctx->list);
+ spin_unlock(&inode->i_lock);
+ kfree(l_ctx);
+}
+
/**
* nfs_close_context - Common close_context() routine NFSv2/v3
* @ctx: pointer to context
path_get(&ctx->path);
ctx->cred = get_rpccred(cred);
ctx->state = NULL;
- ctx->lockowner = current->files;
ctx->flags = 0;
ctx->error = 0;
ctx->dir_cookie = 0;
- atomic_set(&ctx->count, 1);
+ nfs_init_lock_context(&ctx->lock_context);
+ ctx->lock_context.open_context = ctx;
}
return ctx;
}
struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
if (ctx != NULL)
- atomic_inc(&ctx->count);
+ atomic_inc(&ctx->lock_context.count);
return ctx;
}
{
struct inode *inode = ctx->path.dentry->d_inode;
- if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock))
+ if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
return;
list_del(&ctx->list);
spin_unlock(&inode->i_lock);
* to open() calls that passed nfs_atomic_lookup, but failed to call
* nfs_open().
*/
- void nfs4_clear_inode(struct inode *inode)
+ void nfs4_evict_inode(struct inode *inode)
{
+ truncate_inode_pages(&inode->i_data, 0);
+ end_writeback(inode);
/* If we are holding a delegation, return it! */
nfs_inode_return_delegation_noreclaim(inode);
/* First call standard NFS clear_inode() code */
extern struct inode *nfs_alloc_inode(struct super_block *sb);
extern void nfs_destroy_inode(struct inode *);
extern int nfs_write_inode(struct inode *, struct writeback_control *);
- extern void nfs_clear_inode(struct inode *);
+ extern void nfs_evict_inode(struct inode *);
#ifdef CONFIG_NFS_V4
- extern void nfs4_clear_inode(struct inode *);
+ extern void nfs4_evict_inode(struct inode *);
#endif
void nfs_zap_acl_cache(struct inode *inode);
extern int nfs_wait_bit_killable(void *word);
* Helper for restarting RPC calls in the possible presence of NFSv4.1
* sessions.
*/
-static inline void nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp)
+static inline int nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp)
{
if (nfs4_has_session(clp))
- rpc_restart_call_prepare(task);
- else
- rpc_restart_call(task);
+ return rpc_restart_call_prepare(task);
+ return rpc_restart_call(task);
}
.write_inode = nfs_write_inode,
.put_super = nfs_put_super,
.statfs = nfs_statfs,
- .clear_inode = nfs_clear_inode,
+ .evict_inode = nfs_evict_inode,
.umount_begin = nfs_umount_begin,
.show_options = nfs_show_options,
.show_stats = nfs_show_stats,
.write_inode = nfs_write_inode,
.put_super = nfs_put_super,
.statfs = nfs_statfs,
- .clear_inode = nfs4_clear_inode,
+ .evict_inode = nfs4_evict_inode,
.umount_begin = nfs_umount_begin,
.show_options = nfs_show_options,
.show_stats = nfs_show_stats,
{
struct sockaddr *sap = (struct sockaddr *)&nfss->mountd_address;
+ if (nfss->flags & NFS_MOUNT_LEGACY_INTERFACE)
+ return;
+
switch (sap->sa_family) {
case AF_INET: {
struct sockaddr_in *sin = (struct sockaddr_in *)sap;
* can deal with.
*/
args->flags = data->flags & NFS_MOUNT_FLAGMASK;
+ args->flags |= NFS_MOUNT_LEGACY_INTERFACE;
args->rsize = data->rsize;
args->wsize = data->wsize;
args->timeo = data->timeo;
struct nfs4_acl *acl = NULL;
struct nfsd4_compoundres *resp = rqstp->rq_resp;
u32 minorversion = resp->cstate.minorversion;
+ struct path path = {
+ .mnt = exp->ex_path.mnt,
+ .dentry = dentry,
+ };
BUG_ON(bmval1 & NFSD_WRITEONLY_ATTRS_WORD1);
BUG_ON(bmval0 & ~nfsd_suppattrs0(minorversion));
FATTR4_WORD0_MAXNAME)) ||
(bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
FATTR4_WORD1_SPACE_TOTAL))) {
- err = vfs_statfs(dentry, &statfs);
+ err = vfs_statfs(&path, &statfs);
if (err)
goto out_nfserr;
}
}
read->rd_vlen = v;
- nfserr = nfsd_read(read->rd_rqstp, read->rd_fhp, read->rd_filp,
+ nfserr = nfsd_read_file(read->rd_rqstp, read->rd_fhp, read->rd_filp,
read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen,
&maxcount);
}
/* Renew the clientid on success and on replay */
release_session_client(cs->session);
+ nfsd4_put_session(cs->session);
}
return 1;
}
return error;
}
-#endif /* defined(CONFIG_NFS_V4) */
+#endif /* defined(CONFIG_NFSD_V4) */
#ifdef CONFIG_NFSD_V3
/*
loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
{
struct inode *inode;
- struct raparms *ra;
mm_segment_t oldfs;
__be32 err;
int host_err;
if (svc_msnfs(fhp) && !lock_may_read(inode, offset, *count))
goto out;
- /* Get readahead parameters */
- ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
-
- if (ra && ra->p_set)
- file->f_ra = ra->p_ra;
-
if (file->f_op->splice_read && rqstp->rq_splice_ok) {
struct splice_desc sd = {
.len = 0,
set_fs(oldfs);
}
- /* Write back readahead params */
- if (ra) {
- struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
- spin_lock(&rab->pb_lock);
- ra->p_ra = file->f_ra;
- ra->p_set = 1;
- ra->p_count--;
- spin_unlock(&rab->pb_lock);
- }
-
if (host_err >= 0) {
nfsdstats.io_read += host_err;
*count = host_err;
* on entry. On return, *count contains the number of bytes actually read.
* N.B. After this call fhp needs an fh_put
*/
+__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+{
+ struct file *file;
+ struct inode *inode;
+ struct raparms *ra;
+ __be32 err;
+
+ err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
+ if (err)
+ return err;
+
+ inode = file->f_path.dentry->d_inode;
+
+ /* Get readahead parameters */
+ ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
+
+ if (ra && ra->p_set)
+ file->f_ra = ra->p_ra;
+
+ err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
+
+ /* Write back readahead params */
+ if (ra) {
+ struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
+ spin_lock(&rab->pb_lock);
+ ra->p_ra = file->f_ra;
+ ra->p_set = 1;
+ ra->p_count--;
+ spin_unlock(&rab->pb_lock);
+ }
+
+ nfsd_close(file);
+ return err;
+}
+
+/* As above, but use the provided file descriptor. */
__be32
-nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
+nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
loff_t offset, struct kvec *vec, int vlen,
unsigned long *count)
{
if (err)
goto out;
err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
- } else {
- err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
- if (err)
- goto out;
- err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
- nfsd_close(file);
- }
+ } else /* Note file may still be NULL in NFSv4 special stateid case: */
+ err = nfsd_read(rqstp, fhp, offset, vec, vlen, count);
out:
return err;
}
char *name, int len, struct svc_fh *tfhp)
{
struct dentry *ddir, *dnew, *dold;
- struct inode *dirp, *dest;
+ struct inode *dirp;
__be32 err;
int host_err;
goto out_nfserr;
dold = tfhp->fh_dentry;
- dest = dold->d_inode;
host_err = mnt_want_write(tfhp->fh_export->ex_path.mnt);
if (host_err) {
__be32
nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, int access)
{
- __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
- if (!err && vfs_statfs(fhp->fh_dentry,stat))
+ struct path path = {
+ .mnt = fhp->fh_export->ex_path.mnt,
+ .dentry = fhp->fh_dentry,
+ };
+ __be32 err;
+
+ err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access);
+ if (!err && vfs_statfs(&path, stat))
err = nfserr_io;
return err;
}
struct dentry *dentry, int acc)
{
struct inode *inode = dentry->d_inode;
- struct path path;
int err;
if (acc == NFSD_MAY_NOP)
if (err == -EACCES && S_ISREG(inode->i_mode) &&
acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
err = inode_permission(inode, MAY_EXEC);
- if (err)
- goto nfsd_out;
- /* Do integrity (permission) checking now, but defer incrementing
- * IMA counts to the actual file open.
- */
- path.mnt = exp->ex_path.mnt;
- path.dentry = dentry;
-nfsd_out:
return err? nfserrno(err) : 0;
}
return last_byte;
}
- static int nilfs_prepare_chunk_uninterruptible(struct page *page,
- struct address_space *mapping,
- unsigned from, unsigned to)
+ static int nilfs_prepare_chunk(struct page *page, unsigned from, unsigned to)
{
loff_t pos = page_offset(page) + from;
- return block_write_begin(NULL, mapping, pos, to - from,
- AOP_FLAG_UNINTERRUPTIBLE, &page,
- NULL, nilfs_get_block);
- }
-
- static int nilfs_prepare_chunk(struct page *page,
- struct address_space *mapping,
- unsigned from, unsigned to)
- {
- loff_t pos = page_offset(page) + from;
- return block_write_begin(NULL, mapping, pos, to - from, 0, &page,
- NULL, nilfs_get_block);
+ return __block_write_begin(page, pos, to - from, nilfs_get_block);
}
static void nilfs_commit_chunk(struct page *page,
}
for (offs = 0; offs <= limit - NILFS_DIR_REC_LEN(1); offs += rec_len) {
p = (struct nilfs_dir_entry *)(kaddr + offs);
- rec_len = le16_to_cpu(p->rec_len);
+ rec_len = nilfs_rec_len_from_disk(p->rec_len);
if (rec_len < NILFS_DIR_REC_LEN(1))
goto Eshort;
static struct page *nilfs_get_page(struct inode *dir, unsigned long n)
{
struct address_space *mapping = dir->i_mapping;
- struct page *page = read_cache_page(mapping, n,
- (filler_t *)mapping->a_ops->readpage, NULL);
+ struct page *page = read_mapping_page(mapping, n, NULL);
+
if (!IS_ERR(page)) {
- wait_on_page_locked(page);
kmap(page);
- if (!PageUptodate(page))
- goto fail;
if (!PageChecked(page))
nilfs_check_page(page);
if (PageError(page))
*/
static struct nilfs_dir_entry *nilfs_next_entry(struct nilfs_dir_entry *p)
{
- return (struct nilfs_dir_entry *)((char *)p + le16_to_cpu(p->rec_len));
+ return (struct nilfs_dir_entry *)((char *)p +
+ nilfs_rec_len_from_disk(p->rec_len));
}
static unsigned char
goto success;
}
}
- filp->f_pos += le16_to_cpu(de->rec_len);
+ filp->f_pos += nilfs_rec_len_from_disk(de->rec_len);
}
nilfs_put_page(page);
}
struct page *page, struct inode *inode)
{
unsigned from = (char *) de - (char *) page_address(page);
- unsigned to = from + le16_to_cpu(de->rec_len);
+ unsigned to = from + nilfs_rec_len_from_disk(de->rec_len);
struct address_space *mapping = page->mapping;
int err;
lock_page(page);
- err = nilfs_prepare_chunk_uninterruptible(page, mapping, from, to);
+ err = nilfs_prepare_chunk(page, from, to);
BUG_ON(err);
de->inode = cpu_to_le64(inode->i_ino);
nilfs_set_de_type(de, inode);
/* We hit i_size */
name_len = 0;
rec_len = chunk_size;
- de->rec_len = cpu_to_le16(chunk_size);
+ de->rec_len = nilfs_rec_len_to_disk(chunk_size);
de->inode = 0;
goto got_it;
}
if (nilfs_match(namelen, name, de))
goto out_unlock;
name_len = NILFS_DIR_REC_LEN(de->name_len);
- rec_len = le16_to_cpu(de->rec_len);
+ rec_len = nilfs_rec_len_from_disk(de->rec_len);
if (!de->inode && rec_len >= reclen)
goto got_it;
if (rec_len >= name_len + reclen)
got_it:
from = (char *)de - (char *)page_address(page);
to = from + rec_len;
- err = nilfs_prepare_chunk(page, page->mapping, from, to);
+ err = nilfs_prepare_chunk(page, from, to);
if (err)
goto out_unlock;
if (de->inode) {
struct nilfs_dir_entry *de1;
de1 = (struct nilfs_dir_entry *)((char *)de + name_len);
- de1->rec_len = cpu_to_le16(rec_len - name_len);
- de->rec_len = cpu_to_le16(name_len);
+ de1->rec_len = nilfs_rec_len_to_disk(rec_len - name_len);
+ de->rec_len = nilfs_rec_len_to_disk(name_len);
de = de1;
}
de->name_len = namelen;
struct inode *inode = mapping->host;
char *kaddr = page_address(page);
unsigned from = ((char *)dir - kaddr) & ~(nilfs_chunk_size(inode) - 1);
- unsigned to = ((char *)dir - kaddr) + le16_to_cpu(dir->rec_len);
+ unsigned to = ((char *)dir - kaddr) +
+ nilfs_rec_len_from_disk(dir->rec_len);
struct nilfs_dir_entry *pde = NULL;
struct nilfs_dir_entry *de = (struct nilfs_dir_entry *)(kaddr + from);
int err;
if (pde)
from = (char *)pde - (char *)page_address(page);
lock_page(page);
- err = nilfs_prepare_chunk(page, mapping, from, to);
+ err = nilfs_prepare_chunk(page, from, to);
BUG_ON(err);
if (pde)
- pde->rec_len = cpu_to_le16(to - from);
+ pde->rec_len = nilfs_rec_len_to_disk(to - from);
dir->inode = 0;
nilfs_commit_chunk(page, mapping, from, to);
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
if (!page)
return -ENOMEM;
- err = nilfs_prepare_chunk(page, mapping, 0, chunk_size);
+ err = nilfs_prepare_chunk(page, 0, chunk_size);
if (unlikely(err)) {
unlock_page(page);
goto fail;
memset(kaddr, 0, chunk_size);
de = (struct nilfs_dir_entry *)kaddr;
de->name_len = 1;
- de->rec_len = cpu_to_le16(NILFS_DIR_REC_LEN(1));
+ de->rec_len = nilfs_rec_len_to_disk(NILFS_DIR_REC_LEN(1));
memcpy(de->name, ".\0\0", 4);
de->inode = cpu_to_le64(inode->i_ino);
nilfs_set_de_type(de, inode);
de = (struct nilfs_dir_entry *)(kaddr + NILFS_DIR_REC_LEN(1));
de->name_len = 2;
- de->rec_len = cpu_to_le16(chunk_size - NILFS_DIR_REC_LEN(1));
+ de->rec_len = nilfs_rec_len_to_disk(chunk_size - NILFS_DIR_REC_LEN(1));
de->inode = cpu_to_le64(parent->i_ino);
memcpy(de->name, "..\0", 4);
nilfs_set_de_type(de, inode);
#include "the_nilfs.h"
#include "sb.h"
#include "bmap.h"
-#include "bmap_union.h"
/*
* nilfs inode data in memory
__u32 i_flags;
unsigned long i_state; /* Dynamic state flags */
struct nilfs_bmap *i_bmap;
- union nilfs_bmap_union i_bmap_union;
+ struct nilfs_bmap i_bmap_data;
__u64 i_xattr; /* sector_t ??? */
__u32 i_dir_start_lookup;
__u64 i_cno; /* check point number for GC inode */
static inline struct nilfs_inode_info *
NILFS_BMAP_I(const struct nilfs_bmap *bmap)
{
- return container_of((union nilfs_bmap_union *)bmap,
- struct nilfs_inode_info,
- i_bmap_union);
+ return container_of(bmap, struct nilfs_inode_info, i_bmap_data);
}
static inline struct inode *NILFS_BTNC_I(struct address_space *btnc)
NILFS_I_GCDAT, /* shadow DAT, on memory only */
};
+/*
+ * commit flags for nilfs_commit_super and nilfs_sync_super
+ */
+enum {
+ NILFS_SB_COMMIT = 0, /* Commit a super block alternately */
+ NILFS_SB_COMMIT_ALL /* Commit both super blocks */
+};
+
/*
* Macros to check inode numbers
*/
extern struct inode *nilfs_iget(struct super_block *, unsigned long);
extern void nilfs_update_inode(struct inode *, struct buffer_head *);
extern void nilfs_truncate(struct inode *);
- extern void nilfs_delete_inode(struct inode *);
+ extern void nilfs_evict_inode(struct inode *);
extern int nilfs_setattr(struct dentry *, struct iattr *);
extern int nilfs_load_inode_block(struct nilfs_sb_info *, struct inode *,
struct buffer_head **);
nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **);
extern int nilfs_store_magic_and_option(struct super_block *,
struct nilfs_super_block *, char *);
+extern int nilfs_check_feature_compatibility(struct super_block *,
+ struct nilfs_super_block *);
+extern void nilfs_set_log_cursor(struct nilfs_super_block *,
+ struct the_nilfs *);
+extern struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *,
+ int flip);
extern int nilfs_commit_super(struct nilfs_sb_info *, int);
+extern int nilfs_cleanup_super(struct nilfs_sb_info *);
extern int nilfs_attach_checkpoint(struct nilfs_sb_info *, __u64);
extern void nilfs_detach_checkpoint(struct nilfs_sb_info *);
return -EINVAL;
}
-static void store_segsum_info(struct nilfs_segsum_info *ssi,
- struct nilfs_segment_summary *sum,
- unsigned int blocksize)
-{
- ssi->flags = le16_to_cpu(sum->ss_flags);
- ssi->seg_seq = le64_to_cpu(sum->ss_seq);
- ssi->ctime = le64_to_cpu(sum->ss_create);
- ssi->next = le64_to_cpu(sum->ss_next);
- ssi->nblocks = le32_to_cpu(sum->ss_nblocks);
- ssi->nfinfo = le32_to_cpu(sum->ss_nfinfo);
- ssi->sumbytes = le32_to_cpu(sum->ss_sumbytes);
-
- ssi->nsumblk = DIV_ROUND_UP(ssi->sumbytes, blocksize);
- ssi->nfileblk = ssi->nblocks - ssi->nsumblk - !!NILFS_SEG_HAS_SR(ssi);
-
- /* need to verify ->ss_bytes field if read ->ss_cno */
-}
-
/**
- * calc_crc_cont - check CRC of blocks continuously
- * @sbi: nilfs_sb_info
+ * nilfs_compute_checksum - compute checksum of blocks continuously
+ * @nilfs: nilfs object
* @bhs: buffer head of start block
* @sum: place to store result
* @offset: offset bytes in the first block
* @start: DBN of start block
* @nblock: number of blocks to be checked
*/
-static int calc_crc_cont(struct nilfs_sb_info *sbi, struct buffer_head *bhs,
- u32 *sum, unsigned long offset, u64 check_bytes,
- sector_t start, unsigned long nblock)
+static int nilfs_compute_checksum(struct the_nilfs *nilfs,
+ struct buffer_head *bhs, u32 *sum,
+ unsigned long offset, u64 check_bytes,
+ sector_t start, unsigned long nblock)
{
- unsigned long blocksize = sbi->s_super->s_blocksize;
+ unsigned int blocksize = nilfs->ns_blocksize;
unsigned long size;
u32 crc;
BUG_ON(offset >= blocksize);
check_bytes -= offset;
size = min_t(u64, check_bytes, blocksize - offset);
- crc = crc32_le(sbi->s_nilfs->ns_crc_seed,
+ crc = crc32_le(nilfs->ns_crc_seed,
(unsigned char *)bhs->b_data + offset, size);
if (--nblock > 0) {
do {
- struct buffer_head *bh
- = sb_bread(sbi->s_super, ++start);
+ struct buffer_head *bh;
+
+ bh = __bread(nilfs->ns_bdev, ++start, blocksize);
if (!bh)
return -EIO;
check_bytes -= size;
/**
* nilfs_read_super_root_block - read super root block
- * @sb: super_block
+ * @nilfs: nilfs object
* @sr_block: disk block number of the super root block
* @pbh: address of a buffer_head pointer to return super root buffer
* @check: CRC check flag
*/
-int nilfs_read_super_root_block(struct super_block *sb, sector_t sr_block,
+int nilfs_read_super_root_block(struct the_nilfs *nilfs, sector_t sr_block,
struct buffer_head **pbh, int check)
{
struct buffer_head *bh_sr;
int ret;
*pbh = NULL;
- bh_sr = sb_bread(sb, sr_block);
+ bh_sr = __bread(nilfs->ns_bdev, sr_block, nilfs->ns_blocksize);
if (unlikely(!bh_sr)) {
ret = NILFS_SEG_FAIL_IO;
goto failed;
if (check) {
unsigned bytes = le16_to_cpu(sr->sr_bytes);
- if (bytes == 0 || bytes > sb->s_blocksize) {
+ if (bytes == 0 || bytes > nilfs->ns_blocksize) {
ret = NILFS_SEG_FAIL_CHECKSUM_SUPER_ROOT;
goto failed_bh;
}
- if (calc_crc_cont(NILFS_SB(sb), bh_sr, &crc,
- sizeof(sr->sr_sum), bytes, sr_block, 1)) {
+ if (nilfs_compute_checksum(
+ nilfs, bh_sr, &crc, sizeof(sr->sr_sum), bytes,
+ sr_block, 1)) {
ret = NILFS_SEG_FAIL_IO;
goto failed_bh;
}
}
/**
- * load_segment_summary - read segment summary of the specified partial segment
- * @sbi: nilfs_sb_info
- * @pseg_start: start disk block number of partial segment
- * @seg_seq: sequence number requested
- * @ssi: pointer to nilfs_segsum_info struct to store information
+ * nilfs_read_log_header - read summary header of the specified log
+ * @nilfs: nilfs object
+ * @start_blocknr: start block number of the log
+ * @sum: pointer to return segment summary structure
*/
-static int
-load_segment_summary(struct nilfs_sb_info *sbi, sector_t pseg_start,
- u64 seg_seq, struct nilfs_segsum_info *ssi)
+static struct buffer_head *
+nilfs_read_log_header(struct the_nilfs *nilfs, sector_t start_blocknr,
+ struct nilfs_segment_summary **sum)
{
struct buffer_head *bh_sum;
- struct nilfs_segment_summary *sum;
+
+ bh_sum = __bread(nilfs->ns_bdev, start_blocknr, nilfs->ns_blocksize);
+ if (bh_sum)
+ *sum = (struct nilfs_segment_summary *)bh_sum->b_data;
+ return bh_sum;
+}
+
+/**
+ * nilfs_validate_log - verify consistency of log
+ * @nilfs: nilfs object
+ * @seg_seq: sequence number of segment
+ * @bh_sum: buffer head of summary block
+ * @sum: segment summary struct
+ */
+static int nilfs_validate_log(struct the_nilfs *nilfs, u64 seg_seq,
+ struct buffer_head *bh_sum,
+ struct nilfs_segment_summary *sum)
+{
unsigned long nblock;
u32 crc;
- int ret = NILFS_SEG_FAIL_IO;
+ int ret;
- bh_sum = sb_bread(sbi->s_super, pseg_start);
- if (!bh_sum)
+ ret = NILFS_SEG_FAIL_MAGIC;
+ if (le32_to_cpu(sum->ss_magic) != NILFS_SEGSUM_MAGIC)
goto out;
- sum = (struct nilfs_segment_summary *)bh_sum->b_data;
-
- /* Check consistency of segment summary */
- if (le32_to_cpu(sum->ss_magic) != NILFS_SEGSUM_MAGIC) {
- ret = NILFS_SEG_FAIL_MAGIC;
- goto failed;
- }
- store_segsum_info(ssi, sum, sbi->s_super->s_blocksize);
- if (seg_seq != ssi->seg_seq) {
- ret = NILFS_SEG_FAIL_SEQ;
- goto failed;
- }
+ ret = NILFS_SEG_FAIL_SEQ;
+ if (le64_to_cpu(sum->ss_seq) != seg_seq)
+ goto out;
- nblock = ssi->nblocks;
- if (unlikely(nblock == 0 ||
- nblock > sbi->s_nilfs->ns_blocks_per_segment)) {
+ nblock = le32_to_cpu(sum->ss_nblocks);
+ ret = NILFS_SEG_FAIL_CONSISTENCY;
+ if (unlikely(nblock == 0 || nblock > nilfs->ns_blocks_per_segment))
/* This limits the number of blocks read in the CRC check */
- ret = NILFS_SEG_FAIL_CONSISTENCY;
- goto failed;
- }
- if (calc_crc_cont(sbi, bh_sum, &crc, sizeof(sum->ss_datasum),
- ((u64)nblock << sbi->s_super->s_blocksize_bits),
- pseg_start, nblock)) {
- ret = NILFS_SEG_FAIL_IO;
- goto failed;
- }
- if (crc == le32_to_cpu(sum->ss_datasum))
- ret = 0;
- else
- ret = NILFS_SEG_FAIL_CHECKSUM_FULL;
- failed:
- brelse(bh_sum);
- out:
+ goto out;
+
+ ret = NILFS_SEG_FAIL_IO;
+ if (nilfs_compute_checksum(nilfs, bh_sum, &crc, sizeof(sum->ss_datasum),
+ ((u64)nblock << nilfs->ns_blocksize_bits),
+ bh_sum->b_blocknr, nblock))
+ goto out;
+
+ ret = NILFS_SEG_FAIL_CHECKSUM_FULL;
+ if (crc != le32_to_cpu(sum->ss_datasum))
+ goto out;
+ ret = 0;
+out:
return ret;
}
-static void *segsum_get(struct super_block *sb, struct buffer_head **pbh,
- unsigned int *offset, unsigned int bytes)
+/**
+ * nilfs_read_summary_info - read an item on summary blocks of a log
+ * @nilfs: nilfs object
+ * @pbh: the current buffer head on summary blocks [in, out]
+ * @offset: the current byte offset on summary blocks [in, out]
+ * @bytes: byte size of the item to be read
+ */
+static void *nilfs_read_summary_info(struct the_nilfs *nilfs,
+ struct buffer_head **pbh,
+ unsigned int *offset, unsigned int bytes)
{
void *ptr;
sector_t blocknr;
if (bytes > (*pbh)->b_size - *offset) {
blocknr = (*pbh)->b_blocknr;
brelse(*pbh);
- *pbh = sb_bread(sb, blocknr + 1);
+ *pbh = __bread(nilfs->ns_bdev, blocknr + 1,
+ nilfs->ns_blocksize);
if (unlikely(!*pbh))
return NULL;
*offset = 0;
return ptr;
}
-static void segsum_skip(struct super_block *sb, struct buffer_head **pbh,
- unsigned int *offset, unsigned int bytes,
- unsigned long count)
+/**
+ * nilfs_skip_summary_info - skip items on summary blocks of a log
+ * @nilfs: nilfs object
+ * @pbh: the current buffer head on summary blocks [in, out]
+ * @offset: the current byte offset on summary blocks [in, out]
+ * @bytes: byte size of the item to be skipped
+ * @count: number of items to be skipped
+ */
+static void nilfs_skip_summary_info(struct the_nilfs *nilfs,
+ struct buffer_head **pbh,
+ unsigned int *offset, unsigned int bytes,
+ unsigned long count)
{
unsigned int rest_item_in_current_block
= ((*pbh)->b_size - *offset) / bytes;
*offset = bytes * (count - (bcnt - 1) * nitem_per_block);
brelse(*pbh);
- *pbh = sb_bread(sb, blocknr + bcnt);
+ *pbh = __bread(nilfs->ns_bdev, blocknr + bcnt,
+ nilfs->ns_blocksize);
}
}
-static int
-collect_blocks_from_segsum(struct nilfs_sb_info *sbi, sector_t sum_blocknr,
- struct nilfs_segsum_info *ssi,
- struct list_head *head)
+/**
+ * nilfs_scan_dsync_log - get block information of a log written for data sync
+ * @nilfs: nilfs object
+ * @start_blocknr: start block number of the log
+ * @sum: log summary information
+ * @head: list head to add nilfs_recovery_block struct
+ */
+static int nilfs_scan_dsync_log(struct the_nilfs *nilfs, sector_t start_blocknr,
+ struct nilfs_segment_summary *sum,
+ struct list_head *head)
{
struct buffer_head *bh;
unsigned int offset;
- unsigned long nfinfo = ssi->nfinfo;
- sector_t blocknr = sum_blocknr + ssi->nsumblk;
+ u32 nfinfo, sumbytes;
+ sector_t blocknr;
ino_t ino;
int err = -EIO;
+ nfinfo = le32_to_cpu(sum->ss_nfinfo);
if (!nfinfo)
return 0;
- bh = sb_bread(sbi->s_super, sum_blocknr);
+ sumbytes = le32_to_cpu(sum->ss_sumbytes);
+ blocknr = start_blocknr + DIV_ROUND_UP(sumbytes, nilfs->ns_blocksize);
+ bh = __bread(nilfs->ns_bdev, start_blocknr, nilfs->ns_blocksize);
if (unlikely(!bh))
goto out;
- offset = le16_to_cpu(
- ((struct nilfs_segment_summary *)bh->b_data)->ss_bytes);
+ offset = le16_to_cpu(sum->ss_bytes);
for (;;) {
unsigned long nblocks, ndatablk, nnodeblk;
struct nilfs_finfo *finfo;
- finfo = segsum_get(sbi->s_super, &bh, &offset, sizeof(*finfo));
+ finfo = nilfs_read_summary_info(nilfs, &bh, &offset,
+ sizeof(*finfo));
if (unlikely(!finfo))
goto out;
struct nilfs_recovery_block *rb;
struct nilfs_binfo_v *binfo;
- binfo = segsum_get(sbi->s_super, &bh, &offset,
- sizeof(*binfo));
+ binfo = nilfs_read_summary_info(nilfs, &bh, &offset,
+ sizeof(*binfo));
if (unlikely(!binfo))
goto out;
}
if (--nfinfo == 0)
break;
- blocknr += nnodeblk; /* always 0 for the data sync segments */
- segsum_skip(sbi->s_super, &bh, &offset, sizeof(__le64),
- nnodeblk);
+ blocknr += nnodeblk; /* always 0 for data sync logs */
+ nilfs_skip_summary_info(nilfs, &bh, &offset, sizeof(__le64),
+ nnodeblk);
if (unlikely(!bh))
goto out;
}
return err;
}
-static int nilfs_recovery_copy_block(struct nilfs_sb_info *sbi,
+static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
struct nilfs_recovery_block *rb,
struct page *page)
{
struct buffer_head *bh_org;
void *kaddr;
- bh_org = sb_bread(sbi->s_super, rb->blocknr);
+ bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize);
if (unlikely(!bh_org))
return -EIO;
return 0;
}
-static int recover_dsync_blocks(struct nilfs_sb_info *sbi,
- struct list_head *head,
- unsigned long *nr_salvaged_blocks)
+static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
+ struct nilfs_sb_info *sbi,
+ struct list_head *head,
+ unsigned long *nr_salvaged_blocks)
{
struct inode *inode;
struct nilfs_recovery_block *rb, *n;
- unsigned blocksize = sbi->s_super->s_blocksize;
+ unsigned blocksize = nilfs->ns_blocksize;
struct page *page;
loff_t pos;
int err = 0, err2 = 0;
}
pos = rb->blkoff << inode->i_blkbits;
- page = NULL;
- err = block_write_begin(NULL, inode->i_mapping, pos, blocksize,
- 0, &page, NULL, nilfs_get_block);
- if (unlikely(err))
+ err = block_write_begin(inode->i_mapping, pos, blocksize,
+ 0, &page, nilfs_get_block);
+ if (unlikely(err)) {
+ loff_t isize = inode->i_size;
+ if (pos + blocksize > isize)
+ vmtruncate(inode, isize);
goto failed_inode;
+ }
- err = nilfs_recovery_copy_block(sbi, rb, page);
+ err = nilfs_recovery_copy_block(nilfs, rb, page);
if (unlikely(err))
goto failed_page;
/**
* nilfs_do_roll_forward - salvage logical segments newer than the latest
* checkpoint
+ * @nilfs: nilfs object
* @sbi: nilfs_sb_info
- * @nilfs: the_nilfs
* @ri: pointer to a nilfs_recovery_info
*/
static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
struct nilfs_sb_info *sbi,
struct nilfs_recovery_info *ri)
{
- struct nilfs_segsum_info ssi;
+ struct buffer_head *bh_sum = NULL;
+ struct nilfs_segment_summary *sum;
sector_t pseg_start;
sector_t seg_start, seg_end; /* Starting/ending DBN of full segment */
unsigned long nsalvaged_blocks = 0;
+ unsigned int flags;
u64 seg_seq;
__u64 segnum, nextnum = 0;
int empty_seg = 0;
nilfs_get_segment_range(nilfs, segnum, &seg_start, &seg_end);
while (segnum != ri->ri_segnum || pseg_start <= ri->ri_pseg_start) {
+ brelse(bh_sum);
+ bh_sum = nilfs_read_log_header(nilfs, pseg_start, &sum);
+ if (!bh_sum) {
+ err = -EIO;
+ goto failed;
+ }
- ret = load_segment_summary(sbi, pseg_start, seg_seq, &ssi);
+ ret = nilfs_validate_log(nilfs, seg_seq, bh_sum, sum);
if (ret) {
if (ret == NILFS_SEG_FAIL_IO) {
err = -EIO;
}
goto strayed;
}
- if (unlikely(NILFS_SEG_HAS_SR(&ssi)))
+
+ flags = le16_to_cpu(sum->ss_flags);
+ if (flags & NILFS_SS_SR)
goto confused;
/* Found a valid partial segment; do recovery actions */
- nextnum = nilfs_get_segnum_of_block(nilfs, ssi.next);
+ nextnum = nilfs_get_segnum_of_block(nilfs,
+ le64_to_cpu(sum->ss_next));
empty_seg = 0;
- nilfs->ns_ctime = ssi.ctime;
- if (!(ssi.flags & NILFS_SS_GC))
- nilfs->ns_nongc_ctime = ssi.ctime;
+ nilfs->ns_ctime = le64_to_cpu(sum->ss_create);
+ if (!(flags & NILFS_SS_GC))
+ nilfs->ns_nongc_ctime = nilfs->ns_ctime;
switch (state) {
case RF_INIT_ST:
- if (!NILFS_SEG_LOGBGN(&ssi) || !NILFS_SEG_DSYNC(&ssi))
+ if (!(flags & NILFS_SS_LOGBGN) ||
+ !(flags & NILFS_SS_SYNDT))
goto try_next_pseg;
state = RF_DSYNC_ST;
/* Fall through */
case RF_DSYNC_ST:
- if (!NILFS_SEG_DSYNC(&ssi))
+ if (!(flags & NILFS_SS_SYNDT))
goto confused;
- err = collect_blocks_from_segsum(
- sbi, pseg_start, &ssi, &dsync_blocks);
+ err = nilfs_scan_dsync_log(nilfs, pseg_start, sum,
+ &dsync_blocks);
if (unlikely(err))
goto failed;
- if (NILFS_SEG_LOGEND(&ssi)) {
- err = recover_dsync_blocks(
- sbi, &dsync_blocks, &nsalvaged_blocks);
+ if (flags & NILFS_SS_LOGEND) {
+ err = nilfs_recover_dsync_blocks(
+ nilfs, sbi, &dsync_blocks,
+ &nsalvaged_blocks);
if (unlikely(err))
goto failed;
state = RF_INIT_ST;
try_next_pseg:
if (pseg_start == ri->ri_lsegs_end)
break;
- pseg_start += ssi.nblocks;
+ pseg_start += le32_to_cpu(sum->ss_nblocks);
if (pseg_start < seg_end)
continue;
goto feed_segment;
ri->ri_need_recovery = NILFS_RECOVERY_ROLLFORWARD_DONE;
}
out:
+ brelse(bh_sum);
dispose_recovery_list(&dsync_blocks);
- nilfs_detach_writer(sbi->s_nilfs, sbi);
+ nilfs_detach_writer(nilfs, sbi);
return err;
confused:
}
static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
- struct nilfs_sb_info *sbi,
struct nilfs_recovery_info *ri)
{
struct buffer_head *bh;
nilfs_get_segnum_of_block(nilfs, ri->ri_super_root))
return;
- bh = sb_getblk(sbi->s_super, ri->ri_lsegs_start);
+ bh = __getblk(nilfs->ns_bdev, ri->ri_lsegs_start, nilfs->ns_blocksize);
BUG_ON(!bh);
memset(bh->b_data, 0, bh->b_size);
set_buffer_dirty(bh);
}
/**
- * nilfs_recover_logical_segments - salvage logical segments written after
- * the latest super root
- * @nilfs: the_nilfs
+ * nilfs_salvage_orphan_logs - salvage logs written after the latest checkpoint
+ * @nilfs: nilfs object
* @sbi: nilfs_sb_info
* @ri: pointer to a nilfs_recovery_info struct to store search results.
*
*
* %-ENOMEM - Insufficient memory available.
*/
-int nilfs_recover_logical_segments(struct the_nilfs *nilfs,
- struct nilfs_sb_info *sbi,
- struct nilfs_recovery_info *ri)
+int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
+ struct nilfs_sb_info *sbi,
+ struct nilfs_recovery_info *ri)
{
int err;
goto failed;
}
- nilfs_finish_roll_forward(nilfs, sbi, ri);
+ nilfs_finish_roll_forward(nilfs, ri);
}
failed:
/**
* nilfs_search_super_root - search the latest valid super root
* @nilfs: the_nilfs
- * @sbi: nilfs_sb_info
* @ri: pointer to a nilfs_recovery_info struct to store search results.
*
* nilfs_search_super_root() looks for the latest super-root from a partial
* %-EINVAL - No valid segment found
*
* %-EIO - I/O error
+ *
+ * %-ENOMEM - Insufficient memory available.
*/
-int nilfs_search_super_root(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi,
+int nilfs_search_super_root(struct the_nilfs *nilfs,
struct nilfs_recovery_info *ri)
{
- struct nilfs_segsum_info ssi;
+ struct buffer_head *bh_sum = NULL;
+ struct nilfs_segment_summary *sum;
sector_t pseg_start, pseg_end, sr_pseg_start = 0;
sector_t seg_start, seg_end; /* range of full segment (block number) */
sector_t b, end;
+ unsigned long nblocks;
+ unsigned int flags;
u64 seg_seq;
__u64 segnum, nextnum = 0;
__u64 cno;
/* Read ahead segment */
b = seg_start;
while (b <= seg_end)
- sb_breadahead(sbi->s_super, b++);
+ __breadahead(nilfs->ns_bdev, b++, nilfs->ns_blocksize);
for (;;) {
- /* Load segment summary */
- ret = load_segment_summary(sbi, pseg_start, seg_seq, &ssi);
+ brelse(bh_sum);
+ ret = NILFS_SEG_FAIL_IO;
+ bh_sum = nilfs_read_log_header(nilfs, pseg_start, &sum);
+ if (!bh_sum)
+ goto failed;
+
+ ret = nilfs_validate_log(nilfs, seg_seq, bh_sum, sum);
if (ret) {
if (ret == NILFS_SEG_FAIL_IO)
goto failed;
goto strayed;
}
- pseg_end = pseg_start + ssi.nblocks - 1;
+
+ nblocks = le32_to_cpu(sum->ss_nblocks);
+ pseg_end = pseg_start + nblocks - 1;
if (unlikely(pseg_end > seg_end)) {
ret = NILFS_SEG_FAIL_CONSISTENCY;
goto strayed;
ri->ri_pseg_start = pseg_start;
ri->ri_seq = seg_seq;
ri->ri_segnum = segnum;
- nextnum = nilfs_get_segnum_of_block(nilfs, ssi.next);
+ nextnum = nilfs_get_segnum_of_block(nilfs,
+ le64_to_cpu(sum->ss_next));
ri->ri_nextnum = nextnum;
empty_seg = 0;
- if (!NILFS_SEG_HAS_SR(&ssi) && !scan_newer) {
+ flags = le16_to_cpu(sum->ss_flags);
+ if (!(flags & NILFS_SS_SR) && !scan_newer) {
/* This will never happen because a superblock
(last_segment) always points to a pseg
having a super root. */
if (pseg_start == seg_start) {
nilfs_get_segment_range(nilfs, nextnum, &b, &end);
while (b <= end)
- sb_breadahead(sbi->s_super, b++);
+ __breadahead(nilfs->ns_bdev, b++,
+ nilfs->ns_blocksize);
}
- if (!NILFS_SEG_HAS_SR(&ssi)) {
- if (!ri->ri_lsegs_start && NILFS_SEG_LOGBGN(&ssi)) {
+ if (!(flags & NILFS_SS_SR)) {
+ if (!ri->ri_lsegs_start && (flags & NILFS_SS_LOGBGN)) {
ri->ri_lsegs_start = pseg_start;
ri->ri_lsegs_start_seq = seg_seq;
}
- if (NILFS_SEG_LOGEND(&ssi))
+ if (flags & NILFS_SS_LOGEND)
ri->ri_lsegs_end = pseg_start;
goto try_next_pseg;
}
ri->ri_lsegs_start = ri->ri_lsegs_end = 0;
nilfs_dispose_segment_list(&segments);
- nilfs->ns_pseg_offset = (sr_pseg_start = pseg_start)
- + ssi.nblocks - seg_start;
+ sr_pseg_start = pseg_start;
+ nilfs->ns_pseg_offset = pseg_start + nblocks - seg_start;
nilfs->ns_seg_seq = seg_seq;
nilfs->ns_segnum = segnum;
nilfs->ns_cno = cno; /* nilfs->ns_cno = ri->ri_cno + 1 */
- nilfs->ns_ctime = ssi.ctime;
+ nilfs->ns_ctime = le64_to_cpu(sum->ss_create);
nilfs->ns_nextnum = nextnum;
if (scan_newer)
scan_newer = 1;
}
- /* reset region for roll-forward */
- pseg_start += ssi.nblocks;
- if (pseg_start < seg_end)
- continue;
- goto feed_segment;
-
try_next_pseg:
/* Standing on a course, or met an inconsistent state */
- pseg_start += ssi.nblocks;
+ pseg_start += nblocks;
if (pseg_start < seg_end)
continue;
goto feed_segment;
super_root_found:
/* Updating pointers relating to the latest checkpoint */
+ brelse(bh_sum);
list_splice_tail(&segments, &ri->ri_used_segments);
nilfs->ns_last_pseg = sr_pseg_start;
nilfs->ns_last_seq = nilfs->ns_seg_seq;
return 0;
failed:
+ brelse(bh_sum);
nilfs_dispose_segment_list(&segments);
return (ret < 0) ? ret : nilfs_warn_segment_error(ret);
}
#include "nilfs.h"
#include "mdt.h"
#include "alloc.h"
+#include "btree.h"
+#include "btnode.h"
#include "page.h"
#include "cpfile.h"
#include "ifile.h"
static int nilfs_remount(struct super_block *sb, int *flags, char *data);
+static void nilfs_set_error(struct nilfs_sb_info *sbi)
+{
+ struct the_nilfs *nilfs = sbi->s_nilfs;
+ struct nilfs_super_block **sbp;
+
+ down_write(&nilfs->ns_sem);
+ if (!(nilfs->ns_mount_state & NILFS_ERROR_FS)) {
+ nilfs->ns_mount_state |= NILFS_ERROR_FS;
+ sbp = nilfs_prepare_super(sbi, 0);
+ if (likely(sbp)) {
+ sbp[0]->s_state |= cpu_to_le16(NILFS_ERROR_FS);
+ if (sbp[1])
+ sbp[1]->s_state |= cpu_to_le16(NILFS_ERROR_FS);
+ nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
+ }
+ }
+ up_write(&nilfs->ns_sem);
+}
+
/**
* nilfs_error() - report failure condition on a filesystem
*
va_end(args);
if (!(sb->s_flags & MS_RDONLY)) {
- struct the_nilfs *nilfs = sbi->s_nilfs;
-
- down_write(&nilfs->ns_sem);
- if (!(nilfs->ns_mount_state & NILFS_ERROR_FS)) {
- nilfs->ns_mount_state |= NILFS_ERROR_FS;
- nilfs->ns_sbp[0]->s_state |=
- cpu_to_le16(NILFS_ERROR_FS);
- nilfs_commit_super(sbi, 1);
- }
- up_write(&nilfs->ns_sem);
+ nilfs_set_error(sbi);
if (nilfs_test_opt(sbi, ERRORS_RO)) {
printk(KERN_CRIT "Remounting filesystem read-only\n");
kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode));
}
- static void nilfs_clear_inode(struct inode *inode)
- {
- struct nilfs_inode_info *ii = NILFS_I(inode);
-
- /*
- * Free resources allocated in nilfs_read_inode(), here.
- */
- BUG_ON(!list_empty(&ii->i_dirty));
- brelse(ii->i_bh);
- ii->i_bh = NULL;
-
- if (test_bit(NILFS_I_BMAP, &ii->i_state))
- nilfs_bmap_clear(ii->i_bmap);
-
- nilfs_btnode_cache_clear(&ii->i_btnode_cache);
- }
-
-static int nilfs_sync_super(struct nilfs_sb_info *sbi, int dupsb)
+static int nilfs_sync_super(struct nilfs_sb_info *sbi, int flag)
{
struct the_nilfs *nilfs = sbi->s_nilfs;
int err;
printk(KERN_ERR
"NILFS: unable to write superblock (err=%d)\n", err);
if (err == -EIO && nilfs->ns_sbh[1]) {
+ /*
+ * sbp[0] points to newer log than sbp[1],
+ * so copy sbp[0] to sbp[1] to take over sbp[0].
+ */
+ memcpy(nilfs->ns_sbp[1], nilfs->ns_sbp[0],
+ nilfs->ns_sbsize);
nilfs_fall_back_super_block(nilfs);
goto retry;
}
} else {
struct nilfs_super_block *sbp = nilfs->ns_sbp[0];
+ nilfs->ns_sbwcount++;
+
/*
* The latest segment becomes trailable from the position
* written in superblock.
/* update GC protection for recent segments */
if (nilfs->ns_sbh[1]) {
- sbp = NULL;
- if (dupsb) {
+ if (flag == NILFS_SB_COMMIT_ALL) {
set_buffer_dirty(nilfs->ns_sbh[1]);
- if (!sync_dirty_buffer(nilfs->ns_sbh[1]))
- sbp = nilfs->ns_sbp[1];
+ if (sync_dirty_buffer(nilfs->ns_sbh[1]) < 0)
+ goto out;
}
+ if (le64_to_cpu(nilfs->ns_sbp[1]->s_last_cno) <
+ le64_to_cpu(nilfs->ns_sbp[0]->s_last_cno))
+ sbp = nilfs->ns_sbp[1];
}
- if (sbp) {
- spin_lock(&nilfs->ns_last_segment_lock);
- nilfs->ns_prot_seq = le64_to_cpu(sbp->s_last_seq);
- spin_unlock(&nilfs->ns_last_segment_lock);
- }
- }
+ spin_lock(&nilfs->ns_last_segment_lock);
+ nilfs->ns_prot_seq = le64_to_cpu(sbp->s_last_seq);
+ spin_unlock(&nilfs->ns_last_segment_lock);
+ }
+ out:
return err;
}
-int nilfs_commit_super(struct nilfs_sb_info *sbi, int dupsb)
+void nilfs_set_log_cursor(struct nilfs_super_block *sbp,
+ struct the_nilfs *nilfs)
+{
+ sector_t nfreeblocks;
+
+ /* nilfs->ns_sem must be locked by the caller. */
+ nilfs_count_free_blocks(nilfs, &nfreeblocks);
+ sbp->s_free_blocks_count = cpu_to_le64(nfreeblocks);
+
+ spin_lock(&nilfs->ns_last_segment_lock);
+ sbp->s_last_seq = cpu_to_le64(nilfs->ns_last_seq);
+ sbp->s_last_pseg = cpu_to_le64(nilfs->ns_last_pseg);
+ sbp->s_last_cno = cpu_to_le64(nilfs->ns_last_cno);
+ spin_unlock(&nilfs->ns_last_segment_lock);
+}
+
+struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *sbi,
+ int flip)
{
struct the_nilfs *nilfs = sbi->s_nilfs;
struct nilfs_super_block **sbp = nilfs->ns_sbp;
- sector_t nfreeblocks;
- time_t t;
- int err;
- /* nilfs->sem must be locked by the caller. */
+ /* nilfs->ns_sem must be locked by the caller. */
if (sbp[0]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) {
- if (sbp[1] && sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC))
- nilfs_swap_super_block(nilfs);
- else {
+ if (sbp[1] &&
+ sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC)) {
+ memcpy(sbp[0], sbp[1], nilfs->ns_sbsize);
+ } else {
printk(KERN_CRIT "NILFS: superblock broke on dev %s\n",
sbi->s_super->s_id);
- return -EIO;
+ return NULL;
}
+ } else if (sbp[1] &&
+ sbp[1]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) {
+ memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
}
- err = nilfs_count_free_blocks(nilfs, &nfreeblocks);
- if (unlikely(err)) {
- printk(KERN_ERR "NILFS: failed to count free blocks\n");
- return err;
- }
- spin_lock(&nilfs->ns_last_segment_lock);
- sbp[0]->s_last_seq = cpu_to_le64(nilfs->ns_last_seq);
- sbp[0]->s_last_pseg = cpu_to_le64(nilfs->ns_last_pseg);
- sbp[0]->s_last_cno = cpu_to_le64(nilfs->ns_last_cno);
- spin_unlock(&nilfs->ns_last_segment_lock);
+ if (flip && sbp[1])
+ nilfs_swap_super_block(nilfs);
+
+ return sbp;
+}
+
+int nilfs_commit_super(struct nilfs_sb_info *sbi, int flag)
+{
+ struct the_nilfs *nilfs = sbi->s_nilfs;
+ struct nilfs_super_block **sbp = nilfs->ns_sbp;
+ time_t t;
+
+ /* nilfs->ns_sem must be locked by the caller. */
t = get_seconds();
- nilfs->ns_sbwtime[0] = t;
- sbp[0]->s_free_blocks_count = cpu_to_le64(nfreeblocks);
+ nilfs->ns_sbwtime = t;
sbp[0]->s_wtime = cpu_to_le64(t);
sbp[0]->s_sum = 0;
sbp[0]->s_sum = cpu_to_le32(crc32_le(nilfs->ns_crc_seed,
(unsigned char *)sbp[0],
nilfs->ns_sbsize));
- if (dupsb && sbp[1]) {
- memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
- nilfs->ns_sbwtime[1] = t;
+ if (flag == NILFS_SB_COMMIT_ALL && sbp[1]) {
+ sbp[1]->s_wtime = sbp[0]->s_wtime;
+ sbp[1]->s_sum = 0;
+ sbp[1]->s_sum = cpu_to_le32(crc32_le(nilfs->ns_crc_seed,
+ (unsigned char *)sbp[1],
+ nilfs->ns_sbsize));
}
clear_nilfs_sb_dirty(nilfs);
- return nilfs_sync_super(sbi, dupsb);
+ return nilfs_sync_super(sbi, flag);
+}
+
+/**
+ * nilfs_cleanup_super() - write filesystem state for cleanup
+ * @sbi: nilfs_sb_info to be unmounted or degraded to read-only
+ *
+ * This function restores state flags in the on-disk super block.
+ * This will set "clean" flag (i.e. NILFS_VALID_FS) unless the
+ * filesystem was not clean previously.
+ */
+int nilfs_cleanup_super(struct nilfs_sb_info *sbi)
+{
+ struct nilfs_super_block **sbp;
+ int flag = NILFS_SB_COMMIT;
+ int ret = -EIO;
+
+ sbp = nilfs_prepare_super(sbi, 0);
+ if (sbp) {
+ sbp[0]->s_state = cpu_to_le16(sbi->s_nilfs->ns_mount_state);
+ nilfs_set_log_cursor(sbp[0], sbi->s_nilfs);
+ if (sbp[1] && sbp[0]->s_last_cno == sbp[1]->s_last_cno) {
+ /*
+ * make the "clean" flag also to the opposite
+ * super block if both super blocks point to
+ * the same checkpoint.
+ */
+ sbp[1]->s_state = sbp[0]->s_state;
+ flag = NILFS_SB_COMMIT_ALL;
+ }
+ ret = nilfs_commit_super(sbi, flag);
+ }
+ return ret;
}
static void nilfs_put_super(struct super_block *sb)
if (!(sb->s_flags & MS_RDONLY)) {
down_write(&nilfs->ns_sem);
- nilfs->ns_sbp[0]->s_state = cpu_to_le16(nilfs->ns_mount_state);
- nilfs_commit_super(sbi, 1);
+ nilfs_cleanup_super(sbi);
up_write(&nilfs->ns_sem);
}
down_write(&nilfs->ns_super_sem);
{
struct nilfs_sb_info *sbi = NILFS_SB(sb);
struct the_nilfs *nilfs = sbi->s_nilfs;
+ struct nilfs_super_block **sbp;
int err = 0;
/* This function is called when super block should be written back */
err = nilfs_construct_segment(sb);
down_write(&nilfs->ns_sem);
- if (nilfs_sb_dirty(nilfs))
- nilfs_commit_super(sbi, 1);
+ if (nilfs_sb_dirty(nilfs)) {
+ sbp = nilfs_prepare_super(sbi, nilfs_sb_will_flip(nilfs));
+ if (likely(sbp)) {
+ nilfs_set_log_cursor(sbp[0], nilfs);
+ nilfs_commit_super(sbi, NILFS_SB_COMMIT);
+ }
+ }
up_write(&nilfs->ns_sem);
return err;
struct nilfs_sb_info *sbi = NILFS_SB(sb);
if (!nilfs_test_opt(sbi, BARRIER))
- seq_printf(seq, ",nobarrier");
+ seq_puts(seq, ",nobarrier");
if (nilfs_test_opt(sbi, SNAPSHOT))
seq_printf(seq, ",cp=%llu",
(unsigned long long int)sbi->s_snapshot_cno);
if (nilfs_test_opt(sbi, ERRORS_PANIC))
- seq_printf(seq, ",errors=panic");
+ seq_puts(seq, ",errors=panic");
if (nilfs_test_opt(sbi, ERRORS_CONT))
- seq_printf(seq, ",errors=continue");
+ seq_puts(seq, ",errors=continue");
if (nilfs_test_opt(sbi, STRICT_ORDER))
- seq_printf(seq, ",order=strict");
+ seq_puts(seq, ",order=strict");
if (nilfs_test_opt(sbi, NORECOVERY))
- seq_printf(seq, ",norecovery");
+ seq_puts(seq, ",norecovery");
if (nilfs_test_opt(sbi, DISCARD))
- seq_printf(seq, ",discard");
+ seq_puts(seq, ",discard");
return 0;
}
/* .write_inode = nilfs_write_inode, */
/* .put_inode = nilfs_put_inode, */
/* .drop_inode = nilfs_drop_inode, */
- .delete_inode = nilfs_delete_inode,
+ .evict_inode = nilfs_evict_inode,
.put_super = nilfs_put_super,
/* .write_super = nilfs_write_super, */
.sync_fs = nilfs_sync_fs,
/* .unlockfs */
.statfs = nilfs_statfs,
.remount_fs = nilfs_remount,
- .clear_inode = nilfs_clear_inode,
/* .umount_begin */
.show_options = nilfs_show_options
};
enum {
Opt_err_cont, Opt_err_panic, Opt_err_ro,
- Opt_nobarrier, Opt_snapshot, Opt_order, Opt_norecovery,
- Opt_discard, Opt_err,
+ Opt_barrier, Opt_nobarrier, Opt_snapshot, Opt_order, Opt_norecovery,
+ Opt_discard, Opt_nodiscard, Opt_err,
};
static match_table_t tokens = {
{Opt_err_cont, "errors=continue"},
{Opt_err_panic, "errors=panic"},
{Opt_err_ro, "errors=remount-ro"},
+ {Opt_barrier, "barrier"},
{Opt_nobarrier, "nobarrier"},
{Opt_snapshot, "cp=%u"},
{Opt_order, "order=%s"},
{Opt_norecovery, "norecovery"},
{Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_err, NULL}
};
-static int parse_options(char *options, struct super_block *sb)
+static int parse_options(char *options, struct super_block *sb, int is_remount)
{
struct nilfs_sb_info *sbi = NILFS_SB(sb);
char *p;
token = match_token(p, tokens, args);
switch (token) {
+ case Opt_barrier:
+ nilfs_set_opt(sbi, BARRIER);
+ break;
case Opt_nobarrier:
nilfs_clear_opt(sbi, BARRIER);
break;
case Opt_snapshot:
if (match_int(&args[0], &option) || option <= 0)
return 0;
- if (!(sb->s_flags & MS_RDONLY))
+ if (is_remount) {
+ if (!nilfs_test_opt(sbi, SNAPSHOT)) {
+ printk(KERN_ERR
+ "NILFS: cannot change regular "
+ "mount to snapshot.\n");
+ return 0;
+ } else if (option != sbi->s_snapshot_cno) {
+ printk(KERN_ERR
+ "NILFS: cannot remount to a "
+ "different snapshot.\n");
+ return 0;
+ }
+ break;
+ }
+ if (!(sb->s_flags & MS_RDONLY)) {
+ printk(KERN_ERR "NILFS: cannot mount snapshot "
+ "read/write. A read-only option is "
+ "required.\n");
return 0;
+ }
sbi->s_snapshot_cno = option;
nilfs_set_opt(sbi, SNAPSHOT);
break;
case Opt_discard:
nilfs_set_opt(sbi, DISCARD);
break;
+ case Opt_nodiscard:
+ nilfs_clear_opt(sbi, DISCARD);
+ break;
default:
printk(KERN_ERR
"NILFS: Unrecognized mount option \"%s\"\n", p);
static int nilfs_setup_super(struct nilfs_sb_info *sbi)
{
struct the_nilfs *nilfs = sbi->s_nilfs;
- struct nilfs_super_block *sbp = nilfs->ns_sbp[0];
- int max_mnt_count = le16_to_cpu(sbp->s_max_mnt_count);
- int mnt_count = le16_to_cpu(sbp->s_mnt_count);
+ struct nilfs_super_block **sbp;
+ int max_mnt_count;
+ int mnt_count;
+
+ /* nilfs->ns_sem must be locked by the caller. */
+ sbp = nilfs_prepare_super(sbi, 0);
+ if (!sbp)
+ return -EIO;
+
+ max_mnt_count = le16_to_cpu(sbp[0]->s_max_mnt_count);
+ mnt_count = le16_to_cpu(sbp[0]->s_mnt_count);
- /* nilfs->sem must be locked by the caller. */
if (nilfs->ns_mount_state & NILFS_ERROR_FS) {
printk(KERN_WARNING
"NILFS warning: mounting fs with errors\n");
#endif
}
if (!max_mnt_count)
- sbp->s_max_mnt_count = cpu_to_le16(NILFS_DFL_MAX_MNT_COUNT);
-
- sbp->s_mnt_count = cpu_to_le16(mnt_count + 1);
- sbp->s_state = cpu_to_le16(le16_to_cpu(sbp->s_state) & ~NILFS_VALID_FS);
- sbp->s_mtime = cpu_to_le64(get_seconds());
- return nilfs_commit_super(sbi, 1);
+ sbp[0]->s_max_mnt_count = cpu_to_le16(NILFS_DFL_MAX_MNT_COUNT);
+
+ sbp[0]->s_mnt_count = cpu_to_le16(mnt_count + 1);
+ sbp[0]->s_state =
+ cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_VALID_FS);
+ sbp[0]->s_mtime = cpu_to_le64(get_seconds());
+ /* synchronize sbp[1] with sbp[0] */
+ memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
+ return nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
}
struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb,
sbi->s_interval = le32_to_cpu(sbp->s_c_interval);
sbi->s_watermark = le32_to_cpu(sbp->s_c_block_max);
- return !parse_options(data, sb) ? -EINVAL : 0 ;
+ return !parse_options(data, sb, 0) ? -EINVAL : 0 ;
+}
+
+int nilfs_check_feature_compatibility(struct super_block *sb,
+ struct nilfs_super_block *sbp)
+{
+ __u64 features;
+
+ features = le64_to_cpu(sbp->s_feature_incompat) &
+ ~NILFS_FEATURE_INCOMPAT_SUPP;
+ if (features) {
+ printk(KERN_ERR "NILFS: couldn't mount because of unsupported "
+ "optional features (%llx)\n",
+ (unsigned long long)features);
+ return -EINVAL;
+ }
+ features = le64_to_cpu(sbp->s_feature_compat_ro) &
+ ~NILFS_FEATURE_COMPAT_RO_SUPP;
+ if (!(sb->s_flags & MS_RDONLY) && features) {
+ printk(KERN_ERR "NILFS: couldn't mount RDWR because of "
+ "unsupported optional features (%llx)\n",
+ (unsigned long long)features);
+ return -EINVAL;
+ }
+ return 0;
}
/**
static int nilfs_remount(struct super_block *sb, int *flags, char *data)
{
struct nilfs_sb_info *sbi = NILFS_SB(sb);
- struct nilfs_super_block *sbp;
struct the_nilfs *nilfs = sbi->s_nilfs;
unsigned long old_sb_flags;
struct nilfs_mount_options old_opts;
old_opts.snapshot_cno = sbi->s_snapshot_cno;
was_snapshot = nilfs_test_opt(sbi, SNAPSHOT);
- if (!parse_options(data, sb)) {
+ if (!parse_options(data, sb, 1)) {
err = -EINVAL;
goto restore_opts;
}
sb->s_flags = (sb->s_flags & ~MS_POSIXACL);
err = -EINVAL;
- if (was_snapshot) {
- if (!(*flags & MS_RDONLY)) {
- printk(KERN_ERR "NILFS (device %s): cannot remount "
- "snapshot read/write.\n",
- sb->s_id);
- goto restore_opts;
- } else if (sbi->s_snapshot_cno != old_opts.snapshot_cno) {
- printk(KERN_ERR "NILFS (device %s): cannot "
- "remount to a different snapshot.\n",
- sb->s_id);
- goto restore_opts;
- }
- } else {
- if (nilfs_test_opt(sbi, SNAPSHOT)) {
- printk(KERN_ERR "NILFS (device %s): cannot change "
- "a regular mount to a snapshot.\n",
- sb->s_id);
- goto restore_opts;
- }
+ if (was_snapshot && !(*flags & MS_RDONLY)) {
+ printk(KERN_ERR "NILFS (device %s): cannot remount snapshot "
+ "read/write.\n", sb->s_id);
+ goto restore_opts;
}
if (!nilfs_valid_fs(nilfs)) {
* the RDONLY flag and then mark the partition as valid again.
*/
down_write(&nilfs->ns_sem);
- sbp = nilfs->ns_sbp[0];
- if (!(sbp->s_state & le16_to_cpu(NILFS_VALID_FS)) &&
- (nilfs->ns_mount_state & NILFS_VALID_FS))
- sbp->s_state = cpu_to_le16(nilfs->ns_mount_state);
- sbp->s_mtime = cpu_to_le64(get_seconds());
- nilfs_commit_super(sbi, 1);
+ nilfs_cleanup_super(sbi);
up_write(&nilfs->ns_sem);
} else {
+ __u64 features;
+
/*
* Mounting a RDONLY partition read-write, so reread and
* store the current valid flag. (It may have been changed
* by fsck since we originally mounted the partition.)
*/
+ down_read(&nilfs->ns_sem);
+ features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
+ ~NILFS_FEATURE_COMPAT_RO_SUPP;
+ up_read(&nilfs->ns_sem);
+ if (features) {
+ printk(KERN_WARNING "NILFS (device %s): couldn't "
+ "remount RDWR because of unsupported optional "
+ "features (%llx)\n",
+ sb->s_id, (unsigned long long)features);
+ err = -EROFS;
+ goto restore_opts;
+ }
+
sb->s_flags &= ~MS_RDONLY;
err = nilfs_attach_segment_constructor(sbi);
init_rwsem(&ii->xattr_sem);
#endif
nilfs_btnode_cache_init_once(&ii->i_btnode_cache);
- ii->i_bmap = (struct nilfs_bmap *)&ii->i_bmap_union;
+ ii->i_bmap = &ii->i_bmap_data;
inode_init_once(&ii->vfs_inode);
}
{
int level, status;
struct dlmfs_inode_private *ip = DLMFS_I(inode);
- struct dlmfs_filp_private *fp =
- (struct dlmfs_filp_private *) file->private_data;
+ struct dlmfs_filp_private *fp = file->private_data;
if (S_ISDIR(inode->i_mode))
BUG();
attr->ia_valid &= ~ATTR_SIZE;
error = inode_change_ok(inode, attr);
- if (!error)
- error = inode_setattr(inode, attr);
+ if (error)
+ return error;
- return error;
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+ return 0;
}
static unsigned int dlmfs_file_poll(struct file *file, poll_table *wait)
kmem_cache_free(dlmfs_inode_cache, DLMFS_I(inode));
}
- static void dlmfs_clear_inode(struct inode *inode)
+ static void dlmfs_evict_inode(struct inode *inode)
{
int status;
struct dlmfs_inode_private *ip;
- if (!inode)
- return;
+ end_writeback(inode);
mlog(0, "inode %lu\n", inode->i_ino);
.statfs = simple_statfs,
.alloc_inode = dlmfs_alloc_inode,
.destroy_inode = dlmfs_destroy_inode,
- .clear_inode = dlmfs_clear_inode,
+ .evict_inode = dlmfs_evict_inode,
.drop_inode = generic_delete_inode,
};
.alloc_inode = ocfs2_alloc_inode,
.destroy_inode = ocfs2_destroy_inode,
.drop_inode = ocfs2_drop_inode,
- .clear_inode = ocfs2_clear_inode,
- .delete_inode = ocfs2_delete_inode,
+ .evict_inode = ocfs2_evict_inode,
.sync_fs = ocfs2_sync_fs,
.put_super = ocfs2_put_super,
.remount_fs = ocfs2_remount,
kfree(osb->slot_recovery_generations);
/* FIXME
* This belongs in journal shutdown, but because we have to
- * allocate osb->journal at the start of ocfs2_initalize_osb(),
+ * allocate osb->journal at the start of ocfs2_initialize_osb(),
* we free it here.
*/
kfree(osb->journal);
#include <linux/namei.h>
#include <linux/mnt_namespace.h>
#include <linux/mm.h>
+#include <linux/swap.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
#include <linux/stacktrace.h>
#endif
-/* The badness from the OOM killer */
-unsigned long badness(struct task_struct *p, unsigned long uptime);
static int proc_oom_score(struct task_struct *task, char *buffer)
{
unsigned long points = 0;
- struct timespec uptime;
- do_posix_clock_monotonic_gettime(&uptime);
read_lock(&tasklist_lock);
if (pid_alive(task))
- points = badness(task, uptime.tv_sec);
+ points = oom_badness(task, NULL, NULL,
+ totalram_pages + total_swap_pages);
read_unlock(&tasklist_lock);
return sprintf(buffer, "%lu\n", points);
}
return -EPERM;
error = inode_change_ok(inode, attr);
- if (!error)
- error = inode_setattr(inode, attr);
- return error;
+ if (error)
+ return error;
+
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ error = vmtruncate(inode, attr->ia_size);
+ if (error)
+ return error;
+ }
+
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+ return 0;
}
static const struct inode_operations proc_def_inode_operations = {
return -EACCES;
}
+ /*
+ * Warn that /proc/pid/oom_adj is deprecated, see
+ * Documentation/feature-removal-schedule.txt.
+ */
+ printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, "
+ "please use /proc/%d/oom_score_adj instead.\n",
+ current->comm, task_pid_nr(current),
+ task_pid_nr(task), task_pid_nr(task));
task->signal->oom_adj = oom_adjust;
-
+ /*
+ * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
+ * value is always attainable.
+ */
+ if (task->signal->oom_adj == OOM_ADJUST_MAX)
+ task->signal->oom_score_adj = OOM_SCORE_ADJ_MAX;
+ else
+ task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) /
+ -OOM_DISABLE;
unlock_task_sighand(task, &flags);
put_task_struct(task);
.llseek = generic_file_llseek,
};
+static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ char buffer[PROC_NUMBUF];
+ int oom_score_adj = OOM_SCORE_ADJ_MIN;
+ unsigned long flags;
+ size_t len;
+
+ if (!task)
+ return -ESRCH;
+ if (lock_task_sighand(task, &flags)) {
+ oom_score_adj = task->signal->oom_score_adj;
+ unlock_task_sighand(task, &flags);
+ }
+ put_task_struct(task);
+ len = snprintf(buffer, sizeof(buffer), "%d\n", oom_score_adj);
+ return simple_read_from_buffer(buf, count, ppos, buffer, len);
+}
+
+static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task;
+ char buffer[PROC_NUMBUF];
+ unsigned long flags;
+ long oom_score_adj;
+ int err;
+
+ memset(buffer, 0, sizeof(buffer));
+ if (count > sizeof(buffer) - 1)
+ count = sizeof(buffer) - 1;
+ if (copy_from_user(buffer, buf, count))
+ return -EFAULT;
+
+ err = strict_strtol(strstrip(buffer), 0, &oom_score_adj);
+ if (err)
+ return -EINVAL;
+ if (oom_score_adj < OOM_SCORE_ADJ_MIN ||
+ oom_score_adj > OOM_SCORE_ADJ_MAX)
+ return -EINVAL;
+
+ task = get_proc_task(file->f_path.dentry->d_inode);
+ if (!task)
+ return -ESRCH;
+ if (!lock_task_sighand(task, &flags)) {
+ put_task_struct(task);
+ return -ESRCH;
+ }
+ if (oom_score_adj < task->signal->oom_score_adj &&
+ !capable(CAP_SYS_RESOURCE)) {
+ unlock_task_sighand(task, &flags);
+ put_task_struct(task);
+ return -EACCES;
+ }
+
+ task->signal->oom_score_adj = oom_score_adj;
+ /*
+ * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is
+ * always attainable.
+ */
+ if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ task->signal->oom_adj = OOM_DISABLE;
+ else
+ task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) /
+ OOM_SCORE_ADJ_MAX;
+ unlock_task_sighand(task, &flags);
+ put_task_struct(task);
+ return count;
+}
+
+static const struct file_operations proc_oom_score_adj_operations = {
+ .read = oom_score_adj_read,
+ .write = oom_score_adj_write,
+};
+
#ifdef CONFIG_AUDITSYSCALL
#define TMPBUFLEN 21
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+ REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
#endif
INF("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations),
+ REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUSR, proc_sessionid_operations),
__cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock);
EXPORT_SYMBOL(dq_data_lock);
+void __quota_error(struct super_block *sb, const char *func,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ if (printk_ratelimit()) {
+ va_start(args, fmt);
+ printk(KERN_ERR "Quota error (device %s): %s: ",
+ sb->s_id, func);
+ vprintk(fmt, args);
+ printk("\n");
+ va_end(args);
+ }
+}
+EXPORT_SYMBOL(__quota_error);
+
#if defined(CONFIG_QUOTA_DEBUG) || defined(CONFIG_PRINT_QUOTA_WARNING)
static char *quotatypes[] = INITQFNAMES;
#endif
return;
#ifdef CONFIG_QUOTA_DEBUG
if (!atomic_read(&dquot->dq_count)) {
- printk("VFS: dqput: trying to free free dquot\n");
- printk("VFS: device %s, dquot of %s %d\n",
- dquot->dq_sb->s_id,
- quotatypes[dquot->dq_type],
- dquot->dq_id);
+ quota_error(dquot->dq_sb, "trying to free free dquot of %s %d",
+ quotatypes[dquot->dq_type], dquot->dq_id);
BUG();
}
#endif
/* Commit dquot before releasing */
ret = dquot->dq_sb->dq_op->write_dquot(dquot);
if (ret < 0) {
- printk(KERN_ERR "VFS: cannot write quota structure on "
- "device %s (error %d). Quota may get out of "
- "sync!\n", dquot->dq_sb->s_id, ret);
+ quota_error(dquot->dq_sb, "Can't write quota structure"
+ " (error %d). Quota may get out of sync!",
+ ret);
/*
* We clear dirty bit anyway, so that we avoid
* infinite loop here
spin_lock(&inode_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
- if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+ if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
continue;
#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
- printk(KERN_WARNING "VFS (%s): Writes happened before quota"
- " was turned on thus quota information is probably "
- "inconsistent. Please run quotacheck(8).\n", sb->s_id);
+ quota_error(sb, "Writes happened before quota was turned on "
+ "thus quota information is probably inconsistent. "
+ "Please run quotacheck(8)");
}
#endif
}
if (dqput_blocks(dquot)) {
#ifdef CONFIG_QUOTA_DEBUG
if (atomic_read(&dquot->dq_count) != 1)
- printk(KERN_WARNING "VFS: Adding dquot with dq_count %d to dispose list.\n", atomic_read(&dquot->dq_count));
+ quota_error(inode->i_sb, "Adding dquot with "
+ "dq_count %d to dispose list",
+ atomic_read(&dquot->dq_count));
#endif
spin_lock(&dq_list_lock);
/* As dquot must have currently users it can't be on
struct list_head *tofree_head)
{
struct inode *inode;
+ int reserved = 0;
spin_lock(&inode_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
* only quota pointers and these have separate locking
* (dqptr_sem).
*/
- if (!IS_NOQUOTA(inode))
+ if (!IS_NOQUOTA(inode)) {
+ if (unlikely(inode_get_rsv_space(inode) > 0))
+ reserved = 1;
remove_inode_dquot_ref(inode, type, tofree_head);
+ }
}
spin_unlock(&inode_lock);
+#ifdef CONFIG_QUOTA_DEBUG
+ if (reserved) {
+ printk(KERN_WARNING "VFS (%s): Writes happened after quota"
+ " was disabled thus quota information is probably "
+ "inconsistent. Please run quotacheck(8).\n", sb->s_id);
+ }
+#endif
}
/* Gather all references from inodes and drop them */
return QUOTA_NL_NOWARN;
}
+static int dquot_active(const struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (IS_NOQUOTA(inode))
+ return 0;
+ return sb_any_quota_loaded(sb) & ~sb_any_quota_suspended(sb);
+}
+
/*
* Initialize quota pointers in inode
*
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
- if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode))
+ if (!dquot_active(inode))
return;
/* First get references to structures we might need. */
* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex
*/
- if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode)) {
+ if (!dquot_active(inode)) {
inode_incr_space(inode, number, reserve);
goto out;
}
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
- if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode))
+ if (!dquot_active(inode))
return 0;
for (cnt = 0; cnt < MAXQUOTAS; cnt++)
warntype[cnt] = QUOTA_NL_NOWARN;
{
int cnt;
- if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode)) {
+ if (!dquot_active(inode)) {
inode_claim_rsv_space(inode, number);
return 0;
}
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
- if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode)) {
+ if (!dquot_active(inode)) {
inode_decr_space(inode, number, reserve);
return;
}
/* First test before acquiring mutex - solves deadlocks when we
* re-enter the quota code and are already holding the mutex */
- if (!sb_any_quota_active(inode->i_sb) || IS_NOQUOTA(inode))
+ if (!dquot_active(inode))
return;
down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
struct super_block *sb = inode->i_sb;
int ret;
- if (!sb_any_quota_active(sb) || IS_NOQUOTA(inode))
+ if (!dquot_active(inode))
return 0;
if (iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid)
truncate_inode_pages(&toputinode[cnt]->i_data,
0);
mutex_unlock(&toputinode[cnt]->i_mutex);
- mark_inode_dirty(toputinode[cnt]);
+ mark_inode_dirty_sync(toputinode[cnt]);
}
mutex_unlock(&dqopt->dqonoff_mutex);
}
memset(di, 0, sizeof(*di));
di->d_version = FS_DQUOT_VERSION;
di->d_flags = dquot->dq_type == USRQUOTA ?
- XFS_USER_QUOTA : XFS_GROUP_QUOTA;
+ FS_USER_QUOTA : FS_GROUP_QUOTA;
di->d_id = dquot->dq_id;
spin_lock(&dq_data_lock);
int reiserfs_prepare_write(struct file *f, struct page *page,
unsigned from, unsigned to);
- void reiserfs_delete_inode(struct inode *inode)
+ void reiserfs_evict_inode(struct inode *inode)
{
/* We need blocks for transaction + (user+group) quota update (possibly delete) */
int jbegin_count =
int depth;
int err;
- if (!is_bad_inode(inode))
+ if (!inode->i_nlink && !is_bad_inode(inode))
dquot_initialize(inode);
truncate_inode_pages(&inode->i_data, 0);
+ if (inode->i_nlink)
+ goto no_delete;
depth = reiserfs_write_lock_once(inode->i_sb);
;
}
out:
- clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */
+ end_writeback(inode); /* note this must go after the journal_end to prevent deadlock */
+ dquot_drop(inode);
inode->i_blocks = 0;
reiserfs_write_unlock_once(inode->i_sb, depth);
+
+ no_delete:
+ end_writeback(inode);
+ dquot_drop(inode);
}
static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
REISERFS_I(inode)->i_prealloc_count = 0;
REISERFS_I(inode)->i_trans_id = 0;
REISERFS_I(inode)->i_jl = NULL;
- mutex_init(&(REISERFS_I(inode)->i_mmap));
reiserfs_init_xattr_rwsem(inode);
if (stat_data_v1(ih)) {
inode_set_bytes(inode,
to_real_used_space(inode, inode->i_blocks,
SD_V2_SIZE));
- /* read persistent inode attributes from sd and initalise
+ /* read persistent inode attributes from sd and initialise
generic inode flags from them */
REISERFS_I(inode)->i_attrs = sd_v2_attrs(sd);
sd_attrs_to_i_attrs(sd_v2_attrs(sd), inode);
REISERFS_I(inode)->i_attrs =
REISERFS_I(dir)->i_attrs & REISERFS_INHERIT_MASK;
sd_attrs_to_i_attrs(REISERFS_I(inode)->i_attrs, inode);
- mutex_init(&(REISERFS_I(inode)->i_mmap));
reiserfs_init_xattr_rwsem(inode);
/* key to search for correct place for new stat data */
old_ref = th->t_refcount;
th->t_refcount++;
}
- ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
- reiserfs_get_block);
+ ret = __block_write_begin(page, pos, len, reiserfs_get_block);
if (ret && reiserfs_transaction_running(inode->i_sb)) {
struct reiserfs_transaction_handle *th = current->journal_info;
/* this gets a little ugly. If reiserfs_get_block returned an
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ ssize_t ret;
- return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs,
reiserfs_get_blocks_direct_io, NULL);
+
+ /*
+ * In case of error extending write may have instantiated a few
+ * blocks outside i_size. Trim these off again.
+ */
+ if (unlikely((rw & WRITE) && ret < 0)) {
+ loff_t isize = i_size_read(inode);
+ loff_t end = offset + iov_length(iov, nr_segs);
+
+ if (end > isize)
+ vmtruncate(inode, isize);
+ }
+
+ return ret;
}
int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
int depth;
int error;
+ error = inode_change_ok(inode, attr);
+ if (error)
+ return error;
+
/* must be turned off for recursive notify_change calls */
ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
goto out;
}
- error = inode_change_ok(inode, attr);
- if (!error) {
- if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
- (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
- error = reiserfs_chown_xattrs(inode, attr);
+ if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
+ (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+ struct reiserfs_transaction_handle th;
+ int jbegin_count =
+ 2 *
+ (REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb) +
+ REISERFS_QUOTA_DEL_BLOCKS(inode->i_sb)) +
+ 2;
- if (!error) {
- struct reiserfs_transaction_handle th;
- int jbegin_count =
- 2 *
- (REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb) +
- REISERFS_QUOTA_DEL_BLOCKS(inode->i_sb)) +
- 2;
-
- /* (user+group)*(old+new) structure - we count quota info and , inode write (sb, inode) */
- error =
- journal_begin(&th, inode->i_sb,
- jbegin_count);
- if (error)
- goto out;
- error = dquot_transfer(inode, attr);
- if (error) {
- journal_end(&th, inode->i_sb,
- jbegin_count);
- goto out;
- }
- /* Update corresponding info in inode so that everything is in
- * one transaction */
- if (attr->ia_valid & ATTR_UID)
- inode->i_uid = attr->ia_uid;
- if (attr->ia_valid & ATTR_GID)
- inode->i_gid = attr->ia_gid;
- mark_inode_dirty(inode);
- error =
- journal_end(&th, inode->i_sb, jbegin_count);
- }
- }
- if (!error) {
- /*
- * Relax the lock here, as it might truncate the
- * inode pages and wait for inode pages locks.
- * To release such page lock, the owner needs the
- * reiserfs lock
- */
- reiserfs_write_unlock_once(inode->i_sb, depth);
- error = inode_setattr(inode, attr);
- depth = reiserfs_write_lock_once(inode->i_sb);
+ error = reiserfs_chown_xattrs(inode, attr);
+
+ if (error)
+ return error;
+
+ /* (user+group)*(old+new) structure - we count quota info and , inode write (sb, inode) */
+ error = journal_begin(&th, inode->i_sb, jbegin_count);
+ if (error)
+ goto out;
+ error = dquot_transfer(inode, attr);
+ if (error) {
+ journal_end(&th, inode->i_sb, jbegin_count);
+ goto out;
}
+
+ /* Update corresponding info in inode so that everything is in
+ * one transaction */
+ if (attr->ia_valid & ATTR_UID)
+ inode->i_uid = attr->ia_uid;
+ if (attr->ia_valid & ATTR_GID)
+ inode->i_gid = attr->ia_gid;
+ mark_inode_dirty(inode);
+ error = journal_end(&th, inode->i_sb, jbegin_count);
+ if (error)
+ goto out;
+ }
+
+ /*
+ * Relax the lock here, as it might truncate the
+ * inode pages and wait for inode pages locks.
+ * To release such page lock, the owner needs the
+ * reiserfs lock
+ */
+ reiserfs_write_unlock_once(inode->i_sb, depth);
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode))
+ error = vmtruncate(inode, attr->ia_size);
+
+ if (!error) {
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
}
+ depth = reiserfs_write_lock_once(inode->i_sb);
if (!error && reiserfs_posixacl(inode->i_sb)) {
if (attr->ia_valid & ATTR_MODE)
return err;
}
- static void ubifs_delete_inode(struct inode *inode)
+ static void ubifs_evict_inode(struct inode *inode)
{
int err;
struct ubifs_info *c = inode->i_sb->s_fs_info;
dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
ubifs_assert(!atomic_read(&inode->i_count));
- ubifs_assert(inode->i_nlink == 0);
truncate_inode_pages(&inode->i_data, 0);
+
+ if (inode->i_nlink)
+ goto done;
+
if (is_bad_inode(inode))
goto out;
c->nospace = c->nospace_rp = 0;
smp_wmb();
}
- clear_inode(inode);
+ done:
+ end_writeback(inode);
}
static void ubifs_dirty_inode(struct inode *inode)
if (err)
goto out_orphans;
err = ubifs_rcvry_gc_commit(c);
+ if (err)
+ goto out_orphans;
} else {
err = take_gc_lnum(c);
if (err)
*/
err = ubifs_leb_unmap(c, c->gc_lnum);
if (err)
- return err;
+ goto out_orphans;
}
err = dbg_check_lprops(c);
.destroy_inode = ubifs_destroy_inode,
.put_super = ubifs_put_super,
.write_inode = ubifs_write_inode,
- .delete_inode = ubifs_delete_inode,
+ .evict_inode = ubifs_evict_inode,
.statfs = ubifs_statfs,
.dirty_inode = ubifs_dirty_inode,
.remount_fs = ubifs_remount_fs,
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/aio.h>
-#include <linux/smp_lock.h>
#include "udf_i.h"
#include "udf_sb.h"
.llseek = generic_file_llseek,
};
+ static int udf_setattr(struct dentry *dentry, struct iattr *attr)
+ {
+ struct inode *inode = dentry->d_inode;
+ int error;
+
+ error = inode_change_ok(inode, attr);
+ if (error)
+ return error;
+
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ error = vmtruncate(inode, attr->ia_size);
+ if (error)
+ return error;
+ }
+
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+ return 0;
+ }
+
const struct inode_operations udf_file_inode_operations = {
+ .setattr = udf_setattr,
.truncate = udf_truncate,
};
.alloc_inode = udf_alloc_inode,
.destroy_inode = udf_destroy_inode,
.write_inode = udf_write_inode,
- .delete_inode = udf_delete_inode,
- .clear_inode = udf_clear_inode,
+ .evict_inode = udf_evict_inode,
.put_super = udf_put_super,
.sync_fs = udf_sync_fs,
.statfs = udf_statfs,
{
struct anchorVolDescPtr *anchor;
long main_s, main_e, reserve_s, reserve_e;
- struct udf_sb_info *sbi;
- sbi = UDF_SB(sb);
anchor = (struct anchorVolDescPtr *)bh->b_data;
/* Locate the main sequence */
int block_read_full_page(struct page*, get_block_t*);
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
unsigned long from);
- int block_write_begin_newtrunc(struct file *, struct address_space *,
- loff_t, unsigned, unsigned,
- struct page **, void **, get_block_t*);
- int block_write_begin(struct file *, struct address_space *,
- loff_t, unsigned, unsigned,
- struct page **, void **, get_block_t*);
+ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
+ unsigned flags, struct page **pagep, get_block_t *get_block);
+ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+ get_block_t *get_block);
int block_write_end(struct file *, struct address_space *,
loff_t, unsigned, unsigned,
struct page *, void *);
struct page *, void *);
void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
- int cont_write_begin_newtrunc(struct file *, struct address_space *, loff_t,
- unsigned, unsigned, struct page **, void **,
- get_block_t *, loff_t *);
int cont_write_begin(struct file *, struct address_space *, loff_t,
unsigned, unsigned, struct page **, void **,
get_block_t *, loff_t *);
void block_sync_page(struct page *);
sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
int block_truncate_page(struct address_space *, loff_t, get_block_t *);
- int file_fsync(struct file *, int);
- int nobh_write_begin_newtrunc(struct file *, struct address_space *,
- loff_t, unsigned, unsigned,
- struct page **, void **, get_block_t*);
- int nobh_write_begin(struct file *, struct address_space *,
- loff_t, unsigned, unsigned,
+ int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned,
struct page **, void **, get_block_t*);
int nobh_write_end(struct file *, struct address_space *,
loff_t, unsigned, unsigned,
bh->b_size = sb->s_blocksize;
}
-/*
- * Calling wait_on_buffer() for a zero-ref buffer is illegal, so we call into
- * __wait_on_buffer() just to trip a debug check. Because debug code in inline
- * functions is bloaty.
- */
static inline void wait_on_buffer(struct buffer_head *bh)
{
might_sleep();
- if (buffer_locked(bh) || atomic_read(&bh->b_count) == 0)
+ if (buffer_locked(bh))
__wait_on_buffer(bh);
}
#define EXT3_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
#define EXT3_MOUNT_RESERVATION 0x10000 /* Preallocation */
#define EXT3_MOUNT_BARRIER 0x20000 /* Use block barriers */
-#define EXT3_MOUNT_NOBH 0x40000 /* No bufferheads */
#define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */
#define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
#define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
extern struct inode *ext3_iget(struct super_block *, unsigned long);
extern int ext3_write_inode (struct inode *, struct writeback_control *);
extern int ext3_setattr (struct dentry *, struct iattr *);
- extern void ext3_delete_inode (struct inode *);
+ extern void ext3_evict_inode (struct inode *);
extern int ext3_sync_inode (handle_t *, struct inode *);
extern void ext3_discard_reservation (struct inode *);
extern void ext3_dirty_inode(struct inode *);
#define MAY_APPEND 8
#define MAY_ACCESS 16
#define MAY_OPEN 32
+#define MAY_CHDIR 64
/*
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
+ #define MS_BORN (1<<29)
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
*/
#define PAGECACHE_TAG_DIRTY 0
#define PAGECACHE_TAG_WRITEBACK 1
+#define PAGECACHE_TAG_TOWRITE 2
int mapping_tagged(struct address_space *mapping, int tag);
void (*dirty_inode) (struct inode *);
int (*write_inode) (struct inode *, struct writeback_control *wbc);
- void (*drop_inode) (struct inode *);
- void (*delete_inode) (struct inode *);
+ int (*drop_inode) (struct inode *);
+ void (*evict_inode) (struct inode *);
void (*put_super) (struct super_block *);
void (*write_super) (struct super_block *);
int (*sync_fs)(struct super_block *sb, int wait);
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
int (*remount_fs) (struct super_block *, int *, char *);
- void (*clear_inode) (struct inode *);
void (*umount_begin) (struct super_block *);
int (*show_options)(struct seq_file *, struct vfsmount *);
* I_FREEING Set when inode is about to be freed but still has dirty
* pages or buffers attached or the inode itself is still
* dirty.
- * I_CLEAR Set by clear_inode(). In this state the inode is clean
- * and can be destroyed.
+ * I_CLEAR Added by end_writeback(). In this state the inode is clean
+ * and can be destroyed. Inode keeps I_FREEING.
*
* Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
* prohibited for many purposes. iget() must wait for
extern void drop_collected_mounts(struct vfsmount *);
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
struct vfsmount *);
- extern int vfs_statfs(struct dentry *, struct kstatfs *);
+ extern int vfs_statfs(struct path *, struct kstatfs *);
+ extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
- extern void generic_delete_inode(struct inode *inode);
- extern void generic_drop_inode(struct inode *inode);
- extern int generic_detach_inode(struct inode *inode);
+ extern int generic_delete_inode(struct inode *inode);
+ extern int generic_drop_inode(struct inode *inode);
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
- extern void clear_inode(struct inode *);
+ extern void end_writeback(struct inode *);
extern void destroy_inode(struct inode *);
extern void __destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
struct bio;
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
loff_t file_offset);
- void dio_end_io(struct bio *bio, int error);
-
- ssize_t __blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode,
- struct block_device *bdev, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, int lock_type);
- ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
- struct block_device *bdev, const struct iovec *iov, loff_t offset,
- unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- dio_submit_t submit_io, int lock_type);
enum {
/* need locking between buffered and direct access */
DIO_SKIP_HOLES = 0x02,
};
- static inline ssize_t blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb,
- struct inode *inode, struct block_device *bdev, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs, get_block_t get_block,
- dio_iodone_t end_io)
- {
- return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, NULL,
- DIO_LOCKING | DIO_SKIP_HOLES);
- }
+ void dio_end_io(struct bio *bio, int error);
+
+ ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
+ struct block_device *bdev, const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+ dio_submit_t submit_io, int flags);
- static inline ssize_t blockdev_direct_IO_no_locking_newtrunc(int rw, struct kiocb *iocb,
- struct inode *inode, struct block_device *bdev, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs, get_block_t get_block,
- dio_iodone_t end_io)
- {
- return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, NULL, 0);
- }
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
struct inode *inode, struct block_device *bdev, const struct iovec *iov,
loff_t offset, unsigned long nr_segs, get_block_t get_block,
nr_segs, get_block, end_io, NULL,
DIO_LOCKING | DIO_SKIP_HOLES);
}
-
- static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
- struct inode *inode, struct block_device *bdev, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs, get_block_t get_block,
- dio_iodone_t end_io)
- {
- return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
- nr_segs, get_block, end_io, NULL, 0);
- }
#endif
extern const struct file_operations generic_ro_fops;
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
- extern int simple_setsize(struct inode *, loff_t);
extern int noop_fsync(struct file *, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
extern int inode_change_ok(const struct inode *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
- extern int __must_check inode_setattr(struct inode *, const struct iattr *);
- extern void generic_setattr(struct inode *inode, const struct iattr *attr);
+ extern void setattr_copy(struct inode *inode, const struct iattr *attr);
extern void file_update_time(struct file *file);
}
extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
+ extern void truncate_setsize(struct inode *inode, loff_t newsize);
extern int vmtruncate(struct inode *inode, loff_t offset);
extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end);
extern void shake_page(struct page *p, int access);
extern atomic_long_t mce_bad_pages;
extern int soft_offline_page(struct page *page, int flags);
+#ifdef CONFIG_MEMORY_FAILURE
+int is_hwpoison_address(unsigned long addr);
+#else
+static inline int is_hwpoison_address(unsigned long addr)
+{
+ return 0;
+}
+#endif
extern void dump_page(struct page *page);
/* the spot for the super in versions 3.5 - 3.5.10 (inclusive) */
#define REISERFS_OLD_DISK_OFFSET_IN_BYTES (8 * 1024)
-// reiserfs internal error code (used by search_by_key adn fix_nodes))
+/* reiserfs internal error code (used by search_by_key and fix_nodes)) */
#define CARRY_ON 0
#define REPEAT_SEARCH -1
#define IO_ERROR -2
struct reiserfs_iget_args *args);
int reiserfs_find_actor(struct inode *inode, void *p);
int reiserfs_init_locked_inode(struct inode *inode, void *p);
- void reiserfs_delete_inode(struct inode *inode);
+ void reiserfs_evict_inode(struct inode *inode);
int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc);
int reiserfs_get_block(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int create);
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/module.h>
+#include <linux/percpu_counter.h>
#include <linux/swap.h>
static struct vfsmount *shm_mnt;
{
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += pages;
+ percpu_counter_add(&sbinfo->used_blocks, -pages);
+ spin_lock(&inode->i_lock);
inode->i_blocks -= pages*BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
+ spin_unlock(&inode->i_lock);
}
}
if (sgp == SGP_READ)
return shmem_swp_map(ZERO_PAGE(0));
/*
- * Test free_blocks against 1 not 0, since we have 1 data
+ * Test used_blocks against 1 less max_blocks, since we have 1 data
* page (and perhaps indirect index pages) yet to allocate:
* a waste to allocate index if we cannot allocate data.
*/
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks <= 1) {
- spin_unlock(&sbinfo->stat_lock);
+ if (percpu_counter_compare(&sbinfo->used_blocks, (sbinfo->max_blocks - 1)) > 0)
return ERR_PTR(-ENOSPC);
- }
- sbinfo->free_blocks--;
+ percpu_counter_inc(&sbinfo->used_blocks);
+ spin_lock(&inode->i_lock);
inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
+ spin_unlock(&inode->i_lock);
}
spin_unlock(&info->lock);
loff_t newsize = attr->ia_size;
int error;
+ error = inode_change_ok(inode, attr);
+ if (error)
+ return error;
+
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
&& newsize != inode->i_size) {
struct page *page = NULL;
}
}
- error = simple_setsize(inode, newsize);
+ /* XXX(truncate): truncate_setsize should be called last */
+ truncate_setsize(inode, newsize);
if (page)
page_cache_release(page);
- if (error)
- return error;
shmem_truncate_range(inode, newsize, (loff_t)-1);
}
- error = inode_change_ok(inode, attr);
- if (!error)
- generic_setattr(inode, attr);
+ setattr_copy(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
- if (!error && (attr->ia_valid & ATTR_MODE))
+ if (attr->ia_valid & ATTR_MODE)
error = generic_acl_chmod(inode);
#endif
return error;
}
- static void shmem_delete_inode(struct inode *inode)
+ static void shmem_evict_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
}
BUG_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
- clear_inode(inode);
+ end_writeback(inode);
}
static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
/*
* Move _head_ to start search for next from here.
- * But be careful: shmem_delete_inode checks list_empty without taking
+ * But be careful: shmem_evict_inode checks list_empty without taking
* mutex, and there's an instant in list_move_tail when info->swaplist
* would appear empty, if it were the only one on shmem_swaplist. We
* could avoid doing it if inode NULL; or use this minor optimization.
struct shmem_sb_info *sbinfo;
struct page *filepage = *pagep;
struct page *swappage;
+ struct page *prealloc_page = NULL;
swp_entry_t *entry;
swp_entry_t swap;
gfp_t gfp;
filepage = find_lock_page(mapping, idx);
if (filepage && PageUptodate(filepage))
goto done;
- error = 0;
gfp = mapping_gfp_mask(mapping);
if (!filepage) {
/*
if (error)
goto failed;
radix_tree_preload_end();
+ if (sgp != SGP_READ && !prealloc_page) {
+ /* We don't care if this fails */
+ prealloc_page = shmem_alloc_page(gfp, info, idx);
+ if (prealloc_page) {
+ if (mem_cgroup_cache_charge(prealloc_page,
+ current->mm, GFP_KERNEL)) {
+ page_cache_release(prealloc_page);
+ prealloc_page = NULL;
+ }
+ }
+ }
}
+ error = 0;
spin_lock(&info->lock);
shmem_recalc_inode(inode);
shmem_swp_unmap(entry);
sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks == 0 ||
+ if ((percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks) > 0) ||
shmem_acct_block(info->flags)) {
- spin_unlock(&sbinfo->stat_lock);
spin_unlock(&info->lock);
error = -ENOSPC;
goto failed;
}
- sbinfo->free_blocks--;
+ percpu_counter_inc(&sbinfo->used_blocks);
+ spin_lock(&inode->i_lock);
inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
+ spin_unlock(&inode->i_lock);
} else if (shmem_acct_block(info->flags)) {
spin_unlock(&info->lock);
error = -ENOSPC;
if (!filepage) {
int ret;
- spin_unlock(&info->lock);
- filepage = shmem_alloc_page(gfp, info, idx);
- if (!filepage) {
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- error = -ENOMEM;
- goto failed;
- }
- SetPageSwapBacked(filepage);
+ if (!prealloc_page) {
+ spin_unlock(&info->lock);
+ filepage = shmem_alloc_page(gfp, info, idx);
+ if (!filepage) {
+ shmem_unacct_blocks(info->flags, 1);
+ shmem_free_blocks(inode, 1);
+ error = -ENOMEM;
+ goto failed;
+ }
+ SetPageSwapBacked(filepage);
- /* Precharge page while we can wait, compensate after */
- error = mem_cgroup_cache_charge(filepage, current->mm,
- GFP_KERNEL);
- if (error) {
- page_cache_release(filepage);
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- filepage = NULL;
- goto failed;
+ /*
+ * Precharge page while we can wait, compensate
+ * after
+ */
+ error = mem_cgroup_cache_charge(filepage,
+ current->mm, GFP_KERNEL);
+ if (error) {
+ page_cache_release(filepage);
+ shmem_unacct_blocks(info->flags, 1);
+ shmem_free_blocks(inode, 1);
+ filepage = NULL;
+ goto failed;
+ }
+
+ spin_lock(&info->lock);
+ } else {
+ filepage = prealloc_page;
+ prealloc_page = NULL;
+ SetPageSwapBacked(filepage);
}
- spin_lock(&info->lock);
entry = shmem_swp_alloc(info, idx, sgp);
if (IS_ERR(entry))
error = PTR_ERR(entry);
}
done:
*pagep = filepage;
- return 0;
+ error = 0;
+ goto out;
failed:
if (*pagep != filepage) {
unlock_page(filepage);
page_cache_release(filepage);
}
+out:
+ if (prealloc_page) {
+ mem_cgroup_uncharge_cache_page(prealloc_page);
+ page_cache_release(prealloc_page);
+ }
return error;
}
buf->f_type = TMPFS_MAGIC;
buf->f_bsize = PAGE_CACHE_SIZE;
buf->f_namelen = NAME_MAX;
- spin_lock(&sbinfo->stat_lock);
if (sbinfo->max_blocks) {
buf->f_blocks = sbinfo->max_blocks;
- buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+ buf->f_bavail = buf->f_bfree =
+ sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks);
}
if (sbinfo->max_inodes) {
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
/* else leave those fields 0 like simple_statfs */
- spin_unlock(&sbinfo->stat_lock);
return 0;
}
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
struct shmem_sb_info config = *sbinfo;
- unsigned long blocks;
unsigned long inodes;
int error = -EINVAL;
return error;
spin_lock(&sbinfo->stat_lock);
- blocks = sbinfo->max_blocks - sbinfo->free_blocks;
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (config.max_blocks < blocks)
+ if (percpu_counter_compare(&sbinfo->used_blocks, config.max_blocks) > 0)
goto out;
if (config.max_inodes < inodes)
goto out;
error = 0;
sbinfo->max_blocks = config.max_blocks;
- sbinfo->free_blocks = config.max_blocks - blocks;
sbinfo->max_inodes = config.max_inodes;
sbinfo->free_inodes = config.max_inodes - inodes;
#endif
spin_lock_init(&sbinfo->stat_lock);
- sbinfo->free_blocks = sbinfo->max_blocks;
+ percpu_counter_init(&sbinfo->used_blocks, 0);
sbinfo->free_inodes = sbinfo->max_inodes;
sb->s_maxbytes = SHMEM_MAX_BYTES;
.remount_fs = shmem_remount_fs,
.show_options = shmem_show_options,
#endif
- .delete_inode = shmem_delete_inode,
+ .evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
.put_super = shmem_put_super,
};