Merge remote-tracking branch 'efi/chainsaw' into x86/efi
Resolved Conflicts:
drivers/firmware/efivars.c
fs/efivarsfs/file.c
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig
index 0a93dc1..55abfd6 100644
--- a/fs/9p/Kconfig
+++ b/fs/9p/Kconfig
@@ -11,8 +11,7 @@
if 9P_FS
config 9P_FSCACHE
- bool "Enable 9P client caching support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ bool "Enable 9P client caching support"
depends on 9P_FS=m && FSCACHE || 9P_FS=y && FSCACHE=y
help
Choose Y here to enable persistent, read-only local
diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index 15b6791..7af425f 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -23,6 +23,7 @@
#include "acl.h"
#include "v9fs.h"
#include "v9fs_vfs.h"
+#include "fid.h"
static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name)
{
@@ -113,16 +114,12 @@
}
-static int v9fs_set_acl(struct dentry *dentry, int type, struct posix_acl *acl)
+static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl)
{
int retval;
char *name;
size_t size;
void *buffer;
- struct inode *inode = dentry->d_inode;
-
- set_cached_acl(inode, type, acl);
-
if (!acl)
return 0;
@@ -144,17 +141,16 @@
default:
BUG();
}
- retval = v9fs_xattr_set(dentry, name, buffer, size, 0);
+ retval = v9fs_fid_xattr_set(fid, name, buffer, size, 0);
err_free_out:
kfree(buffer);
return retval;
}
-int v9fs_acl_chmod(struct dentry *dentry)
+int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
{
int retval = 0;
struct posix_acl *acl;
- struct inode *inode = dentry->d_inode;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
@@ -163,25 +159,30 @@
retval = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
if (retval)
return retval;
- retval = v9fs_set_acl(dentry, ACL_TYPE_ACCESS, acl);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+ retval = v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
posix_acl_release(acl);
}
return retval;
}
-int v9fs_set_create_acl(struct dentry *dentry,
- struct posix_acl **dpacl, struct posix_acl **pacl)
+int v9fs_set_create_acl(struct inode *inode, struct p9_fid *fid,
+ struct posix_acl *dacl, struct posix_acl *acl)
{
- if (dentry) {
- v9fs_set_acl(dentry, ACL_TYPE_DEFAULT, *dpacl);
- v9fs_set_acl(dentry, ACL_TYPE_ACCESS, *pacl);
- }
- posix_acl_release(*dpacl);
- posix_acl_release(*pacl);
- *dpacl = *pacl = NULL;
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, acl);
+ v9fs_set_acl(fid, ACL_TYPE_DEFAULT, dacl);
+ v9fs_set_acl(fid, ACL_TYPE_ACCESS, acl);
return 0;
}
+void v9fs_put_acl(struct posix_acl *dacl,
+ struct posix_acl *acl)
+{
+ posix_acl_release(dacl);
+ posix_acl_release(acl);
+}
+
int v9fs_acl_mode(struct inode *dir, umode_t *modep,
struct posix_acl **dpacl, struct posix_acl **pacl)
{
diff --git a/fs/9p/acl.h b/fs/9p/acl.h
index 5595564..e4f7e88 100644
--- a/fs/9p/acl.h
+++ b/fs/9p/acl.h
@@ -17,27 +17,33 @@
#ifdef CONFIG_9P_FS_POSIX_ACL
extern int v9fs_get_acl(struct inode *, struct p9_fid *);
extern struct posix_acl *v9fs_iop_get_acl(struct inode *inode, int type);
-extern int v9fs_acl_chmod(struct dentry *);
-extern int v9fs_set_create_acl(struct dentry *,
- struct posix_acl **, struct posix_acl **);
+extern int v9fs_acl_chmod(struct inode *, struct p9_fid *);
+extern int v9fs_set_create_acl(struct inode *, struct p9_fid *,
+ struct posix_acl *, struct posix_acl *);
extern int v9fs_acl_mode(struct inode *dir, umode_t *modep,
struct posix_acl **dpacl, struct posix_acl **pacl);
+extern void v9fs_put_acl(struct posix_acl *dacl, struct posix_acl *acl);
#else
#define v9fs_iop_get_acl NULL
static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid)
{
return 0;
}
-static inline int v9fs_acl_chmod(struct dentry *dentry)
+static inline int v9fs_acl_chmod(struct inode *inode, struct p9_fid *fid)
{
return 0;
}
-static inline int v9fs_set_create_acl(struct dentry *dentry,
- struct posix_acl **dpacl,
- struct posix_acl **pacl)
+static inline int v9fs_set_create_acl(struct inode *inode,
+ struct p9_fid *fid,
+ struct posix_acl *dacl,
+ struct posix_acl *acl)
{
return 0;
}
+static inline void v9fs_put_acl(struct posix_acl *dacl,
+ struct posix_acl *acl)
+{
+}
static inline int v9fs_acl_mode(struct inode *dir, umode_t *modep,
struct posix_acl **dpacl,
struct posix_acl **pacl)
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index da8eefb..d51ec9f 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -41,29 +41,16 @@
*
*/
-int v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
+static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid)
{
- struct v9fs_dentry *dent;
+ hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata);
+}
- p9_debug(P9_DEBUG_VFS, "fid %d dentry %s\n",
- fid->fid, dentry->d_name.name);
-
- dent = dentry->d_fsdata;
- if (!dent) {
- dent = kmalloc(sizeof(struct v9fs_dentry), GFP_KERNEL);
- if (!dent)
- return -ENOMEM;
-
- spin_lock_init(&dent->lock);
- INIT_LIST_HEAD(&dent->fidlist);
- dentry->d_fsdata = dent;
- }
-
- spin_lock(&dent->lock);
- list_add(&fid->dlist, &dent->fidlist);
- spin_unlock(&dent->lock);
-
- return 0;
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid)
+{
+ spin_lock(&dentry->d_lock);
+ __add_fid(dentry, fid);
+ spin_unlock(&dentry->d_lock);
}
/**
@@ -74,24 +61,25 @@
*
*/
-static struct p9_fid *v9fs_fid_find(struct dentry *dentry, u32 uid, int any)
+static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
{
- struct v9fs_dentry *dent;
struct p9_fid *fid, *ret;
p9_debug(P9_DEBUG_VFS, " dentry: %s (%p) uid %d any %d\n",
- dentry->d_name.name, dentry, uid, any);
- dent = (struct v9fs_dentry *) dentry->d_fsdata;
+ dentry->d_name.name, dentry, from_kuid(&init_user_ns, uid),
+ any);
ret = NULL;
- if (dent) {
- spin_lock(&dent->lock);
- list_for_each_entry(fid, &dent->fidlist, dlist) {
- if (any || fid->uid == uid) {
+ /* we'll recheck under lock if there's anything to look in */
+ if (dentry->d_fsdata) {
+ struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
+ spin_lock(&dentry->d_lock);
+ hlist_for_each_entry(fid, h, dlist) {
+ if (any || uid_eq(fid->uid, uid)) {
ret = fid;
break;
}
}
- spin_unlock(&dent->lock);
+ spin_unlock(&dentry->d_lock);
}
return ret;
@@ -126,7 +114,7 @@
}
static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
- uid_t uid, int any)
+ kuid_t uid, int any)
{
struct dentry *ds;
char **wnames, *uname;
@@ -214,8 +202,17 @@
}
kfree(wnames);
fid_out:
- if (!IS_ERR(fid))
- v9fs_fid_add(dentry, fid);
+ if (!IS_ERR(fid)) {
+ spin_lock(&dentry->d_lock);
+ if (d_unhashed(dentry)) {
+ spin_unlock(&dentry->d_lock);
+ p9_client_clunk(fid);
+ fid = ERR_PTR(-ENOENT);
+ } else {
+ __add_fid(dentry, fid);
+ spin_unlock(&dentry->d_lock);
+ }
+ }
err_out:
up_read(&v9ses->rename_sem);
return fid;
@@ -233,7 +230,7 @@
struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
{
- uid_t uid;
+ kuid_t uid;
int any, access;
struct v9fs_session_info *v9ses;
@@ -253,7 +250,7 @@
break;
default:
- uid = ~0;
+ uid = INVALID_UID;
any = 0;
break;
}
@@ -272,7 +269,7 @@
return ret;
}
-static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, uid_t uid)
+static struct p9_fid *v9fs_fid_clone_with_uid(struct dentry *dentry, kuid_t uid)
{
struct p9_fid *fid, *ret;
@@ -289,7 +286,7 @@
int err;
struct p9_fid *fid;
- fid = v9fs_fid_clone_with_uid(dentry, 0);
+ fid = v9fs_fid_clone_with_uid(dentry, GLOBAL_ROOT_UID);
if (IS_ERR(fid))
goto error_out;
/*
diff --git a/fs/9p/fid.h b/fs/9p/fid.h
index bb0b6e7..2b6787f 100644
--- a/fs/9p/fid.h
+++ b/fs/9p/fid.h
@@ -23,28 +23,8 @@
#define FS_9P_FID_H
#include <linux/list.h>
-/**
- * struct v9fs_dentry - 9p private data stored in dentry d_fsdata
- * @lock: protects the fidlist
- * @fidlist: list of FIDs currently associated with this dentry
- *
- * This structure defines the 9p private data associated with
- * a particular dentry. In particular, this private data is used
- * to lookup which 9P FID handle should be used for a particular VFS
- * operation. FID handles are associated with dentries instead of
- * inodes in order to more closely map functionality to the Plan 9
- * expected behavior for FID reclaimation and tracking.
- *
- * See Also: Mapping FIDs to Linux VFS model in
- * Design and Implementation of the Linux 9P File System documentation
- */
-struct v9fs_dentry {
- spinlock_t lock; /* protect fidlist */
- struct list_head fidlist;
-};
-
struct p9_fid *v9fs_fid_lookup(struct dentry *dentry);
struct p9_fid *v9fs_fid_clone(struct dentry *dentry);
-int v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
+void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid);
struct p9_fid *v9fs_writeback_fid(struct dentry *dentry);
#endif
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index d934f04..58e6cbc 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -161,7 +161,13 @@
ret = r;
continue;
}
- v9ses->dfltuid = option;
+ v9ses->dfltuid = make_kuid(current_user_ns(), option);
+ if (!uid_valid(v9ses->dfltuid)) {
+ p9_debug(P9_DEBUG_ERROR,
+ "uid field, but not a uid?\n");
+ ret = -EINVAL;
+ continue;
+ }
break;
case Opt_dfltgid:
r = match_int(&args[0], &option);
@@ -171,7 +177,13 @@
ret = r;
continue;
}
- v9ses->dfltgid = option;
+ v9ses->dfltgid = make_kgid(current_user_ns(), option);
+ if (!gid_valid(v9ses->dfltgid)) {
+ p9_debug(P9_DEBUG_ERROR,
+ "gid field, but not a gid?\n");
+ ret = -EINVAL;
+ continue;
+ }
break;
case Opt_afid:
r = match_int(&args[0], &option);
@@ -248,8 +260,9 @@
else if (strcmp(s, "client") == 0) {
v9ses->flags |= V9FS_ACCESS_CLIENT;
} else {
+ uid_t uid;
v9ses->flags |= V9FS_ACCESS_SINGLE;
- v9ses->uid = simple_strtoul(s, &e, 10);
+ uid = simple_strtoul(s, &e, 10);
if (*e != '\0') {
ret = -EINVAL;
pr_info("Unknown access argument %s\n",
@@ -257,6 +270,13 @@
kfree(s);
goto free_and_return;
}
+ v9ses->uid = make_kuid(current_user_ns(), uid);
+ if (!uid_valid(v9ses->uid)) {
+ ret = -EINVAL;
+ pr_info("Uknown uid %s\n", s);
+ kfree(s);
+ goto free_and_return;
+ }
}
kfree(s);
@@ -319,7 +339,7 @@
list_add(&v9ses->slist, &v9fs_sessionlist);
spin_unlock(&v9fs_sessionlist_lock);
- v9ses->uid = ~0;
+ v9ses->uid = INVALID_UID;
v9ses->dfltuid = V9FS_DEFUID;
v9ses->dfltgid = V9FS_DEFGID;
@@ -364,7 +384,7 @@
v9ses->flags &= ~V9FS_ACCESS_MASK;
v9ses->flags |= V9FS_ACCESS_ANY;
- v9ses->uid = ~0;
+ v9ses->uid = INVALID_UID;
}
if (!v9fs_proto_dotl(v9ses) ||
!((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) {
@@ -375,7 +395,7 @@
v9ses->flags &= ~V9FS_ACL_MASK;
}
- fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, ~0,
+ fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID,
v9ses->aname);
if (IS_ERR(fid)) {
retval = PTR_ERR(fid);
@@ -387,7 +407,7 @@
if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE)
fid->uid = v9ses->uid;
else
- fid->uid = ~0;
+ fid->uid = INVALID_UID;
#ifdef CONFIG_9P_FSCACHE
/* register the session for caching */
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 34c59f1..a8e127c 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -109,9 +109,9 @@
char *uname; /* user name to mount as */
char *aname; /* name of remote hierarchy being mounted */
unsigned int maxdata; /* max data for client interface */
- unsigned int dfltuid; /* default uid/muid for legacy support */
- unsigned int dfltgid; /* default gid for legacy support */
- u32 uid; /* if ACCESS_SINGLE, the uid that has access */
+ kuid_t dfltuid; /* default uid/muid for legacy support */
+ kgid_t dfltgid; /* default gid for legacy support */
+ kuid_t uid; /* if ACCESS_SINGLE, the uid that has access */
struct p9_client *clnt; /* 9p client */
struct list_head slist; /* list of sessions registered with v9fs */
struct backing_dev_info bdi;
@@ -165,8 +165,8 @@
#define V9FS_PORT 564
#define V9FS_DEFUSER "nobody"
#define V9FS_DEFANAME ""
-#define V9FS_DEFUID (-2)
-#define V9FS_DEFGID (-2)
+#define V9FS_DEFUID KUIDT_INIT(-2)
+#define V9FS_DEFGID KGIDT_INIT(-2)
static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode)
{
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index 64600b5..f039b10 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -83,21 +83,12 @@
static void v9fs_dentry_release(struct dentry *dentry)
{
- struct v9fs_dentry *dent;
- struct p9_fid *temp, *current_fid;
-
+ struct hlist_node *p, *n;
p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
dentry->d_name.name, dentry);
- dent = dentry->d_fsdata;
- if (dent) {
- list_for_each_entry_safe(current_fid, temp, &dent->fidlist,
- dlist) {
- p9_client_clunk(current_fid);
- }
-
- kfree(dent);
- dentry->d_fsdata = NULL;
- }
+ hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+ p9_client_clunk(hlist_entry(p, struct p9_fid, dlist));
+ dentry->d_fsdata = NULL;
}
static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
@@ -137,6 +128,7 @@
const struct dentry_operations v9fs_cached_dentry_operations = {
.d_revalidate = v9fs_lookup_revalidate,
+ .d_weak_revalidate = v9fs_lookup_revalidate,
.d_delete = v9fs_cached_dentry_delete,
.d_release = v9fs_dentry_release,
};
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index ff911e7..be1e34a 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -52,10 +52,9 @@
*/
struct p9_rdir {
- struct mutex mutex;
int head;
int tail;
- uint8_t *buf;
+ uint8_t buf[];
};
/**
@@ -93,33 +92,12 @@
*
*/
-static int v9fs_alloc_rdir_buf(struct file *filp, int buflen)
+static struct p9_rdir *v9fs_alloc_rdir_buf(struct file *filp, int buflen)
{
- struct p9_rdir *rdir;
- struct p9_fid *fid;
- int err = 0;
-
- fid = filp->private_data;
- if (!fid->rdir) {
- rdir = kmalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
-
- if (rdir == NULL) {
- err = -ENOMEM;
- goto exit;
- }
- spin_lock(&filp->f_dentry->d_lock);
- if (!fid->rdir) {
- rdir->buf = (uint8_t *)rdir + sizeof(struct p9_rdir);
- mutex_init(&rdir->mutex);
- rdir->head = rdir->tail = 0;
- fid->rdir = (void *) rdir;
- rdir = NULL;
- }
- spin_unlock(&filp->f_dentry->d_lock);
- kfree(rdir);
- }
-exit:
- return err;
+ struct p9_fid *fid = filp->private_data;
+ if (!fid->rdir)
+ fid->rdir = kzalloc(sizeof(struct p9_rdir) + buflen, GFP_KERNEL);
+ return fid->rdir;
}
/**
@@ -145,20 +123,16 @@
buflen = fid->clnt->msize - P9_IOHDRSZ;
- err = v9fs_alloc_rdir_buf(filp, buflen);
- if (err)
- goto exit;
- rdir = (struct p9_rdir *) fid->rdir;
+ rdir = v9fs_alloc_rdir_buf(filp, buflen);
+ if (!rdir)
+ return -ENOMEM;
- err = mutex_lock_interruptible(&rdir->mutex);
- if (err)
- return err;
- while (err == 0) {
+ while (1) {
if (rdir->tail == rdir->head) {
err = v9fs_file_readn(filp, rdir->buf, NULL,
buflen, filp->f_pos);
if (err <= 0)
- goto unlock_and_exit;
+ return err;
rdir->head = 0;
rdir->tail = err;
@@ -169,9 +143,8 @@
rdir->tail - rdir->head, &st);
if (err) {
p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
- err = -EIO;
p9stat_free(&st);
- goto unlock_and_exit;
+ return -EIO;
}
reclen = st.size+2;
@@ -180,19 +153,13 @@
p9stat_free(&st);
- if (over) {
- err = 0;
- goto unlock_and_exit;
- }
+ if (over)
+ return 0;
+
rdir->head += reclen;
filp->f_pos += reclen;
}
}
-
-unlock_and_exit:
- mutex_unlock(&rdir->mutex);
-exit:
- return err;
}
/**
@@ -218,21 +185,16 @@
buflen = fid->clnt->msize - P9_READDIRHDRSZ;
- err = v9fs_alloc_rdir_buf(filp, buflen);
- if (err)
- goto exit;
- rdir = (struct p9_rdir *) fid->rdir;
+ rdir = v9fs_alloc_rdir_buf(filp, buflen);
+ if (!rdir)
+ return -ENOMEM;
- err = mutex_lock_interruptible(&rdir->mutex);
- if (err)
- return err;
-
- while (err == 0) {
+ while (1) {
if (rdir->tail == rdir->head) {
err = p9_client_readdir(fid, rdir->buf, buflen,
filp->f_pos);
if (err <= 0)
- goto unlock_and_exit;
+ return err;
rdir->head = 0;
rdir->tail = err;
@@ -245,8 +207,7 @@
&curdirent);
if (err < 0) {
p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
- err = -EIO;
- goto unlock_and_exit;
+ return -EIO;
}
/* d_off in dirent structure tracks the offset into
@@ -261,20 +222,13 @@
curdirent.d_type);
oldoffset = curdirent.d_off;
- if (over) {
- err = 0;
- goto unlock_and_exit;
- }
+ if (over)
+ return 0;
filp->f_pos = curdirent.d_off;
rdir->head += err;
}
}
-
-unlock_and_exit:
- mutex_unlock(&rdir->mutex);
-exit:
- return err;
}
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index c2483e9..d384a8b 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -80,10 +80,6 @@
p9_client_clunk(fid);
return err;
}
- if (file->f_flags & O_TRUNC) {
- i_size_write(inode, 0);
- inode->i_blocks = 0;
- }
if ((file->f_flags & O_APPEND) &&
(!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)))
generic_file_llseek(file, 0, SEEK_END);
@@ -133,7 +129,7 @@
static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
{
int res = 0;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);
@@ -302,7 +298,7 @@
static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int ret = -ENOLCK;
p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
@@ -338,7 +334,7 @@
static int v9fs_file_flock_dotl(struct file *filp, int cmd,
struct file_lock *fl)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int ret = -ENOLCK;
p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
@@ -529,7 +525,7 @@
if (!count)
goto out;
- retval = v9fs_file_write_internal(filp->f_path.dentry->d_inode,
+ retval = v9fs_file_write_internal(file_inode(filp),
filp->private_data,
data, count, &origin, 1);
/* update offset on successful write */
@@ -604,7 +600,7 @@
struct v9fs_inode *v9inode;
struct page *page = vmf->page;
struct file *filp = vma->vm_file;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
@@ -620,6 +616,7 @@
lock_page(page);
if (page->mapping != inode->i_mapping)
goto out_unlock;
+ wait_for_stable_page(page);
return VM_FAULT_LOCKED;
out_unlock:
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 890bed5..d86edc8 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -192,9 +192,6 @@
break;
}
- if (uflags & O_TRUNC)
- ret |= P9_OTRUNC;
-
if (extended) {
if (uflags & O_EXCL)
ret |= P9_OEXCL;
@@ -228,9 +225,9 @@
wstat->uid = NULL;
wstat->gid = NULL;
wstat->muid = NULL;
- wstat->n_uid = ~0;
- wstat->n_gid = ~0;
- wstat->n_muid = ~0;
+ wstat->n_uid = INVALID_UID;
+ wstat->n_gid = INVALID_GID;
+ wstat->n_muid = INVALID_UID;
wstat->extension = NULL;
}
@@ -695,9 +692,7 @@
"inode creation failed %d\n", err);
goto error;
}
- err = v9fs_fid_add(dentry, fid);
- if (err < 0)
- goto error;
+ v9fs_fid_add(dentry, fid);
d_instantiate(dentry, inode);
}
return ofid;
@@ -793,7 +788,6 @@
struct p9_fid *dfid, *fid;
struct inode *inode;
char *name;
- int result = 0;
p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n",
dir, dentry->d_name.name, dentry, flags);
@@ -811,13 +805,11 @@
name = (char *) dentry->d_name.name;
fid = p9_client_walk(dfid, 1, &name, 1);
if (IS_ERR(fid)) {
- result = PTR_ERR(fid);
- if (result == -ENOENT) {
- inode = NULL;
- goto inst_out;
+ if (fid == ERR_PTR(-ENOENT)) {
+ d_add(dentry, NULL);
+ return NULL;
}
-
- return ERR_PTR(result);
+ return ERR_CAST(fid);
}
/*
* Make sure we don't use a wrong inode due to parallel
@@ -829,14 +821,9 @@
else
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
- result = PTR_ERR(inode);
- inode = NULL;
- goto error;
+ p9_client_clunk(fid);
+ return ERR_CAST(inode);
}
- result = v9fs_fid_add(dentry, fid);
- if (result < 0)
- goto error_iput;
-inst_out:
/*
* If we had a rename on the server and a parallel lookup
* for the new name, then make sure we instantiate with
@@ -845,15 +832,13 @@
* k/b.
*/
res = d_materialise_unique(dentry, inode);
- if (!IS_ERR(res))
- return res;
- result = PTR_ERR(res);
-error_iput:
- iput(inode);
-error:
- p9_client_clunk(fid);
-
- return ERR_PTR(result);
+ if (!res)
+ v9fs_fid_add(dentry, fid);
+ else if (!IS_ERR(res))
+ v9fs_fid_add(res, fid);
+ else
+ p9_client_clunk(fid);
+ return res;
}
static int
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 4089554..53687bb 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -57,7 +57,7 @@
* group of the new file system object.
*/
-static gid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
+static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode)
{
BUG_ON(dir_inode == NULL);
@@ -186,7 +186,6 @@
{ O_CREAT, P9_DOTL_CREATE },
{ O_EXCL, P9_DOTL_EXCL },
{ O_NOCTTY, P9_DOTL_NOCTTY },
- { O_TRUNC, P9_DOTL_TRUNC },
{ O_APPEND, P9_DOTL_APPEND },
{ O_NONBLOCK, P9_DOTL_NONBLOCK },
{ O_DSYNC, P9_DOTL_DSYNC },
@@ -246,7 +245,7 @@
int *opened)
{
int err = 0;
- gid_t gid;
+ kgid_t gid;
umode_t mode;
char *name = NULL;
struct p9_qid qid;
@@ -268,8 +267,14 @@
}
/* Only creates */
- if (!(flags & O_CREAT) || dentry->d_inode)
- return finish_no_open(file, res);
+ if (!(flags & O_CREAT))
+ return finish_no_open(file, res);
+ else if (dentry->d_inode) {
+ if ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+ return -EEXIST;
+ else
+ return finish_no_open(file, res);
+ }
v9ses = v9fs_inode2v9ses(dir);
@@ -325,13 +330,11 @@
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
goto error;
}
- err = v9fs_fid_add(dentry, fid);
- if (err < 0)
- goto error;
- d_instantiate(dentry, inode);
-
/* Now set the ACL based on the default value */
- v9fs_set_create_acl(dentry, &dacl, &pacl);
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+
+ v9fs_fid_add(dentry, fid);
+ d_instantiate(dentry, inode);
v9inode = V9FS_I(inode);
mutex_lock(&v9inode->v_mutex);
@@ -364,6 +367,7 @@
#endif
*opened |= FILE_CREATED;
out:
+ v9fs_put_acl(dacl, pacl);
dput(res);
return err;
@@ -373,7 +377,6 @@
err_clunk_old_fid:
if (ofid)
p9_client_clunk(ofid);
- v9fs_set_create_acl(NULL, &dacl, &pacl);
goto out;
}
@@ -391,7 +394,7 @@
int err;
struct v9fs_session_info *v9ses;
struct p9_fid *fid = NULL, *dfid = NULL;
- gid_t gid;
+ kgid_t gid;
char *name;
umode_t mode;
struct inode *inode;
@@ -430,17 +433,17 @@
if (err < 0)
goto error;
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ fid = NULL;
+ 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_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
- err);
- fid = NULL;
- goto error;
- }
-
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
@@ -448,11 +451,11 @@
err);
goto error;
}
- err = v9fs_fid_add(dentry, fid);
- if (err < 0)
- goto error;
+ v9fs_fid_add(dentry, fid);
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
d_instantiate(dentry, inode);
fid = NULL;
+ err = 0;
} else {
/*
* Not in cached mode. No need to populate
@@ -464,16 +467,15 @@
err = PTR_ERR(inode);
goto error;
}
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
d_instantiate(dentry, inode);
}
- /* Now set the ACL based on the default value */
- v9fs_set_create_acl(dentry, &dacl, &pacl);
inc_nlink(dir);
v9fs_invalidate_inode_attr(dir);
error:
if (fid)
p9_client_clunk(fid);
- v9fs_set_create_acl(NULL, &dacl, &pacl);
+ v9fs_put_acl(dacl, pacl);
return err;
}
@@ -567,10 +569,11 @@
struct v9fs_session_info *v9ses;
struct p9_fid *fid;
struct p9_iattr_dotl p9attr;
+ struct inode *inode = dentry->d_inode;
p9_debug(P9_DEBUG_VFS, "\n");
- retval = inode_change_ok(dentry->d_inode, iattr);
+ retval = inode_change_ok(inode, iattr);
if (retval)
return retval;
@@ -591,23 +594,23 @@
return PTR_ERR(fid);
/* Write all dirty data */
- if (S_ISREG(dentry->d_inode->i_mode))
- filemap_write_and_wait(dentry->d_inode->i_mapping);
+ if (S_ISREG(inode->i_mode))
+ filemap_write_and_wait(inode->i_mapping);
retval = p9_client_setattr(fid, &p9attr);
if (retval < 0)
return retval;
if ((iattr->ia_valid & ATTR_SIZE) &&
- iattr->ia_size != i_size_read(dentry->d_inode))
- truncate_setsize(dentry->d_inode, iattr->ia_size);
+ iattr->ia_size != i_size_read(inode))
+ truncate_setsize(inode, iattr->ia_size);
- v9fs_invalidate_inode_attr(dentry->d_inode);
- setattr_copy(dentry->d_inode, iattr);
- mark_inode_dirty(dentry->d_inode);
+ v9fs_invalidate_inode_attr(inode);
+ setattr_copy(inode, iattr);
+ mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE) {
/* We also want to update ACL when we update mode bits */
- retval = v9fs_acl_chmod(dentry);
+ retval = v9fs_acl_chmod(inode, fid);
if (retval < 0)
return retval;
}
@@ -692,7 +695,7 @@
const char *symname)
{
int err;
- gid_t gid;
+ kgid_t gid;
char *name;
struct p9_qid qid;
struct inode *inode;
@@ -741,11 +744,10 @@
err);
goto error;
}
- err = v9fs_fid_add(dentry, fid);
- if (err < 0)
- goto error;
+ v9fs_fid_add(dentry, fid);
d_instantiate(dentry, inode);
fid = NULL;
+ err = 0;
} else {
/* Not in cached mode. No need to populate inode with stat */
inode = v9fs_get_inode(dir->i_sb, S_IFLNK, 0);
@@ -832,7 +834,7 @@
dev_t rdev)
{
int err;
- gid_t gid;
+ kgid_t gid;
char *name;
umode_t mode;
struct v9fs_session_info *v9ses;
@@ -875,17 +877,17 @@
goto error;
v9fs_invalidate_inode_attr(dir);
+ fid = p9_client_walk(dfid, 1, &name, 1);
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
+ err);
+ fid = NULL;
+ 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_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n",
- err);
- fid = NULL;
- goto error;
- }
-
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
@@ -893,11 +895,11 @@
err);
goto error;
}
- err = v9fs_fid_add(dentry, fid);
- if (err < 0)
- goto error;
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
+ v9fs_fid_add(dentry, fid);
d_instantiate(dentry, inode);
fid = NULL;
+ err = 0;
} else {
/*
* Not in cached mode. No need to populate inode with stat.
@@ -908,14 +910,13 @@
err = PTR_ERR(inode);
goto error;
}
+ v9fs_set_create_acl(inode, fid, dacl, pacl);
d_instantiate(dentry, inode);
}
- /* Now set the ACL based on the default value */
- v9fs_set_create_acl(dentry, &dacl, &pacl);
error:
if (fid)
p9_client_clunk(fid);
- v9fs_set_create_acl(NULL, &dacl, &pacl);
+ v9fs_put_acl(dacl, pacl);
return err;
}
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 137d503..2756dcd 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -363,5 +363,6 @@
.mount = v9fs_mount,
.kill_sb = v9fs_kill_super,
.owner = THIS_MODULE,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT,
+ .fs_flags = FS_RENAME_DOES_D_MOVE,
};
+MODULE_ALIAS_FS("9p");
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 29653b7..c45e016 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -111,19 +111,26 @@
int v9fs_xattr_set(struct dentry *dentry, const char *name,
const void *value, size_t value_len, int flags)
{
+ struct p9_fid *fid = v9fs_fid_lookup(dentry);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+ return v9fs_fid_xattr_set(fid, name, value, value_len, flags);
+}
+
+int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
+ const void *value, size_t value_len, int flags)
+{
u64 offset = 0;
int retval, msize, write_count;
- struct p9_fid *fid = NULL;
p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
name, value_len, flags);
- fid = v9fs_fid_clone(dentry);
- if (IS_ERR(fid)) {
- retval = PTR_ERR(fid);
- fid = NULL;
- goto error;
- }
+ /* Clone it */
+ fid = p9_client_walk(fid, 0, NULL, 1);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
+
/*
* On success fid points to xattr
*/
@@ -131,7 +138,8 @@
if (retval < 0) {
p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n",
retval);
- goto error;
+ p9_client_clunk(fid);
+ return retval;
}
msize = fid->clnt->msize;
while (value_len) {
@@ -144,17 +152,12 @@
if (write_count < 0) {
/* error in xattr write */
retval = write_count;
- goto error;
+ break;
}
offset += write_count;
value_len -= write_count;
}
- /* Total read xattr bytes */
- retval = offset;
-error:
- if (fid)
- retval = p9_client_clunk(fid);
- return retval;
+ return p9_client_clunk(fid);
}
ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h
index eaa837c..eec348a 100644
--- a/fs/9p/xattr.h
+++ b/fs/9p/xattr.h
@@ -27,6 +27,8 @@
void *, size_t);
extern ssize_t v9fs_xattr_get(struct dentry *, const char *,
void *, size_t);
+extern int v9fs_fid_xattr_set(struct p9_fid *, const char *,
+ const void *, size_t, int);
extern int v9fs_xattr_set(struct dentry *, const char *,
const void *, size_t, int);
extern ssize_t v9fs_listxattr(struct dentry *, char *, size_t);
diff --git a/fs/Kconfig b/fs/Kconfig
index 780725a..c229f82 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -211,6 +211,7 @@
source "fs/ufs/Kconfig"
source "fs/exofs/Kconfig"
source "fs/f2fs/Kconfig"
+source "fs/efivarfs/Kconfig"
endif # MISC_FILESYSTEMS
diff --git a/fs/Makefile b/fs/Makefile
index 9d53192..0fde6a3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -127,3 +127,4 @@
obj-y += exofs/ # Multiple modules
obj-$(CONFIG_CEPH_FS) += ceph/
obj-$(CONFIG_PSTORE) += pstore/
+obj-$(CONFIG_EFIVAR_FS) += efivarfs/
diff --git a/fs/adfs/Kconfig b/fs/adfs/Kconfig
index e55182a..c5a7787 100644
--- a/fs/adfs/Kconfig
+++ b/fs/adfs/Kconfig
@@ -1,6 +1,6 @@
config ADFS_FS
- tristate "ADFS file system support (EXPERIMENTAL)"
- depends on BLOCK && EXPERIMENTAL
+ tristate "ADFS file system support"
+ depends on BLOCK
help
The Acorn Disc Filing System is the standard file system of the
RiscOS operating system which runs on Acorn's ARM-based Risc PC
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index b3be2e7..9cf874c 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -19,7 +19,7 @@
static int
adfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
struct object_info obj;
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index d571229..0ff4bae 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -524,6 +524,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("adfs");
static int __init init_adfs_fs(void)
{
diff --git a/fs/affs/Kconfig b/fs/affs/Kconfig
index cfad9af..a04d9e8 100644
--- a/fs/affs/Kconfig
+++ b/fs/affs/Kconfig
@@ -1,6 +1,6 @@
config AFFS_FS
- tristate "Amiga FFS file system support (EXPERIMENTAL)"
- depends on BLOCK && EXPERIMENTAL
+ tristate "Amiga FFS file system support"
+ depends on BLOCK
help
The Fast File System (FFS) is the common file system used on hard
disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20). Say Y
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index eb82ee5..d9a4367 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -125,9 +125,8 @@
affs_fix_dcache(struct inode *inode, u32 entry_ino)
{
struct dentry *dentry;
- struct hlist_node *p;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
if (entry_ino == (u32)(long)dentry->d_fsdata) {
dentry->d_fsdata = (void *)inode->i_ino;
break;
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index 8ca8f3a..fd11a6d 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -42,7 +42,7 @@
static int
affs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct buffer_head *dir_bh;
struct buffer_head *fh_bh;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index b84dc73..45161a8 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -622,6 +622,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("affs");
static int __init init_affs_fs(void)
{
diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig
index 8f975f2..ebba3b1 100644
--- a/fs/afs/Kconfig
+++ b/fs/afs/Kconfig
@@ -1,6 +1,6 @@
config AFS_FS
- tristate "Andrew File System support (AFS) (EXPERIMENTAL)"
- depends on INET && EXPERIMENTAL
+ tristate "Andrew File System support (AFS)"
+ depends on INET
select AF_RXRPC
select DNS_RESOLVER
help
@@ -22,8 +22,7 @@
If unsure, say N.
config AFS_FSCACHE
- bool "Provide AFS client caching support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ bool "Provide AFS client caching support"
depends on AFS_FS=m && FSCACHE || AFS_FS=y && FSCACHE=y
help
Say Y here if you want AFS data to be cached locally on disk through
diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index c548aa3..3c462ff 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -119,8 +119,8 @@
u64 size; /* file size */
afs_dataversion_t data_version; /* current data version */
u32 author; /* author ID */
- u32 owner; /* owner ID */
- u32 group; /* group ID */
+ kuid_t owner; /* owner ID */
+ kgid_t group; /* group ID */
afs_access_t caller_access; /* access rights for authenticated caller */
afs_access_t anon_access; /* access rights for unauthenticated caller */
umode_t mode; /* UNIX mode */
@@ -133,13 +133,6 @@
/*
* AFS file status change request
*/
-struct afs_store_status {
- u32 mask; /* which bits of the struct are set */
- u32 mtime_client; /* last time client changed data */
- u32 owner; /* owner ID */
- u32 group; /* group ID */
- umode_t mode; /* UNIX mode */
-};
#define AFS_SET_MTIME 0x01 /* set the mtime */
#define AFS_SET_OWNER 0x02 /* set the owner ID */
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index db47790..7a465ed 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -393,12 +393,12 @@
int ret;
_enter("{%Ld,{%lu}}",
- file->f_pos, file->f_path.dentry->d_inode->i_ino);
+ file->f_pos, file_inode(file)->i_ino);
ASSERT(file->private_data != NULL);
fpos = file->f_pos;
- ret = afs_dir_iterate(file->f_path.dentry->d_inode, &fpos,
+ ret = afs_dir_iterate(file_inode(file), &fpos,
cookie, filldir, file->private_data);
file->f_pos = fpos;
diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index 757d6645..2497bf3 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -514,7 +514,7 @@
*/
int afs_lock(struct file *file, int cmd, struct file_lock *fl)
{
- struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
_enter("{%x:%u},%d,{t=%x,fl=%x,r=%Ld:%Ld}",
vnode->fid.vid, vnode->fid.vnode, cmd,
@@ -537,7 +537,7 @@
*/
int afs_flock(struct file *file, int cmd, struct file_lock *fl)
{
- struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
_enter("{%x:%u},%d,{t=%x,fl=%x}",
vnode->fid.vid, vnode->fid.vnode, cmd,
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index b960ff0..c2e930e 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -42,6 +42,8 @@
umode_t mode;
u64 data_version, size;
u32 changed = 0; /* becomes non-zero if ctime-type changes seen */
+ kuid_t owner;
+ kgid_t group;
#define EXTRACT(DST) \
do { \
@@ -56,7 +58,9 @@
size = ntohl(*bp++);
data_version = ntohl(*bp++);
EXTRACT(status->author);
- EXTRACT(status->owner);
+ owner = make_kuid(&init_user_ns, ntohl(*bp++));
+ changed |= !uid_eq(owner, status->owner);
+ status->owner = owner;
EXTRACT(status->caller_access); /* call ticket dependent */
EXTRACT(status->anon_access);
EXTRACT(status->mode);
@@ -65,7 +69,9 @@
bp++; /* seg size */
status->mtime_client = ntohl(*bp++);
status->mtime_server = ntohl(*bp++);
- EXTRACT(status->group);
+ group = make_kgid(&init_user_ns, ntohl(*bp++));
+ changed |= !gid_eq(group, status->group);
+ status->group = group;
bp++; /* sync counter */
data_version |= (u64) ntohl(*bp++) << 32;
EXTRACT(status->lock_count);
@@ -181,12 +187,12 @@
if (attr->ia_valid & ATTR_UID) {
mask |= AFS_SET_OWNER;
- owner = attr->ia_uid;
+ owner = from_kuid(&init_user_ns, attr->ia_uid);
}
if (attr->ia_valid & ATTR_GID) {
mask |= AFS_SET_GROUP;
- group = attr->ia_gid;
+ group = from_kgid(&init_user_ns, attr->ia_gid);
}
if (attr->ia_valid & ATTR_MODE) {
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 95cffd3..789bc25 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -69,7 +69,7 @@
set_nlink(inode, vnode->status.nlink);
inode->i_uid = vnode->status.owner;
- inode->i_gid = 0;
+ inode->i_gid = GLOBAL_ROOT_GID;
inode->i_size = vnode->status.size;
inode->i_ctime.tv_sec = vnode->status.mtime_server;
inode->i_ctime.tv_nsec = 0;
@@ -175,8 +175,8 @@
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
inode->i_op = &afs_autocell_inode_operations;
set_nlink(inode, 2);
- inode->i_uid = 0;
- inode->i_gid = 0;
+ inode->i_uid = GLOBAL_ROOT_UID;
+ inode->i_gid = GLOBAL_ROOT_GID;
inode->i_ctime.tv_sec = get_seconds();
inode->i_ctime.tv_nsec = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime;
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 4316500..c486155 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -24,6 +24,8 @@
#include <linux/parser.h>
#include <linux/statfs.h>
#include <linux/sched.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
#include "internal.h"
#define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */
@@ -43,6 +45,7 @@
.kill_sb = afs_kill_super,
.fs_flags = 0,
};
+MODULE_ALIAS_FS("afs");
static const struct super_operations afs_super_ops = {
.statfs = afs_statfs,
@@ -363,6 +366,10 @@
memset(¶ms, 0, sizeof(params));
+ ret = -EINVAL;
+ if (current->nsproxy->net_ns != &init_net)
+ goto error;
+
/* parse the options and device name */
if (options) {
ret = afs_parse_options(¶ms, options, &dev_name);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 9aa52d9..7e03ead 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -120,7 +120,7 @@
struct page **pagep, void **fsdata)
{
struct afs_writeback *candidate, *wb;
- struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
struct page *page;
struct key *key = file->private_data;
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
@@ -245,7 +245,7 @@
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
- struct afs_vnode *vnode = AFS_FS_I(file->f_dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
loff_t i_size, maybe_i_size;
_enter("{%x:%u},{%lx}",
@@ -627,8 +627,7 @@
ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
- struct dentry *dentry = iocb->ki_filp->f_path.dentry;
- struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
ssize_t result;
size_t count = iov_length(iov, nr_segs);
diff --git a/fs/aio.c b/fs/aio.c
index 71f613c..3f941f2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -101,7 +101,7 @@
struct aio_ring *ring;
struct aio_ring_info *info = &ctx->ring_info;
unsigned nr_events = ctx->max_reqs;
- unsigned long size;
+ unsigned long size, populate;
int nr_pages;
/* Compensate for the ring buffer's head/tail overlap entry */
@@ -129,7 +129,8 @@
down_write(&ctx->mm->mmap_sem);
info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size,
PROT_READ|PROT_WRITE,
- MAP_ANONYMOUS|MAP_PRIVATE, 0);
+ MAP_ANONYMOUS|MAP_PRIVATE, 0,
+ &populate);
if (IS_ERR((void *)info->mmap_base)) {
up_write(&ctx->mm->mmap_sem);
info->mmap_size = 0;
@@ -147,6 +148,8 @@
aio_free_ring(ctx);
return -EAGAIN;
}
+ if (populate)
+ mm_populate(info->mmap_base, populate);
ctx->user_id = info->mmap_base;
@@ -588,11 +591,10 @@
{
struct mm_struct *mm = current->mm;
struct kioctx *ctx, *ret = NULL;
- struct hlist_node *n;
rcu_read_lock();
- hlist_for_each_entry_rcu(ctx, n, &mm->ioctx_list, list) {
+ hlist_for_each_entry_rcu(ctx, &mm->ioctx_list, list) {
/*
* RCU protects us against accessing freed memory but
* we have to be careful not to get a reference when the
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 28d39fb..47a65df 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -131,7 +131,6 @@
struct qstr this;
struct path path;
struct file *file;
- int error;
if (IS_ERR(anon_inode_inode))
return ERR_PTR(-ENODEV);
@@ -143,7 +142,7 @@
* Link the inode to a directory entry by creating a unique name
* using the inode sequence number.
*/
- error = -ENOMEM;
+ file = ERR_PTR(-ENOMEM);
this.name = name;
this.len = strlen(name);
this.hash = 0;
@@ -160,15 +159,12 @@
d_instantiate(path.dentry, anon_inode_inode);
- error = -ENFILE;
file = alloc_file(&path, OPEN_FMODE(flags), fops);
- if (!file)
+ if (IS_ERR(file))
goto err_dput;
file->f_mapping = anon_inode_inode->i_mapping;
- file->f_pos = 0;
file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
- file->f_version = 0;
file->private_data = priv;
return file;
@@ -177,7 +173,7 @@
path_put(&path);
err_module:
module_put(fops->owner);
- return ERR_PTR(error);
+ return file;
}
EXPORT_SYMBOL_GPL(anon_inode_getfile);
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index b785e77..3f1128b 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -273,7 +273,7 @@
{
if (!pipe->f_op || !pipe->f_op->write)
return -EINVAL;
- if (!S_ISFIFO(pipe->f_dentry->d_inode->i_mode))
+ if (!S_ISFIFO(file_inode(pipe)->i_mode))
return -EINVAL;
/* We want a packet pipe */
pipe->f_flags |= O_DIRECT;
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 9f68a37..743c7c2 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -159,7 +159,7 @@
struct inode *inode;
if (f) {
- inode = f->f_path.dentry->d_inode;
+ inode = file_inode(f);
sbi = autofs4_sbi(inode->i_sb);
}
return sbi;
diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c
index cddc74b..b3db517 100644
--- a/fs/autofs4/init.c
+++ b/fs/autofs4/init.c
@@ -26,6 +26,7 @@
.mount = autofs_mount,
.kill_sb = autofs4_kill_sb,
};
+MODULE_ALIAS_FS("autofs");
static int __init init_autofs4_fs(void)
{
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index c934476..9bd1625 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -383,8 +383,10 @@
goto done;
}
} else {
- if (!simple_empty(dentry))
+ if (!simple_empty(dentry)) {
+ spin_unlock(&sbi->fs_lock);
goto done;
+ }
}
ino->flags |= AUTOFS_INF_PENDING;
spin_unlock(&sbi->fs_lock);
@@ -587,7 +589,7 @@
/* This allows root to remove symlinks */
if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
if (atomic_dec_and_test(&ino->count)) {
p_ino = autofs4_dentry_ino(dentry->d_parent);
@@ -874,7 +876,7 @@
static long autofs4_root_ioctl(struct file *filp,
unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg);
}
@@ -882,7 +884,7 @@
static long autofs4_root_compat_ioctl(struct file *filp,
unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int ret;
if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL)
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 03bc1d3..3db70da 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -42,10 +42,8 @@
while (wq) {
nwq = wq->next;
wq->status = -ENOENT; /* Magic is gone - report failure */
- if (wq->name.name) {
- kfree(wq->name.name);
- wq->name.name = NULL;
- }
+ kfree(wq->name.name);
+ wq->name.name = NULL;
wq->wait_ctr--;
wake_up_interruptible(&wq->queue);
wq = nwq;
diff --git a/fs/befs/Kconfig b/fs/befs/Kconfig
index 7835d30..edc5cc2 100644
--- a/fs/befs/Kconfig
+++ b/fs/befs/Kconfig
@@ -1,6 +1,6 @@
config BEFS_FS
- tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)"
- depends on BLOCK && EXPERIMENTAL
+ tristate "BeOS file system (BeFS) support (read only)"
+ depends on BLOCK
select NLS
help
The BeOS File System (BeFS) is the native file system of Be, Inc's
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 2b3bda8..8615ee8 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -213,7 +213,7 @@
static int
befs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
befs_data_stream *ds = &BEFS_I(inode)->i_data.ds;
befs_off_t value;
@@ -951,6 +951,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("befs");
static int __init
init_befs_fs(void)
diff --git a/fs/bfs/Kconfig b/fs/bfs/Kconfig
index c2336c6..3728a64 100644
--- a/fs/bfs/Kconfig
+++ b/fs/bfs/Kconfig
@@ -1,6 +1,6 @@
config BFS_FS
- tristate "BFS file system support (EXPERIMENTAL)"
- depends on BLOCK && EXPERIMENTAL
+ tristate "BFS file system support"
+ depends on BLOCK
help
Boot File System (BFS) is a file system used under SCO UnixWare to
allow the bootloader access to the kernel image and other important
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 2785ef9..3f422f6 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -28,7 +28,7 @@
static int bfs_readdir(struct file *f, void *dirent, filldir_t filldir)
{
- struct inode *dir = f->f_path.dentry->d_inode;
+ struct inode *dir = file_inode(f);
struct buffer_head *bh;
struct bfs_dirent *de;
struct bfs_sb_info *info = BFS_SB(dir->i_sb);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 737aaa3..5e376bb 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -473,6 +473,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("bfs");
static int __init init_bfs_fs(void)
{
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 6043567..bbc8f88 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -214,7 +214,7 @@
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
N_TRSIZE(ex) || N_DRSIZE(ex) ||
- i_size_read(bprm->file->f_path.dentry->d_inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
+ i_size_read(file_inode(bprm->file)) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
return -ENOEXEC;
}
@@ -367,7 +367,7 @@
int retval;
struct exec ex;
- inode = file->f_path.dentry->d_inode;
+ inode = file_inode(file);
retval = -ENOEXEC;
error = kernel_read(file, 0, (char *) &ex, sizeof(ex));
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0c42cdb..3939829 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -33,6 +33,7 @@
#include <linux/elf.h>
#include <linux/utsname.h>
#include <linux/coredump.h>
+#include <linux/sched.h>
#include <asm/uaccess.h>
#include <asm/param.h>
#include <asm/page.h>
@@ -321,6 +322,8 @@
return 0;
}
+#ifndef elf_map
+
static unsigned long elf_map(struct file *filep, unsigned long addr,
struct elf_phdr *eppnt, int prot, int type,
unsigned long total_size)
@@ -355,6 +358,8 @@
return(map_addr);
}
+#endif /* !elf_map */
+
static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
{
int i, first_idx = -1, last_idx = -1;
@@ -1140,7 +1145,7 @@
/* By default, dump shared memory if mapped from an anonymous file. */
if (vma->vm_flags & VM_SHARED) {
- if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0 ?
+ if (file_inode(vma->vm_file)->i_nlink == 0 ?
FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
goto whole;
return 0;
@@ -1248,7 +1253,7 @@
#undef DUMP_WRITE
static void fill_elf_header(struct elfhdr *elf, int segs,
- u16 machine, u32 flags, u8 osabi)
+ u16 machine, u32 flags)
{
memset(elf, 0, sizeof(*elf));
@@ -1320,8 +1325,11 @@
cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
} else {
- cputime_to_timeval(p->utime, &prstatus->pr_utime);
- cputime_to_timeval(p->stime, &prstatus->pr_stime);
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+ cputime_to_timeval(utime, &prstatus->pr_utime);
+ cputime_to_timeval(stime, &prstatus->pr_stime);
}
cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
@@ -1630,7 +1638,7 @@
* Initialize the ELF file header.
*/
fill_elf_header(elf, phdrs,
- view->e_machine, view->e_flags, view->ei_osabi);
+ view->e_machine, view->e_flags);
/*
* Allocate a structure for each thread.
@@ -1870,7 +1878,7 @@
elf_core_copy_regs(&info->prstatus->pr_reg, regs);
/* Set up header */
- fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS, ELF_OSABI);
+ fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS);
/*
* Set up the notes in similar form to SVR4 core dumps made
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index dc84732..9c13e02 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -909,7 +909,7 @@
dynamic_error:
printk("ELF FDPIC %s with invalid DYNAMIC section (inode=%lu)\n",
- what, file->f_path.dentry->d_inode->i_ino);
+ what, file_inode(file)->i_ino);
return -ELIBBAD;
}
@@ -1219,7 +1219,7 @@
/* By default, dump shared memory if mapped from an anonymous file. */
if (vma->vm_flags & VM_SHARED) {
- if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0) {
+ if (file_inode(vma->vm_file)->i_nlink == 0) {
dump_ok = test_bit(MMF_DUMP_ANON_SHARED, &mm_flags);
kdcore("%08lx: %08lx: %s (share)", vma->vm_start,
vma->vm_flags, dump_ok ? "yes" : "no");
@@ -1375,8 +1375,11 @@
cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
} else {
- cputime_to_timeval(p->utime, &prstatus->pr_utime);
- cputime_to_timeval(p->stime, &prstatus->pr_stime);
+ cputime_t utime, stime;
+
+ task_cputime(p, &utime, &stime);
+ cputime_to_timeval(utime, &prstatus->pr_utime);
+ cputime_to_timeval(stime, &prstatus->pr_stime);
}
cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index b563719..2036d21 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -438,7 +438,7 @@
int ret;
hdr = ((struct flat_hdr *) bprm->buf); /* exec-header */
- inode = bprm->file->f_path.dentry->d_inode;
+ inode = file_inode(bprm->file);
text_len = ntohl(hdr->data_start);
data_len = ntohl(hdr->data_end) - ntohl(hdr->data_start);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 0c8869f..751df5e 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -531,7 +531,7 @@
static ssize_t
bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
{
- Node *e = file->f_path.dentry->d_inode->i_private;
+ Node *e = file_inode(file)->i_private;
ssize_t res;
char *page;
@@ -550,7 +550,7 @@
size_t count, loff_t *ppos)
{
struct dentry *root;
- Node *e = file->f_path.dentry->d_inode->i_private;
+ Node *e = file_inode(file)->i_private;
int res = parse_command(buffer, count);
switch (res) {
@@ -720,6 +720,7 @@
.mount = bm_mount,
.kill_sb = kill_litter_super,
};
+MODULE_ALIAS_FS("binfmt_misc");
static int __init init_misc_binfmt(void)
{
diff --git a/fs/bio.c b/fs/bio.c
index b96fc6c..bb5768f 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1428,6 +1428,8 @@
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
+ trace_block_bio_complete(bio, error);
+
if (bio->bi_end_io)
bio->bi_end_io(bio, error);
}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 172f849..aea605c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -318,7 +318,7 @@
/*
* private llseek:
- * for a block special file file->f_path.dentry->d_inode->i_size is zero
+ * for a block special file file_inode(file)->i_size is zero
* so we compute the size by hand (just as in block_read/write above)
*/
static loff_t block_llseek(struct file *file, loff_t offset, int whence)
@@ -994,6 +994,7 @@
mutex_lock(&bdev->bd_mutex);
check_disk_size_change(disk, bdev);
+ bdev->bd_invalidated = 0;
mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
return ret;
@@ -1032,7 +1033,9 @@
{
unsigned bsize = bdev_logical_block_size(bdev);
- bdev->bd_inode->i_size = size;
+ mutex_lock(&bdev->bd_inode->i_mutex);
+ i_size_write(bdev->bd_inode, size);
+ mutex_unlock(&bdev->bd_inode->i_mutex);
while (bsize < PAGE_CACHE_SIZE) {
if (size & bsize)
break;
@@ -1117,7 +1120,7 @@
}
}
- if (!ret && !bdev->bd_openers) {
+ if (!ret) {
bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
bdi = blk_get_backing_dev_info(bdev);
if (bdi == NULL)
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index d33f01c..9a8622a 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -1,11 +1,13 @@
config BTRFS_FS
- tristate "Btrfs filesystem (EXPERIMENTAL) Unstable disk format"
- depends on EXPERIMENTAL
+ tristate "Btrfs filesystem Unstable disk format"
select LIBCRC32C
select ZLIB_INFLATE
select ZLIB_DEFLATE
select LZO_COMPRESS
select LZO_DECOMPRESS
+ select RAID6_PQ
+ select XOR_BLOCKS
+
help
Btrfs is a new filesystem with extents, writable snapshotting,
support for multiple devices and many more features.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 7df3e0f..3932224 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -8,7 +8,7 @@
extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
export.o tree-log.o free-space-cache.o zlib.o lzo.o \
compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
- reada.o backref.o ulist.o qgroup.o send.o dev-replace.o
+ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o
btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 04edf69..bd605c8 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -352,11 +352,8 @@
err = __resolve_indirect_ref(fs_info, search_commit_root,
time_seq, ref, parents,
extent_item_pos);
- if (err) {
- if (ret == 0)
- ret = err;
+ if (err)
continue;
- }
/* we put the first parent into the ref at hand */
ULIST_ITER_INIT(&uiter);
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index d61feca7..310a7f6 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -19,7 +19,7 @@
#ifndef __BTRFS_BACKREF__
#define __BTRFS_BACKREF__
-#include "ioctl.h"
+#include <linux/btrfs.h>
#include "ulist.h"
#include "extent_io.h"
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 2a8c242..d9b97d4 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -40,6 +40,8 @@
#define BTRFS_INODE_HAS_ASYNC_EXTENT 6
#define BTRFS_INODE_NEEDS_FULL_SYNC 7
#define BTRFS_INODE_COPY_EVERYTHING 8
+#define BTRFS_INODE_IN_DELALLOC_LIST 9
+#define BTRFS_INODE_READDIO_NEED_LOCK 10
/* in memory btrfs inode */
struct btrfs_inode {
@@ -216,4 +218,22 @@
return 0;
}
+/*
+ * Disable DIO read nolock optimization, so new dio readers will be forced
+ * to grab i_mutex. It is used to avoid the endless truncate due to
+ * nonlocked dio read.
+ */
+static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
+{
+ set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags);
+ smp_mb();
+}
+
+static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
+{
+ smp_mb__before_clear_bit();
+ clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
+ &BTRFS_I(inode)->runtime_flags);
+}
+
#endif
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 11d47bf..18af6f4 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -813,8 +813,7 @@
(bh->b_data + (dev_bytenr & 4095));
if (btrfs_super_bytenr(super_tmp) != dev_bytenr ||
- strncmp((char *)(&(super_tmp->magic)), BTRFS_MAGIC,
- sizeof(super_tmp->magic)) ||
+ super_tmp->magic != cpu_to_le64(BTRFS_MAGIC) ||
memcmp(device->uuid, super_tmp->dev_item.uuid, BTRFS_UUID_SIZE) ||
btrfs_super_nodesize(super_tmp) != state->metablock_size ||
btrfs_super_leafsize(super_tmp) != state->metablock_size ||
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 94ab2f8..15b9408 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -372,7 +372,7 @@
page = compressed_pages[pg_index];
page->mapping = inode->i_mapping;
if (bio->bi_size)
- ret = io_tree->ops->merge_bio_hook(page, 0,
+ ret = io_tree->ops->merge_bio_hook(WRITE, page, 0,
PAGE_CACHE_SIZE,
bio, 0);
else
@@ -655,7 +655,7 @@
page->index = em_start >> PAGE_CACHE_SHIFT;
if (comp_bio->bi_size)
- ret = tree->ops->merge_bio_hook(page, 0,
+ ret = tree->ops->merge_bio_hook(READ, page, 0,
PAGE_CACHE_SIZE,
comp_bio, 0);
else
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index eea5da7..ca9d8f1 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -651,6 +651,8 @@
if (tree_mod_dont_log(fs_info, NULL))
return 0;
+ __tree_mod_log_free_eb(fs_info, old_root);
+
ret = tree_mod_alloc(fs_info, flags, &tm);
if (ret < 0)
goto out;
@@ -736,7 +738,7 @@
static noinline void
tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
struct extent_buffer *src, unsigned long dst_offset,
- unsigned long src_offset, int nr_items)
+ unsigned long src_offset, int nr_items, int log_removal)
{
int ret;
int i;
@@ -750,10 +752,12 @@
}
for (i = 0; i < nr_items; i++) {
- ret = tree_mod_log_insert_key_locked(fs_info, src,
- i + src_offset,
- MOD_LOG_KEY_REMOVE);
- BUG_ON(ret < 0);
+ if (log_removal) {
+ ret = tree_mod_log_insert_key_locked(fs_info, src,
+ i + src_offset,
+ MOD_LOG_KEY_REMOVE);
+ BUG_ON(ret < 0);
+ }
ret = tree_mod_log_insert_key_locked(fs_info, dst,
i + dst_offset,
MOD_LOG_KEY_ADD);
@@ -927,7 +931,6 @@
ret = btrfs_dec_ref(trans, root, buf, 1, 1);
BUG_ON(ret); /* -ENOMEM */
}
- tree_mod_log_free_eb(root->fs_info, buf);
clean_tree_block(trans, root, buf);
*last_ref = 1;
}
@@ -1046,6 +1049,7 @@
btrfs_set_node_ptr_generation(parent, parent_slot,
trans->transid);
btrfs_mark_buffer_dirty(parent);
+ tree_mod_log_free_eb(root->fs_info, buf);
btrfs_free_tree_block(trans, root, buf, parent_start,
last_ref);
}
@@ -1138,6 +1142,7 @@
switch (tm->op) {
case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
BUG_ON(tm->slot < n);
+ /* Fallthrough */
case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
case MOD_LOG_KEY_REMOVE:
btrfs_set_node_key(eb, &tm->key, tm->slot);
@@ -1222,7 +1227,7 @@
__tree_mod_log_rewind(eb_rewin, time_seq, tm);
WARN_ON(btrfs_header_nritems(eb_rewin) >
- BTRFS_NODEPTRS_PER_BLOCK(fs_info->fs_root));
+ BTRFS_NODEPTRS_PER_BLOCK(fs_info->tree_root));
return eb_rewin;
}
@@ -1441,7 +1446,7 @@
*/
int btrfs_realloc_node(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *parent,
- int start_slot, int cache_only, u64 *last_ret,
+ int start_slot, u64 *last_ret,
struct btrfs_key *progress)
{
struct extent_buffer *cur;
@@ -1461,8 +1466,6 @@
struct btrfs_disk_key disk_key;
parent_level = btrfs_header_level(parent);
- if (cache_only && parent_level != 1)
- return 0;
WARN_ON(trans->transaction != root->fs_info->running_transaction);
WARN_ON(trans->transid != root->fs_info->generation);
@@ -1508,10 +1511,6 @@
else
uptodate = 0;
if (!cur || !uptodate) {
- if (cache_only) {
- free_extent_buffer(cur);
- continue;
- }
if (!cur) {
cur = read_tree_block(root, blocknr,
blocksize, gen);
@@ -1755,7 +1754,6 @@
goto enospc;
}
- tree_mod_log_free_eb(root->fs_info, root->node);
tree_mod_log_set_root_pointer(root, child);
rcu_assign_pointer(root->node, child);
@@ -3000,7 +2998,7 @@
push_items = min(src_nritems - 8, push_items);
tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0,
- push_items);
+ push_items, 1);
copy_extent_buffer(dst, src,
btrfs_node_key_ptr_offset(dst_nritems),
btrfs_node_key_ptr_offset(0),
@@ -3071,7 +3069,7 @@
sizeof(struct btrfs_key_ptr));
tree_mod_log_eb_copy(root->fs_info, dst, src, 0,
- src_nritems - push_items, push_items);
+ src_nritems - push_items, push_items, 1);
copy_extent_buffer(dst, src,
btrfs_node_key_ptr_offset(0),
btrfs_node_key_ptr_offset(src_nritems - push_items),
@@ -3223,12 +3221,18 @@
int mid;
int ret;
u32 c_nritems;
+ int tree_mod_log_removal = 1;
c = path->nodes[level];
WARN_ON(btrfs_header_generation(c) != trans->transid);
if (c == root->node) {
/* trying to split the root, lets make a new one */
ret = insert_new_root(trans, root, path, level + 1);
+ /*
+ * removal of root nodes has been logged by
+ * tree_mod_log_set_root_pointer due to locking
+ */
+ tree_mod_log_removal = 0;
if (ret)
return ret;
} else {
@@ -3266,7 +3270,8 @@
(unsigned long)btrfs_header_chunk_tree_uuid(split),
BTRFS_UUID_SIZE);
- tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid);
+ tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid,
+ tree_mod_log_removal);
copy_extent_buffer(split, c,
btrfs_node_key_ptr_offset(0),
btrfs_node_key_ptr_offset(mid),
@@ -4825,8 +4830,8 @@
/*
* A helper function to walk down the tree starting at min_key, and looking
- * for nodes or leaves that are either in cache or have a minimum
- * transaction id. This is used by the btree defrag code, and tree logging
+ * for nodes or leaves that are have a minimum transaction id.
+ * This is used by the btree defrag code, and tree logging
*
* This does not cow, but it does stuff the starting key it finds back
* into min_key, so you can call btrfs_search_slot with cow=1 on the
@@ -4847,7 +4852,7 @@
*/
int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
struct btrfs_key *max_key,
- struct btrfs_path *path, int cache_only,
+ struct btrfs_path *path,
u64 min_trans)
{
struct extent_buffer *cur;
@@ -4887,15 +4892,12 @@
if (sret && slot > 0)
slot--;
/*
- * check this node pointer against the cache_only and
- * min_trans parameters. If it isn't in cache or is too
- * old, skip to the next one.
+ * check this node pointer against the min_trans parameters.
+ * If it is too old, old, skip to the next one.
*/
while (slot < nritems) {
u64 blockptr;
u64 gen;
- struct extent_buffer *tmp;
- struct btrfs_disk_key disk_key;
blockptr = btrfs_node_blockptr(cur, slot);
gen = btrfs_node_ptr_generation(cur, slot);
@@ -4903,27 +4905,7 @@
slot++;
continue;
}
- if (!cache_only)
- break;
-
- if (max_key) {
- btrfs_node_key(cur, &disk_key, slot);
- if (comp_keys(&disk_key, max_key) >= 0) {
- ret = 1;
- goto out;
- }
- }
-
- tmp = btrfs_find_tree_block(root, blockptr,
- btrfs_level_size(root, level - 1));
-
- if (tmp && btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
- free_extent_buffer(tmp);
- break;
- }
- if (tmp)
- free_extent_buffer(tmp);
- slot++;
+ break;
}
find_next_key:
/*
@@ -4934,7 +4916,7 @@
path->slots[level] = slot;
btrfs_set_path_blocking(path);
sret = btrfs_find_next_key(root, path, min_key, level,
- cache_only, min_trans);
+ min_trans);
if (sret == 0) {
btrfs_release_path(path);
goto again;
@@ -5399,8 +5381,7 @@
/*
* this is similar to btrfs_next_leaf, but does not try to preserve
* and fixup the path. It looks for and returns the next key in the
- * tree based on the current path and the cache_only and min_trans
- * parameters.
+ * tree based on the current path and the min_trans parameters.
*
* 0 is returned if another key is found, < 0 if there are any errors
* and 1 is returned if there are no higher keys in the tree
@@ -5409,8 +5390,7 @@
* calling this function.
*/
int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
- struct btrfs_key *key, int level,
- int cache_only, u64 min_trans)
+ struct btrfs_key *key, int level, u64 min_trans)
{
int slot;
struct extent_buffer *c;
@@ -5461,22 +5441,8 @@
if (level == 0)
btrfs_item_key_to_cpu(c, key, slot);
else {
- u64 blockptr = btrfs_node_blockptr(c, slot);
u64 gen = btrfs_node_ptr_generation(c, slot);
- if (cache_only) {
- struct extent_buffer *cur;
- cur = btrfs_find_tree_block(root, blockptr,
- btrfs_level_size(root, level - 1));
- if (!cur ||
- btrfs_buffer_uptodate(cur, gen, 1) <= 0) {
- slot++;
- if (cur)
- free_extent_buffer(cur);
- goto next;
- }
- free_extent_buffer(cur);
- }
if (gen < min_trans) {
slot++;
goto next;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 547b7b0..0d82922 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -31,10 +31,10 @@
#include <trace/events/btrfs.h>
#include <asm/kmap_types.h>
#include <linux/pagemap.h>
+#include <linux/btrfs.h>
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
-#include "ioctl.h"
struct btrfs_trans_handle;
struct btrfs_transaction;
@@ -46,7 +46,7 @@
extern struct kmem_cache *btrfs_free_space_cachep;
struct btrfs_ordered_sum;
-#define BTRFS_MAGIC "_BHRfS_M"
+#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
#define BTRFS_MAX_MIRRORS 3
@@ -191,6 +191,8 @@
/* ioprio of readahead is set to idle */
#define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
+#define BTRFS_DIRTY_METADATA_THRESH (32 * 1024 * 1024)
+
/*
* The key defines the order in the tree, and so it also defines (optimal)
* block layout.
@@ -336,7 +338,10 @@
/*
* File system states
*/
+#define BTRFS_FS_STATE_ERROR 0
+#define BTRFS_FS_STATE_REMOUNTING 1
+/* Super block flags */
/* Errors detected */
#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2)
@@ -502,6 +507,7 @@
#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA (1ULL << 5)
#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6)
+#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7)
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SUPP 0ULL
@@ -511,6 +517,7 @@
BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \
BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \
BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \
+ BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
/*
@@ -952,8 +959,20 @@
#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4)
#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5)
#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6)
+#define BTRFS_BLOCK_GROUP_RAID5 (1 << 7)
+#define BTRFS_BLOCK_GROUP_RAID6 (1 << 8)
#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE
-#define BTRFS_NR_RAID_TYPES 5
+
+enum btrfs_raid_types {
+ BTRFS_RAID_RAID10,
+ BTRFS_RAID_RAID1,
+ BTRFS_RAID_DUP,
+ BTRFS_RAID_RAID0,
+ BTRFS_RAID_SINGLE,
+ BTRFS_RAID_RAID5,
+ BTRFS_RAID_RAID6,
+ BTRFS_NR_RAID_TYPES
+};
#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \
BTRFS_BLOCK_GROUP_SYSTEM | \
@@ -961,6 +980,8 @@
#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \
BTRFS_BLOCK_GROUP_RAID1 | \
+ BTRFS_BLOCK_GROUP_RAID5 | \
+ BTRFS_BLOCK_GROUP_RAID6 | \
BTRFS_BLOCK_GROUP_DUP | \
BTRFS_BLOCK_GROUP_RAID10)
/*
@@ -1185,6 +1206,10 @@
u64 flags;
u64 sectorsize;
u64 cache_generation;
+
+ /* for raid56, this is a full stripe, without parity */
+ unsigned long full_stripe_len;
+
unsigned int ro:1;
unsigned int dirty:1;
unsigned int iref:1;
@@ -1225,6 +1250,28 @@
u64 seq;
};
+enum btrfs_orphan_cleanup_state {
+ ORPHAN_CLEANUP_STARTED = 1,
+ ORPHAN_CLEANUP_DONE = 2,
+};
+
+/* used by the raid56 code to lock stripes for read/modify/write */
+struct btrfs_stripe_hash {
+ struct list_head hash_list;
+ wait_queue_head_t wait;
+ spinlock_t lock;
+};
+
+/* used by the raid56 code to lock stripes for read/modify/write */
+struct btrfs_stripe_hash_table {
+ struct list_head stripe_cache;
+ spinlock_t cache_lock;
+ int cache_size;
+ struct btrfs_stripe_hash table[];
+};
+
+#define BTRFS_STRIPE_HASH_TABLE_BITS 11
+
/* fs_info */
struct reloc_control;
struct btrfs_device;
@@ -1250,6 +1297,7 @@
/* block group cache stuff */
spinlock_t block_group_cache_lock;
+ u64 first_logical_byte;
struct rb_root block_group_cache_tree;
/* keep track of unallocated space */
@@ -1288,7 +1336,23 @@
u64 last_trans_log_full_commit;
unsigned long mount_opt;
unsigned long compress_type:4;
+ /*
+ * It is a suggestive number, the read side is safe even it gets a
+ * wrong number because we will write out the data into a regular
+ * extent. The write side(mount/remount) is under ->s_umount lock,
+ * so it is also safe.
+ */
u64 max_inline;
+ /*
+ * Protected by ->chunk_mutex and sb->s_umount.
+ *
+ * The reason that we use two lock to protect it is because only
+ * remount and mount operations can change it and these two operations
+ * are under sb->s_umount, but the read side (chunk allocation) can not
+ * acquire sb->s_umount or the deadlock would happen. So we use two
+ * locks to protect it. On the write side, we must acquire two locks,
+ * and on the read side, we just need acquire one of them.
+ */
u64 alloc_start;
struct btrfs_transaction *running_transaction;
wait_queue_head_t transaction_throttle;
@@ -1307,6 +1371,13 @@
struct mutex cleaner_mutex;
struct mutex chunk_mutex;
struct mutex volume_mutex;
+
+ /* this is used during read/modify/write to make sure
+ * no two ios are trying to mod the same stripe at the same
+ * time
+ */
+ struct btrfs_stripe_hash_table *stripe_hash_table;
+
/*
* this protects the ordered operations list only while we are
* processing all of the entries on it. This way we make
@@ -1365,6 +1436,7 @@
*/
struct list_head ordered_extents;
+ spinlock_t delalloc_lock;
/*
* all of the inodes that have delalloc bytes. It is possible for
* this list to be empty even when there is still dirty data=ordered
@@ -1373,13 +1445,6 @@
struct list_head delalloc_inodes;
/*
- * special rename and truncate targets that must be on disk before
- * we're allowed to commit. This is basically the ext3 style
- * data=ordered list.
- */
- struct list_head ordered_operations;
-
- /*
* there is a pool of worker threads for checksumming during writes
* and a pool for checksumming after reads. This is because readers
* can run with FS locks held, and the writers may be waiting for
@@ -1395,6 +1460,8 @@
struct btrfs_workers flush_workers;
struct btrfs_workers endio_workers;
struct btrfs_workers endio_meta_workers;
+ struct btrfs_workers endio_raid56_workers;
+ struct btrfs_workers rmw_workers;
struct btrfs_workers endio_meta_write_workers;
struct btrfs_workers endio_write_workers;
struct btrfs_workers endio_freespace_worker;
@@ -1423,10 +1490,12 @@
u64 total_pinned;
- /* protected by the delalloc lock, used to keep from writing
- * metadata until there is a nice batch
- */
- u64 dirty_metadata_bytes;
+ /* used to keep from writing metadata until there is a nice batch */
+ struct percpu_counter dirty_metadata_bytes;
+ struct percpu_counter delalloc_bytes;
+ s32 dirty_metadata_batch;
+ s32 delalloc_batch;
+
struct list_head dirty_cowonly_roots;
struct btrfs_fs_devices *fs_devices;
@@ -1442,9 +1511,6 @@
struct reloc_control *reloc_ctl;
- spinlock_t delalloc_lock;
- u64 delalloc_bytes;
-
/* data_alloc_cluster is only used in ssd mode */
struct btrfs_free_cluster data_alloc_cluster;
@@ -1456,6 +1522,8 @@
struct rb_root defrag_inodes;
atomic_t defrag_running;
+ /* Used to protect avail_{data, metadata, system}_alloc_bits */
+ seqlock_t profiles_lock;
/*
* these three are in extended format (availability of single
* chunks is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE bit, other
@@ -1520,7 +1588,7 @@
u64 qgroup_seq;
/* filesystem state */
- u64 fs_state;
+ unsigned long fs_state;
struct btrfs_delayed_root *delayed_root;
@@ -1623,6 +1691,9 @@
struct list_head root_list;
+ spinlock_t log_extents_lock[2];
+ struct list_head logged_list[2];
+
spinlock_t orphan_lock;
atomic_t orphan_inodes;
struct btrfs_block_rsv *orphan_block_rsv;
@@ -1832,6 +1903,7 @@
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
+#define btrfs_raw_test_opt(o, opt) ((o) & BTRFS_MOUNT_##opt)
#define btrfs_test_opt(root, opt) ((root)->fs_info->mount_opt & \
BTRFS_MOUNT_##opt)
/*
@@ -2936,8 +3008,7 @@
u64 num_bytes, u64 *refs, u64 *flags);
int btrfs_pin_extent(struct btrfs_root *root,
u64 bytenr, u64 num, int reserved);
-int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+int btrfs_pin_extent_for_log_replay(struct btrfs_root *root,
u64 bytenr, u64 num_bytes);
int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -3035,8 +3106,13 @@
int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
struct inode *inode);
void btrfs_orphan_release_metadata(struct inode *inode);
-int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
- struct btrfs_pending_snapshot *pending);
+int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
+ struct btrfs_block_rsv *rsv,
+ int nitems,
+ u64 *qgroup_reserved);
+void btrfs_subvolume_release_metadata(struct btrfs_root *root,
+ struct btrfs_block_rsv *rsv,
+ u64 qgroup_reserved);
int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes);
@@ -3092,10 +3168,10 @@
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *key, int lowest_level,
- int cache_only, u64 min_trans);
+ u64 min_trans);
int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
struct btrfs_key *max_key,
- struct btrfs_path *path, int cache_only,
+ struct btrfs_path *path,
u64 min_trans);
enum btrfs_compare_tree_result {
BTRFS_COMPARE_TREE_NEW,
@@ -3148,7 +3224,7 @@
int find_higher, int return_any);
int btrfs_realloc_node(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *parent,
- int start_slot, int cache_only, u64 *last_ret,
+ int start_slot, u64 *last_ret,
struct btrfs_key *progress);
void btrfs_release_path(struct btrfs_path *p);
struct btrfs_path *btrfs_alloc_path(void);
@@ -3459,9 +3535,9 @@
struct writeback_control *wbc);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
struct btrfs_root *new_root, u64 new_dirid);
-int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
- size_t size, struct bio *bio, unsigned long bio_flags);
-
+int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
+ size_t size, struct bio *bio,
+ unsigned long bio_flags);
int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
@@ -3543,7 +3619,7 @@
/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, int cache_only);
+ struct btrfs_root *root);
/* sysfs.c */
int btrfs_init_sysfs(void);
@@ -3620,11 +3696,14 @@
void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
+/*
+ * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
+ * will panic(). Otherwise we BUG() here.
+ */
#define btrfs_panic(fs_info, errno, fmt, args...) \
do { \
- struct btrfs_fs_info *_i = (fs_info); \
- __btrfs_panic(_i, __func__, __LINE__, errno, fmt, ##args); \
- BUG_ON(!(_i->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR)); \
+ __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \
+ BUG(); \
} while (0)
/* acl.c */
@@ -3745,4 +3824,11 @@
return 1;
return 0;
}
+
+static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
+{
+ return signal_pending(current);
+}
+
+
#endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 3483603..14fce27 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -22,8 +22,9 @@
#include "disk-io.h"
#include "transaction.h"
-#define BTRFS_DELAYED_WRITEBACK 400
-#define BTRFS_DELAYED_BACKGROUND 100
+#define BTRFS_DELAYED_WRITEBACK 512
+#define BTRFS_DELAYED_BACKGROUND 128
+#define BTRFS_DELAYED_BATCH 16
static struct kmem_cache *delayed_node_cache;
@@ -494,6 +495,15 @@
BTRFS_DELAYED_DELETION_ITEM);
}
+static void finish_one_item(struct btrfs_delayed_root *delayed_root)
+{
+ int seq = atomic_inc_return(&delayed_root->items_seq);
+ if ((atomic_dec_return(&delayed_root->items) <
+ BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) &&
+ waitqueue_active(&delayed_root->wait))
+ wake_up(&delayed_root->wait);
+}
+
static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
{
struct rb_root *root;
@@ -512,10 +522,8 @@
rb_erase(&delayed_item->rb_node, root);
delayed_item->delayed_node->count--;
- if (atomic_dec_return(&delayed_root->items) <
- BTRFS_DELAYED_BACKGROUND &&
- waitqueue_active(&delayed_root->wait))
- wake_up(&delayed_root->wait);
+
+ finish_one_item(delayed_root);
}
static void btrfs_release_delayed_item(struct btrfs_delayed_item *item)
@@ -875,7 +883,6 @@
struct btrfs_delayed_item *delayed_item)
{
struct extent_buffer *leaf;
- struct btrfs_item *item;
char *ptr;
int ret;
@@ -886,7 +893,6 @@
leaf = path->nodes[0];
- item = btrfs_item_nr(leaf, path->slots[0]);
ptr = btrfs_item_ptr(leaf, path->slots[0], char);
write_extent_buffer(leaf, delayed_item->data, (unsigned long)ptr,
@@ -1058,39 +1064,29 @@
delayed_node->count--;
delayed_root = delayed_node->root->fs_info->delayed_root;
- if (atomic_dec_return(&delayed_root->items) <
- BTRFS_DELAYED_BACKGROUND &&
- waitqueue_active(&delayed_root->wait))
- wake_up(&delayed_root->wait);
+ finish_one_item(delayed_root);
}
}
-static int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path,
- struct btrfs_delayed_node *node)
+static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_delayed_node *node)
{
struct btrfs_key key;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
int ret;
- mutex_lock(&node->mutex);
- if (!node->inode_dirty) {
- mutex_unlock(&node->mutex);
- return 0;
- }
-
key.objectid = node->inode_id;
btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
key.offset = 0;
+
ret = btrfs_lookup_inode(trans, root, path, &key, 1);
if (ret > 0) {
btrfs_release_path(path);
- mutex_unlock(&node->mutex);
return -ENOENT;
} else if (ret < 0) {
- mutex_unlock(&node->mutex);
return ret;
}
@@ -1105,11 +1101,47 @@
btrfs_delayed_inode_release_metadata(root, node);
btrfs_release_delayed_inode(node);
- mutex_unlock(&node->mutex);
return 0;
}
+static inline int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_path *path,
+ struct btrfs_delayed_node *node)
+{
+ int ret;
+
+ mutex_lock(&node->mutex);
+ if (!node->inode_dirty) {
+ mutex_unlock(&node->mutex);
+ return 0;
+ }
+
+ ret = __btrfs_update_delayed_inode(trans, root, path, node);
+ mutex_unlock(&node->mutex);
+ return ret;
+}
+
+static inline int
+__btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
+ struct btrfs_path *path,
+ struct btrfs_delayed_node *node)
+{
+ int ret;
+
+ ret = btrfs_insert_delayed_items(trans, path, node->root, node);
+ if (ret)
+ return ret;
+
+ ret = btrfs_delete_delayed_items(trans, path, node->root, node);
+ if (ret)
+ return ret;
+
+ ret = btrfs_update_delayed_inode(trans, node->root, path, node);
+ return ret;
+}
+
/*
* Called when committing the transaction.
* Returns 0 on success.
@@ -1119,7 +1151,6 @@
static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root, int nr)
{
- struct btrfs_root *curr_root = root;
struct btrfs_delayed_root *delayed_root;
struct btrfs_delayed_node *curr_node, *prev_node;
struct btrfs_path *path;
@@ -1142,15 +1173,8 @@
curr_node = btrfs_first_delayed_node(delayed_root);
while (curr_node && (!count || (count && nr--))) {
- curr_root = curr_node->root;
- ret = btrfs_insert_delayed_items(trans, path, curr_root,
- curr_node);
- if (!ret)
- ret = btrfs_delete_delayed_items(trans, path,
- curr_root, curr_node);
- if (!ret)
- ret = btrfs_update_delayed_inode(trans, curr_root,
- path, curr_node);
+ ret = __btrfs_commit_inode_delayed_items(trans, path,
+ curr_node);
if (ret) {
btrfs_release_delayed_node(curr_node);
curr_node = NULL;
@@ -1183,36 +1207,12 @@
return __btrfs_run_delayed_items(trans, root, nr);
}
-static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
- struct btrfs_delayed_node *node)
-{
- struct btrfs_path *path;
- struct btrfs_block_rsv *block_rsv;
- int ret;
-
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
- path->leave_spinning = 1;
-
- block_rsv = trans->block_rsv;
- trans->block_rsv = &node->root->fs_info->delayed_block_rsv;
-
- ret = btrfs_insert_delayed_items(trans, path, node->root, node);
- if (!ret)
- ret = btrfs_delete_delayed_items(trans, path, node->root, node);
- if (!ret)
- ret = btrfs_update_delayed_inode(trans, node->root, path, node);
- btrfs_free_path(path);
-
- trans->block_rsv = block_rsv;
- return ret;
-}
-
int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
struct inode *inode)
{
struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
+ struct btrfs_path *path;
+ struct btrfs_block_rsv *block_rsv;
int ret;
if (!delayed_node)
@@ -1226,8 +1226,74 @@
}
mutex_unlock(&delayed_node->mutex);
- ret = __btrfs_commit_inode_delayed_items(trans, delayed_node);
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ path->leave_spinning = 1;
+
+ block_rsv = trans->block_rsv;
+ trans->block_rsv = &delayed_node->root->fs_info->delayed_block_rsv;
+
+ ret = __btrfs_commit_inode_delayed_items(trans, path, delayed_node);
+
btrfs_release_delayed_node(delayed_node);
+ btrfs_free_path(path);
+ trans->block_rsv = block_rsv;
+
+ return ret;
+}
+
+int btrfs_commit_inode_delayed_inode(struct inode *inode)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
+ struct btrfs_path *path;
+ struct btrfs_block_rsv *block_rsv;
+ int ret;
+
+ if (!delayed_node)
+ return 0;
+
+ mutex_lock(&delayed_node->mutex);
+ if (!delayed_node->inode_dirty) {
+ mutex_unlock(&delayed_node->mutex);
+ btrfs_release_delayed_node(delayed_node);
+ return 0;
+ }
+ mutex_unlock(&delayed_node->mutex);
+
+ trans = btrfs_join_transaction(delayed_node->root);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto trans_out;
+ }
+ path->leave_spinning = 1;
+
+ block_rsv = trans->block_rsv;
+ trans->block_rsv = &delayed_node->root->fs_info->delayed_block_rsv;
+
+ mutex_lock(&delayed_node->mutex);
+ if (delayed_node->inode_dirty)
+ ret = __btrfs_update_delayed_inode(trans, delayed_node->root,
+ path, delayed_node);
+ else
+ ret = 0;
+ mutex_unlock(&delayed_node->mutex);
+
+ btrfs_free_path(path);
+ trans->block_rsv = block_rsv;
+trans_out:
+ btrfs_end_transaction(trans, delayed_node->root);
+ btrfs_btree_balance_dirty(delayed_node->root);
+out:
+ btrfs_release_delayed_node(delayed_node);
+
return ret;
}
@@ -1243,48 +1309,49 @@
btrfs_release_delayed_node(delayed_node);
}
-struct btrfs_async_delayed_node {
- struct btrfs_root *root;
- struct btrfs_delayed_node *delayed_node;
+struct btrfs_async_delayed_work {
+ struct btrfs_delayed_root *delayed_root;
+ int nr;
struct btrfs_work work;
};
-static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
+static void btrfs_async_run_delayed_root(struct btrfs_work *work)
{
- struct btrfs_async_delayed_node *async_node;
+ struct btrfs_async_delayed_work *async_work;
+ struct btrfs_delayed_root *delayed_root;
struct btrfs_trans_handle *trans;
struct btrfs_path *path;
struct btrfs_delayed_node *delayed_node = NULL;
struct btrfs_root *root;
struct btrfs_block_rsv *block_rsv;
- int need_requeue = 0;
- int ret;
+ int total_done = 0;
- async_node = container_of(work, struct btrfs_async_delayed_node, work);
+ async_work = container_of(work, struct btrfs_async_delayed_work, work);
+ delayed_root = async_work->delayed_root;
path = btrfs_alloc_path();
if (!path)
goto out;
- path->leave_spinning = 1;
- delayed_node = async_node->delayed_node;
+again:
+ if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND / 2)
+ goto free_path;
+
+ delayed_node = btrfs_first_prepared_delayed_node(delayed_root);
+ if (!delayed_node)
+ goto free_path;
+
+ path->leave_spinning = 1;
root = delayed_node->root;
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
- goto free_path;
+ goto release_path;
block_rsv = trans->block_rsv;
trans->block_rsv = &root->fs_info->delayed_block_rsv;
- ret = btrfs_insert_delayed_items(trans, path, root, delayed_node);
- if (!ret)
- ret = btrfs_delete_delayed_items(trans, path, root,
- delayed_node);
-
- if (!ret)
- btrfs_update_delayed_inode(trans, root, path, delayed_node);
-
+ __btrfs_commit_inode_delayed_items(trans, path, delayed_node);
/*
* Maybe new delayed items have been inserted, so we need requeue
* the work. Besides that, we must dequeue the empty delayed nodes
@@ -1310,57 +1377,47 @@
* Task1 will sleep until the transaction is commited.
*/
mutex_lock(&delayed_node->mutex);
- if (delayed_node->count)
- need_requeue = 1;
- else
- btrfs_dequeue_delayed_node(root->fs_info->delayed_root,
- delayed_node);
+ btrfs_dequeue_delayed_node(root->fs_info->delayed_root, delayed_node);
mutex_unlock(&delayed_node->mutex);
trans->block_rsv = block_rsv;
btrfs_end_transaction_dmeta(trans, root);
btrfs_btree_balance_dirty_nodelay(root);
+
+release_path:
+ btrfs_release_path(path);
+ total_done++;
+
+ btrfs_release_prepared_delayed_node(delayed_node);
+ if (async_work->nr == 0 || total_done < async_work->nr)
+ goto again;
+
free_path:
btrfs_free_path(path);
out:
- if (need_requeue)
- btrfs_requeue_work(&async_node->work);
- else {
- btrfs_release_prepared_delayed_node(delayed_node);
- kfree(async_node);
- }
+ wake_up(&delayed_root->wait);
+ kfree(async_work);
}
-static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
- struct btrfs_root *root, int all)
-{
- struct btrfs_async_delayed_node *async_node;
- struct btrfs_delayed_node *curr;
- int count = 0;
-again:
- curr = btrfs_first_prepared_delayed_node(delayed_root);
- if (!curr)
+static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
+ struct btrfs_root *root, int nr)
+{
+ struct btrfs_async_delayed_work *async_work;
+
+ if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
return 0;
- async_node = kmalloc(sizeof(*async_node), GFP_NOFS);
- if (!async_node) {
- btrfs_release_prepared_delayed_node(curr);
+ async_work = kmalloc(sizeof(*async_work), GFP_NOFS);
+ if (!async_work)
return -ENOMEM;
- }
- async_node->root = root;
- async_node->delayed_node = curr;
+ async_work->delayed_root = delayed_root;
+ async_work->work.func = btrfs_async_run_delayed_root;
+ async_work->work.flags = 0;
+ async_work->nr = nr;
- async_node->work.func = btrfs_async_run_delayed_node_done;
- async_node->work.flags = 0;
-
- btrfs_queue_worker(&root->fs_info->delayed_workers, &async_node->work);
- count++;
-
- if (all || count < 4)
- goto again;
-
+ btrfs_queue_worker(&root->fs_info->delayed_workers, &async_work->work);
return 0;
}
@@ -1371,30 +1428,55 @@
WARN_ON(btrfs_first_delayed_node(delayed_root));
}
+static int refs_newer(struct btrfs_delayed_root *delayed_root,
+ int seq, int count)
+{
+ int val = atomic_read(&delayed_root->items_seq);
+
+ if (val < seq || val >= seq + count)
+ return 1;
+ return 0;
+}
+
void btrfs_balance_delayed_items(struct btrfs_root *root)
{
struct btrfs_delayed_root *delayed_root;
+ int seq;
delayed_root = btrfs_get_delayed_root(root);
if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
return;
+ seq = atomic_read(&delayed_root->items_seq);
+
if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
int ret;
- ret = btrfs_wq_run_delayed_node(delayed_root, root, 1);
+ DEFINE_WAIT(__wait);
+
+ ret = btrfs_wq_run_delayed_node(delayed_root, root, 0);
if (ret)
return;
- wait_event_interruptible_timeout(
- delayed_root->wait,
- (atomic_read(&delayed_root->items) <
- BTRFS_DELAYED_BACKGROUND),
- HZ);
- return;
+ while (1) {
+ prepare_to_wait(&delayed_root->wait, &__wait,
+ TASK_INTERRUPTIBLE);
+
+ if (refs_newer(delayed_root, seq,
+ BTRFS_DELAYED_BATCH) ||
+ atomic_read(&delayed_root->items) <
+ BTRFS_DELAYED_BACKGROUND) {
+ break;
+ }
+ if (!signal_pending(current))
+ schedule();
+ else
+ break;
+ }
+ finish_wait(&delayed_root->wait, &__wait);
}
- btrfs_wq_run_delayed_node(delayed_root, root, 0);
+ btrfs_wq_run_delayed_node(delayed_root, root, BTRFS_DELAYED_BATCH);
}
/* Will return 0 or -ENOMEM */
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 4f808e1..1d5c5f7 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -43,6 +43,7 @@
*/
struct list_head prepare_list;
atomic_t items; /* for delayed items */
+ atomic_t items_seq; /* for delayed items */
int nodes; /* for delayed nodes */
wait_queue_head_t wait;
};
@@ -86,6 +87,7 @@
struct btrfs_delayed_root *delayed_root)
{
atomic_set(&delayed_root->items, 0);
+ atomic_set(&delayed_root->items_seq, 0);
delayed_root->nodes = 0;
spin_lock_init(&delayed_root->lock);
init_waitqueue_head(&delayed_root->wait);
@@ -117,6 +119,7 @@
/* Used for evicting the inode. */
void btrfs_remove_delayed_node(struct inode *inode);
void btrfs_kill_delayed_inode_items(struct inode *inode);
+int btrfs_commit_inode_delayed_inode(struct inode *inode);
int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index ae94117..b7a0641 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -23,6 +23,10 @@
#include "delayed-ref.h"
#include "transaction.h"
+struct kmem_cache *btrfs_delayed_ref_head_cachep;
+struct kmem_cache *btrfs_delayed_tree_ref_cachep;
+struct kmem_cache *btrfs_delayed_data_ref_cachep;
+struct kmem_cache *btrfs_delayed_extent_op_cachep;
/*
* delayed back reference update tracking. For subvolume trees
* we queue up extent allocations and backref maintenance for
@@ -422,6 +426,14 @@
return 1;
}
+void btrfs_release_ref_cluster(struct list_head *cluster)
+{
+ struct list_head *pos, *q;
+
+ list_for_each_safe(pos, q, cluster)
+ list_del_init(pos);
+}
+
/*
* helper function to update an extent delayed ref in the
* rbtree. existing and update must both have the same
@@ -511,7 +523,7 @@
ref->extent_op->flags_to_set;
existing_ref->extent_op->update_flags = 1;
}
- kfree(ref->extent_op);
+ btrfs_free_delayed_extent_op(ref->extent_op);
}
}
/*
@@ -592,7 +604,7 @@
* we've updated the existing ref, free the newly
* allocated ref
*/
- kfree(head_ref);
+ kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
} else {
delayed_refs->num_heads++;
delayed_refs->num_heads_ready++;
@@ -653,7 +665,7 @@
* we've updated the existing ref, free the newly
* allocated ref
*/
- kfree(full_ref);
+ kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
} else {
delayed_refs->num_entries++;
trans->delayed_ref_updates++;
@@ -714,7 +726,7 @@
* we've updated the existing ref, free the newly
* allocated ref
*/
- kfree(full_ref);
+ kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
} else {
delayed_refs->num_entries++;
trans->delayed_ref_updates++;
@@ -738,13 +750,13 @@
struct btrfs_delayed_ref_root *delayed_refs;
BUG_ON(extent_op && extent_op->is_data);
- ref = kmalloc(sizeof(*ref), GFP_NOFS);
+ ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
- head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
+ head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref) {
- kfree(ref);
+ kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
return -ENOMEM;
}
@@ -786,13 +798,13 @@
struct btrfs_delayed_ref_root *delayed_refs;
BUG_ON(extent_op && !extent_op->is_data);
- ref = kmalloc(sizeof(*ref), GFP_NOFS);
+ ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
- head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
+ head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref) {
- kfree(ref);
+ kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
return -ENOMEM;
}
@@ -826,7 +838,7 @@
struct btrfs_delayed_ref_head *head_ref;
struct btrfs_delayed_ref_root *delayed_refs;
- head_ref = kmalloc(sizeof(*head_ref), GFP_NOFS);
+ head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref)
return -ENOMEM;
@@ -860,3 +872,51 @@
return btrfs_delayed_node_to_head(ref);
return NULL;
}
+
+void btrfs_delayed_ref_exit(void)
+{
+ if (btrfs_delayed_ref_head_cachep)
+ kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
+ if (btrfs_delayed_tree_ref_cachep)
+ kmem_cache_destroy(btrfs_delayed_tree_ref_cachep);
+ if (btrfs_delayed_data_ref_cachep)
+ kmem_cache_destroy(btrfs_delayed_data_ref_cachep);
+ if (btrfs_delayed_extent_op_cachep)
+ kmem_cache_destroy(btrfs_delayed_extent_op_cachep);
+}
+
+int btrfs_delayed_ref_init(void)
+{
+ btrfs_delayed_ref_head_cachep = kmem_cache_create(
+ "btrfs_delayed_ref_head",
+ sizeof(struct btrfs_delayed_ref_head), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!btrfs_delayed_ref_head_cachep)
+ goto fail;
+
+ btrfs_delayed_tree_ref_cachep = kmem_cache_create(
+ "btrfs_delayed_tree_ref",
+ sizeof(struct btrfs_delayed_tree_ref), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!btrfs_delayed_tree_ref_cachep)
+ goto fail;
+
+ btrfs_delayed_data_ref_cachep = kmem_cache_create(
+ "btrfs_delayed_data_ref",
+ sizeof(struct btrfs_delayed_data_ref), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!btrfs_delayed_data_ref_cachep)
+ goto fail;
+
+ btrfs_delayed_extent_op_cachep = kmem_cache_create(
+ "btrfs_delayed_extent_op",
+ sizeof(struct btrfs_delayed_extent_op), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!btrfs_delayed_extent_op_cachep)
+ goto fail;
+
+ return 0;
+fail:
+ btrfs_delayed_ref_exit();
+ return -ENOMEM;
+}
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index c9d7036..f75fcaf 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -132,6 +132,15 @@
unsigned long num_heads_ready;
/*
+ * bumped when someone is making progress on the delayed
+ * refs, so that other procs know they are just adding to
+ * contention intead of helping
+ */
+ atomic_t procs_running_refs;
+ atomic_t ref_seq;
+ wait_queue_head_t wait;
+
+ /*
* set when the tree is flushing before a transaction commit,
* used by the throttling code to decide if new updates need
* to be run right away
@@ -141,12 +150,47 @@
u64 run_delayed_start;
};
+extern struct kmem_cache *btrfs_delayed_ref_head_cachep;
+extern struct kmem_cache *btrfs_delayed_tree_ref_cachep;
+extern struct kmem_cache *btrfs_delayed_data_ref_cachep;
+extern struct kmem_cache *btrfs_delayed_extent_op_cachep;
+
+int btrfs_delayed_ref_init(void);
+void btrfs_delayed_ref_exit(void);
+
+static inline struct btrfs_delayed_extent_op *
+btrfs_alloc_delayed_extent_op(void)
+{
+ return kmem_cache_alloc(btrfs_delayed_extent_op_cachep, GFP_NOFS);
+}
+
+static inline void
+btrfs_free_delayed_extent_op(struct btrfs_delayed_extent_op *op)
+{
+ if (op)
+ kmem_cache_free(btrfs_delayed_extent_op_cachep, op);
+}
+
static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
{
WARN_ON(atomic_read(&ref->refs) == 0);
if (atomic_dec_and_test(&ref->refs)) {
WARN_ON(ref->in_tree);
- kfree(ref);
+ switch (ref->type) {
+ case BTRFS_TREE_BLOCK_REF_KEY:
+ case BTRFS_SHARED_BLOCK_REF_KEY:
+ kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+ break;
+ case BTRFS_EXTENT_DATA_REF_KEY:
+ case BTRFS_SHARED_DATA_REF_KEY:
+ kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+ break;
+ case 0:
+ kmem_cache_free(btrfs_delayed_ref_head_cachep, ref);
+ break;
+ default:
+ BUG();
+ }
}
}
@@ -176,8 +220,14 @@
btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr);
int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *head);
+static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head)
+{
+ mutex_unlock(&head->mutex);
+}
+
int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
struct list_head *cluster, u64 search_start);
+void btrfs_release_ref_cluster(struct list_head *cluster);
int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 66dbc8d..7ba7b39 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -465,7 +465,11 @@
* flush all outstanding I/O and inode extent mappings before the
* copy operation is declared as being finished
*/
- btrfs_start_delalloc_inodes(root, 0);
+ ret = btrfs_start_delalloc_inodes(root, 0);
+ if (ret) {
+ mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
+ return ret;
+ }
btrfs_wait_ordered_extents(root, 0);
trans = btrfs_start_transaction(root, 0);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a8f652d..6d19a0a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -46,6 +46,7 @@
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
+#include "raid56.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
@@ -56,11 +57,12 @@
static void free_fs_root(struct btrfs_root *root);
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only);
-static void btrfs_destroy_ordered_operations(struct btrfs_root *root);
+static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
+ struct btrfs_root *root);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
struct btrfs_root *root);
-static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
+static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages,
@@ -420,7 +422,7 @@
static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
{
struct extent_io_tree *tree;
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 found_start;
struct extent_buffer *eb;
@@ -639,8 +641,15 @@
btree_readahead_hook(root, eb, eb->start, ret);
}
- if (ret)
+ if (ret) {
+ /*
+ * our io error hook is going to dec the io pages
+ * again, we have to make sure it has something
+ * to decrement
+ */
+ atomic_inc(&eb->io_pages);
clear_extent_buffer_uptodate(eb);
+ }
free_extent_buffer(eb);
out:
return ret;
@@ -654,6 +663,7 @@
eb = (struct extent_buffer *)page->private;
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
eb->read_mirror = failed_mirror;
+ atomic_dec(&eb->io_pages);
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
btree_readahead_hook(root, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
@@ -670,17 +680,23 @@
end_io_wq->work.flags = 0;
if (bio->bi_rw & REQ_WRITE) {
- if (end_io_wq->metadata == 1)
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
btrfs_queue_worker(&fs_info->endio_meta_write_workers,
&end_io_wq->work);
- else if (end_io_wq->metadata == 2)
+ else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
btrfs_queue_worker(&fs_info->endio_freespace_worker,
&end_io_wq->work);
+ else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
+ btrfs_queue_worker(&fs_info->endio_raid56_workers,
+ &end_io_wq->work);
else
btrfs_queue_worker(&fs_info->endio_write_workers,
&end_io_wq->work);
} else {
- if (end_io_wq->metadata)
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
+ btrfs_queue_worker(&fs_info->endio_raid56_workers,
+ &end_io_wq->work);
+ else if (end_io_wq->metadata)
btrfs_queue_worker(&fs_info->endio_meta_workers,
&end_io_wq->work);
else
@@ -695,6 +711,7 @@
* 0 - if data
* 1 - if normal metadta
* 2 - if writing to the free space cache area
+ * 3 - raid parity work
*/
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
int metadata)
@@ -946,18 +963,20 @@
struct writeback_control *wbc)
{
struct extent_io_tree *tree;
+ struct btrfs_fs_info *fs_info;
+ int ret;
+
tree = &BTRFS_I(mapping->host)->io_tree;
if (wbc->sync_mode == WB_SYNC_NONE) {
- struct btrfs_root *root = BTRFS_I(mapping->host)->root;
- u64 num_dirty;
- unsigned long thresh = 32 * 1024 * 1024;
if (wbc->for_kupdate)
return 0;
+ fs_info = BTRFS_I(mapping->host)->root->fs_info;
/* this is a bit racy, but that's ok */
- num_dirty = root->fs_info->dirty_metadata_bytes;
- if (num_dirty < thresh)
+ ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+ BTRFS_DIRTY_METADATA_THRESH);
+ if (ret < 0)
return 0;
}
return btree_write_cache_pages(mapping, wbc);
@@ -1125,24 +1144,16 @@
void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf)
{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+
if (btrfs_header_generation(buf) ==
- root->fs_info->running_transaction->transid) {
+ fs_info->running_transaction->transid) {
btrfs_assert_tree_locked(buf);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
- spin_lock(&root->fs_info->delalloc_lock);
- if (root->fs_info->dirty_metadata_bytes >= buf->len)
- root->fs_info->dirty_metadata_bytes -= buf->len;
- else {
- spin_unlock(&root->fs_info->delalloc_lock);
- btrfs_panic(root->fs_info, -EOVERFLOW,
- "Can't clear %lu bytes from "
- " dirty_mdatadata_bytes (%llu)",
- buf->len,
- root->fs_info->dirty_metadata_bytes);
- }
- spin_unlock(&root->fs_info->delalloc_lock);
-
+ __percpu_counter_add(&fs_info->dirty_metadata_bytes,
+ -buf->len,
+ fs_info->dirty_metadata_batch);
/* ugh, clear_extent_buffer_dirty needs to lock the page */
btrfs_set_lock_blocking(buf);
clear_extent_buffer_dirty(buf);
@@ -1178,9 +1189,13 @@
INIT_LIST_HEAD(&root->dirty_list);
INIT_LIST_HEAD(&root->root_list);
+ INIT_LIST_HEAD(&root->logged_list[0]);
+ INIT_LIST_HEAD(&root->logged_list[1]);
spin_lock_init(&root->orphan_lock);
spin_lock_init(&root->inode_lock);
spin_lock_init(&root->accounting_lock);
+ spin_lock_init(&root->log_extents_lock[0]);
+ spin_lock_init(&root->log_extents_lock[1]);
mutex_init(&root->objectid_mutex);
mutex_init(&root->log_mutex);
init_waitqueue_head(&root->log_writer_wait);
@@ -1276,6 +1291,7 @@
0, objectid, NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
+ leaf = NULL;
goto fail;
}
@@ -1319,11 +1335,16 @@
btrfs_tree_unlock(leaf);
-fail:
- if (ret)
- return ERR_PTR(ret);
-
return root;
+
+fail:
+ if (leaf) {
+ btrfs_tree_unlock(leaf);
+ free_extent_buffer(leaf);
+ }
+ kfree(root);
+
+ return ERR_PTR(ret);
}
static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
@@ -2004,10 +2025,24 @@
goto fail_srcu;
}
+ ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0);
+ if (ret) {
+ err = ret;
+ goto fail_bdi;
+ }
+ fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
+ (1 + ilog2(nr_cpu_ids));
+
+ ret = percpu_counter_init(&fs_info->delalloc_bytes, 0);
+ if (ret) {
+ err = ret;
+ goto fail_dirty_metadata_bytes;
+ }
+
fs_info->btree_inode = new_inode(sb);
if (!fs_info->btree_inode) {
err = -ENOMEM;
- goto fail_bdi;
+ goto fail_delalloc_bytes;
}
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
@@ -2017,7 +2052,6 @@
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
INIT_LIST_HEAD(&fs_info->delalloc_inodes);
- INIT_LIST_HEAD(&fs_info->ordered_operations);
INIT_LIST_HEAD(&fs_info->caching_block_groups);
spin_lock_init(&fs_info->delalloc_lock);
spin_lock_init(&fs_info->trans_lock);
@@ -2028,6 +2062,7 @@
spin_lock_init(&fs_info->tree_mod_seq_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->reloc_mutex);
+ seqlock_init(&fs_info->profiles_lock);
init_completion(&fs_info->kobj_unregister);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
@@ -2126,6 +2161,7 @@
spin_lock_init(&fs_info->block_group_cache_lock);
fs_info->block_group_cache_tree = RB_ROOT;
+ fs_info->first_logical_byte = (u64)-1;
extent_io_tree_init(&fs_info->freed_extents[0],
fs_info->btree_inode->i_mapping);
@@ -2165,6 +2201,12 @@
init_waitqueue_head(&fs_info->transaction_blocked_wait);
init_waitqueue_head(&fs_info->async_submit_wait);
+ ret = btrfs_alloc_stripe_hash_table(fs_info);
+ if (ret) {
+ err = ret;
+ goto fail_alloc;
+ }
+
__setup_root(4096, 4096, 4096, 4096, tree_root,
fs_info, BTRFS_ROOT_TREE_OBJECTID);
@@ -2187,7 +2229,8 @@
goto fail_alloc;
/* check FS state, whether FS is broken. */
- fs_info->fs_state |= btrfs_super_flags(disk_super);
+ if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR)
+ set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
if (ret) {
@@ -2261,6 +2304,8 @@
leafsize = btrfs_super_leafsize(disk_super);
sectorsize = btrfs_super_sectorsize(disk_super);
stripesize = btrfs_super_stripesize(disk_super);
+ fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids));
+ fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
/*
* mixed block groups end up with duplicate but slightly offset
@@ -2332,6 +2377,12 @@
btrfs_init_workers(&fs_info->endio_meta_write_workers,
"endio-meta-write", fs_info->thread_pool_size,
&fs_info->generic_worker);
+ btrfs_init_workers(&fs_info->endio_raid56_workers,
+ "endio-raid56", fs_info->thread_pool_size,
+ &fs_info->generic_worker);
+ btrfs_init_workers(&fs_info->rmw_workers,
+ "rmw", fs_info->thread_pool_size,
+ &fs_info->generic_worker);
btrfs_init_workers(&fs_info->endio_write_workers, "endio-write",
fs_info->thread_pool_size,
&fs_info->generic_worker);
@@ -2350,6 +2401,8 @@
*/
fs_info->endio_workers.idle_thresh = 4;
fs_info->endio_meta_workers.idle_thresh = 4;
+ fs_info->endio_raid56_workers.idle_thresh = 4;
+ fs_info->rmw_workers.idle_thresh = 2;
fs_info->endio_write_workers.idle_thresh = 2;
fs_info->endio_meta_write_workers.idle_thresh = 2;
@@ -2366,6 +2419,8 @@
ret |= btrfs_start_workers(&fs_info->fixup_workers);
ret |= btrfs_start_workers(&fs_info->endio_workers);
ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
+ ret |= btrfs_start_workers(&fs_info->rmw_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_raid56_workers);
ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
ret |= btrfs_start_workers(&fs_info->endio_write_workers);
ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
@@ -2390,8 +2445,7 @@
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
- if (strncmp((char *)(&disk_super->magic), BTRFS_MAGIC,
- sizeof(disk_super->magic))) {
+ if (disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) {
printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
@@ -2694,13 +2748,13 @@
* kthreads
*/
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
- invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
fail_block_groups:
btrfs_free_block_groups(fs_info);
fail_tree_roots:
free_root_pointers(fs_info, 1);
+ invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
fail_sb_buffer:
btrfs_stop_workers(&fs_info->generic_worker);
@@ -2710,6 +2764,8 @@
btrfs_stop_workers(&fs_info->workers);
btrfs_stop_workers(&fs_info->endio_workers);
btrfs_stop_workers(&fs_info->endio_meta_workers);
+ btrfs_stop_workers(&fs_info->endio_raid56_workers);
+ btrfs_stop_workers(&fs_info->rmw_workers);
btrfs_stop_workers(&fs_info->endio_meta_write_workers);
btrfs_stop_workers(&fs_info->endio_write_workers);
btrfs_stop_workers(&fs_info->endio_freespace_worker);
@@ -2721,13 +2777,17 @@
fail_iput:
btrfs_mapping_tree_free(&fs_info->mapping_tree);
- invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
iput(fs_info->btree_inode);
+fail_delalloc_bytes:
+ percpu_counter_destroy(&fs_info->delalloc_bytes);
+fail_dirty_metadata_bytes:
+ percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
fail_bdi:
bdi_destroy(&fs_info->bdi);
fail_srcu:
cleanup_srcu_struct(&fs_info->subvol_srcu);
fail:
+ btrfs_free_stripe_hash_table(fs_info);
btrfs_close_devices(fs_info->fs_devices);
return err;
@@ -2795,8 +2855,7 @@
super = (struct btrfs_super_block *)bh->b_data;
if (btrfs_super_bytenr(super) != bytenr ||
- strncmp((char *)(&super->magic), BTRFS_MAGIC,
- sizeof(super->magic))) {
+ super->magic != cpu_to_le64(BTRFS_MAGIC)) {
brelse(bh);
continue;
}
@@ -3076,11 +3135,16 @@
((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK)
== 0)))
num_tolerated_disk_barrier_failures = 0;
- else if (num_tolerated_disk_barrier_failures > 1
- &&
- (flags & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10)))
- num_tolerated_disk_barrier_failures = 1;
+ else if (num_tolerated_disk_barrier_failures > 1) {
+ if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID10)) {
+ num_tolerated_disk_barrier_failures = 1;
+ } else if (flags &
+ BTRFS_BLOCK_GROUP_RAID5) {
+ num_tolerated_disk_barrier_failures = 2;
+ }
+ }
}
}
up_read(&sinfo->groups_sem);
@@ -3195,6 +3259,11 @@
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ btrfs_free_log(NULL, root);
+ btrfs_free_log_root_tree(NULL, fs_info);
+ }
+
__btrfs_remove_free_space_cache(root->free_ino_pinned);
__btrfs_remove_free_space_cache(root->free_ino_ctl);
free_fs_root(root);
@@ -3339,7 +3408,7 @@
printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
}
- if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
btrfs_error_commit_super(root);
btrfs_put_block_group_cache(fs_info);
@@ -3352,9 +3421,9 @@
btrfs_free_qgroup_config(root->fs_info);
- if (fs_info->delalloc_bytes) {
- printk(KERN_INFO "btrfs: at unmount delalloc count %llu\n",
- (unsigned long long)fs_info->delalloc_bytes);
+ if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
+ printk(KERN_INFO "btrfs: at unmount delalloc count %lld\n",
+ percpu_counter_sum(&fs_info->delalloc_bytes));
}
free_extent_buffer(fs_info->extent_root->node);
@@ -3384,6 +3453,8 @@
btrfs_stop_workers(&fs_info->workers);
btrfs_stop_workers(&fs_info->endio_workers);
btrfs_stop_workers(&fs_info->endio_meta_workers);
+ btrfs_stop_workers(&fs_info->endio_raid56_workers);
+ btrfs_stop_workers(&fs_info->rmw_workers);
btrfs_stop_workers(&fs_info->endio_meta_write_workers);
btrfs_stop_workers(&fs_info->endio_write_workers);
btrfs_stop_workers(&fs_info->endio_freespace_worker);
@@ -3401,9 +3472,13 @@
btrfs_close_devices(fs_info->fs_devices);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
+ percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
+ percpu_counter_destroy(&fs_info->delalloc_bytes);
bdi_destroy(&fs_info->bdi);
cleanup_srcu_struct(&fs_info->subvol_srcu);
+ btrfs_free_stripe_hash_table(fs_info);
+
return 0;
}
@@ -3443,11 +3518,10 @@
(unsigned long long)transid,
(unsigned long long)root->fs_info->generation);
was_dirty = set_extent_buffer_dirty(buf);
- if (!was_dirty) {
- spin_lock(&root->fs_info->delalloc_lock);
- root->fs_info->dirty_metadata_bytes += buf->len;
- spin_unlock(&root->fs_info->delalloc_lock);
- }
+ if (!was_dirty)
+ __percpu_counter_add(&root->fs_info->dirty_metadata_bytes,
+ buf->len,
+ root->fs_info->dirty_metadata_batch);
}
static void __btrfs_btree_balance_dirty(struct btrfs_root *root,
@@ -3457,8 +3531,7 @@
* looks as though older kernels can get into trouble with
* this code, they end up stuck in balance_dirty_pages forever
*/
- u64 num_dirty;
- unsigned long thresh = 32 * 1024 * 1024;
+ int ret;
if (current->flags & PF_MEMALLOC)
return;
@@ -3466,9 +3539,9 @@
if (flush_delayed)
btrfs_balance_delayed_items(root);
- num_dirty = root->fs_info->dirty_metadata_bytes;
-
- if (num_dirty > thresh) {
+ ret = percpu_counter_compare(&root->fs_info->dirty_metadata_bytes,
+ BTRFS_DIRTY_METADATA_THRESH);
+ if (ret > 0) {
balance_dirty_pages_ratelimited(
root->fs_info->btree_inode->i_mapping);
}
@@ -3518,7 +3591,8 @@
btrfs_cleanup_transaction(root);
}
-static void btrfs_destroy_ordered_operations(struct btrfs_root *root)
+static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
+ struct btrfs_root *root)
{
struct btrfs_inode *btrfs_inode;
struct list_head splice;
@@ -3528,7 +3602,7 @@
mutex_lock(&root->fs_info->ordered_operations_mutex);
spin_lock(&root->fs_info->ordered_extent_lock);
- list_splice_init(&root->fs_info->ordered_operations, &splice);
+ list_splice_init(&t->ordered_operations, &splice);
while (!list_empty(&splice)) {
btrfs_inode = list_entry(splice.next, struct btrfs_inode,
ordered_operations);
@@ -3544,35 +3618,16 @@
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
{
- struct list_head splice;
struct btrfs_ordered_extent *ordered;
- struct inode *inode;
-
- INIT_LIST_HEAD(&splice);
spin_lock(&root->fs_info->ordered_extent_lock);
-
- list_splice_init(&root->fs_info->ordered_extents, &splice);
- while (!list_empty(&splice)) {
- ordered = list_entry(splice.next, struct btrfs_ordered_extent,
- root_extent_list);
-
- list_del_init(&ordered->root_extent_list);
- atomic_inc(&ordered->refs);
-
- /* the inode may be getting freed (in sys_unlink path). */
- inode = igrab(ordered->inode);
-
- spin_unlock(&root->fs_info->ordered_extent_lock);
- if (inode)
- iput(inode);
-
- atomic_set(&ordered->refs, 1);
- btrfs_put_ordered_extent(ordered);
-
- spin_lock(&root->fs_info->ordered_extent_lock);
- }
-
+ /*
+ * This will just short circuit the ordered completion stuff which will
+ * make sure the ordered extent gets properly cleaned up.
+ */
+ list_for_each_entry(ordered, &root->fs_info->ordered_extents,
+ root_extent_list)
+ set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
spin_unlock(&root->fs_info->ordered_extent_lock);
}
@@ -3594,11 +3649,11 @@
}
while ((node = rb_first(&delayed_refs->root)) != NULL) {
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+ struct btrfs_delayed_ref_head *head = NULL;
+ ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
atomic_set(&ref->refs, 1);
if (btrfs_delayed_ref_is_head(ref)) {
- struct btrfs_delayed_ref_head *head;
head = btrfs_delayed_node_to_head(ref);
if (!mutex_trylock(&head->mutex)) {
@@ -3614,16 +3669,18 @@
continue;
}
- kfree(head->extent_op);
+ btrfs_free_delayed_extent_op(head->extent_op);
delayed_refs->num_heads--;
if (list_empty(&head->cluster))
delayed_refs->num_heads_ready--;
list_del_init(&head->cluster);
}
+
ref->in_tree = 0;
rb_erase(&ref->rb_node, &delayed_refs->root);
delayed_refs->num_entries--;
-
+ if (head)
+ mutex_unlock(&head->mutex);
spin_unlock(&delayed_refs->lock);
btrfs_put_delayed_ref(ref);
@@ -3636,7 +3693,7 @@
return ret;
}
-static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
+static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t)
{
struct btrfs_pending_snapshot *snapshot;
struct list_head splice;
@@ -3649,10 +3706,8 @@
snapshot = list_entry(splice.next,
struct btrfs_pending_snapshot,
list);
-
+ snapshot->error = -ECANCELED;
list_del_init(&snapshot->list);
-
- kfree(snapshot);
}
}
@@ -3671,6 +3726,8 @@
delalloc_inodes);
list_del_init(&btrfs_inode->delalloc_inodes);
+ clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &btrfs_inode->runtime_flags);
btrfs_invalidate_inodes(btrfs_inode->root);
}
@@ -3787,6 +3844,8 @@
cur_trans->blocked = 1;
wake_up(&root->fs_info->transaction_blocked_wait);
+ btrfs_evict_pending_snapshots(cur_trans);
+
cur_trans->blocked = 0;
wake_up(&root->fs_info->transaction_wait);
@@ -3796,8 +3855,6 @@
btrfs_destroy_delayed_inodes(root);
btrfs_assert_delayed_root_empty(root);
- btrfs_destroy_pending_snapshots(cur_trans);
-
btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages,
EXTENT_DIRTY);
btrfs_destroy_pinned_extent(root,
@@ -3823,10 +3880,8 @@
while (!list_empty(&list)) {
t = list_entry(list.next, struct btrfs_transaction, list);
- if (!t)
- break;
- btrfs_destroy_ordered_operations(root);
+ btrfs_destroy_ordered_operations(t, root);
btrfs_destroy_ordered_extents(root);
@@ -3843,6 +3898,8 @@
if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
wake_up(&root->fs_info->transaction_blocked_wait);
+ btrfs_evict_pending_snapshots(t);
+
t->blocked = 0;
smp_mb();
if (waitqueue_active(&root->fs_info->transaction_wait))
@@ -3856,8 +3913,6 @@
btrfs_destroy_delayed_inodes(root);
btrfs_assert_delayed_root_empty(root);
- btrfs_destroy_pending_snapshots(t);
-
btrfs_destroy_delalloc_inodes(root);
spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 305c33e..034d7dc 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -25,6 +25,13 @@
#define BTRFS_SUPER_MIRROR_MAX 3
#define BTRFS_SUPER_MIRROR_SHIFT 12
+enum {
+ BTRFS_WQ_ENDIO_DATA = 0,
+ BTRFS_WQ_ENDIO_METADATA = 1,
+ BTRFS_WQ_ENDIO_FREE_SPACE = 2,
+ BTRFS_WQ_ENDIO_RAID56 = 3,
+};
+
static inline u64 btrfs_sb_offset(int mirror)
{
u64 start = 16 * 1024;
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 614f34a..81ee29e 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -22,10 +22,10 @@
if (parent && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
*max_len = BTRFS_FID_SIZE_CONNECTABLE;
- return 255;
+ return FILEID_INVALID;
} else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) {
*max_len = BTRFS_FID_SIZE_NON_CONNECTABLE;
- return 255;
+ return FILEID_INVALID;
}
len = BTRFS_FID_SIZE_NON_CONNECTABLE;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a8b8adc..3d55123 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -31,6 +31,7 @@
#include "print-tree.h"
#include "transaction.h"
#include "volumes.h"
+#include "raid56.h"
#include "locking.h"
#include "free-space-cache.h"
#include "math.h"
@@ -72,8 +73,7 @@
RESERVE_ALLOC_NO_ACCOUNT = 2,
};
-static int update_block_group(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+static int update_block_group(struct btrfs_root *root,
u64 bytenr, u64 num_bytes, int alloc);
static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -103,6 +103,8 @@
int dump_block_groups);
static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
u64 num_bytes, int reserve);
+static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
+ u64 num_bytes);
static noinline int
block_group_cache_done(struct btrfs_block_group_cache *cache)
@@ -162,6 +164,10 @@
rb_link_node(&block_group->cache_node, parent, p);
rb_insert_color(&block_group->cache_node,
&info->block_group_cache_tree);
+
+ if (info->first_logical_byte > block_group->key.objectid)
+ info->first_logical_byte = block_group->key.objectid;
+
spin_unlock(&info->block_group_cache_lock);
return 0;
@@ -203,8 +209,11 @@
break;
}
}
- if (ret)
+ if (ret) {
btrfs_get_block_group(ret);
+ if (bytenr == 0 && info->first_logical_byte > ret->key.objectid)
+ info->first_logical_byte = ret->key.objectid;
+ }
spin_unlock(&info->block_group_cache_lock);
return ret;
@@ -248,7 +257,8 @@
cache->bytes_super += stripe_len;
ret = add_excluded_extent(root, cache->key.objectid,
stripe_len);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ return ret;
}
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
@@ -256,13 +266,17 @@
ret = btrfs_rmap_block(&root->fs_info->mapping_tree,
cache->key.objectid, bytenr,
0, &logical, &nr, &stripe_len);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ return ret;
while (nr--) {
cache->bytes_super += stripe_len;
ret = add_excluded_extent(root, logical[nr],
stripe_len);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret) {
+ kfree(logical);
+ return ret;
+ }
}
kfree(logical);
@@ -468,8 +482,6 @@
}
static int cache_block_group(struct btrfs_block_group_cache *cache,
- struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
int load_cache_only)
{
DEFINE_WAIT(wait);
@@ -527,12 +539,6 @@
cache->cached = BTRFS_CACHE_FAST;
spin_unlock(&cache->lock);
- /*
- * We can't do the read from on-disk cache during a commit since we need
- * to have the normal tree locking. Also if we are currently trying to
- * allocate blocks for the tree root we can't do the fast caching since
- * we likely hold important locks.
- */
if (fs_info->mount_opt & BTRFS_MOUNT_SPACE_CACHE) {
ret = load_free_space_cache(fs_info, cache);
@@ -1466,8 +1472,11 @@
if (ret && !insert) {
err = -ENOENT;
goto out;
+ } else if (ret) {
+ err = -EIO;
+ WARN_ON(1);
+ goto out;
}
- BUG_ON(ret); /* Corruption */
leaf = path->nodes[0];
item_size = btrfs_item_size_nr(leaf, path->slots[0]);
@@ -1852,6 +1861,8 @@
*actual_bytes = discarded_bytes;
+ if (ret == -EOPNOTSUPP)
+ ret = 0;
return ret;
}
@@ -2143,7 +2154,6 @@
node->num_bytes);
}
}
- mutex_unlock(&head->mutex);
return ret;
}
@@ -2258,7 +2268,7 @@
* process of being added. Don't run this ref yet.
*/
list_del_init(&locked_ref->cluster);
- mutex_unlock(&locked_ref->mutex);
+ btrfs_delayed_ref_unlock(locked_ref);
locked_ref = NULL;
delayed_refs->num_heads_ready++;
spin_unlock(&delayed_refs->lock);
@@ -2285,7 +2295,7 @@
ref = &locked_ref->node;
if (extent_op && must_insert_reserved) {
- kfree(extent_op);
+ btrfs_free_delayed_extent_op(extent_op);
extent_op = NULL;
}
@@ -2294,28 +2304,25 @@
ret = run_delayed_extent_op(trans, root,
ref, extent_op);
- kfree(extent_op);
+ btrfs_free_delayed_extent_op(extent_op);
if (ret) {
- list_del_init(&locked_ref->cluster);
- mutex_unlock(&locked_ref->mutex);
-
- printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret);
+ printk(KERN_DEBUG
+ "btrfs: run_delayed_extent_op "
+ "returned %d\n", ret);
spin_lock(&delayed_refs->lock);
+ btrfs_delayed_ref_unlock(locked_ref);
return ret;
}
goto next;
}
-
- list_del_init(&locked_ref->cluster);
- locked_ref = NULL;
}
ref->in_tree = 0;
rb_erase(&ref->rb_node, &delayed_refs->root);
delayed_refs->num_entries--;
- if (locked_ref) {
+ if (!btrfs_delayed_ref_is_head(ref)) {
/*
* when we play the delayed ref, also correct the
* ref_mod on head
@@ -2337,20 +2344,29 @@
ret = run_one_delayed_ref(trans, root, ref, extent_op,
must_insert_reserved);
- btrfs_put_delayed_ref(ref);
- kfree(extent_op);
- count++;
-
+ btrfs_free_delayed_extent_op(extent_op);
if (ret) {
- if (locked_ref) {
- list_del_init(&locked_ref->cluster);
- mutex_unlock(&locked_ref->mutex);
- }
- printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret);
+ btrfs_delayed_ref_unlock(locked_ref);
+ btrfs_put_delayed_ref(ref);
+ printk(KERN_DEBUG
+ "btrfs: run_one_delayed_ref returned %d\n", ret);
spin_lock(&delayed_refs->lock);
return ret;
}
+ /*
+ * If this node is a head, that means all the refs in this head
+ * have been dealt with, and we will pick the next head to deal
+ * with, so we must unlock the head and drop it from the cluster
+ * list before we release it.
+ */
+ if (btrfs_delayed_ref_is_head(ref)) {
+ list_del_init(&locked_ref->cluster);
+ btrfs_delayed_ref_unlock(locked_ref);
+ locked_ref = NULL;
+ }
+ btrfs_put_delayed_ref(ref);
+ count++;
next:
cond_resched();
spin_lock(&delayed_refs->lock);
@@ -2435,6 +2451,16 @@
return ret;
}
+static int refs_newer(struct btrfs_delayed_ref_root *delayed_refs, int seq,
+ int count)
+{
+ int val = atomic_read(&delayed_refs->ref_seq);
+
+ if (val < seq || val >= seq + count)
+ return 1;
+ return 0;
+}
+
/*
* this starts processing the delayed reference count updates and
* extent insertions we have queued up so far. count can be
@@ -2469,6 +2495,44 @@
delayed_refs = &trans->transaction->delayed_refs;
INIT_LIST_HEAD(&cluster);
+ if (count == 0) {
+ count = delayed_refs->num_entries * 2;
+ run_most = 1;
+ }
+
+ if (!run_all && !run_most) {
+ int old;
+ int seq = atomic_read(&delayed_refs->ref_seq);
+
+progress:
+ old = atomic_cmpxchg(&delayed_refs->procs_running_refs, 0, 1);
+ if (old) {
+ DEFINE_WAIT(__wait);
+ if (delayed_refs->num_entries < 16348)
+ return 0;
+
+ prepare_to_wait(&delayed_refs->wait, &__wait,
+ TASK_UNINTERRUPTIBLE);
+
+ old = atomic_cmpxchg(&delayed_refs->procs_running_refs, 0, 1);
+ if (old) {
+ schedule();
+ finish_wait(&delayed_refs->wait, &__wait);
+
+ if (!refs_newer(delayed_refs, seq, 256))
+ goto progress;
+ else
+ return 0;
+ } else {
+ finish_wait(&delayed_refs->wait, &__wait);
+ goto again;
+ }
+ }
+
+ } else {
+ atomic_inc(&delayed_refs->procs_running_refs);
+ }
+
again:
loops = 0;
spin_lock(&delayed_refs->lock);
@@ -2477,10 +2541,6 @@
delayed_refs->run_delayed_start = find_middle(&delayed_refs->root);
#endif
- if (count == 0) {
- count = delayed_refs->num_entries * 2;
- run_most = 1;
- }
while (1) {
if (!(run_all || run_most) &&
delayed_refs->num_heads_ready < 64)
@@ -2500,11 +2560,15 @@
ret = run_clustered_refs(trans, root, &cluster);
if (ret < 0) {
+ btrfs_release_ref_cluster(&cluster);
spin_unlock(&delayed_refs->lock);
btrfs_abort_transaction(trans, root, ret);
+ atomic_dec(&delayed_refs->procs_running_refs);
return ret;
}
+ atomic_add(ret, &delayed_refs->ref_seq);
+
count -= min_t(unsigned long, ret, count);
if (count == 0)
@@ -2573,6 +2637,11 @@
goto again;
}
out:
+ atomic_dec(&delayed_refs->procs_running_refs);
+ smp_mb();
+ if (waitqueue_active(&delayed_refs->wait))
+ wake_up(&delayed_refs->wait);
+
spin_unlock(&delayed_refs->lock);
assert_qgroups_uptodate(trans);
return 0;
@@ -2586,7 +2655,7 @@
struct btrfs_delayed_extent_op *extent_op;
int ret;
- extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
+ extent_op = btrfs_alloc_delayed_extent_op();
if (!extent_op)
return -ENOMEM;
@@ -2598,7 +2667,7 @@
ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr,
num_bytes, extent_op);
if (ret)
- kfree(extent_op);
+ btrfs_free_delayed_extent_op(extent_op);
return ret;
}
@@ -3223,12 +3292,14 @@
u64 extra_flags = chunk_to_extended(flags) &
BTRFS_EXTENDED_PROFILE_MASK;
+ write_seqlock(&fs_info->profiles_lock);
if (flags & BTRFS_BLOCK_GROUP_DATA)
fs_info->avail_data_alloc_bits |= extra_flags;
if (flags & BTRFS_BLOCK_GROUP_METADATA)
fs_info->avail_metadata_alloc_bits |= extra_flags;
if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
fs_info->avail_system_alloc_bits |= extra_flags;
+ write_sequnlock(&fs_info->profiles_lock);
}
/*
@@ -3276,6 +3347,7 @@
u64 num_devices = root->fs_info->fs_devices->rw_devices +
root->fs_info->fs_devices->missing_devices;
u64 target;
+ u64 tmp;
/*
* see if restripe for this chunk_type is in progress, if so
@@ -3292,40 +3364,48 @@
}
spin_unlock(&root->fs_info->balance_lock);
+ /* First, mask out the RAID levels which aren't possible */
if (num_devices == 1)
- flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0);
+ flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID5);
+ if (num_devices < 3)
+ flags &= ~BTRFS_BLOCK_GROUP_RAID6;
if (num_devices < 4)
flags &= ~BTRFS_BLOCK_GROUP_RAID10;
- if ((flags & BTRFS_BLOCK_GROUP_DUP) &&
- (flags & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10))) {
- flags &= ~BTRFS_BLOCK_GROUP_DUP;
- }
+ tmp = flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6 | BTRFS_BLOCK_GROUP_RAID10);
+ flags &= ~tmp;
- if ((flags & BTRFS_BLOCK_GROUP_RAID1) &&
- (flags & BTRFS_BLOCK_GROUP_RAID10)) {
- flags &= ~BTRFS_BLOCK_GROUP_RAID1;
- }
+ if (tmp & BTRFS_BLOCK_GROUP_RAID6)
+ tmp = BTRFS_BLOCK_GROUP_RAID6;
+ else if (tmp & BTRFS_BLOCK_GROUP_RAID5)
+ tmp = BTRFS_BLOCK_GROUP_RAID5;
+ else if (tmp & BTRFS_BLOCK_GROUP_RAID10)
+ tmp = BTRFS_BLOCK_GROUP_RAID10;
+ else if (tmp & BTRFS_BLOCK_GROUP_RAID1)
+ tmp = BTRFS_BLOCK_GROUP_RAID1;
+ else if (tmp & BTRFS_BLOCK_GROUP_RAID0)
+ tmp = BTRFS_BLOCK_GROUP_RAID0;
- if ((flags & BTRFS_BLOCK_GROUP_RAID0) &&
- ((flags & BTRFS_BLOCK_GROUP_RAID1) |
- (flags & BTRFS_BLOCK_GROUP_RAID10) |
- (flags & BTRFS_BLOCK_GROUP_DUP))) {
- flags &= ~BTRFS_BLOCK_GROUP_RAID0;
- }
-
- return extended_to_chunk(flags);
+ return extended_to_chunk(flags | tmp);
}
static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
{
- if (flags & BTRFS_BLOCK_GROUP_DATA)
- flags |= root->fs_info->avail_data_alloc_bits;
- else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
- flags |= root->fs_info->avail_system_alloc_bits;
- else if (flags & BTRFS_BLOCK_GROUP_METADATA)
- flags |= root->fs_info->avail_metadata_alloc_bits;
+ unsigned seq;
+
+ do {
+ seq = read_seqbegin(&root->fs_info->profiles_lock);
+
+ if (flags & BTRFS_BLOCK_GROUP_DATA)
+ flags |= root->fs_info->avail_data_alloc_bits;
+ else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+ flags |= root->fs_info->avail_system_alloc_bits;
+ else if (flags & BTRFS_BLOCK_GROUP_METADATA)
+ flags |= root->fs_info->avail_metadata_alloc_bits;
+ } while (read_seqretry(&root->fs_info->profiles_lock, seq));
return btrfs_reduce_alloc_profile(root, flags);
}
@@ -3333,6 +3413,7 @@
u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
{
u64 flags;
+ u64 ret;
if (data)
flags = BTRFS_BLOCK_GROUP_DATA;
@@ -3341,7 +3422,8 @@
else
flags = BTRFS_BLOCK_GROUP_METADATA;
- return get_alloc_profile(root, flags);
+ ret = get_alloc_profile(root, flags);
+ return ret;
}
/*
@@ -3357,7 +3439,7 @@
int ret = 0, committed = 0, alloc_chunk = 1;
/* make sure bytes are sectorsize aligned */
- bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
+ bytes = ALIGN(bytes, root->sectorsize);
if (root == root->fs_info->tree_root ||
BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID) {
@@ -3452,7 +3534,7 @@
struct btrfs_space_info *data_sinfo;
/* make sure bytes are sectorsize aligned */
- bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
+ bytes = ALIGN(bytes, root->sectorsize);
data_sinfo = root->fs_info->data_sinfo;
spin_lock(&data_sinfo->lock);
@@ -3516,8 +3598,10 @@
{
u64 num_dev;
- if (type & BTRFS_BLOCK_GROUP_RAID10 ||
- type & BTRFS_BLOCK_GROUP_RAID0)
+ if (type & (BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6))
num_dev = root->fs_info->fs_devices->rw_devices;
else if (type & BTRFS_BLOCK_GROUP_RAID1)
num_dev = 2;
@@ -3564,6 +3648,10 @@
int wait_for_alloc = 0;
int ret = 0;
+ /* Don't re-enter if we're already allocating a chunk */
+ if (trans->allocating_chunk)
+ return -ENOSPC;
+
space_info = __find_space_info(extent_root->fs_info, flags);
if (!space_info) {
ret = update_space_info(extent_root->fs_info, flags,
@@ -3606,6 +3694,8 @@
goto again;
}
+ trans->allocating_chunk = true;
+
/*
* If we have mixed data/metadata chunks we want to make sure we keep
* allocating mixed chunks instead of individual chunks.
@@ -3632,19 +3722,20 @@
check_system_chunk(trans, extent_root, flags);
ret = btrfs_alloc_chunk(trans, extent_root, flags);
- if (ret < 0 && ret != -ENOSPC)
- goto out;
+ trans->allocating_chunk = false;
spin_lock(&space_info->lock);
+ if (ret < 0 && ret != -ENOSPC)
+ goto out;
if (ret)
space_info->full = 1;
else
ret = 1;
space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
+out:
space_info->chunk_alloc = 0;
spin_unlock(&space_info->lock);
-out:
mutex_unlock(&fs_info->chunk_mutex);
return ret;
}
@@ -3653,13 +3744,31 @@
struct btrfs_space_info *space_info, u64 bytes,
enum btrfs_reserve_flush_enum flush)
{
+ struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv;
u64 profile = btrfs_get_alloc_profile(root, 0);
+ u64 rsv_size = 0;
u64 avail;
u64 used;
+ u64 to_add;
used = space_info->bytes_used + space_info->bytes_reserved +
- space_info->bytes_pinned + space_info->bytes_readonly +
- space_info->bytes_may_use;
+ space_info->bytes_pinned + space_info->bytes_readonly;
+
+ spin_lock(&global_rsv->lock);
+ rsv_size = global_rsv->size;
+ spin_unlock(&global_rsv->lock);
+
+ /*
+ * We only want to allow over committing if we have lots of actual space
+ * free, but if we don't have enough space to handle the global reserve
+ * space then we could end up having a real enospc problem when trying
+ * to allocate a chunk or some other such important allocation.
+ */
+ rsv_size <<= 1;
+ if (used + rsv_size >= space_info->total_bytes)
+ return 0;
+
+ used += space_info->bytes_may_use;
spin_lock(&root->fs_info->free_chunk_lock);
avail = root->fs_info->free_chunk_space;
@@ -3667,40 +3776,58 @@
/*
* If we have dup, raid1 or raid10 then only half of the free
- * space is actually useable.
+ * space is actually useable. For raid56, the space info used
+ * doesn't include the parity drive, so we don't have to
+ * change the math
*/
if (profile & (BTRFS_BLOCK_GROUP_DUP |
BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10))
avail >>= 1;
+ to_add = space_info->total_bytes;
+
/*
* If we aren't flushing all things, let us overcommit up to
* 1/2th of the space. If we can flush, don't let us overcommit
* too much, let it overcommit up to 1/8 of the space.
*/
if (flush == BTRFS_RESERVE_FLUSH_ALL)
- avail >>= 3;
+ to_add >>= 3;
else
- avail >>= 1;
+ to_add >>= 1;
- if (used + bytes < space_info->total_bytes + avail)
+ /*
+ * Limit the overcommit to the amount of free space we could possibly
+ * allocate for chunks.
+ */
+ to_add = min(avail, to_add);
+
+ if (used + bytes < space_info->total_bytes + to_add)
return 1;
return 0;
}
-static int writeback_inodes_sb_nr_if_idle_safe(struct super_block *sb,
- unsigned long nr_pages,
- enum wb_reason reason)
+void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root,
+ unsigned long nr_pages)
{
- if (!writeback_in_progress(sb->s_bdi) &&
- down_read_trylock(&sb->s_umount)) {
- writeback_inodes_sb_nr(sb, nr_pages, reason);
- up_read(&sb->s_umount);
- return 1;
- }
+ struct super_block *sb = root->fs_info->sb;
+ int started;
- return 0;
+ /* If we can not start writeback, just sync all the delalloc file. */
+ started = try_to_writeback_inodes_sb_nr(sb, nr_pages,
+ WB_REASON_FS_FREE_SPACE);
+ if (!started) {
+ /*
+ * We needn't worry the filesystem going from r/w to r/o though
+ * we don't acquire ->s_umount mutex, because the filesystem
+ * should guarantee the delalloc inodes list be empty after
+ * the filesystem is readonly(all dirty pages are written to
+ * the disk).
+ */
+ btrfs_start_delalloc_inodes(root, 0);
+ btrfs_wait_ordered_extents(root, 0);
+ }
}
/*
@@ -3724,7 +3851,8 @@
space_info = block_rsv->space_info;
smp_mb();
- delalloc_bytes = root->fs_info->delalloc_bytes;
+ delalloc_bytes = percpu_counter_sum_positive(
+ &root->fs_info->delalloc_bytes);
if (delalloc_bytes == 0) {
if (trans)
return;
@@ -3735,10 +3863,7 @@
while (delalloc_bytes && loops < 3) {
max_reclaim = min(delalloc_bytes, to_reclaim);
nr_pages = max_reclaim >> PAGE_CACHE_SHIFT;
- writeback_inodes_sb_nr_if_idle_safe(root->fs_info->sb,
- nr_pages,
- WB_REASON_FS_FREE_SPACE);
-
+ btrfs_writeback_inodes_sb_nr(root, nr_pages);
/*
* We need to wait for the async pages to actually start before
* we do anything.
@@ -3766,7 +3891,8 @@
break;
}
smp_mb();
- delalloc_bytes = root->fs_info->delalloc_bytes;
+ delalloc_bytes = percpu_counter_sum_positive(
+ &root->fs_info->delalloc_bytes);
}
}
@@ -4030,6 +4156,15 @@
goto again;
out:
+ if (ret == -ENOSPC &&
+ unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
+ struct btrfs_block_rsv *global_rsv =
+ &root->fs_info->global_block_rsv;
+
+ if (block_rsv != global_rsv &&
+ !block_rsv_use_bytes(global_rsv, orig_bytes))
+ ret = 0;
+ }
if (flushing) {
spin_lock(&space_info->lock);
space_info->flush = 0;
@@ -4308,7 +4443,7 @@
spin_lock(&sinfo->lock);
spin_lock(&block_rsv->lock);
- block_rsv->size = num_bytes;
+ block_rsv->size = min_t(u64, num_bytes, 512 * 1024 * 1024);
num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
sinfo->bytes_reserved + sinfo->bytes_readonly +
@@ -4416,19 +4551,60 @@
btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
}
-int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
- struct btrfs_pending_snapshot *pending)
+/*
+ * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
+ * root: the root of the parent directory
+ * rsv: block reservation
+ * items: the number of items that we need do reservation
+ * qgroup_reserved: used to return the reserved size in qgroup
+ *
+ * This function is used to reserve the space for snapshot/subvolume
+ * creation and deletion. Those operations are different with the
+ * common file/directory operations, they change two fs/file trees
+ * and root tree, the number of items that the qgroup reserves is
+ * different with the free space reservation. So we can not use
+ * the space reseravtion mechanism in start_transaction().
+ */
+int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
+ struct btrfs_block_rsv *rsv,
+ int items,
+ u64 *qgroup_reserved)
{
- struct btrfs_root *root = pending->root;
- struct btrfs_block_rsv *src_rsv = get_block_rsv(trans, root);
- struct btrfs_block_rsv *dst_rsv = &pending->block_rsv;
- /*
- * two for root back/forward refs, two for directory entries,
- * one for root of the snapshot and one for parent inode.
- */
- u64 num_bytes = btrfs_calc_trans_metadata_size(root, 6);
- dst_rsv->space_info = src_rsv->space_info;
- return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
+ u64 num_bytes;
+ int ret;
+
+ if (root->fs_info->quota_enabled) {
+ /* One for parent inode, two for dir entries */
+ num_bytes = 3 * root->leafsize;
+ ret = btrfs_qgroup_reserve(root, num_bytes);
+ if (ret)
+ return ret;
+ } else {
+ num_bytes = 0;
+ }
+
+ *qgroup_reserved = num_bytes;
+
+ num_bytes = btrfs_calc_trans_metadata_size(root, items);
+ rsv->space_info = __find_space_info(root->fs_info,
+ BTRFS_BLOCK_GROUP_METADATA);
+ ret = btrfs_block_rsv_add(root, rsv, num_bytes,
+ BTRFS_RESERVE_FLUSH_ALL);
+ if (ret) {
+ if (*qgroup_reserved)
+ btrfs_qgroup_free(root, *qgroup_reserved);
+ }
+
+ return ret;
+}
+
+void btrfs_subvolume_release_metadata(struct btrfs_root *root,
+ struct btrfs_block_rsv *rsv,
+ u64 qgroup_reserved)
+{
+ btrfs_block_rsv_release(root, rsv, (u64)-1);
+ if (qgroup_reserved)
+ btrfs_qgroup_free(root, qgroup_reserved);
}
/**
@@ -4534,8 +4710,10 @@
unsigned nr_extents = 0;
int extra_reserve = 0;
enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
- int ret;
+ int ret = 0;
bool delalloc_lock = true;
+ u64 to_free = 0;
+ unsigned dropped;
/* If we are a free space inode we need to not flush since we will be in
* the middle of a transaction commit. We also don't need the delalloc
@@ -4582,53 +4760,16 @@
if (root->fs_info->quota_enabled) {
ret = btrfs_qgroup_reserve(root, num_bytes +
nr_extents * root->leafsize);
- if (ret) {
- spin_lock(&BTRFS_I(inode)->lock);
- calc_csum_metadata_size(inode, num_bytes, 0);
- spin_unlock(&BTRFS_I(inode)->lock);
- if (delalloc_lock)
- mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
- return ret;
- }
+ if (ret)
+ goto out_fail;
}
ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
- if (ret) {
- u64 to_free = 0;
- unsigned dropped;
-
- spin_lock(&BTRFS_I(inode)->lock);
- dropped = drop_outstanding_extent(inode);
- /*
- * If the inodes csum_bytes is the same as the original
- * csum_bytes then we know we haven't raced with any free()ers
- * so we can just reduce our inodes csum bytes and carry on.
- * Otherwise we have to do the normal free thing to account for
- * the case that the free side didn't free up its reserve
- * because of this outstanding reservation.
- */
- if (BTRFS_I(inode)->csum_bytes == csum_bytes)
- calc_csum_metadata_size(inode, num_bytes, 0);
- else
- to_free = calc_csum_metadata_size(inode, num_bytes, 0);
- spin_unlock(&BTRFS_I(inode)->lock);
- if (dropped)
- to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
- if (to_free) {
- btrfs_block_rsv_release(root, block_rsv, to_free);
- trace_btrfs_space_reservation(root->fs_info,
- "delalloc",
- btrfs_ino(inode),
- to_free, 0);
- }
- if (root->fs_info->quota_enabled) {
+ if (unlikely(ret)) {
+ if (root->fs_info->quota_enabled)
btrfs_qgroup_free(root, num_bytes +
nr_extents * root->leafsize);
- }
- if (delalloc_lock)
- mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
- return ret;
+ goto out_fail;
}
spin_lock(&BTRFS_I(inode)->lock);
@@ -4649,6 +4790,69 @@
block_rsv_add_bytes(block_rsv, to_reserve, 1);
return 0;
+
+out_fail:
+ spin_lock(&BTRFS_I(inode)->lock);
+ dropped = drop_outstanding_extent(inode);
+ /*
+ * If the inodes csum_bytes is the same as the original
+ * csum_bytes then we know we haven't raced with any free()ers
+ * so we can just reduce our inodes csum bytes and carry on.
+ */
+ if (BTRFS_I(inode)->csum_bytes == csum_bytes) {
+ calc_csum_metadata_size(inode, num_bytes, 0);
+ } else {
+ u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes;
+ u64 bytes;
+
+ /*
+ * This is tricky, but first we need to figure out how much we
+ * free'd from any free-ers that occured during this
+ * reservation, so we reset ->csum_bytes to the csum_bytes
+ * before we dropped our lock, and then call the free for the
+ * number of bytes that were freed while we were trying our
+ * reservation.
+ */
+ bytes = csum_bytes - BTRFS_I(inode)->csum_bytes;
+ BTRFS_I(inode)->csum_bytes = csum_bytes;
+ to_free = calc_csum_metadata_size(inode, bytes, 0);
+
+
+ /*
+ * Now we need to see how much we would have freed had we not
+ * been making this reservation and our ->csum_bytes were not
+ * artificially inflated.
+ */
+ BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes;
+ bytes = csum_bytes - orig_csum_bytes;
+ bytes = calc_csum_metadata_size(inode, bytes, 0);
+
+ /*
+ * Now reset ->csum_bytes to what it should be. If bytes is
+ * more than to_free then we would have free'd more space had we
+ * not had an artificially high ->csum_bytes, so we need to free
+ * the remainder. If bytes is the same or less then we don't
+ * need to do anything, the other free-ers did the correct
+ * thing.
+ */
+ BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes;
+ if (bytes > to_free)
+ to_free = bytes - to_free;
+ else
+ to_free = 0;
+ }
+ spin_unlock(&BTRFS_I(inode)->lock);
+ if (dropped)
+ to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
+ if (to_free) {
+ btrfs_block_rsv_release(root, block_rsv, to_free);
+ trace_btrfs_space_reservation(root->fs_info, "delalloc",
+ btrfs_ino(inode), to_free, 0);
+ }
+ if (delalloc_lock)
+ mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
+ return ret;
}
/**
@@ -4670,7 +4874,8 @@
spin_lock(&BTRFS_I(inode)->lock);
dropped = drop_outstanding_extent(inode);
- to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+ if (num_bytes)
+ to_free = calc_csum_metadata_size(inode, num_bytes, 0);
spin_unlock(&BTRFS_I(inode)->lock);
if (dropped > 0)
to_free += btrfs_calc_trans_metadata_size(root, dropped);
@@ -4737,8 +4942,7 @@
btrfs_free_reserved_data_space(inode, num_bytes);
}
-static int update_block_group(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+static int update_block_group(struct btrfs_root *root,
u64 bytenr, u64 num_bytes, int alloc)
{
struct btrfs_block_group_cache *cache = NULL;
@@ -4775,7 +4979,7 @@
* space back to the block group, otherwise we will leak space.
*/
if (!alloc && cache->cached == BTRFS_CACHE_NO)
- cache_block_group(cache, trans, NULL, 1);
+ cache_block_group(cache, 1);
byte_in_group = bytenr - cache->key.objectid;
WARN_ON(byte_in_group > cache->key.offset);
@@ -4825,6 +5029,13 @@
struct btrfs_block_group_cache *cache;
u64 bytenr;
+ spin_lock(&root->fs_info->block_group_cache_lock);
+ bytenr = root->fs_info->first_logical_byte;
+ spin_unlock(&root->fs_info->block_group_cache_lock);
+
+ if (bytenr < (u64)-1)
+ return bytenr;
+
cache = btrfs_lookup_first_block_group(root->fs_info, search_start);
if (!cache)
return 0;
@@ -4875,8 +5086,7 @@
/*
* this function must be called within transaction
*/
-int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+int btrfs_pin_extent_for_log_replay(struct btrfs_root *root,
u64 bytenr, u64 num_bytes)
{
struct btrfs_block_group_cache *cache;
@@ -4890,7 +5100,7 @@
* to one because the slow code to read in the free extents does check
* the pinned extents.
*/
- cache_block_group(cache, trans, root, 1);
+ cache_block_group(cache, 1);
pin_down_extent(root, cache, bytenr, num_bytes, 0);
@@ -5287,7 +5497,7 @@
}
}
- ret = update_block_group(trans, root, bytenr, num_bytes, 0);
+ ret = update_block_group(root, bytenr, num_bytes, 0);
if (ret) {
btrfs_abort_transaction(trans, extent_root, ret);
goto out;
@@ -5332,7 +5542,7 @@
if (head->extent_op) {
if (!head->must_insert_reserved)
goto out;
- kfree(head->extent_op);
+ btrfs_free_delayed_extent_op(head->extent_op);
head->extent_op = NULL;
}
@@ -5455,10 +5665,11 @@
return ret;
}
-static u64 stripe_align(struct btrfs_root *root, u64 val)
+static u64 stripe_align(struct btrfs_root *root,
+ struct btrfs_block_group_cache *cache,
+ u64 val, u64 num_bytes)
{
- u64 mask = ((u64)root->stripesize - 1);
- u64 ret = (val + mask) & ~mask;
+ u64 ret = ALIGN(val, root->stripesize);
return ret;
}
@@ -5478,7 +5689,6 @@
u64 num_bytes)
{
struct btrfs_caching_control *caching_ctl;
- DEFINE_WAIT(wait);
caching_ctl = get_caching_control(cache);
if (!caching_ctl)
@@ -5495,7 +5705,6 @@
wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
{
struct btrfs_caching_control *caching_ctl;
- DEFINE_WAIT(wait);
caching_ctl = get_caching_control(cache);
if (!caching_ctl)
@@ -5509,20 +5718,20 @@
int __get_raid_index(u64 flags)
{
- int index;
-
if (flags & BTRFS_BLOCK_GROUP_RAID10)
- index = 0;
+ return BTRFS_RAID_RAID10;
else if (flags & BTRFS_BLOCK_GROUP_RAID1)
- index = 1;
+ return BTRFS_RAID_RAID1;
else if (flags & BTRFS_BLOCK_GROUP_DUP)
- index = 2;
+ return BTRFS_RAID_DUP;
else if (flags & BTRFS_BLOCK_GROUP_RAID0)
- index = 3;
- else
- index = 4;
+ return BTRFS_RAID_RAID0;
+ else if (flags & BTRFS_BLOCK_GROUP_RAID5)
+ return BTRFS_RAID_RAID5;
+ else if (flags & BTRFS_BLOCK_GROUP_RAID6)
+ return BTRFS_RAID_RAID6;
- return index;
+ return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
}
static int get_block_group_index(struct btrfs_block_group_cache *cache)
@@ -5665,6 +5874,8 @@
if (!block_group_bits(block_group, data)) {
u64 extra = BTRFS_BLOCK_GROUP_DUP |
BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6 |
BTRFS_BLOCK_GROUP_RAID10;
/*
@@ -5680,8 +5891,7 @@
cached = block_group_cache_done(block_group);
if (unlikely(!cached)) {
found_uncached_bg = true;
- ret = cache_block_group(block_group, trans,
- orig_root, 0);
+ ret = cache_block_group(block_group, 0);
BUG_ON(ret < 0);
ret = 0;
}
@@ -5694,6 +5904,7 @@
* lets look there
*/
if (last_ptr) {
+ unsigned long aligned_cluster;
/*
* the refill lock keeps out other
* people trying to start a new cluster
@@ -5760,11 +5971,15 @@
goto unclustered_alloc;
}
+ aligned_cluster = max_t(unsigned long,
+ empty_cluster + empty_size,
+ block_group->full_stripe_len);
+
/* allocate a cluster in this block group */
ret = btrfs_find_space_cluster(trans, root,
block_group, last_ptr,
search_start, num_bytes,
- empty_cluster + empty_size);
+ aligned_cluster);
if (ret == 0) {
/*
* now pull our allocation out of this
@@ -5835,7 +6050,8 @@
goto loop;
}
checks:
- search_start = stripe_align(root, offset);
+ search_start = stripe_align(root, used_block_group,
+ offset, num_bytes);
/* move on to the next group */
if (search_start + num_bytes >
@@ -5986,7 +6202,7 @@
if (ret == -ENOSPC) {
if (!final_tried) {
num_bytes = num_bytes >> 1;
- num_bytes = num_bytes & ~(root->sectorsize - 1);
+ num_bytes = round_down(num_bytes, root->sectorsize);
num_bytes = max(num_bytes, min_alloc_size);
if (num_bytes == min_alloc_size)
final_tried = true;
@@ -6110,7 +6326,7 @@
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_free_path(path);
- ret = update_block_group(trans, root, ins->objectid, ins->offset, 1);
+ ret = update_block_group(root, ins->objectid, ins->offset, 1);
if (ret) { /* -ENOENT, logic error */
printk(KERN_ERR "btrfs update block group failed for %llu "
"%llu\n", (unsigned long long)ins->objectid,
@@ -6174,7 +6390,7 @@
btrfs_mark_buffer_dirty(leaf);
btrfs_free_path(path);
- ret = update_block_group(trans, root, ins->objectid, ins->offset, 1);
+ ret = update_block_group(root, ins->objectid, ins->offset, 1);
if (ret) { /* -ENOENT, logic error */
printk(KERN_ERR "btrfs update block group failed for %llu "
"%llu\n", (unsigned long long)ins->objectid,
@@ -6217,7 +6433,7 @@
u64 num_bytes = ins->offset;
block_group = btrfs_lookup_block_group(root->fs_info, ins->objectid);
- cache_block_group(block_group, trans, NULL, 0);
+ cache_block_group(block_group, 0);
caching_ctl = get_caching_control(block_group);
if (!caching_ctl) {
@@ -6331,12 +6547,14 @@
if (!ret)
return block_rsv;
if (ret && !block_rsv->failfast) {
- static DEFINE_RATELIMIT_STATE(_rs,
- DEFAULT_RATELIMIT_INTERVAL,
- /*DEFAULT_RATELIMIT_BURST*/ 2);
- if (__ratelimit(&_rs))
- WARN(1, KERN_DEBUG "btrfs: block rsv returned %d\n",
- ret);
+ if (btrfs_test_opt(root, ENOSPC_DEBUG)) {
+ static DEFINE_RATELIMIT_STATE(_rs,
+ DEFAULT_RATELIMIT_INTERVAL * 10,
+ /*DEFAULT_RATELIMIT_BURST*/ 1);
+ if (__ratelimit(&_rs))
+ WARN(1, KERN_DEBUG
+ "btrfs: block rsv returned %d\n", ret);
+ }
ret = reserve_metadata_bytes(root, block_rsv, blocksize,
BTRFS_RESERVE_NO_FLUSH);
if (!ret) {
@@ -6402,7 +6620,7 @@
if (root_objectid != BTRFS_TREE_LOG_OBJECTID) {
struct btrfs_delayed_extent_op *extent_op;
- extent_op = kmalloc(sizeof(*extent_op), GFP_NOFS);
+ extent_op = btrfs_alloc_delayed_extent_op();
BUG_ON(!extent_op); /* -ENOMEM */
if (key)
memcpy(&extent_op->key, key, sizeof(extent_op->key));
@@ -6524,7 +6742,7 @@
}
/*
- * hepler to process tree block while walking down the tree.
+ * helper to process tree block while walking down the tree.
*
* when wc->stage == UPDATE_BACKREF, this function updates
* back refs for pointers in the block.
@@ -6599,7 +6817,7 @@
}
/*
- * hepler to process tree block pointer.
+ * helper to process tree block pointer.
*
* when wc->stage == DROP_REFERENCE, this function checks
* reference count of the block pointed to. if the block
@@ -6737,7 +6955,7 @@
}
/*
- * hepler to process tree block while walking up the tree.
+ * helper to process tree block while walking up the tree.
*
* when wc->stage == DROP_REFERENCE, this function drops
* reference count on the block.
@@ -7205,6 +7423,7 @@
root->fs_info->fs_devices->missing_devices;
stripped = BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
if (num_devices == 1) {
@@ -7483,16 +7702,16 @@
index = get_block_group_index(block_group);
}
- if (index == 0) {
+ if (index == BTRFS_RAID_RAID10) {
dev_min = 4;
/* Divide by 2 */
min_free >>= 1;
- } else if (index == 1) {
+ } else if (index == BTRFS_RAID_RAID1) {
dev_min = 2;
- } else if (index == 2) {
+ } else if (index == BTRFS_RAID_DUP) {
/* Multiply by 2 */
min_free <<= 1;
- } else if (index == 3) {
+ } else if (index == BTRFS_RAID_RAID0) {
dev_min = fs_devices->rw_devices;
do_div(min_free, dev_min);
}
@@ -7653,11 +7872,13 @@
space_info = list_entry(info->space_info.next,
struct btrfs_space_info,
list);
- if (space_info->bytes_pinned > 0 ||
- space_info->bytes_reserved > 0 ||
- space_info->bytes_may_use > 0) {
- WARN_ON(1);
- dump_space_info(space_info, 0, 0);
+ if (btrfs_test_opt(info->tree_root, ENOSPC_DEBUG)) {
+ if (space_info->bytes_pinned > 0 ||
+ space_info->bytes_reserved > 0 ||
+ space_info->bytes_may_use > 0) {
+ WARN_ON(1);
+ dump_space_info(space_info, 0, 0);
+ }
}
list_del(&space_info->list);
kfree(space_info);
@@ -7756,7 +7977,9 @@
btrfs_release_path(path);
cache->flags = btrfs_block_group_flags(&cache->item);
cache->sectorsize = root->sectorsize;
-
+ cache->full_stripe_len = btrfs_full_stripe_len(root,
+ &root->fs_info->mapping_tree,
+ found_key.objectid);
btrfs_init_free_space_ctl(cache);
/*
@@ -7764,7 +7987,17 @@
* info has super bytes accounted for, otherwise we'll think
* we have more space than we actually do.
*/
- exclude_super_stripes(root, cache);
+ ret = exclude_super_stripes(root, cache);
+ if (ret) {
+ /*
+ * We may have excluded something, so call this just in
+ * case.
+ */
+ free_excluded_extents(root, cache);
+ kfree(cache->free_space_ctl);
+ kfree(cache);
+ goto error;
+ }
/*
* check for two cases, either we are full, and therefore
@@ -7810,6 +8043,8 @@
if (!(get_alloc_profile(root, space_info->flags) &
(BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6 |
BTRFS_BLOCK_GROUP_DUP)))
continue;
/*
@@ -7885,6 +8120,9 @@
cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
cache->sectorsize = root->sectorsize;
cache->fs_info = root->fs_info;
+ cache->full_stripe_len = btrfs_full_stripe_len(root,
+ &root->fs_info->mapping_tree,
+ chunk_offset);
atomic_set(&cache->count, 1);
spin_lock_init(&cache->lock);
@@ -7901,7 +8139,17 @@
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
- exclude_super_stripes(root, cache);
+ ret = exclude_super_stripes(root, cache);
+ if (ret) {
+ /*
+ * We may have excluded something, so call this just in
+ * case.
+ */
+ free_excluded_extents(root, cache);
+ kfree(cache->free_space_ctl);
+ kfree(cache);
+ return ret;
+ }
add_new_free_space(cache, root->fs_info, chunk_offset,
chunk_offset + size);
@@ -7934,12 +8182,14 @@
u64 extra_flags = chunk_to_extended(flags) &
BTRFS_EXTENDED_PROFILE_MASK;
+ write_seqlock(&fs_info->profiles_lock);
if (flags & BTRFS_BLOCK_GROUP_DATA)
fs_info->avail_data_alloc_bits &= ~extra_flags;
if (flags & BTRFS_BLOCK_GROUP_METADATA)
fs_info->avail_metadata_alloc_bits &= ~extra_flags;
if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
fs_info->avail_system_alloc_bits &= ~extra_flags;
+ write_sequnlock(&fs_info->profiles_lock);
}
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
@@ -8038,6 +8288,9 @@
spin_lock(&root->fs_info->block_group_cache_lock);
rb_erase(&block_group->cache_node,
&root->fs_info->block_group_cache_tree);
+
+ if (root->fs_info->first_logical_byte == block_group->key.objectid)
+ root->fs_info->first_logical_byte = (u64)-1;
spin_unlock(&root->fs_info->block_group_cache_lock);
down_write(&block_group->space_info->groups_sem);
@@ -8160,7 +8413,7 @@
if (end - start >= range->minlen) {
if (!block_group_cache_done(cache)) {
- ret = cache_block_group(cache, NULL, root, 0);
+ ret = cache_block_group(cache, 0);
if (!ret)
wait_block_group_cache_done(cache);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1b319df..cdee391 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4,7 +4,6 @@
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/page-flags.h>
-#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
@@ -1258,6 +1257,39 @@
GFP_NOFS);
}
+int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+ unsigned long index = start >> PAGE_CACHE_SHIFT;
+ unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ struct page *page;
+
+ while (index <= end_index) {
+ page = find_get_page(inode->i_mapping, index);
+ BUG_ON(!page); /* Pages should be in the extent_io_tree */
+ clear_page_dirty_for_io(page);
+ page_cache_release(page);
+ index++;
+ }
+ return 0;
+}
+
+int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
+{
+ unsigned long index = start >> PAGE_CACHE_SHIFT;
+ unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ struct page *page;
+
+ while (index <= end_index) {
+ page = find_get_page(inode->i_mapping, index);
+ BUG_ON(!page); /* Pages should be in the extent_io_tree */
+ account_page_redirty(page);
+ __set_page_dirty_nobuffers(page);
+ page_cache_release(page);
+ index++;
+ }
+ return 0;
+}
+
/*
* helper function to set both pages and extents in the tree writeback
*/
@@ -1834,7 +1866,7 @@
*/
static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
{
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL))
SetPageUptodate(page);
@@ -1846,7 +1878,7 @@
*/
static void check_page_locked(struct extent_io_tree *tree, struct page *page)
{
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
if (!test_range_bit(tree, start, end, EXTENT_LOCKED, 0, NULL))
unlock_page(page);
@@ -1895,13 +1927,11 @@
if (ret)
err = ret;
- if (did_repair) {
- ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
- rec->start + rec->len - 1,
- EXTENT_DAMAGED, GFP_NOFS);
- if (ret && !err)
- err = ret;
- }
+ ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
+ rec->start + rec->len - 1,
+ EXTENT_DAMAGED, GFP_NOFS);
+ if (ret && !err)
+ err = ret;
kfree(rec);
return err;
@@ -1932,10 +1962,15 @@
u64 map_length = 0;
u64 sector;
struct btrfs_bio *bbio = NULL;
+ struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
int ret;
BUG_ON(!mirror_num);
+ /* we can't repair anything in raid56 yet */
+ if (btrfs_is_parity_mirror(map_tree, logical, length, mirror_num))
+ return 0;
+
bio = bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
@@ -1960,7 +1995,7 @@
return -EIO;
}
bio->bi_bdev = dev->bdev;
- bio_add_page(bio, page, length, start-page_offset(page));
+ bio_add_page(bio, page, length, start - page_offset(page));
btrfsic_submit_bio(WRITE_SYNC, bio);
wait_for_completion(&compl);
@@ -2052,6 +2087,7 @@
failrec->failed_mirror);
did_repair = !ret;
}
+ ret = 0;
}
out:
@@ -2293,8 +2329,7 @@
struct page *page = bvec->bv_page;
tree = &BTRFS_I(page->mapping->host)->io_tree;
- start = ((u64)page->index << PAGE_CACHE_SHIFT) +
- bvec->bv_offset;
+ start = page_offset(page) + bvec->bv_offset;
end = start + bvec->bv_len - 1;
if (bvec->bv_offset == 0 && bvec->bv_len == PAGE_CACHE_SIZE)
@@ -2353,8 +2388,7 @@
(long int)bio->bi_bdev);
tree = &BTRFS_I(page->mapping->host)->io_tree;
- start = ((u64)page->index << PAGE_CACHE_SHIFT) +
- bvec->bv_offset;
+ start = page_offset(page) + bvec->bv_offset;
end = start + bvec->bv_len - 1;
if (bvec->bv_offset == 0 && bvec->bv_len == PAGE_CACHE_SIZE)
@@ -2471,7 +2505,7 @@
struct extent_io_tree *tree = bio->bi_private;
u64 start;
- start = ((u64)page->index << PAGE_CACHE_SHIFT) + bvec->bv_offset;
+ start = page_offset(page) + bvec->bv_offset;
bio->bi_private = NULL;
@@ -2489,13 +2523,13 @@
return ret;
}
-static int merge_bio(struct extent_io_tree *tree, struct page *page,
+static int merge_bio(int rw, struct extent_io_tree *tree, struct page *page,
unsigned long offset, size_t size, struct bio *bio,
unsigned long bio_flags)
{
int ret = 0;
if (tree->ops && tree->ops->merge_bio_hook)
- ret = tree->ops->merge_bio_hook(page, offset, size, bio,
+ ret = tree->ops->merge_bio_hook(rw, page, offset, size, bio,
bio_flags);
BUG_ON(ret < 0);
return ret;
@@ -2530,7 +2564,7 @@
sector;
if (prev_bio_flags != bio_flags || !contig ||
- merge_bio(tree, page, offset, page_size, bio, bio_flags) ||
+ merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
bio_add_page(bio, page, page_size, offset) < page_size) {
ret = submit_one_bio(rw, bio, mirror_num,
prev_bio_flags);
@@ -2595,7 +2629,7 @@
unsigned long *bio_flags)
{
struct inode *inode = page->mapping->host;
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 page_end = start + PAGE_CACHE_SIZE - 1;
u64 end;
u64 cur = start;
@@ -2648,6 +2682,8 @@
}
}
while (cur <= end) {
+ unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+
if (cur >= last_byte) {
char *userpage;
struct extent_state *cached = NULL;
@@ -2682,7 +2718,7 @@
iosize = min(extent_map_end(em) - cur, end - cur + 1);
cur_end = min(extent_map_end(em) - 1, end);
- iosize = (iosize + blocksize - 1) & ~((u64)blocksize - 1);
+ iosize = ALIGN(iosize, blocksize);
if (this_bio_flag & EXTENT_BIO_COMPRESSED) {
disk_io_size = em->block_len;
sector = em->block_start >> 9;
@@ -2735,26 +2771,17 @@
continue;
}
- ret = 0;
- if (tree->ops && tree->ops->readpage_io_hook) {
- ret = tree->ops->readpage_io_hook(page, cur,
- cur + iosize - 1);
- }
- if (!ret) {
- unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
- pnr -= page->index;
- ret = submit_extent_page(READ, tree, page,
+ pnr -= page->index;
+ ret = submit_extent_page(READ, tree, page,
sector, disk_io_size, pg_offset,
bdev, bio, pnr,
end_bio_extent_readpage, mirror_num,
*bio_flags,
this_bio_flag);
- if (!ret) {
- nr++;
- *bio_flags = this_bio_flag;
- }
- }
- if (ret) {
+ if (!ret) {
+ nr++;
+ *bio_flags = this_bio_flag;
+ } else {
SetPageError(page);
unlock_extent(tree, cur, cur + iosize - 1);
}
@@ -2806,7 +2833,7 @@
struct inode *inode = page->mapping->host;
struct extent_page_data *epd = data;
struct extent_io_tree *tree = epd->tree;
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 delalloc_start;
u64 page_end = start + PAGE_CACHE_SIZE - 1;
u64 end;
@@ -2982,7 +3009,7 @@
BUG_ON(extent_map_end(em) <= cur);
BUG_ON(end < cur);
iosize = min(extent_map_end(em) - cur, end - cur + 1);
- iosize = (iosize + blocksize - 1) & ~((u64)blocksize - 1);
+ iosize = ALIGN(iosize, blocksize);
sector = (em->block_start + extent_offset) >> 9;
bdev = em->bdev;
block_start = em->block_start;
@@ -3124,12 +3151,9 @@
set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
spin_unlock(&eb->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
- spin_lock(&fs_info->delalloc_lock);
- if (fs_info->dirty_metadata_bytes >= eb->len)
- fs_info->dirty_metadata_bytes -= eb->len;
- else
- WARN_ON(1);
- spin_unlock(&fs_info->delalloc_lock);
+ __percpu_counter_add(&fs_info->dirty_metadata_bytes,
+ -eb->len,
+ fs_info->dirty_metadata_batch);
ret = 1;
} else {
spin_unlock(&eb->refs_lock);
@@ -3446,15 +3470,9 @@
* swizzled back from swapper_space to tmpfs file
* mapping
*/
- if (tree->ops &&
- tree->ops->write_cache_pages_lock_hook) {
- tree->ops->write_cache_pages_lock_hook(page,
- data, flush_fn);
- } else {
- if (!trylock_page(page)) {
- flush_fn(data);
- lock_page(page);
- }
+ if (!trylock_page(page)) {
+ flush_fn(data);
+ lock_page(page);
}
if (unlikely(page->mapping != mapping)) {
@@ -3674,11 +3692,11 @@
struct page *page, unsigned long offset)
{
struct extent_state *cached_state = NULL;
- u64 start = ((u64)page->index << PAGE_CACHE_SHIFT);
+ u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
size_t blocksize = page->mapping->host->i_sb->s_blocksize;
- start += (offset + blocksize - 1) & ~(blocksize - 1);
+ start += ALIGN(offset, blocksize);
if (start > end)
return 0;
@@ -3700,7 +3718,7 @@
struct extent_io_tree *tree, struct page *page,
gfp_t mask)
{
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
int ret = 1;
@@ -3739,7 +3757,7 @@
gfp_t mask)
{
struct extent_map *em;
- u64 start = (u64)page->index << PAGE_CACHE_SHIFT;
+ u64 start = page_offset(page);
u64 end = start + PAGE_CACHE_SIZE - 1;
if ((mask & __GFP_WAIT) &&
@@ -3797,7 +3815,7 @@
len = last - offset;
if (len == 0)
break;
- len = (len + sectorsize - 1) & ~(sectorsize - 1);
+ len = ALIGN(len, sectorsize);
em = get_extent(inode, NULL, 0, offset, len, 0);
if (IS_ERR_OR_NULL(em))
return em;
@@ -3995,8 +4013,6 @@
list_del(&eb->leak_list);
spin_unlock_irqrestore(&leak_lock, flags);
#endif
- if (eb->pages && eb->pages != eb->inline_pages)
- kfree(eb->pages);
kmem_cache_free(extent_buffer_cache, eb);
}
@@ -4037,19 +4053,12 @@
atomic_set(&eb->refs, 1);
atomic_set(&eb->io_pages, 0);
- if (len > MAX_INLINE_EXTENT_BUFFER_SIZE) {
- struct page **pages;
- int num_pages = (len + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
- pages = kzalloc(num_pages, mask);
- if (!pages) {
- __free_extent_buffer(eb);
- return NULL;
- }
- eb->pages = pages;
- } else {
- eb->pages = eb->inline_pages;
- }
+ /*
+ * Sanity checks, currently the maximum is 64k covered by 16x 4k pages
+ */
+ BUILD_BUG_ON(BTRFS_MAX_METADATA_BLOCKSIZE
+ > MAX_INLINE_EXTENT_BUFFER_SIZE);
+ BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE);
return eb;
}
@@ -4180,6 +4189,7 @@
static void check_buffer_tree_ref(struct extent_buffer *eb)
{
+ int refs;
/* the ref bit is tricky. We have to make sure it is set
* if we have the buffer dirty. Otherwise the
* code to free a buffer can end up dropping a dirty
@@ -4200,6 +4210,10 @@
* So bump the ref count first, then set the bit. If someone
* beat us to it, drop the ref we added.
*/
+ refs = atomic_read(&eb->refs);
+ if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
+ return;
+
spin_lock(&eb->refs_lock);
if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
atomic_inc(&eb->refs);
@@ -4401,9 +4415,20 @@
void free_extent_buffer(struct extent_buffer *eb)
{
+ int refs;
+ int old;
if (!eb)
return;
+ while (1) {
+ refs = atomic_read(&eb->refs);
+ if (refs <= 3)
+ break;
+ old = atomic_cmpxchg(&eb->refs, refs, refs - 1);
+ if (old == refs)
+ return;
+ }
+
spin_lock(&eb->refs_lock);
if (atomic_read(&eb->refs) == 2 &&
test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 2eacfab..258c921 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -72,10 +72,9 @@
int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
int (*writepage_io_hook)(struct page *page, u64 start, u64 end);
extent_submit_bio_hook_t *submit_bio_hook;
- int (*merge_bio_hook)(struct page *page, unsigned long offset,
+ int (*merge_bio_hook)(int rw, struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags);
- int (*readpage_io_hook)(struct page *page, u64 start, u64 end);
int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end,
struct extent_state *state, int mirror);
@@ -90,8 +89,6 @@
struct extent_state *other);
void (*split_extent_hook)(struct inode *inode,
struct extent_state *orig, u64 split);
- int (*write_cache_pages_lock_hook)(struct page *page, void *data,
- void (*flush_fn)(void *));
};
struct extent_io_tree {
@@ -161,8 +158,7 @@
*/
wait_queue_head_t read_lock_wq;
wait_queue_head_t lock_wq;
- struct page *inline_pages[INLINE_EXTENT_BUFFER_PAGES];
- struct page **pages;
+ struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
};
static inline void extent_set_compress_type(unsigned long *bio_flags,
@@ -329,6 +325,8 @@
unsigned long *map_len);
int extent_range_uptodate(struct extent_io_tree *tree,
u64 start, u64 end);
+int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
+int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
int extent_clear_unlock_delalloc(struct inode *inode,
struct extent_io_tree *tree,
u64 start, u64 end, struct page *locked_page,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 2e8cae6..2834ca5 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1,6 +1,5 @@
#include <linux/err.h>
#include <linux/slab.h>
-#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/hardirq.h>
#include "ctree.h"
@@ -288,7 +287,8 @@
void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em)
{
clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
- try_merge_map(tree, em);
+ if (em->in_tree)
+ try_merge_map(tree, em);
}
/**
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 94aa53b..c4628a2 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -118,9 +118,11 @@
csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]);
csums_in_item /= csum_size;
- if (csum_offset >= csums_in_item) {
+ if (csum_offset == csums_in_item) {
ret = -EFBIG;
goto fail;
+ } else if (csum_offset > csums_in_item) {
+ goto fail;
}
}
item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item);
@@ -684,6 +686,24 @@
return ret;
}
+static u64 btrfs_sector_sum_left(struct btrfs_ordered_sum *sums,
+ struct btrfs_sector_sum *sector_sum,
+ u64 total_bytes, u64 sectorsize)
+{
+ u64 tmp = sectorsize;
+ u64 next_sector = sector_sum->bytenr;
+ struct btrfs_sector_sum *next = sector_sum + 1;
+
+ while ((tmp + total_bytes) < sums->len) {
+ if (next_sector + sectorsize != next->bytenr)
+ break;
+ tmp += sectorsize;
+ next_sector = next->bytenr;
+ next++;
+ }
+ return tmp;
+}
+
int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_ordered_sum *sums)
@@ -710,7 +730,6 @@
return -ENOMEM;
sector_sum = sums->sums;
- trans->adding_csums = 1;
again:
next_offset = (u64)-1;
found_next = 0;
@@ -789,20 +808,32 @@
goto insert;
}
- if (csum_offset >= btrfs_item_size_nr(leaf, path->slots[0]) /
+ if (csum_offset == btrfs_item_size_nr(leaf, path->slots[0]) /
csum_size) {
- u32 diff = (csum_offset + 1) * csum_size;
+ int extend_nr;
+ u64 tmp;
+ u32 diff;
+ u32 free_space;
- /*
- * is the item big enough already? we dropped our lock
- * before and need to recheck
- */
- if (diff < btrfs_item_size_nr(leaf, path->slots[0]))
- goto csum;
+ if (btrfs_leaf_free_space(root, leaf) <
+ sizeof(struct btrfs_item) + csum_size * 2)
+ goto insert;
+
+ free_space = btrfs_leaf_free_space(root, leaf) -
+ sizeof(struct btrfs_item) - csum_size;
+ tmp = btrfs_sector_sum_left(sums, sector_sum, total_bytes,
+ root->sectorsize);
+ tmp >>= root->fs_info->sb->s_blocksize_bits;
+ WARN_ON(tmp < 1);
+
+ extend_nr = max_t(int, 1, (int)tmp);
+ diff = (csum_offset + extend_nr) * csum_size;
+ diff = min(diff, MAX_CSUM_ITEMS(root, csum_size) * csum_size);
diff = diff - btrfs_item_size_nr(leaf, path->slots[0]);
- if (diff != csum_size)
- goto insert;
+ diff = min(free_space, diff);
+ diff /= csum_size;
+ diff *= csum_size;
btrfs_extend_item(trans, root, path, diff);
goto csum;
@@ -812,19 +843,14 @@
btrfs_release_path(path);
csum_offset = 0;
if (found_next) {
- u64 tmp = total_bytes + root->sectorsize;
- u64 next_sector = sector_sum->bytenr;
- struct btrfs_sector_sum *next = sector_sum + 1;
+ u64 tmp;
- while (tmp < sums->len) {
- if (next_sector + root->sectorsize != next->bytenr)
- break;
- tmp += root->sectorsize;
- next_sector = next->bytenr;
- next++;
- }
- tmp = min(tmp, next_offset - file_key.offset);
+ tmp = btrfs_sector_sum_left(sums, sector_sum, total_bytes,
+ root->sectorsize);
tmp >>= root->fs_info->sb->s_blocksize_bits;
+ tmp = min(tmp, (next_offset - file_key.offset) >>
+ root->fs_info->sb->s_blocksize_bits);
+
tmp = max((u64)1, tmp);
tmp = min(tmp, (u64)MAX_CSUM_ITEMS(root, csum_size));
ins_size = csum_size * tmp;
@@ -874,7 +900,6 @@
goto again;
}
out:
- trans->adding_csums = 0;
btrfs_free_path(path);
return ret;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f76b1fd..ade03e6 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -30,11 +30,11 @@
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/slab.h>
+#include <linux/btrfs.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
-#include "ioctl.h"
#include "print-tree.h"
#include "tree-log.h"
#include "locking.h"
@@ -293,15 +293,24 @@
struct btrfs_key key;
struct btrfs_ioctl_defrag_range_args range;
int num_defrag;
+ int index;
+ int ret;
/* get the inode */
key.objectid = defrag->root;
btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
key.offset = (u64)-1;
+
+ index = srcu_read_lock(&fs_info->subvol_srcu);
+
inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
if (IS_ERR(inode_root)) {
- kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
- return PTR_ERR(inode_root);
+ ret = PTR_ERR(inode_root);
+ goto cleanup;
+ }
+ if (btrfs_root_refs(&inode_root->root_item) == 0) {
+ ret = -ENOENT;
+ goto cleanup;
}
key.objectid = defrag->ino;
@@ -309,9 +318,10 @@
key.offset = 0;
inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
if (IS_ERR(inode)) {
- kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
- return PTR_ERR(inode);
+ ret = PTR_ERR(inode);
+ goto cleanup;
}
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
/* do a chunk of defrag */
clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
@@ -346,6 +356,10 @@
iput(inode);
return 0;
+cleanup:
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
+ return ret;
}
/*
@@ -360,6 +374,11 @@
atomic_inc(&fs_info->defrag_running);
while(1) {
+ /* Pause the auto defragger. */
+ if (test_bit(BTRFS_FS_STATE_REMOUNTING,
+ &fs_info->fs_state))
+ break;
+
if (!__need_auto_defrag(fs_info->tree_root))
break;
@@ -491,8 +510,7 @@
loff_t isize = i_size_read(inode);
start_pos = pos & ~((u64)root->sectorsize - 1);
- num_bytes = (write_bytes + pos - start_pos +
- root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
+ num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
end_of_last_block = start_pos + num_bytes - 1;
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
@@ -573,6 +591,7 @@
}
compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ clear_bit(EXTENT_FLAG_LOGGING, &flags);
remove_extent_mapping(em_tree, em);
if (no_splits)
goto next;
@@ -1211,7 +1230,7 @@
struct extent_state *cached_state = NULL;
int i;
unsigned long index = pos >> PAGE_CACHE_SHIFT;
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
int err = 0;
int faili = 0;
@@ -1298,7 +1317,7 @@
struct iov_iter *i,
loff_t pos)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct page **pages = NULL;
unsigned long first_index;
@@ -1486,7 +1505,7 @@
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
loff_t *ppos = &iocb->ki_pos;
u64 start_pos;
@@ -1530,7 +1549,7 @@
* although we have opened a file as writable, we have
* to stop this write operation to ensure FS consistency.
*/
- if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
mutex_unlock(&inode->i_mutex);
err = -EROFS;
goto out;
@@ -1594,9 +1613,10 @@
if (err < 0 && num_written > 0)
num_written = err;
}
-out:
+
if (sync)
atomic_dec(&BTRFS_I(inode)->sync_writers);
+out:
sb_end_write(inode->i_sb);
current->backing_dev_info = NULL;
return num_written ? num_written : err;
@@ -1612,7 +1632,20 @@
*/
if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
&BTRFS_I(inode)->runtime_flags)) {
- btrfs_add_ordered_operation(NULL, BTRFS_I(inode)->root, inode);
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+
+ /*
+ * We need to block on a committing transaction to keep us from
+ * throwing a ordered operation on to the list and causing
+ * something like sync to deadlock trying to flush out this
+ * inode.
+ */
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ btrfs_add_ordered_operation(trans, BTRFS_I(inode)->root, inode);
+ btrfs_end_transaction(trans, root);
if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
filemap_flush(inode->i_mapping);
}
@@ -1639,16 +1672,21 @@
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
struct btrfs_trans_handle *trans;
+ bool full_sync = 0;
trace_btrfs_sync_file(file, datasync);
/*
* We write the dirty pages in the range and wait until they complete
* out of the ->i_mutex. If so, we can flush the dirty pages by
- * multi-task, and make the performance up.
+ * multi-task, and make the performance up. See
+ * btrfs_wait_ordered_range for an explanation of the ASYNC check.
*/
atomic_inc(&BTRFS_I(inode)->sync_writers);
- ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
+ if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
+ &BTRFS_I(inode)->runtime_flags))
+ ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
atomic_dec(&BTRFS_I(inode)->sync_writers);
if (ret)
return ret;
@@ -1660,7 +1698,10 @@
* range being left.
*/
atomic_inc(&root->log_batch);
- btrfs_wait_ordered_range(inode, start, end - start + 1);
+ full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+ &BTRFS_I(inode)->runtime_flags);
+ if (full_sync)
+ btrfs_wait_ordered_range(inode, start, end - start + 1);
atomic_inc(&root->log_batch);
/*
@@ -1727,13 +1768,25 @@
if (ret != BTRFS_NO_LOG_SYNC) {
if (ret > 0) {
+ /*
+ * If we didn't already wait for ordered extents we need
+ * to do that now.
+ */
+ if (!full_sync)
+ btrfs_wait_ordered_range(inode, start,
+ end - start + 1);
ret = btrfs_commit_transaction(trans, root);
} else {
ret = btrfs_sync_log(trans, root);
- if (ret == 0)
+ if (ret == 0) {
ret = btrfs_end_transaction(trans, root);
- else
+ } else {
+ if (!full_sync)
+ btrfs_wait_ordered_range(inode, start,
+ end -
+ start + 1);
ret = btrfs_commit_transaction(trans, root);
+ }
}
} else {
ret = btrfs_end_transaction(trans, root);
@@ -2087,8 +2140,9 @@
static long btrfs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct extent_state *cached_state = NULL;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
u64 cur_offset;
u64 last_byte;
u64 alloc_start;
@@ -2116,6 +2170,11 @@
ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
if (ret)
return ret;
+ if (root->fs_info->quota_enabled) {
+ ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start);
+ if (ret)
+ goto out_reserve_fail;
+ }
/*
* wait for ordered IO before we have any locks. We'll loop again
@@ -2219,6 +2278,9 @@
&cached_state, GFP_NOFS);
out:
mutex_unlock(&inode->i_mutex);
+ if (root->fs_info->quota_enabled)
+ btrfs_qgroup_free(root, alloc_end - alloc_start);
+out_reserve_fail:
/* Let go of our reservation. */
btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
return ret;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 0be7a87..1f84fc0 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1356,6 +1356,8 @@
u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
int max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
+ max_bitmaps = max(max_bitmaps, 1);
+
BUG_ON(ctl->total_bitmaps > max_bitmaps);
/*
@@ -1463,10 +1465,14 @@
}
static struct btrfs_free_space *
-find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes)
+find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
+ unsigned long align)
{
struct btrfs_free_space *entry;
struct rb_node *node;
+ u64 ctl_off;
+ u64 tmp;
+ u64 align_off;
int ret;
if (!ctl->free_space_offset.rb_node)
@@ -1481,15 +1487,34 @@
if (entry->bytes < *bytes)
continue;
+ /* make sure the space returned is big enough
+ * to match our requested alignment
+ */
+ if (*bytes >= align) {
+ ctl_off = entry->offset - ctl->start;
+ tmp = ctl_off + align - 1;;
+ do_div(tmp, align);
+ tmp = tmp * align + ctl->start;
+ align_off = tmp - entry->offset;
+ } else {
+ align_off = 0;
+ tmp = entry->offset;
+ }
+
+ if (entry->bytes < *bytes + align_off)
+ continue;
+
if (entry->bitmap) {
- ret = search_bitmap(ctl, entry, offset, bytes);
- if (!ret)
+ ret = search_bitmap(ctl, entry, &tmp, bytes);
+ if (!ret) {
+ *offset = tmp;
return entry;
+ }
continue;
}
- *offset = entry->offset;
- *bytes = entry->bytes;
+ *offset = tmp;
+ *bytes = entry->bytes - align_off;
return entry;
}
@@ -1636,10 +1661,14 @@
}
/*
- * some block groups are so tiny they can't be enveloped by a bitmap, so
- * don't even bother to create a bitmap for this
+ * The original block groups from mkfs can be really small, like 8
+ * megabytes, so don't bother with a bitmap for those entries. However
+ * some block groups can be smaller than what a bitmap would cover but
+ * are still large enough that they could overflow the 32k memory limit,
+ * so allow those block groups to still be allowed to have a bitmap
+ * entry.
*/
- if (BITS_PER_BITMAP * ctl->unit > block_group->key.offset)
+ if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->key.offset)
return false;
return true;
@@ -2095,9 +2124,12 @@
struct btrfs_free_space *entry = NULL;
u64 bytes_search = bytes + empty_size;
u64 ret = 0;
+ u64 align_gap = 0;
+ u64 align_gap_len = 0;
spin_lock(&ctl->tree_lock);
- entry = find_free_space(ctl, &offset, &bytes_search);
+ entry = find_free_space(ctl, &offset, &bytes_search,
+ block_group->full_stripe_len);
if (!entry)
goto out;
@@ -2107,9 +2139,15 @@
if (!entry->bytes)
free_bitmap(ctl, entry);
} else {
+
unlink_free_space(ctl, entry);
- entry->offset += bytes;
- entry->bytes -= bytes;
+ align_gap_len = offset - entry->offset;
+ align_gap = entry->offset;
+
+ entry->offset = offset + bytes;
+ WARN_ON(entry->bytes < bytes + align_gap_len);
+
+ entry->bytes -= bytes + align_gap_len;
if (!entry->bytes)
kmem_cache_free(btrfs_free_space_cachep, entry);
else
@@ -2119,6 +2157,8 @@
out:
spin_unlock(&ctl->tree_lock);
+ if (align_gap_len)
+ __btrfs_add_free_space(ctl, align_gap, align_gap_len);
return ret;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cc93b23..09c58a3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -39,12 +39,13 @@
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/mount.h>
+#include <linux/btrfs.h>
+#include <linux/blkdev.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
-#include "ioctl.h"
#include "print-tree.h"
#include "ordered-data.h"
#include "xattr.h"
@@ -54,6 +55,7 @@
#include "locking.h"
#include "free-space-cache.h"
#include "inode-map.h"
+#include "backref.h"
struct btrfs_iget_args {
u64 ino;
@@ -231,8 +233,7 @@
u64 isize = i_size_read(inode);
u64 actual_end = min(end + 1, isize);
u64 inline_len = actual_end - start;
- u64 aligned_end = (end + root->sectorsize - 1) &
- ~((u64)root->sectorsize - 1);
+ u64 aligned_end = ALIGN(end, root->sectorsize);
u64 data_len = inline_len;
int ret;
@@ -265,6 +266,7 @@
return 1;
}
+ set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
btrfs_delalloc_release_metadata(inode, end + 1 - start);
btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
return 0;
@@ -351,6 +353,7 @@
int i;
int will_compress;
int compress_type = root->fs_info->compress_type;
+ int redirty = 0;
/* if this is a small write inside eof, kick off a defrag */
if ((end - start + 1) < 16 * 1024 &&
@@ -389,7 +392,7 @@
* a compressed extent to 128k.
*/
total_compressed = min(total_compressed, max_uncompressed);
- num_bytes = (end - start + blocksize) & ~(blocksize - 1);
+ num_bytes = ALIGN(end - start + 1, blocksize);
num_bytes = max(blocksize, num_bytes);
total_in = 0;
ret = 0;
@@ -413,6 +416,17 @@
if (BTRFS_I(inode)->force_compress)
compress_type = BTRFS_I(inode)->force_compress;
+ /*
+ * we need to call clear_page_dirty_for_io on each
+ * page in the range. Otherwise applications with the file
+ * mmap'd can wander in and change the page contents while
+ * we are compressing them.
+ *
+ * If the compression fails for any reason, we set the pages
+ * dirty again later on.
+ */
+ extent_range_clear_dirty_for_io(inode, start, end);
+ redirty = 1;
ret = btrfs_compress_pages(compress_type,
inode->i_mapping, start,
total_compressed, pages,
@@ -488,15 +502,13 @@
* up to a block size boundary so the allocator does sane
* things
*/
- total_compressed = (total_compressed + blocksize - 1) &
- ~(blocksize - 1);
+ total_compressed = ALIGN(total_compressed, blocksize);
/*
* one last check to make sure the compression is really a
* win, compare the page count read with the blocks on disk
*/
- total_in = (total_in + PAGE_CACHE_SIZE - 1) &
- ~(PAGE_CACHE_SIZE - 1);
+ total_in = ALIGN(total_in, PAGE_CACHE_SIZE);
if (total_compressed >= total_in) {
will_compress = 0;
} else {
@@ -554,6 +566,8 @@
__set_page_dirty_nobuffers(locked_page);
/* unlocked later on in the async handlers */
}
+ if (redirty)
+ extent_range_redirty_for_io(inode, start, end);
add_async_extent(async_cow, start, end - start + 1,
0, NULL, 0, BTRFS_COMPRESS_NONE);
*num_added += 1;
@@ -608,7 +622,7 @@
if (list_empty(&async_cow->extents))
return 0;
-
+again:
while (!list_empty(&async_cow->extents)) {
async_extent = list_entry(async_cow->extents.next,
struct async_extent, list);
@@ -648,6 +662,8 @@
async_extent->ram_size - 1,
btrfs_get_extent,
WB_SYNC_ALL);
+ else if (ret)
+ unlock_page(async_cow->locked_page);
kfree(async_extent);
cond_resched();
continue;
@@ -672,6 +688,7 @@
if (ret) {
int i;
+
for (i = 0; i < async_extent->nr_pages; i++) {
WARN_ON(async_extent->pages[i]->mapping);
page_cache_release(async_extent->pages[i]);
@@ -679,12 +696,10 @@
kfree(async_extent->pages);
async_extent->nr_pages = 0;
async_extent->pages = NULL;
- unlock_extent(io_tree, async_extent->start,
- async_extent->start +
- async_extent->ram_size - 1);
+
if (ret == -ENOSPC)
goto retry;
- goto out_free; /* JDM: Requeue? */
+ goto out_free;
}
/*
@@ -696,10 +711,13 @@
async_extent->ram_size - 1, 0);
em = alloc_extent_map();
- BUG_ON(!em); /* -ENOMEM */
+ if (!em)
+ goto out_free_reserve;
em->start = async_extent->start;
em->len = async_extent->ram_size;
em->orig_start = em->start;
+ em->mod_start = em->start;
+ em->mod_len = em->len;
em->block_start = ins.objectid;
em->block_len = ins.offset;
@@ -726,6 +744,9 @@
async_extent->ram_size - 1, 0);
}
+ if (ret)
+ goto out_free_reserve;
+
ret = btrfs_add_ordered_extent_compress(inode,
async_extent->start,
ins.objectid,
@@ -733,7 +754,8 @@
ins.offset,
BTRFS_ORDERED_COMPRESSED,
async_extent->compress_type);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ goto out_free_reserve;
/*
* clear dirty, set writeback and unlock the pages.
@@ -754,18 +776,30 @@
ins.objectid,
ins.offset, async_extent->pages,
async_extent->nr_pages);
-
- BUG_ON(ret); /* -ENOMEM */
alloc_hint = ins.objectid + ins.offset;
kfree(async_extent);
+ if (ret)
+ goto out;
cond_resched();
}
ret = 0;
out:
return ret;
+out_free_reserve:
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
out_free:
+ extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
+ async_extent->start,
+ async_extent->start +
+ async_extent->ram_size - 1,
+ NULL, EXTENT_CLEAR_UNLOCK_PAGE |
+ EXTENT_CLEAR_UNLOCK |
+ EXTENT_CLEAR_DELALLOC |
+ EXTENT_CLEAR_DIRTY |
+ EXTENT_SET_WRITEBACK |
+ EXTENT_END_WRITEBACK);
kfree(async_extent);
- goto out;
+ goto again;
}
static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
@@ -834,7 +868,7 @@
BUG_ON(btrfs_is_free_space_inode(inode));
- num_bytes = (end - start + blocksize) & ~(blocksize - 1);
+ num_bytes = ALIGN(end - start + 1, blocksize);
num_bytes = max(blocksize, num_bytes);
disk_num_bytes = num_bytes;
@@ -892,6 +926,8 @@
em->orig_start = em->start;
ram_size = ins.offset;
em->len = ins.offset;
+ em->mod_start = em->start;
+ em->mod_len = em->len;
em->block_start = ins.objectid;
em->block_len = ins.offset;
@@ -1338,6 +1374,8 @@
em->block_start = disk_bytenr;
em->orig_block_len = disk_num_bytes;
em->bdev = root->fs_info->fs_devices->latest_bdev;
+ em->mod_start = em->start;
+ em->mod_len = em->len;
set_bit(EXTENT_FLAG_PINNED, &em->flags);
set_bit(EXTENT_FLAG_FILLING, &em->flags);
em->generation = -1;
@@ -1508,14 +1546,22 @@
spin_unlock(&BTRFS_I(inode)->lock);
}
- spin_lock(&root->fs_info->delalloc_lock);
+ __percpu_counter_add(&root->fs_info->delalloc_bytes, len,
+ root->fs_info->delalloc_batch);
+ spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->delalloc_bytes += len;
- root->fs_info->delalloc_bytes += len;
- if (do_list && list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
- list_add_tail(&BTRFS_I(inode)->delalloc_inodes,
- &root->fs_info->delalloc_inodes);
+ if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags)) {
+ spin_lock(&root->fs_info->delalloc_lock);
+ if (list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
+ list_add_tail(&BTRFS_I(inode)->delalloc_inodes,
+ &root->fs_info->delalloc_inodes);
+ set_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags);
+ }
+ spin_unlock(&root->fs_info->delalloc_lock);
}
- spin_unlock(&root->fs_info->delalloc_lock);
+ spin_unlock(&BTRFS_I(inode)->lock);
}
}
@@ -1550,15 +1596,22 @@
&& do_list)
btrfs_free_reserved_data_space(inode, len);
- spin_lock(&root->fs_info->delalloc_lock);
- root->fs_info->delalloc_bytes -= len;
+ __percpu_counter_add(&root->fs_info->delalloc_bytes, -len,
+ root->fs_info->delalloc_batch);
+ spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->delalloc_bytes -= len;
-
if (do_list && BTRFS_I(inode)->delalloc_bytes == 0 &&
- !list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
- list_del_init(&BTRFS_I(inode)->delalloc_inodes);
+ test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags)) {
+ spin_lock(&root->fs_info->delalloc_lock);
+ if (!list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
+ list_del_init(&BTRFS_I(inode)->delalloc_inodes);
+ clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags);
+ }
+ spin_unlock(&root->fs_info->delalloc_lock);
}
- spin_unlock(&root->fs_info->delalloc_lock);
+ spin_unlock(&BTRFS_I(inode)->lock);
}
}
@@ -1566,7 +1619,7 @@
* extent_io.c merge_bio_hook, this must check the chunk tree to make sure
* we don't create bios that span stripes or chunks
*/
-int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
+int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags)
{
@@ -1581,7 +1634,7 @@
length = bio->bi_size;
map_length = length;
- ret = btrfs_map_block(root->fs_info, READ, logical,
+ ret = btrfs_map_block(root->fs_info, rw, logical,
&map_length, NULL, 0);
/* Will always return 0 with map_multi == NULL */
BUG_ON(ret < 0);
@@ -1704,8 +1757,10 @@
struct btrfs_ordered_sum *sum;
list_for_each_entry(sum, list, list) {
+ trans->adding_csums = 1;
btrfs_csum_file_blocks(trans,
BTRFS_I(inode)->root->fs_info->csum_root, sum);
+ trans->adding_csums = 0;
}
return 0;
}
@@ -1892,6 +1947,643 @@
return ret;
}
+/* snapshot-aware defrag */
+struct sa_defrag_extent_backref {
+ struct rb_node node;
+ struct old_sa_defrag_extent *old;
+ u64 root_id;
+ u64 inum;
+ u64 file_pos;
+ u64 extent_offset;
+ u64 num_bytes;
+ u64 generation;
+};
+
+struct old_sa_defrag_extent {
+ struct list_head list;
+ struct new_sa_defrag_extent *new;
+
+ u64 extent_offset;
+ u64 bytenr;
+ u64 offset;
+ u64 len;
+ int count;
+};
+
+struct new_sa_defrag_extent {
+ struct rb_root root;
+ struct list_head head;
+ struct btrfs_path *path;
+ struct inode *inode;
+ u64 file_pos;
+ u64 len;
+ u64 bytenr;
+ u64 disk_len;
+ u8 compress_type;
+};
+
+static int backref_comp(struct sa_defrag_extent_backref *b1,
+ struct sa_defrag_extent_backref *b2)
+{
+ if (b1->root_id < b2->root_id)
+ return -1;
+ else if (b1->root_id > b2->root_id)
+ return 1;
+
+ if (b1->inum < b2->inum)
+ return -1;
+ else if (b1->inum > b2->inum)
+ return 1;
+
+ if (b1->file_pos < b2->file_pos)
+ return -1;
+ else if (b1->file_pos > b2->file_pos)
+ return 1;
+
+ /*
+ * [------------------------------] ===> (a range of space)
+ * |<--->| |<---->| =============> (fs/file tree A)
+ * |<---------------------------->| ===> (fs/file tree B)
+ *
+ * A range of space can refer to two file extents in one tree while
+ * refer to only one file extent in another tree.
+ *
+ * So we may process a disk offset more than one time(two extents in A)
+ * and locate at the same extent(one extent in B), then insert two same
+ * backrefs(both refer to the extent in B).
+ */
+ return 0;
+}
+
+static void backref_insert(struct rb_root *root,
+ struct sa_defrag_extent_backref *backref)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *parent = NULL;
+ struct sa_defrag_extent_backref *entry;
+ int ret;
+
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct sa_defrag_extent_backref, node);
+
+ ret = backref_comp(backref, entry);
+ if (ret < 0)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ rb_link_node(&backref->node, parent, p);
+ rb_insert_color(&backref->node, root);
+}
+
+/*
+ * Note the backref might has changed, and in this case we just return 0.
+ */
+static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
+ void *ctx)
+{
+ struct btrfs_file_extent_item *extent;
+ struct btrfs_fs_info *fs_info;
+ struct old_sa_defrag_extent *old = ctx;
+ struct new_sa_defrag_extent *new = old->new;
+ struct btrfs_path *path = new->path;
+ struct btrfs_key key;
+ struct btrfs_root *root;
+ struct sa_defrag_extent_backref *backref;
+ struct extent_buffer *leaf;
+ struct inode *inode = new->inode;
+ int slot;
+ int ret;
+ u64 extent_offset;
+ u64 num_bytes;
+
+ if (BTRFS_I(inode)->root->root_key.objectid == root_id &&
+ inum == btrfs_ino(inode))
+ return 0;
+
+ key.objectid = root_id;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ fs_info = BTRFS_I(inode)->root->fs_info;
+ root = btrfs_read_fs_root_no_name(fs_info, &key);
+ if (IS_ERR(root)) {
+ if (PTR_ERR(root) == -ENOENT)
+ return 0;
+ WARN_ON(1);
+ pr_debug("inum=%llu, offset=%llu, root_id=%llu\n",
+ inum, offset, root_id);
+ return PTR_ERR(root);
+ }
+
+ key.objectid = inum;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ if (offset > (u64)-1 << 32)
+ key.offset = 0;
+ else
+ key.offset = offset;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ WARN_ON(1);
+ return ret;
+ }
+
+ while (1) {
+ cond_resched();
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = 0;
+ goto out;
+ }
+ continue;
+ }
+
+ path->slots[0]++;
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+
+ if (key.objectid > inum)
+ goto out;
+
+ if (key.objectid < inum || key.type != BTRFS_EXTENT_DATA_KEY)
+ continue;
+
+ extent = btrfs_item_ptr(leaf, slot,
+ struct btrfs_file_extent_item);
+
+ if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr)
+ continue;
+
+ extent_offset = btrfs_file_extent_offset(leaf, extent);
+ if (key.offset - extent_offset != offset)
+ continue;
+
+ num_bytes = btrfs_file_extent_num_bytes(leaf, extent);
+ if (extent_offset >= old->extent_offset + old->offset +
+ old->len || extent_offset + num_bytes <=
+ old->extent_offset + old->offset)
+ continue;
+
+ break;
+ }
+
+ backref = kmalloc(sizeof(*backref), GFP_NOFS);
+ if (!backref) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ backref->root_id = root_id;
+ backref->inum = inum;
+ backref->file_pos = offset + extent_offset;
+ backref->num_bytes = num_bytes;
+ backref->extent_offset = extent_offset;
+ backref->generation = btrfs_file_extent_generation(leaf, extent);
+ backref->old = old;
+ backref_insert(&new->root, backref);
+ old->count++;
+out:
+ btrfs_release_path(path);
+ WARN_ON(ret);
+ return ret;
+}
+
+static noinline bool record_extent_backrefs(struct btrfs_path *path,
+ struct new_sa_defrag_extent *new)
+{
+ struct btrfs_fs_info *fs_info = BTRFS_I(new->inode)->root->fs_info;
+ struct old_sa_defrag_extent *old, *tmp;
+ int ret;
+
+ new->path = path;
+
+ list_for_each_entry_safe(old, tmp, &new->head, list) {
+ ret = iterate_inodes_from_logical(old->bytenr, fs_info,
+ path, record_one_backref,
+ old);
+ BUG_ON(ret < 0 && ret != -ENOENT);
+
+ /* no backref to be processed for this extent */
+ if (!old->count) {
+ list_del(&old->list);
+ kfree(old);
+ }
+ }
+
+ if (list_empty(&new->head))
+ return false;
+
+ return true;
+}
+
+static int relink_is_mergable(struct extent_buffer *leaf,
+ struct btrfs_file_extent_item *fi,
+ u64 disk_bytenr)
+{
+ if (btrfs_file_extent_disk_bytenr(leaf, fi) != disk_bytenr)
+ return 0;
+
+ if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG)
+ return 0;
+
+ if (btrfs_file_extent_compression(leaf, fi) ||
+ btrfs_file_extent_encryption(leaf, fi) ||
+ btrfs_file_extent_other_encoding(leaf, fi))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * Note the backref might has changed, and in this case we just return 0.
+ */
+static noinline int relink_extent_backref(struct btrfs_path *path,
+ struct sa_defrag_extent_backref *prev,
+ struct sa_defrag_extent_backref *backref)
+{
+ struct btrfs_file_extent_item *extent;
+ struct btrfs_file_extent_item *item;
+ struct btrfs_ordered_extent *ordered;
+ struct btrfs_trans_handle *trans;
+ struct btrfs_fs_info *fs_info;
+ struct btrfs_root *root;
+ struct btrfs_key key;
+ struct extent_buffer *leaf;
+ struct old_sa_defrag_extent *old = backref->old;
+ struct new_sa_defrag_extent *new = old->new;
+ struct inode *src_inode = new->inode;
+ struct inode *inode;
+ struct extent_state *cached = NULL;
+ int ret = 0;
+ u64 start;
+ u64 len;
+ u64 lock_start;
+ u64 lock_end;
+ bool merge = false;
+ int index;
+
+ if (prev && prev->root_id == backref->root_id &&
+ prev->inum == backref->inum &&
+ prev->file_pos + prev->num_bytes == backref->file_pos)
+ merge = true;
+
+ /* step 1: get root */
+ key.objectid = backref->root_id;
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ fs_info = BTRFS_I(src_inode)->root->fs_info;
+ index = srcu_read_lock(&fs_info->subvol_srcu);
+
+ root = btrfs_read_fs_root_no_name(fs_info, &key);
+ if (IS_ERR(root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ if (PTR_ERR(root) == -ENOENT)
+ return 0;
+ return PTR_ERR(root);
+ }
+ if (btrfs_root_refs(&root->root_item) == 0) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ /* parse ENOENT to 0 */
+ return 0;
+ }
+
+ /* step 2: get inode */
+ key.objectid = backref->inum;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+ if (IS_ERR(inode)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ return 0;
+ }
+
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+
+ /* step 3: relink backref */
+ lock_start = backref->file_pos;
+ lock_end = backref->file_pos + backref->num_bytes - 1;
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
+ 0, &cached);
+
+ ordered = btrfs_lookup_first_ordered_extent(inode, lock_end);
+ if (ordered) {
+ btrfs_put_ordered_extent(ordered);
+ goto out_unlock;
+ }
+
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_unlock;
+ }
+
+ key.objectid = backref->inum;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = backref->file_pos;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0) {
+ goto out_free_path;
+ } else if (ret > 0) {
+ ret = 0;
+ goto out_free_path;
+ }
+
+ extent = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+
+ if (btrfs_file_extent_generation(path->nodes[0], extent) !=
+ backref->generation)
+ goto out_free_path;
+
+ btrfs_release_path(path);
+
+ start = backref->file_pos;
+ if (backref->extent_offset < old->extent_offset + old->offset)
+ start += old->extent_offset + old->offset -
+ backref->extent_offset;
+
+ len = min(backref->extent_offset + backref->num_bytes,
+ old->extent_offset + old->offset + old->len);
+ len -= max(backref->extent_offset, old->extent_offset + old->offset);
+
+ ret = btrfs_drop_extents(trans, root, inode, start,
+ start + len, 1);
+ if (ret)
+ goto out_free_path;
+again:
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = start;
+
+ path->leave_spinning = 1;
+ if (merge) {
+ struct btrfs_file_extent_item *fi;
+ u64 extent_len;
+ struct btrfs_key found_key;
+
+ ret = btrfs_search_slot(trans, root, &key, path, 1, 1);
+ if (ret < 0)
+ goto out_free_path;
+
+ path->slots[0]--;
+ leaf = path->nodes[0];
+ btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+
+ fi = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
+ extent_len = btrfs_file_extent_num_bytes(leaf, fi);
+
+ if (relink_is_mergable(leaf, fi, new->bytenr) &&
+ extent_len + found_key.offset == start) {
+ btrfs_set_file_extent_num_bytes(leaf, fi,
+ extent_len + len);
+ btrfs_mark_buffer_dirty(leaf);
+ inode_add_bytes(inode, len);
+
+ ret = 1;
+ goto out_free_path;
+ } else {
+ merge = false;
+ btrfs_release_path(path);
+ goto again;
+ }
+ }
+
+ ret = btrfs_insert_empty_item(trans, root, path, &key,
+ sizeof(*extent));
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_free_path;
+ }
+
+ leaf = path->nodes[0];
+ item = btrfs_item_ptr(leaf, path->slots[0],
+ struct btrfs_file_extent_item);
+ btrfs_set_file_extent_disk_bytenr(leaf, item, new->bytenr);
+ btrfs_set_file_extent_disk_num_bytes(leaf, item, new->disk_len);
+ btrfs_set_file_extent_offset(leaf, item, start - new->file_pos);
+ btrfs_set_file_extent_num_bytes(leaf, item, len);
+ btrfs_set_file_extent_ram_bytes(leaf, item, new->len);
+ btrfs_set_file_extent_generation(leaf, item, trans->transid);
+ btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG);
+ btrfs_set_file_extent_compression(leaf, item, new->compress_type);
+ btrfs_set_file_extent_encryption(leaf, item, 0);
+ btrfs_set_file_extent_other_encoding(leaf, item, 0);
+
+ btrfs_mark_buffer_dirty(leaf);
+ inode_add_bytes(inode, len);
+ btrfs_release_path(path);
+
+ ret = btrfs_inc_extent_ref(trans, root, new->bytenr,
+ new->disk_len, 0,
+ backref->root_id, backref->inum,
+ new->file_pos, 0); /* start - extent_offset */
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_free_path;
+ }
+
+ ret = 1;
+out_free_path:
+ btrfs_release_path(path);
+ path->leave_spinning = 0;
+ btrfs_end_transaction(trans, root);
+out_unlock:
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, lock_end,
+ &cached, GFP_NOFS);
+ iput(inode);
+ return ret;
+}
+
+static void relink_file_extents(struct new_sa_defrag_extent *new)
+{
+ struct btrfs_path *path;
+ struct old_sa_defrag_extent *old, *tmp;
+ struct sa_defrag_extent_backref *backref;
+ struct sa_defrag_extent_backref *prev = NULL;
+ struct inode *inode;
+ struct btrfs_root *root;
+ struct rb_node *node;
+ int ret;
+
+ inode = new->inode;
+ root = BTRFS_I(inode)->root;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return;
+
+ if (!record_extent_backrefs(path, new)) {
+ btrfs_free_path(path);
+ goto out;
+ }
+ btrfs_release_path(path);
+
+ while (1) {
+ node = rb_first(&new->root);
+ if (!node)
+ break;
+ rb_erase(node, &new->root);
+
+ backref = rb_entry(node, struct sa_defrag_extent_backref, node);
+
+ ret = relink_extent_backref(path, prev, backref);
+ WARN_ON(ret < 0);
+
+ kfree(prev);
+
+ if (ret == 1)
+ prev = backref;
+ else
+ prev = NULL;
+ cond_resched();
+ }
+ kfree(prev);
+
+ btrfs_free_path(path);
+
+ list_for_each_entry_safe(old, tmp, &new->head, list) {
+ list_del(&old->list);
+ kfree(old);
+ }
+out:
+ atomic_dec(&root->fs_info->defrag_running);
+ wake_up(&root->fs_info->transaction_wait);
+
+ kfree(new);
+}
+
+static struct new_sa_defrag_extent *
+record_old_file_extents(struct inode *inode,
+ struct btrfs_ordered_extent *ordered)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ struct old_sa_defrag_extent *old, *tmp;
+ struct new_sa_defrag_extent *new;
+ int ret;
+
+ new = kmalloc(sizeof(*new), GFP_NOFS);
+ if (!new)
+ return NULL;
+
+ new->inode = inode;
+ new->file_pos = ordered->file_offset;
+ new->len = ordered->len;
+ new->bytenr = ordered->start;
+ new->disk_len = ordered->disk_len;
+ new->compress_type = ordered->compress_type;
+ new->root = RB_ROOT;
+ INIT_LIST_HEAD(&new->head);
+
+ path = btrfs_alloc_path();
+ if (!path)
+ goto out_kfree;
+
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = new->file_pos;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out_free_path;
+ if (ret > 0 && path->slots[0] > 0)
+ path->slots[0]--;
+
+ /* find out all the old extents for the file range */
+ while (1) {
+ struct btrfs_file_extent_item *extent;
+ struct extent_buffer *l;
+ int slot;
+ u64 num_bytes;
+ u64 offset;
+ u64 end;
+ u64 disk_bytenr;
+ u64 extent_offset;
+
+ l = path->nodes[0];
+ slot = path->slots[0];
+
+ if (slot >= btrfs_header_nritems(l)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out_free_list;
+ else if (ret > 0)
+ break;
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(l, &key, slot);
+
+ if (key.objectid != btrfs_ino(inode))
+ break;
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ break;
+ if (key.offset >= new->file_pos + new->len)
+ break;
+
+ extent = btrfs_item_ptr(l, slot, struct btrfs_file_extent_item);
+
+ num_bytes = btrfs_file_extent_num_bytes(l, extent);
+ if (key.offset + num_bytes < new->file_pos)
+ goto next;
+
+ disk_bytenr = btrfs_file_extent_disk_bytenr(l, extent);
+ if (!disk_bytenr)
+ goto next;
+
+ extent_offset = btrfs_file_extent_offset(l, extent);
+
+ old = kmalloc(sizeof(*old), GFP_NOFS);
+ if (!old)
+ goto out_free_list;
+
+ offset = max(new->file_pos, key.offset);
+ end = min(new->file_pos + new->len, key.offset + num_bytes);
+
+ old->bytenr = disk_bytenr;
+ old->extent_offset = extent_offset;
+ old->offset = offset - key.offset;
+ old->len = end - offset;
+ old->new = new;
+ old->count = 0;
+ list_add_tail(&old->list, &new->head);
+next:
+ path->slots[0]++;
+ cond_resched();
+ }
+
+ btrfs_free_path(path);
+ atomic_inc(&root->fs_info->defrag_running);
+
+ return new;
+
+out_free_list:
+ list_for_each_entry_safe(old, tmp, &new->head, list) {
+ list_del(&old->list);
+ kfree(old);
+ }
+out_free_path:
+ btrfs_free_path(path);
+out_kfree:
+ kfree(new);
+ return NULL;
+}
+
/*
* helper function for btrfs_finish_ordered_io, this
* just reads in some of the csum leaves to prime them into ram
@@ -1909,6 +2601,7 @@
struct btrfs_trans_handle *trans = NULL;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_state *cached_state = NULL;
+ struct new_sa_defrag_extent *new = NULL;
int compress_type = 0;
int ret;
bool nolock;
@@ -1943,6 +2636,20 @@
ordered_extent->file_offset + ordered_extent->len - 1,
0, &cached_state);
+ ret = test_range_bit(io_tree, ordered_extent->file_offset,
+ ordered_extent->file_offset + ordered_extent->len - 1,
+ EXTENT_DEFRAG, 1, cached_state);
+ if (ret) {
+ u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
+ if (last_snapshot >= BTRFS_I(inode)->generation)
+ /* the inode is shared */
+ new = record_old_file_extents(inode, ordered_extent);
+
+ clear_extent_bit(io_tree, ordered_extent->file_offset,
+ ordered_extent->file_offset + ordered_extent->len - 1,
+ EXTENT_DEFRAG, 0, 0, &cached_state, GFP_NOFS);
+ }
+
if (nolock)
trans = btrfs_join_transaction_nolock(root);
else
@@ -2001,17 +2708,33 @@
if (trans)
btrfs_end_transaction(trans, root);
- if (ret)
+ if (ret) {
clear_extent_uptodate(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset +
ordered_extent->len - 1, NULL, GFP_NOFS);
+ /*
+ * If the ordered extent had an IOERR or something else went
+ * wrong we need to return the space for this ordered extent
+ * back to the allocator.
+ */
+ if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
+ !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
+ btrfs_free_reserved_extent(root, ordered_extent->start,
+ ordered_extent->disk_len);
+ }
+
+
/*
* This needs to be done to make sure anybody waiting knows we are done
* updating everything for this ordered extent.
*/
btrfs_remove_ordered_extent(inode, ordered_extent);
+ /* for snapshot-aware defrag */
+ if (new)
+ relink_file_extents(new);
+
/* once for us */
btrfs_put_ordered_extent(ordered_extent);
/* once for the tree */
@@ -2062,7 +2785,7 @@
static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
struct extent_state *state, int mirror)
{
- size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT);
+ size_t offset = start - page_offset(page);
struct inode *inode = page->mapping->host;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
char *kaddr;
@@ -2167,11 +2890,6 @@
}
}
-enum btrfs_orphan_cleanup_state {
- ORPHAN_CLEANUP_STARTED = 1,
- ORPHAN_CLEANUP_DONE = 2,
-};
-
/*
* This is called in transaction commit time. If there are no orphan
* files in the subvolume, it removes orphan item and frees block_rsv
@@ -2469,6 +3187,7 @@
*/
set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
&BTRFS_I(inode)->runtime_flags);
+ atomic_inc(&root->orphan_inodes);
/* if we have links, this was a truncate, lets do that */
if (inode->i_nlink) {
@@ -2491,6 +3210,8 @@
goto out;
ret = btrfs_truncate(inode);
+ if (ret)
+ btrfs_orphan_del(NULL, inode);
} else {
nr_unlink++;
}
@@ -2709,34 +3430,41 @@
struct btrfs_inode_item *item,
struct inode *inode)
{
- btrfs_set_inode_uid(leaf, item, i_uid_read(inode));
- btrfs_set_inode_gid(leaf, item, i_gid_read(inode));
- btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size);
- btrfs_set_inode_mode(leaf, item, inode->i_mode);
- btrfs_set_inode_nlink(leaf, item, inode->i_nlink);
+ struct btrfs_map_token token;
- btrfs_set_timespec_sec(leaf, btrfs_inode_atime(item),
- inode->i_atime.tv_sec);
- btrfs_set_timespec_nsec(leaf, btrfs_inode_atime(item),
- inode->i_atime.tv_nsec);
+ btrfs_init_map_token(&token);
- btrfs_set_timespec_sec(leaf, btrfs_inode_mtime(item),
- inode->i_mtime.tv_sec);
- btrfs_set_timespec_nsec(leaf, btrfs_inode_mtime(item),
- inode->i_mtime.tv_nsec);
+ btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
+ btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
+ btrfs_set_token_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size,
+ &token);
+ btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
+ btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
- btrfs_set_timespec_sec(leaf, btrfs_inode_ctime(item),
- inode->i_ctime.tv_sec);
- btrfs_set_timespec_nsec(leaf, btrfs_inode_ctime(item),
- inode->i_ctime.tv_nsec);
+ btrfs_set_token_timespec_sec(leaf, btrfs_inode_atime(item),
+ inode->i_atime.tv_sec, &token);
+ btrfs_set_token_timespec_nsec(leaf, btrfs_inode_atime(item),
+ inode->i_atime.tv_nsec, &token);
- btrfs_set_inode_nbytes(leaf, item, inode_get_bytes(inode));
- btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation);
- btrfs_set_inode_sequence(leaf, item, inode->i_version);
- btrfs_set_inode_transid(leaf, item, trans->transid);
- btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
- btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
- btrfs_set_inode_block_group(leaf, item, 0);
+ btrfs_set_token_timespec_sec(leaf, btrfs_inode_mtime(item),
+ inode->i_mtime.tv_sec, &token);
+ btrfs_set_token_timespec_nsec(leaf, btrfs_inode_mtime(item),
+ inode->i_mtime.tv_nsec, &token);
+
+ btrfs_set_token_timespec_sec(leaf, btrfs_inode_ctime(item),
+ inode->i_ctime.tv_sec, &token);
+ btrfs_set_token_timespec_nsec(leaf, btrfs_inode_ctime(item),
+ inode->i_ctime.tv_nsec, &token);
+
+ btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
+ &token);
+ btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
+ &token);
+ btrfs_set_token_inode_sequence(leaf, item, inode->i_version, &token);
+ btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
+ btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
+ btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
+ btrfs_set_token_inode_block_group(leaf, item, 0, &token);
}
/*
@@ -2967,11 +3695,9 @@
* 1 for the dir item
* 1 for the dir index
* 1 for the inode ref
- * 1 for the inode ref in the tree log
- * 2 for the dir entries in the log
* 1 for the inode
*/
- trans = btrfs_start_transaction(root, 8);
+ trans = btrfs_start_transaction(root, 5);
if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
return trans;
@@ -3304,7 +4030,6 @@
u64 extent_num_bytes = 0;
u64 extent_offset = 0;
u64 item_end = 0;
- u64 mask = root->sectorsize - 1;
u32 found_type = (u8)-1;
int found_extent;
int del_item;
@@ -3328,7 +4053,8 @@
* extent just the way it is.
*/
if (root->ref_cows || root == root->fs_info->tree_root)
- btrfs_drop_extent_cache(inode, (new_size + mask) & (~mask), (u64)-1, 0);
+ btrfs_drop_extent_cache(inode, ALIGN(new_size,
+ root->sectorsize), (u64)-1, 0);
/*
* This function is also used to drop the items in the log tree before
@@ -3407,10 +4133,9 @@
if (!del_item) {
u64 orig_num_bytes =
btrfs_file_extent_num_bytes(leaf, fi);
- extent_num_bytes = new_size -
- found_key.offset + root->sectorsize - 1;
- extent_num_bytes = extent_num_bytes &
- ~((u64)root->sectorsize - 1);
+ extent_num_bytes = ALIGN(new_size -
+ found_key.offset,
+ root->sectorsize);
btrfs_set_file_extent_num_bytes(leaf, fi,
extent_num_bytes);
num_dec = (orig_num_bytes -
@@ -3646,9 +4371,8 @@
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
- u64 mask = root->sectorsize - 1;
- u64 hole_start = (oldsize + mask) & ~mask;
- u64 block_end = (size + mask) & ~mask;
+ u64 hole_start = ALIGN(oldsize, root->sectorsize);
+ u64 block_end = ALIGN(size, root->sectorsize);
u64 last_byte;
u64 cur_offset;
u64 hole_size;
@@ -3681,7 +4405,7 @@
break;
}
last_byte = min(extent_map_end(em), block_end);
- last_byte = (last_byte + mask) & ~mask;
+ last_byte = ALIGN(last_byte , root->sectorsize);
if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
struct extent_map *hole_em;
hole_size = last_byte - cur_offset;
@@ -3832,6 +4556,12 @@
/* we don't support swapfiles, so vmtruncate shouldn't fail */
truncate_setsize(inode, newsize);
+
+ /* Disable nonlocked read DIO to avoid the end less truncate */
+ btrfs_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+ btrfs_inode_resume_unlocked_dio(inode);
+
ret = btrfs_truncate(inode);
if (ret && inode->i_nlink)
btrfs_orphan_del(NULL, inode);
@@ -3904,6 +4634,12 @@
goto no_delete;
}
+ ret = btrfs_commit_inode_delayed_inode(inode);
+ if (ret) {
+ btrfs_orphan_del(NULL, inode);
+ goto no_delete;
+ }
+
rsv = btrfs_alloc_block_rsv(root, BTRFS_BLOCK_RSV_TEMP);
if (!rsv) {
btrfs_orphan_del(NULL, inode);
@@ -3941,7 +4677,7 @@
goto no_delete;
}
- trans = btrfs_start_transaction_lflush(root, 1);
+ trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
btrfs_orphan_del(NULL, inode);
btrfs_free_block_rsv(root, rsv);
@@ -3955,9 +4691,6 @@
break;
trans->block_rsv = &root->fs_info->trans_block_rsv;
- ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
-
btrfs_end_transaction(trans, root);
trans = NULL;
btrfs_btree_balance_dirty(root);
@@ -4391,7 +5124,7 @@
static int btrfs_real_readdir(struct file *filp, void *dirent,
filldir_t filldir)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_item *item;
struct btrfs_dir_item *di;
@@ -4854,7 +5587,8 @@
if (btrfs_test_opt(root, NODATASUM))
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
if (btrfs_test_opt(root, NODATACOW))
- BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
+ BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_NODATASUM;
}
insert_inode_hash(inode);
@@ -5006,12 +5740,6 @@
goto out_unlock;
}
- err = btrfs_update_inode(trans, root, inode);
- if (err) {
- drop_inode = 1;
- goto out_unlock;
- }
-
/*
* If the active LSM wants to access the inode during
* d_instantiate it needs these. Smack checks to see
@@ -5396,8 +6124,7 @@
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size_t size;
size = btrfs_file_extent_inline_len(leaf, item);
- extent_end = (extent_start + size + root->sectorsize - 1) &
- ~((u64)root->sectorsize - 1);
+ extent_end = ALIGN(extent_start + size, root->sectorsize);
}
if (start >= extent_end) {
@@ -5469,8 +6196,7 @@
copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
size - extent_offset);
em->start = extent_start + extent_offset;
- em->len = (copy_size + root->sectorsize - 1) &
- ~((u64)root->sectorsize - 1);
+ em->len = ALIGN(copy_size, root->sectorsize);
em->orig_block_len = em->len;
em->orig_start = em->start;
if (compress_type) {
@@ -5949,6 +6675,8 @@
em->start = start;
em->orig_start = orig_start;
+ em->mod_start = start;
+ em->mod_len = len;
em->len = len;
em->block_len = block_len;
em->block_start = block_start;
@@ -5990,16 +6718,12 @@
u64 len = bh_result->b_size;
struct btrfs_trans_handle *trans;
int unlock_bits = EXTENT_LOCKED;
- int ret;
+ int ret = 0;
- if (create) {
- ret = btrfs_delalloc_reserve_space(inode, len);
- if (ret)
- return ret;
+ if (create)
unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY;
- } else {
+ else
len = min_t(u64, len, root->sectorsize);
- }
lockstart = start;
lockend = start + len - 1;
@@ -6011,14 +6735,6 @@
if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create))
return -ENOTBLK;
- if (create) {
- ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, EXTENT_DELALLOC, NULL,
- &cached_state, GFP_NOFS);
- if (ret)
- goto unlock_err;
- }
-
em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
@@ -6050,7 +6766,6 @@
if (!create && (em->block_start == EXTENT_MAP_HOLE ||
test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
free_extent_map(em);
- ret = 0;
goto unlock_err;
}
@@ -6148,6 +6863,15 @@
*/
if (start + len > i_size_read(inode))
i_size_write(inode, start + len);
+
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->outstanding_extents++;
+ spin_unlock(&BTRFS_I(inode)->lock);
+
+ ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
+ lockstart + len - 1, EXTENT_DELALLOC, NULL,
+ &cached_state, GFP_NOFS);
+ BUG_ON(ret);
}
/*
@@ -6156,24 +6880,9 @@
* aren't using if there is any left over space.
*/
if (lockstart < lockend) {
- if (create && len < lockend - lockstart) {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockstart + len - 1,
- unlock_bits | EXTENT_DEFRAG, 1, 0,
- &cached_state, GFP_NOFS);
- /*
- * Beside unlock, we also need to cleanup reserved space
- * for the left range by attaching EXTENT_DO_ACCOUNTING.
- */
- clear_extent_bit(&BTRFS_I(inode)->io_tree,
- lockstart + len, lockend,
- unlock_bits | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 0, NULL, GFP_NOFS);
- } else {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, unlock_bits, 1, 0,
- &cached_state, GFP_NOFS);
- }
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
+ lockend, unlock_bits, 1, 0,
+ &cached_state, GFP_NOFS);
} else {
free_extent_state(cached_state);
}
@@ -6183,9 +6892,6 @@
return 0;
unlock_err:
- if (create)
- unlock_bits |= EXTENT_DO_ACCOUNTING;
-
clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
unlock_bits, 1, 0, &cached_state, GFP_NOFS);
return ret;
@@ -6426,19 +7132,24 @@
int async_submit = 0;
map_length = orig_bio->bi_size;
- ret = btrfs_map_block(root->fs_info, READ, start_sector << 9,
+ ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
&map_length, NULL, 0);
if (ret) {
bio_put(orig_bio);
return -EIO;
}
-
if (map_length >= orig_bio->bi_size) {
bio = orig_bio;
goto submit;
}
- async_submit = 1;
+ /* async crcs make it difficult to collect full stripe writes. */
+ if (btrfs_get_alloc_profile(root, 1) &
+ (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6))
+ async_submit = 0;
+ else
+ async_submit = 1;
+
bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
if (!bio)
return -ENOMEM;
@@ -6480,7 +7191,7 @@
bio->bi_end_io = btrfs_end_dio_bio;
map_length = orig_bio->bi_size;
- ret = btrfs_map_block(root->fs_info, READ,
+ ret = btrfs_map_block(root->fs_info, rw,
start_sector << 9,
&map_length, NULL, 0);
if (ret) {
@@ -6623,15 +7334,60 @@
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ size_t count = 0;
+ int flags = 0;
+ bool wakeup = true;
+ bool relock = false;
+ ssize_t ret;
if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov,
offset, nr_segs))
return 0;
- return __blockdev_direct_IO(rw, iocb, inode,
- BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
- btrfs_submit_direct, 0);
+ atomic_inc(&inode->i_dio_count);
+ smp_mb__after_atomic_inc();
+
+ if (rw & WRITE) {
+ count = iov_length(iov, nr_segs);
+ /*
+ * If the write DIO is beyond the EOF, we need update
+ * the isize, but it is protected by i_mutex. So we can
+ * not unlock the i_mutex at this case.
+ */
+ if (offset + count <= inode->i_size) {
+ mutex_unlock(&inode->i_mutex);
+ relock = true;
+ }
+ ret = btrfs_delalloc_reserve_space(inode, count);
+ if (ret)
+ goto out;
+ } else if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
+ &BTRFS_I(inode)->runtime_flags))) {
+ inode_dio_done(inode);
+ flags = DIO_LOCKING | DIO_SKIP_HOLES;
+ wakeup = false;
+ }
+
+ ret = __blockdev_direct_IO(rw, iocb, inode,
+ BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
+ iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
+ btrfs_submit_direct, flags);
+ if (rw & WRITE) {
+ if (ret < 0 && ret != -EIOCBQUEUED)
+ btrfs_delalloc_release_space(inode, count);
+ else if (ret >= 0 && (size_t)ret < count)
+ btrfs_delalloc_release_space(inode,
+ count - (size_t)ret);
+ else
+ btrfs_delalloc_release_metadata(inode, 0);
+ }
+out:
+ if (wakeup)
+ inode_dio_done(inode);
+ if (relock)
+ mutex_lock(&inode->i_mutex);
+
+ return ret;
}
#define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
@@ -6735,8 +7491,7 @@
return;
}
lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
- ordered = btrfs_lookup_ordered_extent(inode,
- page_offset(page));
+ ordered = btrfs_lookup_ordered_extent(inode, page_offset(page));
if (ordered) {
/*
* IO on this page will never be started, so we need
@@ -6791,7 +7546,7 @@
int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = fdentry(vma->vm_file)->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
@@ -7216,8 +7971,9 @@
{
struct btrfs_root *root = BTRFS_I(inode)->root;
+ /* the snap/subvol tree is on deleting */
if (btrfs_root_refs(&root->root_item) == 0 &&
- !btrfs_is_free_space_inode(inode))
+ root != root->fs_info->tree_root)
return 1;
else
return generic_drop_inode(inode);
@@ -7299,40 +8055,22 @@
static int btrfs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
+ u64 delalloc_bytes;
struct inode *inode = dentry->d_inode;
u32 blocksize = inode->i_sb->s_blocksize;
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
stat->blksize = PAGE_CACHE_SIZE;
+
+ spin_lock(&BTRFS_I(inode)->lock);
+ delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
+ spin_unlock(&BTRFS_I(inode)->lock);
stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
- ALIGN(BTRFS_I(inode)->delalloc_bytes, blocksize)) >> 9;
+ ALIGN(delalloc_bytes, blocksize)) >> 9;
return 0;
}
-/*
- * If a file is moved, it will inherit the cow and compression flags of the new
- * directory.
- */
-static void fixup_inode_flags(struct inode *dir, struct inode *inode)
-{
- struct btrfs_inode *b_dir = BTRFS_I(dir);
- struct btrfs_inode *b_inode = BTRFS_I(inode);
-
- if (b_dir->flags & BTRFS_INODE_NODATACOW)
- b_inode->flags |= BTRFS_INODE_NODATACOW;
- else
- b_inode->flags &= ~BTRFS_INODE_NODATACOW;
-
- if (b_dir->flags & BTRFS_INODE_COMPRESS) {
- b_inode->flags |= BTRFS_INODE_COMPRESS;
- b_inode->flags &= ~BTRFS_INODE_NOCOMPRESS;
- } else {
- b_inode->flags &= ~(BTRFS_INODE_COMPRESS |
- BTRFS_INODE_NOCOMPRESS);
- }
-}
-
static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
@@ -7403,7 +8141,7 @@
* inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items
* should cover the worst case number of items we'll modify.
*/
- trans = btrfs_start_transaction(root, 20);
+ trans = btrfs_start_transaction(root, 11);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_notrans;
@@ -7498,8 +8236,6 @@
}
}
- fixup_inode_flags(new_dir, old_inode);
-
ret = btrfs_add_link(trans, new_dir, old_inode,
new_dentry->d_name.name,
new_dentry->d_name.len, 0, index);
@@ -7583,7 +8319,7 @@
INIT_LIST_HEAD(&works);
INIT_LIST_HEAD(&splice);
-again:
+
spin_lock(&root->fs_info->delalloc_lock);
list_splice_init(&root->fs_info->delalloc_inodes, &splice);
while (!list_empty(&splice)) {
@@ -7593,8 +8329,11 @@
list_del_init(&binode->delalloc_inodes);
inode = igrab(&binode->vfs_inode);
- if (!inode)
+ if (!inode) {
+ clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &binode->runtime_flags);
continue;
+ }
list_add_tail(&binode->delalloc_inodes,
&root->fs_info->delalloc_inodes);
@@ -7619,13 +8358,6 @@
btrfs_wait_and_free_delalloc_work(work);
}
- spin_lock(&root->fs_info->delalloc_lock);
- if (!list_empty(&root->fs_info->delalloc_inodes)) {
- spin_unlock(&root->fs_info->delalloc_lock);
- goto again;
- }
- spin_unlock(&root->fs_info->delalloc_lock);
-
/* the filemap_flush will queue IO into the worker threads, but
* we have to make sure the IO is actually started and that
* ordered extents get created before we return
@@ -7787,6 +8519,7 @@
struct btrfs_key ins;
u64 cur_offset = start;
u64 i_size;
+ u64 cur_bytes;
int ret = 0;
bool own_trans = true;
@@ -7801,8 +8534,10 @@
}
}
- ret = btrfs_reserve_extent(trans, root, num_bytes, min_size,
- 0, *alloc_hint, &ins, 1);
+ cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
+ cur_bytes = max(cur_bytes, min_size);
+ ret = btrfs_reserve_extent(trans, root, cur_bytes,
+ min_size, 0, *alloc_hint, &ins, 1);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5b22d45..2c02310 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -42,12 +42,12 @@
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/uuid.h>
+#include <linux/btrfs.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
-#include "ioctl.h"
#include "print-tree.h"
#include "volumes.h"
#include "locking.h"
@@ -152,7 +152,7 @@
static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
{
- struct btrfs_inode *ip = BTRFS_I(file->f_path.dentry->d_inode);
+ struct btrfs_inode *ip = BTRFS_I(file_inode(file));
unsigned int flags = btrfs_flags_to_ioctl(ip->flags);
if (copy_to_user(arg, &flags, sizeof(flags)))
@@ -177,7 +177,7 @@
static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_inode *ip = BTRFS_I(inode);
struct btrfs_root *root = ip->root;
struct btrfs_trans_handle *trans;
@@ -310,7 +310,7 @@
static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
return put_user(inode->i_generation, arg);
}
@@ -363,46 +363,52 @@
return 0;
}
-static noinline int create_subvol(struct btrfs_root *root,
+static noinline int create_subvol(struct inode *dir,
struct dentry *dentry,
char *name, int namelen,
u64 *async_transid,
- struct btrfs_qgroup_inherit **inherit)
+ struct btrfs_qgroup_inherit *inherit)
{
struct btrfs_trans_handle *trans;
struct btrfs_key key;
struct btrfs_root_item root_item;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
+ struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *new_root;
- struct dentry *parent = dentry->d_parent;
- struct inode *dir;
+ struct btrfs_block_rsv block_rsv;
struct timespec cur_time = CURRENT_TIME;
int ret;
int err;
u64 objectid;
u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
u64 index = 0;
+ u64 qgroup_reserved;
uuid_le new_uuid;
ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
if (ret)
return ret;
- dir = parent->d_inode;
-
+ btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
- * 1 - inode item
- * 2 - refs
- * 1 - root item
- * 2 - dir items
+ * The same as the snapshot creation, please see the comment
+ * of create_snapshot().
*/
- trans = btrfs_start_transaction(root, 6);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
+ 7, &qgroup_reserved);
+ if (ret)
+ return ret;
- ret = btrfs_qgroup_inherit(trans, root->fs_info, 0, objectid,
- inherit ? *inherit : NULL);
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+ trans->block_rsv = &block_rsv;
+ trans->bytes_reserved = block_rsv.size;
+
+ ret = btrfs_qgroup_inherit(trans, root->fs_info, 0, objectid, inherit);
if (ret)
goto fail;
@@ -515,22 +521,31 @@
BUG_ON(ret);
- d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
fail:
+ trans->block_rsv = NULL;
+ trans->bytes_reserved = 0;
if (async_transid) {
*async_transid = trans->transid;
err = btrfs_commit_transaction_async(trans, root, 1);
+ if (err)
+ err = btrfs_commit_transaction(trans, root);
} else {
err = btrfs_commit_transaction(trans, root);
}
if (err && !ret)
ret = err;
+
+ if (!ret)
+ d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
+out:
+ btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
return ret;
}
-static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
- char *name, int namelen, u64 *async_transid,
- bool readonly, struct btrfs_qgroup_inherit **inherit)
+static int create_snapshot(struct btrfs_root *root, struct inode *dir,
+ struct dentry *dentry, char *name, int namelen,
+ u64 *async_transid, bool readonly,
+ struct btrfs_qgroup_inherit *inherit)
{
struct inode *inode;
struct btrfs_pending_snapshot *pending_snapshot;
@@ -546,23 +561,31 @@
btrfs_init_block_rsv(&pending_snapshot->block_rsv,
BTRFS_BLOCK_RSV_TEMP);
+ /*
+ * 1 - parent dir inode
+ * 2 - dir entries
+ * 1 - root item
+ * 2 - root ref/backref
+ * 1 - root of snapshot
+ */
+ ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
+ &pending_snapshot->block_rsv, 7,
+ &pending_snapshot->qgroup_reserved);
+ if (ret)
+ goto out;
+
pending_snapshot->dentry = dentry;
pending_snapshot->root = root;
pending_snapshot->readonly = readonly;
- if (inherit) {
- pending_snapshot->inherit = *inherit;
- *inherit = NULL; /* take responsibility to free it */
- }
+ pending_snapshot->dir = dir;
+ pending_snapshot->inherit = inherit;
- trans = btrfs_start_transaction(root->fs_info->extent_root, 6);
+ trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto fail;
}
- ret = btrfs_snap_reserve_metadata(trans, pending_snapshot);
- BUG_ON(ret);
-
spin_lock(&root->fs_info->trans_lock);
list_add(&pending_snapshot->list,
&trans->transaction->pending_snapshots);
@@ -571,16 +594,14 @@
*async_transid = trans->transid;
ret = btrfs_commit_transaction_async(trans,
root->fs_info->extent_root, 1);
+ if (ret)
+ ret = btrfs_commit_transaction(trans, root);
} else {
ret = btrfs_commit_transaction(trans,
root->fs_info->extent_root);
}
- if (ret) {
- /* cleanup_transaction has freed this for us */
- if (trans->aborted)
- pending_snapshot = NULL;
+ if (ret)
goto fail;
- }
ret = pending_snapshot->error;
if (ret)
@@ -599,6 +620,10 @@
d_instantiate(dentry, inode);
ret = 0;
fail:
+ btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
+ &pending_snapshot->block_rsv,
+ pending_snapshot->qgroup_reserved);
+out:
kfree(pending_snapshot);
return ret;
}
@@ -692,7 +717,7 @@
char *name, int namelen,
struct btrfs_root *snap_src,
u64 *async_transid, bool readonly,
- struct btrfs_qgroup_inherit **inherit)
+ struct btrfs_qgroup_inherit *inherit)
{
struct inode *dir = parent->dentry->d_inode;
struct dentry *dentry;
@@ -729,11 +754,11 @@
goto out_up_read;
if (snap_src) {
- error = create_snapshot(snap_src, dentry, name, namelen,
+ error = create_snapshot(snap_src, dir, dentry, name, namelen,
async_transid, readonly, inherit);
} else {
- error = create_subvol(BTRFS_I(dir)->root, dentry,
- name, namelen, async_transid, inherit);
+ error = create_subvol(dir, dentry, name, namelen,
+ async_transid, inherit);
}
if (!error)
fsnotify_mkdir(dir, dentry);
@@ -815,7 +840,7 @@
while(1) {
ret = btrfs_search_forward(root, &min_key, &max_key,
- path, 0, newer_than);
+ path, newer_than);
if (ret != 0)
goto none;
if (min_key.objectid != ino)
@@ -1203,6 +1228,12 @@
if (!(inode->i_sb->s_flags & MS_ACTIVE))
break;
+ if (btrfs_defrag_cancelled(root->fs_info)) {
+ printk(KERN_DEBUG "btrfs: defrag_file cancelled\n");
+ ret = -EAGAIN;
+ break;
+ }
+
if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
extent_thresh, &last_len, &skip,
&defrag_end, range->flags &
@@ -1317,7 +1348,7 @@
u64 new_size;
u64 old_size;
u64 devid = 1;
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_vol_args *vol_args;
struct btrfs_trans_handle *trans;
struct btrfs_device *device = NULL;
@@ -1326,9 +1357,6 @@
int ret = 0;
int mod = 0;
- if (root->fs_info->sb->s_flags & MS_RDONLY)
- return -EROFS;
-
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1360,6 +1388,10 @@
*devstr = '\0';
devstr = vol_args->name;
devid = simple_strtoull(devstr, &end, 10);
+ if (!devid) {
+ ret = -EINVAL;
+ goto out_free;
+ }
printk(KERN_INFO "btrfs: resizing devid %llu\n",
(unsigned long long)devid);
}
@@ -1368,7 +1400,7 @@
if (!device) {
printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
(unsigned long long)devid);
- ret = -EINVAL;
+ ret = -ENODEV;
goto out_free;
}
@@ -1376,7 +1408,7 @@
printk(KERN_INFO "btrfs: resizer unable to apply on "
"readonly device %llu\n",
(unsigned long long)devid);
- ret = -EINVAL;
+ ret = -EPERM;
goto out_free;
}
@@ -1398,7 +1430,7 @@
}
if (device->is_tgtdev_for_dev_replace) {
- ret = -EINVAL;
+ ret = -EPERM;
goto out_free;
}
@@ -1454,7 +1486,7 @@
static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
char *name, unsigned long fd, int subvol,
u64 *transid, bool readonly,
- struct btrfs_qgroup_inherit **inherit)
+ struct btrfs_qgroup_inherit *inherit)
{
int namelen;
int ret = 0;
@@ -1486,8 +1518,8 @@
goto out_drop_write;
}
- src_inode = src.file->f_path.dentry->d_inode;
- if (src_inode->i_sb != file->f_path.dentry->d_inode->i_sb) {
+ src_inode = file_inode(src.file);
+ if (src_inode->i_sb != file_inode(file)->i_sb) {
printk(KERN_INFO "btrfs: Snapshot src from "
"another FS\n");
ret = -EINVAL;
@@ -1563,7 +1595,7 @@
ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
vol_args->fd, subvol, ptr,
- readonly, &inherit);
+ readonly, inherit);
if (ret == 0 && ptr &&
copy_to_user(arg +
@@ -1579,7 +1611,7 @@
static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
void __user *arg)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret = 0;
u64 flags = 0;
@@ -1601,7 +1633,7 @@
static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
void __user *arg)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
u64 root_flags;
@@ -1860,7 +1892,7 @@
path->keep_locks = 1;
while(1) {
- ret = btrfs_search_forward(root, &key, &max_key, path, 0,
+ ret = btrfs_search_forward(root, &key, &max_key, path,
sk->min_transid);
if (ret != 0) {
if (ret > 0)
@@ -1895,7 +1927,7 @@
if (IS_ERR(args))
return PTR_ERR(args);
- inode = fdentry(file)->d_inode;
+ inode = file_inode(file);
ret = search_ioctl(inode, args);
if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
ret = -EFAULT;
@@ -2005,7 +2037,7 @@
if (IS_ERR(args))
return PTR_ERR(args);
- inode = fdentry(file)->d_inode;
+ inode = file_inode(file);
if (args->treeid == 0)
args->treeid = BTRFS_I(inode)->root->root_key.objectid;
@@ -2032,6 +2064,8 @@
struct btrfs_root *dest = NULL;
struct btrfs_ioctl_vol_args *vol_args;
struct btrfs_trans_handle *trans;
+ struct btrfs_block_rsv block_rsv;
+ u64 qgroup_reserved;
int namelen;
int ret;
int err = 0;
@@ -2121,12 +2155,23 @@
if (err)
goto out_up_write;
+ btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
+ /*
+ * One for dir inode, two for dir entries, two for root
+ * ref/backref.
+ */
+ err = btrfs_subvolume_reserve_metadata(root, &block_rsv,
+ 5, &qgroup_reserved);
+ if (err)
+ goto out_up_write;
+
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- goto out_up_write;
+ goto out_release;
}
- trans->block_rsv = &root->fs_info->global_block_rsv;
+ trans->block_rsv = &block_rsv;
+ trans->bytes_reserved = block_rsv.size;
ret = btrfs_unlink_subvol(trans, root, dir,
dest->root_key.objectid,
@@ -2156,10 +2201,14 @@
}
}
out_end_trans:
+ trans->block_rsv = NULL;
+ trans->bytes_reserved = 0;
ret = btrfs_end_transaction(trans, root);
if (ret && !err)
err = ret;
inode->i_flags |= S_DEAD;
+out_release:
+ btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
out_up_write:
up_write(&root->fs_info->subvol_sem);
out_unlock:
@@ -2168,6 +2217,12 @@
shrink_dcache_sb(root->fs_info->sb);
btrfs_invalidate_inodes(dest);
d_delete(dentry);
+
+ /* the last ref */
+ if (dest->cache_inode) {
+ iput(dest->cache_inode);
+ dest->cache_inode = NULL;
+ }
}
out_dput:
dput(dentry);
@@ -2181,7 +2236,7 @@
static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ioctl_defrag_range_args *range;
int ret;
@@ -2190,13 +2245,6 @@
if (ret)
return ret;
- if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
- 1)) {
- pr_info("btrfs: dev add/delete/balance/replace/resize operation in progress\n");
- mnt_drop_write_file(file);
- return -EINVAL;
- }
-
if (btrfs_root_readonly(root)) {
ret = -EROFS;
goto out;
@@ -2208,10 +2256,10 @@
ret = -EPERM;
goto out;
}
- ret = btrfs_defrag_root(root, 0);
+ ret = btrfs_defrag_root(root);
if (ret)
goto out;
- ret = btrfs_defrag_root(root->fs_info->extent_root, 0);
+ ret = btrfs_defrag_root(root->fs_info->extent_root);
break;
case S_IFREG:
if (!(file->f_mode & FMODE_WRITE)) {
@@ -2241,7 +2289,7 @@
/* the rest are all set to zero by kzalloc */
range->len = (u64)-1;
}
- ret = btrfs_defrag_file(fdentry(file)->d_inode, file,
+ ret = btrfs_defrag_file(file_inode(file), file,
range, 0, 0);
if (ret > 0)
ret = 0;
@@ -2251,7 +2299,6 @@
ret = -EINVAL;
}
out:
- atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
mnt_drop_write_file(file);
return ret;
}
@@ -2289,7 +2336,7 @@
static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_vol_args *vol_args;
int ret;
@@ -2412,7 +2459,7 @@
static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
u64 off, u64 olen, u64 destoff)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct fd src_file;
struct inode *src;
@@ -2458,7 +2505,7 @@
if (src_file.file->f_path.mnt != file->f_path.mnt)
goto out_fput;
- src = src_file.file->f_dentry->d_inode;
+ src = file_inode(src_file.file);
ret = -EINVAL;
if (src == inode)
@@ -2820,7 +2867,7 @@
*/
static long btrfs_ioctl_trans_start(struct file *file)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret;
@@ -2860,7 +2907,7 @@
static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_root *new_root;
struct btrfs_dir_item *di;
@@ -3084,7 +3131,7 @@
*/
long btrfs_ioctl_trans_end(struct file *file)
{
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
@@ -3108,7 +3155,7 @@
u64 transid;
int ret;
- trans = btrfs_attach_transaction(root);
+ trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
return PTR_ERR(trans);
@@ -3146,7 +3193,7 @@
static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_scrub_args *sa;
int ret;
@@ -3286,7 +3333,7 @@
struct inode_fs_paths *ipath = NULL;
struct btrfs_path *path;
- if (!capable(CAP_SYS_ADMIN))
+ if (!capable(CAP_DAC_READ_SEARCH))
return -EPERM;
path = btrfs_alloc_path();
@@ -3437,7 +3484,7 @@
static long btrfs_ioctl_balance(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_ioctl_balance_args *bargs;
struct btrfs_balance_control *bctl;
@@ -3627,7 +3674,7 @@
static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_quota_ctl_args *sa;
struct btrfs_trans_handle *trans = NULL;
int ret;
@@ -3686,7 +3733,7 @@
static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_qgroup_assign_args *sa;
struct btrfs_trans_handle *trans;
int ret;
@@ -3733,7 +3780,7 @@
static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_qgroup_create_args *sa;
struct btrfs_trans_handle *trans;
int ret;
@@ -3784,7 +3831,7 @@
static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
struct btrfs_ioctl_qgroup_limit_args *sa;
struct btrfs_trans_handle *trans;
int ret;
@@ -3834,7 +3881,7 @@
void __user *arg)
{
struct btrfs_ioctl_received_subvol_args *sa = NULL;
- struct inode *inode = fdentry(file)->d_inode;
+ struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_root_item *root_item = &root->root_item;
struct btrfs_trans_handle *trans;
@@ -3911,10 +3958,69 @@
return ret;
}
+static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
+{
+ struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ const char *label = root->fs_info->super_copy->label;
+ size_t len = strnlen(label, BTRFS_LABEL_SIZE);
+ int ret;
+
+ if (len == BTRFS_LABEL_SIZE) {
+ pr_warn("btrfs: label is too long, return the first %zu bytes\n",
+ --len);
+ }
+
+ mutex_lock(&root->fs_info->volume_mutex);
+ ret = copy_to_user(arg, label, len);
+ mutex_unlock(&root->fs_info->volume_mutex);
+
+ return ret ? -EFAULT : 0;
+}
+
+static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg)
+{
+ struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_super_block *super_block = root->fs_info->super_copy;
+ struct btrfs_trans_handle *trans;
+ char label[BTRFS_LABEL_SIZE];
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(label, arg, sizeof(label)))
+ return -EFAULT;
+
+ if (strnlen(label, BTRFS_LABEL_SIZE) == BTRFS_LABEL_SIZE) {
+ pr_err("btrfs: unable to set label with more than %d bytes\n",
+ BTRFS_LABEL_SIZE - 1);
+ return -EINVAL;
+ }
+
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
+ mutex_lock(&root->fs_info->volume_mutex);
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_unlock;
+ }
+
+ strcpy(super_block->label, label);
+ ret = btrfs_end_transaction(trans, root);
+
+out_unlock:
+ mutex_unlock(&root->fs_info->volume_mutex);
+ mnt_drop_write_file(file);
+ return ret;
+}
+
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
void __user *argp = (void __user *)arg;
switch (cmd) {
@@ -4011,6 +4117,10 @@
return btrfs_ioctl_qgroup_limit(file, argp);
case BTRFS_IOC_DEV_REPLACE:
return btrfs_ioctl_dev_replace(root, argp);
+ case BTRFS_IOC_GET_FSLABEL:
+ return btrfs_ioctl_get_fslabel(file, argp);
+ case BTRFS_IOC_SET_FSLABEL:
+ return btrfs_ioctl_set_fslabel(file, argp);
}
return -ENOTTY;
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
deleted file mode 100644
index dabca9c..0000000
--- a/fs/btrfs/ioctl.h
+++ /dev/null
@@ -1,502 +0,0 @@
-/*
- * Copyright (C) 2007 Oracle. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public
- * License v2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
- */
-
-#ifndef __IOCTL_
-#define __IOCTL_
-#include <linux/ioctl.h>
-
-#define BTRFS_IOCTL_MAGIC 0x94
-#define BTRFS_VOL_NAME_MAX 255
-
-/* this should be 4k */
-#define BTRFS_PATH_NAME_MAX 4087
-struct btrfs_ioctl_vol_args {
- __s64 fd;
- char name[BTRFS_PATH_NAME_MAX + 1];
-};
-
-#define BTRFS_DEVICE_PATH_NAME_MAX 1024
-
-#define BTRFS_SUBVOL_CREATE_ASYNC (1ULL << 0)
-#define BTRFS_SUBVOL_RDONLY (1ULL << 1)
-#define BTRFS_SUBVOL_QGROUP_INHERIT (1ULL << 2)
-#define BTRFS_FSID_SIZE 16
-#define BTRFS_UUID_SIZE 16
-
-#define BTRFS_QGROUP_INHERIT_SET_LIMITS (1ULL << 0)
-
-struct btrfs_qgroup_limit {
- __u64 flags;
- __u64 max_rfer;
- __u64 max_excl;
- __u64 rsv_rfer;
- __u64 rsv_excl;
-};
-
-struct btrfs_qgroup_inherit {
- __u64 flags;
- __u64 num_qgroups;
- __u64 num_ref_copies;
- __u64 num_excl_copies;
- struct btrfs_qgroup_limit lim;
- __u64 qgroups[0];
-};
-
-struct btrfs_ioctl_qgroup_limit_args {
- __u64 qgroupid;
- struct btrfs_qgroup_limit lim;
-};
-
-#define BTRFS_SUBVOL_NAME_MAX 4039
-struct btrfs_ioctl_vol_args_v2 {
- __s64 fd;
- __u64 transid;
- __u64 flags;
- union {
- struct {
- __u64 size;
- struct btrfs_qgroup_inherit __user *qgroup_inherit;
- };
- __u64 unused[4];
- };
- char name[BTRFS_SUBVOL_NAME_MAX + 1];
-};
-
-/*
- * structure to report errors and progress to userspace, either as a
- * result of a finished scrub, a canceled scrub or a progress inquiry
- */
-struct btrfs_scrub_progress {
- __u64 data_extents_scrubbed; /* # of data extents scrubbed */
- __u64 tree_extents_scrubbed; /* # of tree extents scrubbed */
- __u64 data_bytes_scrubbed; /* # of data bytes scrubbed */
- __u64 tree_bytes_scrubbed; /* # of tree bytes scrubbed */
- __u64 read_errors; /* # of read errors encountered (EIO) */
- __u64 csum_errors; /* # of failed csum checks */
- __u64 verify_errors; /* # of occurences, where the metadata
- * of a tree block did not match the
- * expected values, like generation or
- * logical */
- __u64 no_csum; /* # of 4k data block for which no csum
- * is present, probably the result of
- * data written with nodatasum */
- __u64 csum_discards; /* # of csum for which no data was found
- * in the extent tree. */
- __u64 super_errors; /* # of bad super blocks encountered */
- __u64 malloc_errors; /* # of internal kmalloc errors. These
- * will likely cause an incomplete
- * scrub */
- __u64 uncorrectable_errors; /* # of errors where either no intact
- * copy was found or the writeback
- * failed */
- __u64 corrected_errors; /* # of errors corrected */
- __u64 last_physical; /* last physical address scrubbed. In
- * case a scrub was aborted, this can
- * be used to restart the scrub */
- __u64 unverified_errors; /* # of occurences where a read for a
- * full (64k) bio failed, but the re-
- * check succeeded for each 4k piece.
- * Intermittent error. */
-};
-
-#define BTRFS_SCRUB_READONLY 1
-struct btrfs_ioctl_scrub_args {
- __u64 devid; /* in */
- __u64 start; /* in */
- __u64 end; /* in */
- __u64 flags; /* in */
- struct btrfs_scrub_progress progress; /* out */
- /* pad to 1k */
- __u64 unused[(1024-32-sizeof(struct btrfs_scrub_progress))/8];
-};
-
-#define BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS 0
-#define BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID 1
-struct btrfs_ioctl_dev_replace_start_params {
- __u64 srcdevid; /* in, if 0, use srcdev_name instead */
- __u64 cont_reading_from_srcdev_mode; /* in, see #define
- * above */
- __u8 srcdev_name[BTRFS_DEVICE_PATH_NAME_MAX + 1]; /* in */
- __u8 tgtdev_name[BTRFS_DEVICE_PATH_NAME_MAX + 1]; /* in */
-};
-
-#define BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED 0
-#define BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED 1
-#define BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED 2
-#define BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED 3
-#define BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED 4
-struct btrfs_ioctl_dev_replace_status_params {
- __u64 replace_state; /* out, see #define above */
- __u64 progress_1000; /* out, 0 <= x <= 1000 */
- __u64 time_started; /* out, seconds since 1-Jan-1970 */
- __u64 time_stopped; /* out, seconds since 1-Jan-1970 */
- __u64 num_write_errors; /* out */
- __u64 num_uncorrectable_read_errors; /* out */
-};
-
-#define BTRFS_IOCTL_DEV_REPLACE_CMD_START 0
-#define BTRFS_IOCTL_DEV_REPLACE_CMD_STATUS 1
-#define BTRFS_IOCTL_DEV_REPLACE_CMD_CANCEL 2
-#define BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR 0
-#define BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED 1
-#define BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED 2
-struct btrfs_ioctl_dev_replace_args {
- __u64 cmd; /* in */
- __u64 result; /* out */
-
- union {
- struct btrfs_ioctl_dev_replace_start_params start;
- struct btrfs_ioctl_dev_replace_status_params status;
- }; /* in/out */
-
- __u64 spare[64];
-};
-
-struct btrfs_ioctl_dev_info_args {
- __u64 devid; /* in/out */
- __u8 uuid[BTRFS_UUID_SIZE]; /* in/out */
- __u64 bytes_used; /* out */
- __u64 total_bytes; /* out */
- __u64 unused[379]; /* pad to 4k */
- __u8 path[BTRFS_DEVICE_PATH_NAME_MAX]; /* out */
-};
-
-struct btrfs_ioctl_fs_info_args {
- __u64 max_id; /* out */
- __u64 num_devices; /* out */
- __u8 fsid[BTRFS_FSID_SIZE]; /* out */
- __u64 reserved[124]; /* pad to 1k */
-};
-
-/* balance control ioctl modes */
-#define BTRFS_BALANCE_CTL_PAUSE 1
-#define BTRFS_BALANCE_CTL_CANCEL 2
-
-/*
- * this is packed, because it should be exactly the same as its disk
- * byte order counterpart (struct btrfs_disk_balance_args)
- */
-struct btrfs_balance_args {
- __u64 profiles;
- __u64 usage;
- __u64 devid;
- __u64 pstart;
- __u64 pend;
- __u64 vstart;
- __u64 vend;
-
- __u64 target;
-
- __u64 flags;
-
- __u64 unused[8];
-} __attribute__ ((__packed__));
-
-/* report balance progress to userspace */
-struct btrfs_balance_progress {
- __u64 expected; /* estimated # of chunks that will be
- * relocated to fulfill the request */
- __u64 considered; /* # of chunks we have considered so far */
- __u64 completed; /* # of chunks relocated so far */
-};
-
-#define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0)
-#define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1)
-#define BTRFS_BALANCE_STATE_CANCEL_REQ (1ULL << 2)
-
-struct btrfs_ioctl_balance_args {
- __u64 flags; /* in/out */
- __u64 state; /* out */
-
- struct btrfs_balance_args data; /* in/out */
- struct btrfs_balance_args meta; /* in/out */
- struct btrfs_balance_args sys; /* in/out */
-
- struct btrfs_balance_progress stat; /* out */
-
- __u64 unused[72]; /* pad to 1k */
-};
-
-#define BTRFS_INO_LOOKUP_PATH_MAX 4080
-struct btrfs_ioctl_ino_lookup_args {
- __u64 treeid;
- __u64 objectid;
- char name[BTRFS_INO_LOOKUP_PATH_MAX];
-};
-
-struct btrfs_ioctl_search_key {
- /* which root are we searching. 0 is the tree of tree roots */
- __u64 tree_id;
-
- /* keys returned will be >= min and <= max */
- __u64 min_objectid;
- __u64 max_objectid;
-
- /* keys returned will be >= min and <= max */
- __u64 min_offset;
- __u64 max_offset;
-
- /* max and min transids to search for */
- __u64 min_transid;
- __u64 max_transid;
-
- /* keys returned will be >= min and <= max */
- __u32 min_type;
- __u32 max_type;
-
- /*
- * how many items did userland ask for, and how many are we
- * returning
- */
- __u32 nr_items;
-
- /* align to 64 bits */
- __u32 unused;
-
- /* some extra for later */
- __u64 unused1;
- __u64 unused2;
- __u64 unused3;
- __u64 unused4;
-};
-
-struct btrfs_ioctl_search_header {
- __u64 transid;
- __u64 objectid;
- __u64 offset;
- __u32 type;
- __u32 len;
-};
-
-#define BTRFS_SEARCH_ARGS_BUFSIZE (4096 - sizeof(struct btrfs_ioctl_search_key))
-/*
- * the buf is an array of search headers where
- * each header is followed by the actual item
- * the type field is expanded to 32 bits for alignment
- */
-struct btrfs_ioctl_search_args {
- struct btrfs_ioctl_search_key key;
- char buf[BTRFS_SEARCH_ARGS_BUFSIZE];
-};
-
-struct btrfs_ioctl_clone_range_args {
- __s64 src_fd;
- __u64 src_offset, src_length;
- __u64 dest_offset;
-};
-
-/* flags for the defrag range ioctl */
-#define BTRFS_DEFRAG_RANGE_COMPRESS 1
-#define BTRFS_DEFRAG_RANGE_START_IO 2
-
-struct btrfs_ioctl_space_info {
- __u64 flags;
- __u64 total_bytes;
- __u64 used_bytes;
-};
-
-struct btrfs_ioctl_space_args {
- __u64 space_slots;
- __u64 total_spaces;
- struct btrfs_ioctl_space_info spaces[0];
-};
-
-struct btrfs_data_container {
- __u32 bytes_left; /* out -- bytes not needed to deliver output */
- __u32 bytes_missing; /* out -- additional bytes needed for result */
- __u32 elem_cnt; /* out */
- __u32 elem_missed; /* out */
- __u64 val[0]; /* out */
-};
-
-struct btrfs_ioctl_ino_path_args {
- __u64 inum; /* in */
- __u64 size; /* in */
- __u64 reserved[4];
- /* struct btrfs_data_container *fspath; out */
- __u64 fspath; /* out */
-};
-
-struct btrfs_ioctl_logical_ino_args {
- __u64 logical; /* in */
- __u64 size; /* in */
- __u64 reserved[4];
- /* struct btrfs_data_container *inodes; out */
- __u64 inodes;
-};
-
-enum btrfs_dev_stat_values {
- /* disk I/O failure stats */
- BTRFS_DEV_STAT_WRITE_ERRS, /* EIO or EREMOTEIO from lower layers */
- BTRFS_DEV_STAT_READ_ERRS, /* EIO or EREMOTEIO from lower layers */
- BTRFS_DEV_STAT_FLUSH_ERRS, /* EIO or EREMOTEIO from lower layers */
-
- /* stats for indirect indications for I/O failures */
- BTRFS_DEV_STAT_CORRUPTION_ERRS, /* checksum error, bytenr error or
- * contents is illegal: this is an
- * indication that the block was damaged
- * during read or write, or written to
- * wrong location or read from wrong
- * location */
- BTRFS_DEV_STAT_GENERATION_ERRS, /* an indication that blocks have not
- * been written */
-
- BTRFS_DEV_STAT_VALUES_MAX
-};
-
-/* Reset statistics after reading; needs SYS_ADMIN capability */
-#define BTRFS_DEV_STATS_RESET (1ULL << 0)
-
-struct btrfs_ioctl_get_dev_stats {
- __u64 devid; /* in */
- __u64 nr_items; /* in/out */
- __u64 flags; /* in/out */
-
- /* out values: */
- __u64 values[BTRFS_DEV_STAT_VALUES_MAX];
-
- __u64 unused[128 - 2 - BTRFS_DEV_STAT_VALUES_MAX]; /* pad to 1k */
-};
-
-#define BTRFS_QUOTA_CTL_ENABLE 1
-#define BTRFS_QUOTA_CTL_DISABLE 2
-#define BTRFS_QUOTA_CTL_RESCAN 3
-struct btrfs_ioctl_quota_ctl_args {
- __u64 cmd;
- __u64 status;
-};
-
-struct btrfs_ioctl_qgroup_assign_args {
- __u64 assign;
- __u64 src;
- __u64 dst;
-};
-
-struct btrfs_ioctl_qgroup_create_args {
- __u64 create;
- __u64 qgroupid;
-};
-struct btrfs_ioctl_timespec {
- __u64 sec;
- __u32 nsec;
-};
-
-struct btrfs_ioctl_received_subvol_args {
- char uuid[BTRFS_UUID_SIZE]; /* in */
- __u64 stransid; /* in */
- __u64 rtransid; /* out */
- struct btrfs_ioctl_timespec stime; /* in */
- struct btrfs_ioctl_timespec rtime; /* out */
- __u64 flags; /* in */
- __u64 reserved[16]; /* in */
-};
-
-struct btrfs_ioctl_send_args {
- __s64 send_fd; /* in */
- __u64 clone_sources_count; /* in */
- __u64 __user *clone_sources; /* in */
- __u64 parent_root; /* in */
- __u64 flags; /* in */
- __u64 reserved[4]; /* in */
-};
-
-#define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_RESIZE _IOW(BTRFS_IOCTL_MAGIC, 3, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_SCAN_DEV _IOW(BTRFS_IOCTL_MAGIC, 4, \
- struct btrfs_ioctl_vol_args)
-/* trans start and trans end are dangerous, and only for
- * use by applications that know how to avoid the
- * resulting deadlocks
- */
-#define BTRFS_IOC_TRANS_START _IO(BTRFS_IOCTL_MAGIC, 6)
-#define BTRFS_IOC_TRANS_END _IO(BTRFS_IOCTL_MAGIC, 7)
-#define BTRFS_IOC_SYNC _IO(BTRFS_IOCTL_MAGIC, 8)
-
-#define BTRFS_IOC_CLONE _IOW(BTRFS_IOCTL_MAGIC, 9, int)
-#define BTRFS_IOC_ADD_DEV _IOW(BTRFS_IOCTL_MAGIC, 10, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_RM_DEV _IOW(BTRFS_IOCTL_MAGIC, 11, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_BALANCE _IOW(BTRFS_IOCTL_MAGIC, 12, \
- struct btrfs_ioctl_vol_args)
-
-#define BTRFS_IOC_CLONE_RANGE _IOW(BTRFS_IOCTL_MAGIC, 13, \
- struct btrfs_ioctl_clone_range_args)
-
-#define BTRFS_IOC_SUBVOL_CREATE _IOW(BTRFS_IOCTL_MAGIC, 14, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_SNAP_DESTROY _IOW(BTRFS_IOCTL_MAGIC, 15, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_DEFRAG_RANGE _IOW(BTRFS_IOCTL_MAGIC, 16, \
- struct btrfs_ioctl_defrag_range_args)
-#define BTRFS_IOC_TREE_SEARCH _IOWR(BTRFS_IOCTL_MAGIC, 17, \
- struct btrfs_ioctl_search_args)
-#define BTRFS_IOC_INO_LOOKUP _IOWR(BTRFS_IOCTL_MAGIC, 18, \
- struct btrfs_ioctl_ino_lookup_args)
-#define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, u64)
-#define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \
- struct btrfs_ioctl_space_args)
-#define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64)
-#define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
-#define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
- struct btrfs_ioctl_vol_args_v2)
-#define BTRFS_IOC_SUBVOL_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 24, \
- struct btrfs_ioctl_vol_args_v2)
-#define BTRFS_IOC_SUBVOL_GETFLAGS _IOR(BTRFS_IOCTL_MAGIC, 25, __u64)
-#define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64)
-#define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \
- struct btrfs_ioctl_scrub_args)
-#define BTRFS_IOC_SCRUB_CANCEL _IO(BTRFS_IOCTL_MAGIC, 28)
-#define BTRFS_IOC_SCRUB_PROGRESS _IOWR(BTRFS_IOCTL_MAGIC, 29, \
- struct btrfs_ioctl_scrub_args)
-#define BTRFS_IOC_DEV_INFO _IOWR(BTRFS_IOCTL_MAGIC, 30, \
- struct btrfs_ioctl_dev_info_args)
-#define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \
- struct btrfs_ioctl_fs_info_args)
-#define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \
- struct btrfs_ioctl_balance_args)
-#define BTRFS_IOC_BALANCE_CTL _IOW(BTRFS_IOCTL_MAGIC, 33, int)
-#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 34, \
- struct btrfs_ioctl_balance_args)
-#define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \
- struct btrfs_ioctl_ino_path_args)
-#define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
- struct btrfs_ioctl_ino_path_args)
-#define BTRFS_IOC_SET_RECEIVED_SUBVOL _IOWR(BTRFS_IOCTL_MAGIC, 37, \
- struct btrfs_ioctl_received_subvol_args)
-#define BTRFS_IOC_SEND _IOW(BTRFS_IOCTL_MAGIC, 38, struct btrfs_ioctl_send_args)
-#define BTRFS_IOC_DEVICES_READY _IOR(BTRFS_IOCTL_MAGIC, 39, \
- struct btrfs_ioctl_vol_args)
-#define BTRFS_IOC_QUOTA_CTL _IOWR(BTRFS_IOCTL_MAGIC, 40, \
- struct btrfs_ioctl_quota_ctl_args)
-#define BTRFS_IOC_QGROUP_ASSIGN _IOW(BTRFS_IOCTL_MAGIC, 41, \
- struct btrfs_ioctl_qgroup_assign_args)
-#define BTRFS_IOC_QGROUP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 42, \
- struct btrfs_ioctl_qgroup_create_args)
-#define BTRFS_IOC_QGROUP_LIMIT _IOR(BTRFS_IOCTL_MAGIC, 43, \
- struct btrfs_ioctl_qgroup_limit_args)
-#define BTRFS_IOC_GET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 52, \
- struct btrfs_ioctl_get_dev_stats)
-#define BTRFS_IOC_DEV_REPLACE _IOWR(BTRFS_IOCTL_MAGIC, 53, \
- struct btrfs_ioctl_dev_replace_args)
-
-#endif
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 2a1762c..e95df43 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -113,11 +113,10 @@
read_unlock(&eb->lock);
return;
}
- read_unlock(&eb->lock);
- wait_event(eb->write_lock_wq, atomic_read(&eb->blocking_writers) == 0);
- read_lock(&eb->lock);
if (atomic_read(&eb->blocking_writers)) {
read_unlock(&eb->lock);
+ wait_event(eb->write_lock_wq,
+ atomic_read(&eb->blocking_writers) == 0);
goto again;
}
atomic_inc(&eb->read_locks);
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index ca52681..b81e0e9 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -26,7 +26,6 @@
void btrfs_tree_lock(struct extent_buffer *eb);
void btrfs_tree_unlock(struct extent_buffer *eb);
-int btrfs_try_spin_lock(struct extent_buffer *eb);
void btrfs_tree_read_lock(struct extent_buffer *eb);
void btrfs_tree_read_unlock(struct extent_buffer *eb);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index f107312..005c45d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -196,6 +196,9 @@
entry->file_offset = file_offset;
entry->start = start;
entry->len = len;
+ if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) &&
+ !(type == BTRFS_ORDERED_NOCOW))
+ entry->csum_bytes_left = disk_len;
entry->disk_len = disk_len;
entry->bytes_left = len;
entry->inode = igrab(inode);
@@ -213,6 +216,7 @@
INIT_LIST_HEAD(&entry->root_extent_list);
INIT_LIST_HEAD(&entry->work_list);
init_completion(&entry->completion);
+ INIT_LIST_HEAD(&entry->log_list);
trace_btrfs_ordered_extent_add(inode, entry);
@@ -270,6 +274,10 @@
tree = &BTRFS_I(inode)->ordered_tree;
spin_lock_irq(&tree->lock);
list_add_tail(&sum->list, &entry->list);
+ WARN_ON(entry->csum_bytes_left < sum->len);
+ entry->csum_bytes_left -= sum->len;
+ if (entry->csum_bytes_left == 0)
+ wake_up(&entry->wait);
spin_unlock_irq(&tree->lock);
}
@@ -405,6 +413,66 @@
return ret == 0;
}
+/* Needs to either be called under a log transaction or the log_mutex */
+void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode)
+{
+ struct btrfs_ordered_inode_tree *tree;
+ struct btrfs_ordered_extent *ordered;
+ struct rb_node *n;
+ int index = log->log_transid % 2;
+
+ tree = &BTRFS_I(inode)->ordered_tree;
+ spin_lock_irq(&tree->lock);
+ for (n = rb_first(&tree->tree); n; n = rb_next(n)) {
+ ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
+ spin_lock(&log->log_extents_lock[index]);
+ if (list_empty(&ordered->log_list)) {
+ list_add_tail(&ordered->log_list, &log->logged_list[index]);
+ atomic_inc(&ordered->refs);
+ }
+ spin_unlock(&log->log_extents_lock[index]);
+ }
+ spin_unlock_irq(&tree->lock);
+}
+
+void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
+{
+ struct btrfs_ordered_extent *ordered;
+ int index = transid % 2;
+
+ spin_lock_irq(&log->log_extents_lock[index]);
+ while (!list_empty(&log->logged_list[index])) {
+ ordered = list_first_entry(&log->logged_list[index],
+ struct btrfs_ordered_extent,
+ log_list);
+ list_del_init(&ordered->log_list);
+ spin_unlock_irq(&log->log_extents_lock[index]);
+ wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
+ &ordered->flags));
+ btrfs_put_ordered_extent(ordered);
+ spin_lock_irq(&log->log_extents_lock[index]);
+ }
+ spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
+void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid)
+{
+ struct btrfs_ordered_extent *ordered;
+ int index = transid % 2;
+
+ spin_lock_irq(&log->log_extents_lock[index]);
+ while (!list_empty(&log->logged_list[index])) {
+ ordered = list_first_entry(&log->logged_list[index],
+ struct btrfs_ordered_extent,
+ log_list);
+ list_del_init(&ordered->log_list);
+ spin_unlock_irq(&log->log_extents_lock[index]);
+ btrfs_put_ordered_extent(ordered);
+ spin_lock_irq(&log->log_extents_lock[index]);
+ }
+ spin_unlock_irq(&log->log_extents_lock[index]);
+}
+
/*
* used to drop a reference on an ordered extent. This will free
* the extent if the last reference is dropped
@@ -489,6 +557,7 @@
INIT_LIST_HEAD(&splice);
INIT_LIST_HEAD(&works);
+ mutex_lock(&root->fs_info->ordered_operations_mutex);
spin_lock(&root->fs_info->ordered_extent_lock);
list_splice_init(&root->fs_info->ordered_extents, &splice);
while (!list_empty(&splice)) {
@@ -532,6 +601,7 @@
cond_resched();
}
+ mutex_unlock(&root->fs_info->ordered_operations_mutex);
}
/*
@@ -544,10 +614,12 @@
* extra check to make sure the ordered operation list really is empty
* before we return
*/
-int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
+int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, int wait)
{
struct btrfs_inode *btrfs_inode;
struct inode *inode;
+ struct btrfs_transaction *cur_trans = trans->transaction;
struct list_head splice;
struct list_head works;
struct btrfs_delalloc_work *work, *next;
@@ -558,14 +630,10 @@
mutex_lock(&root->fs_info->ordered_operations_mutex);
spin_lock(&root->fs_info->ordered_extent_lock);
-again:
- list_splice_init(&root->fs_info->ordered_operations, &splice);
-
+ list_splice_init(&cur_trans->ordered_operations, &splice);
while (!list_empty(&splice)) {
-
btrfs_inode = list_entry(splice.next, struct btrfs_inode,
ordered_operations);
-
inode = &btrfs_inode->vfs_inode;
list_del_init(&btrfs_inode->ordered_operations);
@@ -574,24 +642,22 @@
* the inode may be getting freed (in sys_unlink path).
*/
inode = igrab(inode);
-
- if (!wait && inode) {
- list_add_tail(&BTRFS_I(inode)->ordered_operations,
- &root->fs_info->ordered_operations);
- }
-
if (!inode)
continue;
+
+ if (!wait)
+ list_add_tail(&BTRFS_I(inode)->ordered_operations,
+ &cur_trans->ordered_operations);
spin_unlock(&root->fs_info->ordered_extent_lock);
work = btrfs_alloc_delalloc_work(inode, wait, 1);
if (!work) {
+ spin_lock(&root->fs_info->ordered_extent_lock);
if (list_empty(&BTRFS_I(inode)->ordered_operations))
list_add_tail(&btrfs_inode->ordered_operations,
&splice);
- spin_lock(&root->fs_info->ordered_extent_lock);
list_splice_tail(&splice,
- &root->fs_info->ordered_operations);
+ &cur_trans->ordered_operations);
spin_unlock(&root->fs_info->ordered_extent_lock);
ret = -ENOMEM;
goto out;
@@ -603,9 +669,6 @@
cond_resched();
spin_lock(&root->fs_info->ordered_extent_lock);
}
- if (wait && !list_empty(&root->fs_info->ordered_operations))
- goto again;
-
spin_unlock(&root->fs_info->ordered_extent_lock);
out:
list_for_each_entry_safe(work, next, &works, list) {
@@ -836,9 +899,16 @@
* if the disk i_size is already at the inode->i_size, or
* this ordered extent is inside the disk i_size, we're done
*/
- if (disk_i_size == i_size || offset <= disk_i_size) {
+ if (disk_i_size == i_size)
goto out;
- }
+
+ /*
+ * We still need to update disk_i_size if outstanding_isize is greater
+ * than disk_i_size.
+ */
+ if (offset <= disk_i_size &&
+ (!ordered || ordered->outstanding_isize <= disk_i_size))
+ goto out;
/*
* walk backward from this ordered extent to disk_i_size.
@@ -870,7 +940,7 @@
break;
if (test->file_offset >= i_size)
break;
- if (test->file_offset >= disk_i_size) {
+ if (entry_end(test) > disk_i_size) {
/*
* we don't update disk_i_size now, so record this
* undealt i_size. Or we will not know the real
@@ -967,6 +1037,7 @@
void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode)
{
+ struct btrfs_transaction *cur_trans = trans->transaction;
u64 last_mod;
last_mod = max(BTRFS_I(inode)->generation, BTRFS_I(inode)->last_trans);
@@ -981,7 +1052,7 @@
spin_lock(&root->fs_info->ordered_extent_lock);
if (list_empty(&BTRFS_I(inode)->ordered_operations)) {
list_add_tail(&BTRFS_I(inode)->ordered_operations,
- &root->fs_info->ordered_operations);
+ &cur_trans->ordered_operations);
}
spin_unlock(&root->fs_info->ordered_extent_lock);
}
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index f29d4bf..8eadfe4 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -79,6 +79,8 @@
#define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
* has done its due diligence in updating
* the isize. */
+#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered
+ ordered extent */
struct btrfs_ordered_extent {
/* logical offset in the file */
@@ -96,6 +98,9 @@
/* number of bytes that still need writing */
u64 bytes_left;
+ /* number of bytes that still need csumming */
+ u64 csum_bytes_left;
+
/*
* the end of the ordered extent which is behind it but
* didn't update disk_i_size. Please see the comment of
@@ -118,6 +123,9 @@
/* list of checksums for insertion when the extent io is done */
struct list_head list;
+ /* If we need to wait on this to be done */
+ struct list_head log_list;
+
/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
wait_queue_head_t wait;
@@ -189,11 +197,15 @@
int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
struct btrfs_ordered_extent *ordered);
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum);
-int btrfs_run_ordered_operations(struct btrfs_root *root, int wait);
+int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, int wait);
void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode);
void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput);
+void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode);
+void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid);
+void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
int __init ordered_data_init(void);
void ordered_data_exit(void);
#endif
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 50d95fd..920957e 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -294,6 +294,7 @@
btrfs_dev_extent_chunk_offset(l, dev_extent),
(unsigned long long)
btrfs_dev_extent_length(l, dev_extent));
+ break;
case BTRFS_DEV_STATS_KEY:
printk(KERN_INFO "\t\tdevice stats\n");
break;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index a5c8562..b44124d 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -23,13 +23,13 @@
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
+#include <linux/btrfs.h>
#include "ctree.h"
#include "transaction.h"
#include "disk-io.h"
#include "locking.h"
#include "ulist.h"
-#include "ioctl.h"
#include "backref.h"
/* TODO XXX FIXME
@@ -620,7 +620,9 @@
key.offset = qgroupid;
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path)
+ return -ENOMEM;
+
ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret > 0)
ret = -ENOENT;
@@ -661,7 +663,9 @@
key.offset = qgroup->qgroupid;
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path)
+ return -ENOMEM;
+
ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret > 0)
ret = -ENOENT;
@@ -702,7 +706,9 @@
key.offset = 0;
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path)
+ return -ENOMEM;
+
ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret > 0)
ret = -ENOENT;
@@ -732,33 +738,38 @@
{
struct btrfs_path *path;
struct btrfs_key key;
+ struct extent_buffer *leaf = NULL;
int ret;
-
- if (!root)
- return -EINVAL;
+ int nr = 0;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
+ path->leave_spinning = 1;
+
+ key.objectid = 0;
+ key.offset = 0;
+ key.type = 0;
+
while (1) {
- key.objectid = 0;
- key.offset = 0;
- key.type = 0;
-
- path->leave_spinning = 1;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
- if (ret > 0) {
- if (path->slots[0] == 0)
- break;
- path->slots[0]--;
- } else if (ret < 0) {
+ if (ret < 0)
+ goto out;
+ leaf = path->nodes[0];
+ nr = btrfs_header_nritems(leaf);
+ if (!nr)
break;
- }
-
- ret = btrfs_del_item(trans, root, path);
+ /*
+ * delete the leaf one by one
+ * since the whole tree is going
+ * to be deleted.
+ */
+ path->slots[0] = 0;
+ ret = btrfs_del_items(trans, root, path, 0, nr);
if (ret)
goto out;
+
btrfs_release_path(path);
}
ret = 0;
@@ -847,6 +858,10 @@
int ret = 0;
spin_lock(&fs_info->qgroup_lock);
+ if (!fs_info->quota_root) {
+ spin_unlock(&fs_info->qgroup_lock);
+ return 0;
+ }
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
quota_root = fs_info->quota_root;
@@ -1138,7 +1153,7 @@
ret = btrfs_find_all_roots(trans, fs_info, node->bytenr,
sgn > 0 ? node->seq - 1 : node->seq, &roots);
if (ret < 0)
- goto out;
+ return ret;
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
@@ -1260,7 +1275,6 @@
ret = 0;
unlock:
spin_unlock(&fs_info->qgroup_lock);
-out:
ulist_free(roots);
ulist_free(tmp);
@@ -1510,21 +1524,23 @@
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
qg->reserved + qg->rfer + num_bytes >
- qg->max_rfer)
+ qg->max_rfer) {
ret = -EDQUOT;
+ goto out;
+ }
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
qg->reserved + qg->excl + num_bytes >
- qg->max_excl)
+ qg->max_excl) {
ret = -EDQUOT;
+ goto out;
+ }
list_for_each_entry(glist, &qg->groups, next_group) {
ulist_add(ulist, glist->group->qgroupid,
(uintptr_t)glist->group, GFP_ATOMIC);
}
}
- if (ret)
- goto out;
/*
* no limits exceeded, now record the reservation into all qgroups
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
new file mode 100644
index 0000000..9a79fb7
--- /dev/null
+++ b/fs/btrfs/raid56.c
@@ -0,0 +1,2100 @@
+/*
+ * Copyright (C) 2012 Fusion-io All rights reserved.
+ * Copyright (C) 2012 Intel Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/bio.h>
+#include <linux/slab.h>
+#include <linux/buffer_head.h>
+#include <linux/blkdev.h>
+#include <linux/random.h>
+#include <linux/iocontext.h>
+#include <linux/capability.h>
+#include <linux/ratelimit.h>
+#include <linux/kthread.h>
+#include <linux/raid/pq.h>
+#include <linux/hash.h>
+#include <linux/list_sort.h>
+#include <linux/raid/xor.h>
+#include <linux/vmalloc.h>
+#include <asm/div64.h>
+#include "compat.h"
+#include "ctree.h"
+#include "extent_map.h"
+#include "disk-io.h"
+#include "transaction.h"
+#include "print-tree.h"
+#include "volumes.h"
+#include "raid56.h"
+#include "async-thread.h"
+#include "check-integrity.h"
+#include "rcu-string.h"
+
+/* set when additional merges to this rbio are not allowed */
+#define RBIO_RMW_LOCKED_BIT 1
+
+/*
+ * set when this rbio is sitting in the hash, but it is just a cache
+ * of past RMW
+ */
+#define RBIO_CACHE_BIT 2
+
+/*
+ * set when it is safe to trust the stripe_pages for caching
+ */
+#define RBIO_CACHE_READY_BIT 3
+
+
+#define RBIO_CACHE_SIZE 1024
+
+struct btrfs_raid_bio {
+ struct btrfs_fs_info *fs_info;
+ struct btrfs_bio *bbio;
+
+ /*
+ * logical block numbers for the start of each stripe
+ * The last one or two are p/q. These are sorted,
+ * so raid_map[0] is the start of our full stripe
+ */
+ u64 *raid_map;
+
+ /* while we're doing rmw on a stripe
+ * we put it into a hash table so we can
+ * lock the stripe and merge more rbios
+ * into it.
+ */
+ struct list_head hash_list;
+
+ /*
+ * LRU list for the stripe cache
+ */
+ struct list_head stripe_cache;
+
+ /*
+ * for scheduling work in the helper threads
+ */
+ struct btrfs_work work;
+
+ /*
+ * bio list and bio_list_lock are used
+ * to add more bios into the stripe
+ * in hopes of avoiding the full rmw
+ */
+ struct bio_list bio_list;
+ spinlock_t bio_list_lock;
+
+ /* also protected by the bio_list_lock, the
+ * plug list is used by the plugging code
+ * to collect partial bios while plugged. The
+ * stripe locking code also uses it to hand off
+ * the stripe lock to the next pending IO
+ */
+ struct list_head plug_list;
+
+ /*
+ * flags that tell us if it is safe to
+ * merge with this bio
+ */
+ unsigned long flags;
+
+ /* size of each individual stripe on disk */
+ int stripe_len;
+
+ /* number of data stripes (no p/q) */
+ int nr_data;
+
+ /*
+ * set if we're doing a parity rebuild
+ * for a read from higher up, which is handled
+ * differently from a parity rebuild as part of
+ * rmw
+ */
+ int read_rebuild;
+
+ /* first bad stripe */
+ int faila;
+
+ /* second bad stripe (for raid6 use) */
+ int failb;
+
+ /*
+ * number of pages needed to represent the full
+ * stripe
+ */
+ int nr_pages;
+
+ /*
+ * size of all the bios in the bio_list. This
+ * helps us decide if the rbio maps to a full
+ * stripe or not
+ */
+ int bio_list_bytes;
+
+ atomic_t refs;
+
+ /*
+ * these are two arrays of pointers. We allocate the
+ * rbio big enough to hold them both and setup their
+ * locations when the rbio is allocated
+ */
+
+ /* pointers to pages that we allocated for
+ * reading/writing stripes directly from the disk (including P/Q)
+ */
+ struct page **stripe_pages;
+
+ /*
+ * pointers to the pages in the bio_list. Stored
+ * here for faster lookup
+ */
+ struct page **bio_pages;
+};
+
+static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
+static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
+static void rmw_work(struct btrfs_work *work);
+static void read_rebuild_work(struct btrfs_work *work);
+static void async_rmw_stripe(struct btrfs_raid_bio *rbio);
+static void async_read_rebuild(struct btrfs_raid_bio *rbio);
+static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
+static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed);
+static void __free_raid_bio(struct btrfs_raid_bio *rbio);
+static void index_rbio_pages(struct btrfs_raid_bio *rbio);
+static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);
+
+/*
+ * the stripe hash table is used for locking, and to collect
+ * bios in hopes of making a full stripe
+ */
+int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info)
+{
+ struct btrfs_stripe_hash_table *table;
+ struct btrfs_stripe_hash_table *x;
+ struct btrfs_stripe_hash *cur;
+ struct btrfs_stripe_hash *h;
+ int num_entries = 1 << BTRFS_STRIPE_HASH_TABLE_BITS;
+ int i;
+ int table_size;
+
+ if (info->stripe_hash_table)
+ return 0;
+
+ /*
+ * The table is large, starting with order 4 and can go as high as
+ * order 7 in case lock debugging is turned on.
+ *
+ * Try harder to allocate and fallback to vmalloc to lower the chance
+ * of a failing mount.
+ */
+ table_size = sizeof(*table) + sizeof(*h) * num_entries;
+ table = kzalloc(table_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!table) {
+ table = vzalloc(table_size);
+ if (!table)
+ return -ENOMEM;
+ }
+
+ spin_lock_init(&table->cache_lock);
+ INIT_LIST_HEAD(&table->stripe_cache);
+
+ h = table->table;
+
+ for (i = 0; i < num_entries; i++) {
+ cur = h + i;
+ INIT_LIST_HEAD(&cur->hash_list);
+ spin_lock_init(&cur->lock);
+ init_waitqueue_head(&cur->wait);
+ }
+
+ x = cmpxchg(&info->stripe_hash_table, NULL, table);
+ if (x) {
+ if (is_vmalloc_addr(x))
+ vfree(x);
+ else
+ kfree(x);
+ }
+ return 0;
+}
+
+/*
+ * caching an rbio means to copy anything from the
+ * bio_pages array into the stripe_pages array. We
+ * use the page uptodate bit in the stripe cache array
+ * to indicate if it has valid data
+ *
+ * once the caching is done, we set the cache ready
+ * bit.
+ */
+static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
+{
+ int i;
+ char *s;
+ char *d;
+ int ret;
+
+ ret = alloc_rbio_pages(rbio);
+ if (ret)
+ return;
+
+ for (i = 0; i < rbio->nr_pages; i++) {
+ if (!rbio->bio_pages[i])
+ continue;
+
+ s = kmap(rbio->bio_pages[i]);
+ d = kmap(rbio->stripe_pages[i]);
+
+ memcpy(d, s, PAGE_CACHE_SIZE);
+
+ kunmap(rbio->bio_pages[i]);
+ kunmap(rbio->stripe_pages[i]);
+ SetPageUptodate(rbio->stripe_pages[i]);
+ }
+ set_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
+}
+
+/*
+ * we hash on the first logical address of the stripe
+ */
+static int rbio_bucket(struct btrfs_raid_bio *rbio)
+{
+ u64 num = rbio->raid_map[0];
+
+ /*
+ * we shift down quite a bit. We're using byte
+ * addressing, and most of the lower bits are zeros.
+ * This tends to upset hash_64, and it consistently
+ * returns just one or two different values.
+ *
+ * shifting off the lower bits fixes things.
+ */
+ return hash_64(num >> 16, BTRFS_STRIPE_HASH_TABLE_BITS);
+}
+
+/*
+ * stealing an rbio means taking all the uptodate pages from the stripe
+ * array in the source rbio and putting them into the destination rbio
+ */
+static void steal_rbio(struct btrfs_raid_bio *src, struct btrfs_raid_bio *dest)
+{
+ int i;
+ struct page *s;
+ struct page *d;
+
+ if (!test_bit(RBIO_CACHE_READY_BIT, &src->flags))
+ return;
+
+ for (i = 0; i < dest->nr_pages; i++) {
+ s = src->stripe_pages[i];
+ if (!s || !PageUptodate(s)) {
+ continue;
+ }
+
+ d = dest->stripe_pages[i];
+ if (d)
+ __free_page(d);
+
+ dest->stripe_pages[i] = s;
+ src->stripe_pages[i] = NULL;
+ }
+}
+
+/*
+ * merging means we take the bio_list from the victim and
+ * splice it into the destination. The victim should
+ * be discarded afterwards.
+ *
+ * must be called with dest->rbio_list_lock held
+ */
+static void merge_rbio(struct btrfs_raid_bio *dest,
+ struct btrfs_raid_bio *victim)
+{
+ bio_list_merge(&dest->bio_list, &victim->bio_list);
+ dest->bio_list_bytes += victim->bio_list_bytes;
+ bio_list_init(&victim->bio_list);
+}
+
+/*
+ * used to prune items that are in the cache. The caller
+ * must hold the hash table lock.
+ */
+static void __remove_rbio_from_cache(struct btrfs_raid_bio *rbio)
+{
+ int bucket = rbio_bucket(rbio);
+ struct btrfs_stripe_hash_table *table;
+ struct btrfs_stripe_hash *h;
+ int freeit = 0;
+
+ /*
+ * check the bit again under the hash table lock.
+ */
+ if (!test_bit(RBIO_CACHE_BIT, &rbio->flags))
+ return;
+
+ table = rbio->fs_info->stripe_hash_table;
+ h = table->table + bucket;
+
+ /* hold the lock for the bucket because we may be
+ * removing it from the hash table
+ */
+ spin_lock(&h->lock);
+
+ /*
+ * hold the lock for the bio list because we need
+ * to make sure the bio list is empty
+ */
+ spin_lock(&rbio->bio_list_lock);
+
+ if (test_and_clear_bit(RBIO_CACHE_BIT, &rbio->flags)) {
+ list_del_init(&rbio->stripe_cache);
+ table->cache_size -= 1;
+ freeit = 1;
+
+ /* if the bio list isn't empty, this rbio is
+ * still involved in an IO. We take it out
+ * of the cache list, and drop the ref that
+ * was held for the list.
+ *
+ * If the bio_list was empty, we also remove
+ * the rbio from the hash_table, and drop
+ * the corresponding ref
+ */
+ if (bio_list_empty(&rbio->bio_list)) {
+ if (!list_empty(&rbio->hash_list)) {
+ list_del_init(&rbio->hash_list);
+ atomic_dec(&rbio->refs);
+ BUG_ON(!list_empty(&rbio->plug_list));
+ }
+ }
+ }
+
+ spin_unlock(&rbio->bio_list_lock);
+ spin_unlock(&h->lock);
+
+ if (freeit)
+ __free_raid_bio(rbio);
+}
+
+/*
+ * prune a given rbio from the cache
+ */
+static void remove_rbio_from_cache(struct btrfs_raid_bio *rbio)
+{
+ struct btrfs_stripe_hash_table *table;
+ unsigned long flags;
+
+ if (!test_bit(RBIO_CACHE_BIT, &rbio->flags))
+ return;
+
+ table = rbio->fs_info->stripe_hash_table;
+
+ spin_lock_irqsave(&table->cache_lock, flags);
+ __remove_rbio_from_cache(rbio);
+ spin_unlock_irqrestore(&table->cache_lock, flags);
+}
+
+/*
+ * remove everything in the cache
+ */
+void btrfs_clear_rbio_cache(struct btrfs_fs_info *info)
+{
+ struct btrfs_stripe_hash_table *table;
+ unsigned long flags;
+ struct btrfs_raid_bio *rbio;
+
+ table = info->stripe_hash_table;
+
+ spin_lock_irqsave(&table->cache_lock, flags);
+ while (!list_empty(&table->stripe_cache)) {
+ rbio = list_entry(table->stripe_cache.next,
+ struct btrfs_raid_bio,
+ stripe_cache);
+ __remove_rbio_from_cache(rbio);
+ }
+ spin_unlock_irqrestore(&table->cache_lock, flags);
+}
+
+/*
+ * remove all cached entries and free the hash table
+ * used by unmount
+ */
+void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info)
+{
+ if (!info->stripe_hash_table)
+ return;
+ btrfs_clear_rbio_cache(info);
+ if (is_vmalloc_addr(info->stripe_hash_table))
+ vfree(info->stripe_hash_table);
+ else
+ kfree(info->stripe_hash_table);
+ info->stripe_hash_table = NULL;
+}
+
+/*
+ * insert an rbio into the stripe cache. It
+ * must have already been prepared by calling
+ * cache_rbio_pages
+ *
+ * If this rbio was already cached, it gets
+ * moved to the front of the lru.
+ *
+ * If the size of the rbio cache is too big, we
+ * prune an item.
+ */
+static void cache_rbio(struct btrfs_raid_bio *rbio)
+{
+ struct btrfs_stripe_hash_table *table;
+ unsigned long flags;
+
+ if (!test_bit(RBIO_CACHE_READY_BIT, &rbio->flags))
+ return;
+
+ table = rbio->fs_info->stripe_hash_table;
+
+ spin_lock_irqsave(&table->cache_lock, flags);
+ spin_lock(&rbio->bio_list_lock);
+
+ /* bump our ref if we were not in the list before */
+ if (!test_and_set_bit(RBIO_CACHE_BIT, &rbio->flags))
+ atomic_inc(&rbio->refs);
+
+ if (!list_empty(&rbio->stripe_cache)){
+ list_move(&rbio->stripe_cache, &table->stripe_cache);
+ } else {
+ list_add(&rbio->stripe_cache, &table->stripe_cache);
+ table->cache_size += 1;
+ }
+
+ spin_unlock(&rbio->bio_list_lock);
+
+ if (table->cache_size > RBIO_CACHE_SIZE) {
+ struct btrfs_raid_bio *found;
+
+ found = list_entry(table->stripe_cache.prev,
+ struct btrfs_raid_bio,
+ stripe_cache);
+
+ if (found != rbio)
+ __remove_rbio_from_cache(found);
+ }
+
+ spin_unlock_irqrestore(&table->cache_lock, flags);
+ return;
+}
+
+/*
+ * helper function to run the xor_blocks api. It is only
+ * able to do MAX_XOR_BLOCKS at a time, so we need to
+ * loop through.
+ */
+static void run_xor(void **pages, int src_cnt, ssize_t len)
+{
+ int src_off = 0;
+ int xor_src_cnt = 0;
+ void *dest = pages[src_cnt];
+
+ while(src_cnt > 0) {
+ xor_src_cnt = min(src_cnt, MAX_XOR_BLOCKS);
+ xor_blocks(xor_src_cnt, len, dest, pages + src_off);
+
+ src_cnt -= xor_src_cnt;
+ src_off += xor_src_cnt;
+ }
+}
+
+/*
+ * returns true if the bio list inside this rbio
+ * covers an entire stripe (no rmw required).
+ * Must be called with the bio list lock held, or
+ * at a time when you know it is impossible to add
+ * new bios into the list
+ */
+static int __rbio_is_full(struct btrfs_raid_bio *rbio)
+{
+ unsigned long size = rbio->bio_list_bytes;
+ int ret = 1;
+
+ if (size != rbio->nr_data * rbio->stripe_len)
+ ret = 0;
+
+ BUG_ON(size > rbio->nr_data * rbio->stripe_len);
+ return ret;
+}
+
+static int rbio_is_full(struct btrfs_raid_bio *rbio)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&rbio->bio_list_lock, flags);
+ ret = __rbio_is_full(rbio);
+ spin_unlock_irqrestore(&rbio->bio_list_lock, flags);
+ return ret;
+}
+
+/*
+ * returns 1 if it is safe to merge two rbios together.
+ * The merging is safe if the two rbios correspond to
+ * the same stripe and if they are both going in the same
+ * direction (read vs write), and if neither one is
+ * locked for final IO
+ *
+ * The caller is responsible for locking such that
+ * rmw_locked is safe to test
+ */
+static int rbio_can_merge(struct btrfs_raid_bio *last,
+ struct btrfs_raid_bio *cur)
+{
+ if (test_bit(RBIO_RMW_LOCKED_BIT, &last->flags) ||
+ test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags))
+ return 0;
+
+ /*
+ * we can't merge with cached rbios, since the
+ * idea is that when we merge the destination
+ * rbio is going to run our IO for us. We can
+ * steal from cached rbio's though, other functions
+ * handle that.
+ */
+ if (test_bit(RBIO_CACHE_BIT, &last->flags) ||
+ test_bit(RBIO_CACHE_BIT, &cur->flags))
+ return 0;
+
+ if (last->raid_map[0] !=
+ cur->raid_map[0])
+ return 0;
+
+ /* reads can't merge with writes */
+ if (last->read_rebuild !=
+ cur->read_rebuild) {
+ return 0;
+ }
+
+ return 1;
+}
+
+/*
+ * helper to index into the pstripe
+ */
+static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
+{
+ index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
+ return rbio->stripe_pages[index];
+}
+
+/*
+ * helper to index into the qstripe, returns null
+ * if there is no qstripe
+ */
+static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
+{
+ if (rbio->nr_data + 1 == rbio->bbio->num_stripes)
+ return NULL;
+
+ index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
+ PAGE_CACHE_SHIFT;
+ return rbio->stripe_pages[index];
+}
+
+/*
+ * The first stripe in the table for a logical address
+ * has the lock. rbios are added in one of three ways:
+ *
+ * 1) Nobody has the stripe locked yet. The rbio is given
+ * the lock and 0 is returned. The caller must start the IO
+ * themselves.
+ *
+ * 2) Someone has the stripe locked, but we're able to merge
+ * with the lock owner. The rbio is freed and the IO will
+ * start automatically along with the existing rbio. 1 is returned.
+ *
+ * 3) Someone has the stripe locked, but we're not able to merge.
+ * The rbio is added to the lock owner's plug list, or merged into
+ * an rbio already on the plug list. When the lock owner unlocks,
+ * the next rbio on the list is run and the IO is started automatically.
+ * 1 is returned
+ *
+ * If we return 0, the caller still owns the rbio and must continue with
+ * IO submission. If we return 1, the caller must assume the rbio has
+ * already been freed.
+ */
+static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
+{
+ int bucket = rbio_bucket(rbio);
+ struct btrfs_stripe_hash *h = rbio->fs_info->stripe_hash_table->table + bucket;
+ struct btrfs_raid_bio *cur;
+ struct btrfs_raid_bio *pending;
+ unsigned long flags;
+ DEFINE_WAIT(wait);
+ struct btrfs_raid_bio *freeit = NULL;
+ struct btrfs_raid_bio *cache_drop = NULL;
+ int ret = 0;
+ int walk = 0;
+
+ spin_lock_irqsave(&h->lock, flags);
+ list_for_each_entry(cur, &h->hash_list, hash_list) {
+ walk++;
+ if (cur->raid_map[0] == rbio->raid_map[0]) {
+ spin_lock(&cur->bio_list_lock);
+
+ /* can we steal this cached rbio's pages? */
+ if (bio_list_empty(&cur->bio_list) &&
+ list_empty(&cur->plug_list) &&
+ test_bit(RBIO_CACHE_BIT, &cur->flags) &&
+ !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
+ list_del_init(&cur->hash_list);
+ atomic_dec(&cur->refs);
+
+ steal_rbio(cur, rbio);
+ cache_drop = cur;
+ spin_unlock(&cur->bio_list_lock);
+
+ goto lockit;
+ }
+
+ /* can we merge into the lock owner? */
+ if (rbio_can_merge(cur, rbio)) {
+ merge_rbio(cur, rbio);
+ spin_unlock(&cur->bio_list_lock);
+ freeit = rbio;
+ ret = 1;
+ goto out;
+ }
+
+
+ /*
+ * we couldn't merge with the running
+ * rbio, see if we can merge with the
+ * pending ones. We don't have to
+ * check for rmw_locked because there
+ * is no way they are inside finish_rmw
+ * right now
+ */
+ list_for_each_entry(pending, &cur->plug_list,
+ plug_list) {
+ if (rbio_can_merge(pending, rbio)) {
+ merge_rbio(pending, rbio);
+ spin_unlock(&cur->bio_list_lock);
+ freeit = rbio;
+ ret = 1;
+ goto out;
+ }
+ }
+
+ /* no merging, put us on the tail of the plug list,
+ * our rbio will be started with the currently
+ * running rbio unlocks
+ */
+ list_add_tail(&rbio->plug_list, &cur->plug_list);
+ spin_unlock(&cur->bio_list_lock);
+ ret = 1;
+ goto out;
+ }
+ }
+lockit:
+ atomic_inc(&rbio->refs);
+ list_add(&rbio->hash_list, &h->hash_list);
+out:
+ spin_unlock_irqrestore(&h->lock, flags);
+ if (cache_drop)
+ remove_rbio_from_cache(cache_drop);
+ if (freeit)
+ __free_raid_bio(freeit);
+ return ret;
+}
+
+/*
+ * called as rmw or parity rebuild is completed. If the plug list has more
+ * rbios waiting for this stripe, the next one on the list will be started
+ */
+static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
+{
+ int bucket;
+ struct btrfs_stripe_hash *h;
+ unsigned long flags;
+ int keep_cache = 0;
+
+ bucket = rbio_bucket(rbio);
+ h = rbio->fs_info->stripe_hash_table->table + bucket;
+
+ if (list_empty(&rbio->plug_list))
+ cache_rbio(rbio);
+
+ spin_lock_irqsave(&h->lock, flags);
+ spin_lock(&rbio->bio_list_lock);
+
+ if (!list_empty(&rbio->hash_list)) {
+ /*
+ * if we're still cached and there is no other IO
+ * to perform, just leave this rbio here for others
+ * to steal from later
+ */
+ if (list_empty(&rbio->plug_list) &&
+ test_bit(RBIO_CACHE_BIT, &rbio->flags)) {
+ keep_cache = 1;
+ clear_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
+ BUG_ON(!bio_list_empty(&rbio->bio_list));
+ goto done;
+ }
+
+ list_del_init(&rbio->hash_list);
+ atomic_dec(&rbio->refs);
+
+ /*
+ * we use the plug list to hold all the rbios
+ * waiting for the chance to lock this stripe.
+ * hand the lock over to one of them.
+ */
+ if (!list_empty(&rbio->plug_list)) {
+ struct btrfs_raid_bio *next;
+ struct list_head *head = rbio->plug_list.next;
+
+ next = list_entry(head, struct btrfs_raid_bio,
+ plug_list);
+
+ list_del_init(&rbio->plug_list);
+
+ list_add(&next->hash_list, &h->hash_list);
+ atomic_inc(&next->refs);
+ spin_unlock(&rbio->bio_list_lock);
+ spin_unlock_irqrestore(&h->lock, flags);
+
+ if (next->read_rebuild)
+ async_read_rebuild(next);
+ else {
+ steal_rbio(rbio, next);
+ async_rmw_stripe(next);
+ }
+
+ goto done_nolock;
+ } else if (waitqueue_active(&h->wait)) {
+ spin_unlock(&rbio->bio_list_lock);
+ spin_unlock_irqrestore(&h->lock, flags);
+ wake_up(&h->wait);
+ goto done_nolock;
+ }
+ }
+done:
+ spin_unlock(&rbio->bio_list_lock);
+ spin_unlock_irqrestore(&h->lock, flags);
+
+done_nolock:
+ if (!keep_cache)
+ remove_rbio_from_cache(rbio);
+}
+
+static void __free_raid_bio(struct btrfs_raid_bio *rbio)
+{
+ int i;
+
+ WARN_ON(atomic_read(&rbio->refs) < 0);
+ if (!atomic_dec_and_test(&rbio->refs))
+ return;
+
+ WARN_ON(!list_empty(&rbio->stripe_cache));
+ WARN_ON(!list_empty(&rbio->hash_list));
+ WARN_ON(!bio_list_empty(&rbio->bio_list));
+
+ for (i = 0; i < rbio->nr_pages; i++) {
+ if (rbio->stripe_pages[i]) {
+ __free_page(rbio->stripe_pages[i]);
+ rbio->stripe_pages[i] = NULL;
+ }
+ }
+ kfree(rbio->raid_map);
+ kfree(rbio->bbio);
+ kfree(rbio);
+}
+
+static void free_raid_bio(struct btrfs_raid_bio *rbio)
+{
+ unlock_stripe(rbio);
+ __free_raid_bio(rbio);
+}
+
+/*
+ * this frees the rbio and runs through all the bios in the
+ * bio_list and calls end_io on them
+ */
+static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate)
+{
+ struct bio *cur = bio_list_get(&rbio->bio_list);
+ struct bio *next;
+ free_raid_bio(rbio);
+
+ while (cur) {
+ next = cur->bi_next;
+ cur->bi_next = NULL;
+ if (uptodate)
+ set_bit(BIO_UPTODATE, &cur->bi_flags);
+ bio_endio(cur, err);
+ cur = next;
+ }
+}
+
+/*
+ * end io function used by finish_rmw. When we finally
+ * get here, we've written a full stripe
+ */
+static void raid_write_end_io(struct bio *bio, int err)
+{
+ struct btrfs_raid_bio *rbio = bio->bi_private;
+
+ if (err)
+ fail_bio_stripe(rbio, bio);
+
+ bio_put(bio);
+
+ if (!atomic_dec_and_test(&rbio->bbio->stripes_pending))
+ return;
+
+ err = 0;
+
+ /* OK, we have read all the stripes we need to. */
+ if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
+ err = -EIO;
+
+ rbio_orig_end_io(rbio, err, 0);
+ return;
+}
+
+/*
+ * the read/modify/write code wants to use the original bio for
+ * any pages it included, and then use the rbio for everything
+ * else. This function decides if a given index (stripe number)
+ * and page number in that stripe fall inside the original bio
+ * or the rbio.
+ *
+ * if you set bio_list_only, you'll get a NULL back for any ranges
+ * that are outside the bio_list
+ *
+ * This doesn't take any refs on anything, you get a bare page pointer
+ * and the caller must bump refs as required.
+ *
+ * You must call index_rbio_pages once before you can trust
+ * the answers from this function.
+ */
+static struct page *page_in_rbio(struct btrfs_raid_bio *rbio,
+ int index, int pagenr, int bio_list_only)
+{
+ int chunk_page;
+ struct page *p = NULL;
+
+ chunk_page = index * (rbio->stripe_len >> PAGE_SHIFT) + pagenr;
+
+ spin_lock_irq(&rbio->bio_list_lock);
+ p = rbio->bio_pages[chunk_page];
+ spin_unlock_irq(&rbio->bio_list_lock);
+
+ if (p || bio_list_only)
+ return p;
+
+ return rbio->stripe_pages[chunk_page];
+}
+
+/*
+ * number of pages we need for the entire stripe across all the
+ * drives
+ */
+static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
+{
+ unsigned long nr = stripe_len * nr_stripes;
+ return (nr + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+}
+
+/*
+ * allocation and initial setup for the btrfs_raid_bio. Not
+ * this does not allocate any pages for rbio->pages.
+ */
+static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len)
+{
+ struct btrfs_raid_bio *rbio;
+ int nr_data = 0;
+ int num_pages = rbio_nr_pages(stripe_len, bbio->num_stripes);
+ void *p;
+
+ rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2,
+ GFP_NOFS);
+ if (!rbio) {
+ kfree(raid_map);
+ kfree(bbio);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ bio_list_init(&rbio->bio_list);
+ INIT_LIST_HEAD(&rbio->plug_list);
+ spin_lock_init(&rbio->bio_list_lock);
+ INIT_LIST_HEAD(&rbio->stripe_cache);
+ INIT_LIST_HEAD(&rbio->hash_list);
+ rbio->bbio = bbio;
+ rbio->raid_map = raid_map;
+ rbio->fs_info = root->fs_info;
+ rbio->stripe_len = stripe_len;
+ rbio->nr_pages = num_pages;
+ rbio->faila = -1;
+ rbio->failb = -1;
+ atomic_set(&rbio->refs, 1);
+
+ /*
+ * the stripe_pages and bio_pages array point to the extra
+ * memory we allocated past the end of the rbio
+ */
+ p = rbio + 1;
+ rbio->stripe_pages = p;
+ rbio->bio_pages = p + sizeof(struct page *) * num_pages;
+
+ if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE)
+ nr_data = bbio->num_stripes - 2;
+ else
+ nr_data = bbio->num_stripes - 1;
+
+ rbio->nr_data = nr_data;
+ return rbio;
+}
+
+/* allocate pages for all the stripes in the bio, including parity */
+static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
+{
+ int i;
+ struct page *page;
+
+ for (i = 0; i < rbio->nr_pages; i++) {
+ if (rbio->stripe_pages[i])
+ continue;
+ page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (!page)
+ return -ENOMEM;
+ rbio->stripe_pages[i] = page;
+ ClearPageUptodate(page);
+ }
+ return 0;
+}
+
+/* allocate pages for just the p/q stripes */
+static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
+{
+ int i;
+ struct page *page;
+
+ i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
+
+ for (; i < rbio->nr_pages; i++) {
+ if (rbio->stripe_pages[i])
+ continue;
+ page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (!page)
+ return -ENOMEM;
+ rbio->stripe_pages[i] = page;
+ }
+ return 0;
+}
+
+/*
+ * add a single page from a specific stripe into our list of bios for IO
+ * this will try to merge into existing bios if possible, and returns
+ * zero if all went well.
+ */
+int rbio_add_io_page(struct btrfs_raid_bio *rbio,
+ struct bio_list *bio_list,
+ struct page *page,
+ int stripe_nr,
+ unsigned long page_index,
+ unsigned long bio_max_len)
+{
+ struct bio *last = bio_list->tail;
+ u64 last_end = 0;
+ int ret;
+ struct bio *bio;
+ struct btrfs_bio_stripe *stripe;
+ u64 disk_start;
+
+ stripe = &rbio->bbio->stripes[stripe_nr];
+ disk_start = stripe->physical + (page_index << PAGE_CACHE_SHIFT);
+
+ /* if the device is missing, just fail this stripe */
+ if (!stripe->dev->bdev)
+ return fail_rbio_index(rbio, stripe_nr);
+
+ /* see if we can add this page onto our existing bio */
+ if (last) {
+ last_end = (u64)last->bi_sector << 9;
+ last_end += last->bi_size;
+
+ /*
+ * we can't merge these if they are from different
+ * devices or if they are not contiguous
+ */
+ if (last_end == disk_start && stripe->dev->bdev &&
+ test_bit(BIO_UPTODATE, &last->bi_flags) &&
+ last->bi_bdev == stripe->dev->bdev) {
+ ret = bio_add_page(last, page, PAGE_CACHE_SIZE, 0);
+ if (ret == PAGE_CACHE_SIZE)
+ return 0;
+ }
+ }
+
+ /* put a new bio on the list */
+ bio = bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1);
+ if (!bio)
+ return -ENOMEM;
+
+ bio->bi_size = 0;
+ bio->bi_bdev = stripe->dev->bdev;
+ bio->bi_sector = disk_start >> 9;
+ set_bit(BIO_UPTODATE, &bio->bi_flags);
+
+ bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
+ bio_list_add(bio_list, bio);
+ return 0;
+}
+
+/*
+ * while we're doing the read/modify/write cycle, we could
+ * have errors in reading pages off the disk. This checks
+ * for errors and if we're not able to read the page it'll
+ * trigger parity reconstruction. The rmw will be finished
+ * after we've reconstructed the failed stripes
+ */
+static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
+{
+ if (rbio->faila >= 0 || rbio->failb >= 0) {
+ BUG_ON(rbio->faila == rbio->bbio->num_stripes - 1);
+ __raid56_parity_recover(rbio);
+ } else {
+ finish_rmw(rbio);
+ }
+}
+
+/*
+ * these are just the pages from the rbio array, not from anything
+ * the FS sent down to us
+ */
+static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, int page)
+{
+ int index;
+ index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT);
+ index += page;
+ return rbio->stripe_pages[index];
+}
+
+/*
+ * helper function to walk our bio list and populate the bio_pages array with
+ * the result. This seems expensive, but it is faster than constantly
+ * searching through the bio list as we setup the IO in finish_rmw or stripe
+ * reconstruction.
+ *
+ * This must be called before you trust the answers from page_in_rbio
+ */
+static void index_rbio_pages(struct btrfs_raid_bio *rbio)
+{
+ struct bio *bio;
+ u64 start;
+ unsigned long stripe_offset;
+ unsigned long page_index;
+ struct page *p;
+ int i;
+
+ spin_lock_irq(&rbio->bio_list_lock);
+ bio_list_for_each(bio, &rbio->bio_list) {
+ start = (u64)bio->bi_sector << 9;
+ stripe_offset = start - rbio->raid_map[0];
+ page_index = stripe_offset >> PAGE_CACHE_SHIFT;
+
+ for (i = 0; i < bio->bi_vcnt; i++) {
+ p = bio->bi_io_vec[i].bv_page;
+ rbio->bio_pages[page_index + i] = p;
+ }
+ }
+ spin_unlock_irq(&rbio->bio_list_lock);
+}
+
+/*
+ * this is called from one of two situations. We either
+ * have a full stripe from the higher layers, or we've read all
+ * the missing bits off disk.
+ *
+ * This will calculate the parity and then send down any
+ * changed blocks.
+ */
+static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
+{
+ struct btrfs_bio *bbio = rbio->bbio;
+ void *pointers[bbio->num_stripes];
+ int stripe_len = rbio->stripe_len;
+ int nr_data = rbio->nr_data;
+ int stripe;
+ int pagenr;
+ int p_stripe = -1;
+ int q_stripe = -1;
+ struct bio_list bio_list;
+ struct bio *bio;
+ int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
+ int ret;
+
+ bio_list_init(&bio_list);
+
+ if (bbio->num_stripes - rbio->nr_data == 1) {
+ p_stripe = bbio->num_stripes - 1;
+ } else if (bbio->num_stripes - rbio->nr_data == 2) {
+ p_stripe = bbio->num_stripes - 2;
+ q_stripe = bbio->num_stripes - 1;
+ } else {
+ BUG();
+ }
+
+ /* at this point we either have a full stripe,
+ * or we've read the full stripe from the drive.
+ * recalculate the parity and write the new results.
+ *
+ * We're not allowed to add any new bios to the
+ * bio list here, anyone else that wants to
+ * change this stripe needs to do their own rmw.
+ */
+ spin_lock_irq(&rbio->bio_list_lock);
+ set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
+ spin_unlock_irq(&rbio->bio_list_lock);
+
+ atomic_set(&rbio->bbio->error, 0);
+
+ /*
+ * now that we've set rmw_locked, run through the
+ * bio list one last time and map the page pointers
+ *
+ * We don't cache full rbios because we're assuming
+ * the higher layers are unlikely to use this area of
+ * the disk again soon. If they do use it again,
+ * hopefully they will send another full bio.
+ */
+ index_rbio_pages(rbio);
+ if (!rbio_is_full(rbio))
+ cache_rbio_pages(rbio);
+ else
+ clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
+
+ for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ struct page *p;
+ /* first collect one page from each data stripe */
+ for (stripe = 0; stripe < nr_data; stripe++) {
+ p = page_in_rbio(rbio, stripe, pagenr, 0);
+ pointers[stripe] = kmap(p);
+ }
+
+ /* then add the parity stripe */
+ p = rbio_pstripe_page(rbio, pagenr);
+ SetPageUptodate(p);
+ pointers[stripe++] = kmap(p);
+
+ if (q_stripe != -1) {
+
+ /*
+ * raid6, add the qstripe and call the
+ * library function to fill in our p/q
+ */
+ p = rbio_qstripe_page(rbio, pagenr);
+ SetPageUptodate(p);
+ pointers[stripe++] = kmap(p);
+
+ raid6_call.gen_syndrome(bbio->num_stripes, PAGE_SIZE,
+ pointers);
+ } else {
+ /* raid5 */
+ memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+ run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE);
+ }
+
+
+ for (stripe = 0; stripe < bbio->num_stripes; stripe++)
+ kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+ }
+
+ /*
+ * time to start writing. Make bios for everything from the
+ * higher layers (the bio_list in our rbio) and our p/q. Ignore
+ * everything else.
+ */
+ for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
+ for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ struct page *page;
+ if (stripe < rbio->nr_data) {
+ page = page_in_rbio(rbio, stripe, pagenr, 1);
+ if (!page)
+ continue;
+ } else {
+ page = rbio_stripe_page(rbio, stripe, pagenr);
+ }
+
+ ret = rbio_add_io_page(rbio, &bio_list,
+ page, stripe, pagenr, rbio->stripe_len);
+ if (ret)
+ goto cleanup;
+ }
+ }
+
+ atomic_set(&bbio->stripes_pending, bio_list_size(&bio_list));
+ BUG_ON(atomic_read(&bbio->stripes_pending) == 0);
+
+ while (1) {
+ bio = bio_list_pop(&bio_list);
+ if (!bio)
+ break;
+
+ bio->bi_private = rbio;
+ bio->bi_end_io = raid_write_end_io;
+ BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
+ submit_bio(WRITE, bio);
+ }
+ return;
+
+cleanup:
+ rbio_orig_end_io(rbio, -EIO, 0);
+}
+
+/*
+ * helper to find the stripe number for a given bio. Used to figure out which
+ * stripe has failed. This expects the bio to correspond to a physical disk,
+ * so it looks up based on physical sector numbers.
+ */
+static int find_bio_stripe(struct btrfs_raid_bio *rbio,
+ struct bio *bio)
+{
+ u64 physical = bio->bi_sector;
+ u64 stripe_start;
+ int i;
+ struct btrfs_bio_stripe *stripe;
+
+ physical <<= 9;
+
+ for (i = 0; i < rbio->bbio->num_stripes; i++) {
+ stripe = &rbio->bbio->stripes[i];
+ stripe_start = stripe->physical;
+ if (physical >= stripe_start &&
+ physical < stripe_start + rbio->stripe_len) {
+ return i;
+ }
+ }
+ return -1;
+}
+
+/*
+ * helper to find the stripe number for a given
+ * bio (before mapping). Used to figure out which stripe has
+ * failed. This looks up based on logical block numbers.
+ */
+static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
+ struct bio *bio)
+{
+ u64 logical = bio->bi_sector;
+ u64 stripe_start;
+ int i;
+
+ logical <<= 9;
+
+ for (i = 0; i < rbio->nr_data; i++) {
+ stripe_start = rbio->raid_map[i];
+ if (logical >= stripe_start &&
+ logical < stripe_start + rbio->stripe_len) {
+ return i;
+ }
+ }
+ return -1;
+}
+
+/*
+ * returns -EIO if we had too many failures
+ */
+static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ spin_lock_irqsave(&rbio->bio_list_lock, flags);
+
+ /* we already know this stripe is bad, move on */
+ if (rbio->faila == failed || rbio->failb == failed)
+ goto out;
+
+ if (rbio->faila == -1) {
+ /* first failure on this rbio */
+ rbio->faila = failed;
+ atomic_inc(&rbio->bbio->error);
+ } else if (rbio->failb == -1) {
+ /* second failure on this rbio */
+ rbio->failb = failed;
+ atomic_inc(&rbio->bbio->error);
+ } else {
+ ret = -EIO;
+ }
+out:
+ spin_unlock_irqrestore(&rbio->bio_list_lock, flags);
+
+ return ret;
+}
+
+/*
+ * helper to fail a stripe based on a physical disk
+ * bio.
+ */
+static int fail_bio_stripe(struct btrfs_raid_bio *rbio,
+ struct bio *bio)
+{
+ int failed = find_bio_stripe(rbio, bio);
+
+ if (failed < 0)
+ return -EIO;
+
+ return fail_rbio_index(rbio, failed);
+}
+
+/*
+ * this sets each page in the bio uptodate. It should only be used on private
+ * rbio pages, nothing that comes in from the higher layers
+ */
+static void set_bio_pages_uptodate(struct bio *bio)
+{
+ int i;
+ struct page *p;
+
+ for (i = 0; i < bio->bi_vcnt; i++) {
+ p = bio->bi_io_vec[i].bv_page;
+ SetPageUptodate(p);
+ }
+}
+
+/*
+ * end io for the read phase of the rmw cycle. All the bios here are physical
+ * stripe bios we've read from the disk so we can recalculate the parity of the
+ * stripe.
+ *
+ * This will usually kick off finish_rmw once all the bios are read in, but it
+ * may trigger parity reconstruction if we had any errors along the way
+ */
+static void raid_rmw_end_io(struct bio *bio, int err)
+{
+ struct btrfs_raid_bio *rbio = bio->bi_private;
+
+ if (err)
+ fail_bio_stripe(rbio, bio);
+ else
+ set_bio_pages_uptodate(bio);
+
+ bio_put(bio);
+
+ if (!atomic_dec_and_test(&rbio->bbio->stripes_pending))
+ return;
+
+ err = 0;
+ if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
+ goto cleanup;
+
+ /*
+ * this will normally call finish_rmw to start our write
+ * but if there are any failed stripes we'll reconstruct
+ * from parity first
+ */
+ validate_rbio_for_rmw(rbio);
+ return;
+
+cleanup:
+
+ rbio_orig_end_io(rbio, -EIO, 0);
+}
+
+static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
+{
+ rbio->work.flags = 0;
+ rbio->work.func = rmw_work;
+
+ btrfs_queue_worker(&rbio->fs_info->rmw_workers,
+ &rbio->work);
+}
+
+static void async_read_rebuild(struct btrfs_raid_bio *rbio)
+{
+ rbio->work.flags = 0;
+ rbio->work.func = read_rebuild_work;
+
+ btrfs_queue_worker(&rbio->fs_info->rmw_workers,
+ &rbio->work);
+}
+
+/*
+ * the stripe must be locked by the caller. It will
+ * unlock after all the writes are done
+ */
+static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
+{
+ int bios_to_read = 0;
+ struct btrfs_bio *bbio = rbio->bbio;
+ struct bio_list bio_list;
+ int ret;
+ int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ int pagenr;
+ int stripe;
+ struct bio *bio;
+
+ bio_list_init(&bio_list);
+
+ ret = alloc_rbio_pages(rbio);
+ if (ret)
+ goto cleanup;
+
+ index_rbio_pages(rbio);
+
+ atomic_set(&rbio->bbio->error, 0);
+ /*
+ * build a list of bios to read all the missing parts of this
+ * stripe
+ */
+ for (stripe = 0; stripe < rbio->nr_data; stripe++) {
+ for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ struct page *page;
+ /*
+ * we want to find all the pages missing from
+ * the rbio and read them from the disk. If
+ * page_in_rbio finds a page in the bio list
+ * we don't need to read it off the stripe.
+ */
+ page = page_in_rbio(rbio, stripe, pagenr, 1);
+ if (page)
+ continue;
+
+ page = rbio_stripe_page(rbio, stripe, pagenr);
+ /*
+ * the bio cache may have handed us an uptodate
+ * page. If so, be happy and use it
+ */
+ if (PageUptodate(page))
+ continue;
+
+ ret = rbio_add_io_page(rbio, &bio_list, page,
+ stripe, pagenr, rbio->stripe_len);
+ if (ret)
+ goto cleanup;
+ }
+ }
+
+ bios_to_read = bio_list_size(&bio_list);
+ if (!bios_to_read) {
+ /*
+ * this can happen if others have merged with
+ * us, it means there is nothing left to read.
+ * But if there are missing devices it may not be
+ * safe to do the full stripe write yet.
+ */
+ goto finish;
+ }
+
+ /*
+ * the bbio may be freed once we submit the last bio. Make sure
+ * not to touch it after that
+ */
+ atomic_set(&bbio->stripes_pending, bios_to_read);
+ while (1) {
+ bio = bio_list_pop(&bio_list);
+ if (!bio)
+ break;
+
+ bio->bi_private = rbio;
+ bio->bi_end_io = raid_rmw_end_io;
+
+ btrfs_bio_wq_end_io(rbio->fs_info, bio,
+ BTRFS_WQ_ENDIO_RAID56);
+
+ BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
+ submit_bio(READ, bio);
+ }
+ /* the actual write will happen once the reads are done */
+ return 0;
+
+cleanup:
+ rbio_orig_end_io(rbio, -EIO, 0);
+ return -EIO;
+
+finish:
+ validate_rbio_for_rmw(rbio);
+ return 0;
+}
+
+/*
+ * if the upper layers pass in a full stripe, we thank them by only allocating
+ * enough pages to hold the parity, and sending it all down quickly.
+ */
+static int full_stripe_write(struct btrfs_raid_bio *rbio)
+{
+ int ret;
+
+ ret = alloc_rbio_parity_pages(rbio);
+ if (ret)
+ return ret;
+
+ ret = lock_stripe_add(rbio);
+ if (ret == 0)
+ finish_rmw(rbio);
+ return 0;
+}
+
+/*
+ * partial stripe writes get handed over to async helpers.
+ * We're really hoping to merge a few more writes into this
+ * rbio before calculating new parity
+ */
+static int partial_stripe_write(struct btrfs_raid_bio *rbio)
+{
+ int ret;
+
+ ret = lock_stripe_add(rbio);
+ if (ret == 0)
+ async_rmw_stripe(rbio);
+ return 0;
+}
+
+/*
+ * sometimes while we were reading from the drive to
+ * recalculate parity, enough new bios come into create
+ * a full stripe. So we do a check here to see if we can
+ * go directly to finish_rmw
+ */
+static int __raid56_parity_write(struct btrfs_raid_bio *rbio)
+{
+ /* head off into rmw land if we don't have a full stripe */
+ if (!rbio_is_full(rbio))
+ return partial_stripe_write(rbio);
+ return full_stripe_write(rbio);
+}
+
+/*
+ * We use plugging call backs to collect full stripes.
+ * Any time we get a partial stripe write while plugged
+ * we collect it into a list. When the unplug comes down,
+ * we sort the list by logical block number and merge
+ * everything we can into the same rbios
+ */
+struct btrfs_plug_cb {
+ struct blk_plug_cb cb;
+ struct btrfs_fs_info *info;
+ struct list_head rbio_list;
+ struct btrfs_work work;
+};
+
+/*
+ * rbios on the plug list are sorted for easier merging.
+ */
+static int plug_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+ struct btrfs_raid_bio *ra = container_of(a, struct btrfs_raid_bio,
+ plug_list);
+ struct btrfs_raid_bio *rb = container_of(b, struct btrfs_raid_bio,
+ plug_list);
+ u64 a_sector = ra->bio_list.head->bi_sector;
+ u64 b_sector = rb->bio_list.head->bi_sector;
+
+ if (a_sector < b_sector)
+ return -1;
+ if (a_sector > b_sector)
+ return 1;
+ return 0;
+}
+
+static void run_plug(struct btrfs_plug_cb *plug)
+{
+ struct btrfs_raid_bio *cur;
+ struct btrfs_raid_bio *last = NULL;
+
+ /*
+ * sort our plug list then try to merge
+ * everything we can in hopes of creating full
+ * stripes.
+ */
+ list_sort(NULL, &plug->rbio_list, plug_cmp);
+ while (!list_empty(&plug->rbio_list)) {
+ cur = list_entry(plug->rbio_list.next,
+ struct btrfs_raid_bio, plug_list);
+ list_del_init(&cur->plug_list);
+
+ if (rbio_is_full(cur)) {
+ /* we have a full stripe, send it down */
+ full_stripe_write(cur);
+ continue;
+ }
+ if (last) {
+ if (rbio_can_merge(last, cur)) {
+ merge_rbio(last, cur);
+ __free_raid_bio(cur);
+ continue;
+
+ }
+ __raid56_parity_write(last);
+ }
+ last = cur;
+ }
+ if (last) {
+ __raid56_parity_write(last);
+ }
+ kfree(plug);
+}
+
+/*
+ * if the unplug comes from schedule, we have to push the
+ * work off to a helper thread
+ */
+static void unplug_work(struct btrfs_work *work)
+{
+ struct btrfs_plug_cb *plug;
+ plug = container_of(work, struct btrfs_plug_cb, work);
+ run_plug(plug);
+}
+
+static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
+{
+ struct btrfs_plug_cb *plug;
+ plug = container_of(cb, struct btrfs_plug_cb, cb);
+
+ if (from_schedule) {
+ plug->work.flags = 0;
+ plug->work.func = unplug_work;
+ btrfs_queue_worker(&plug->info->rmw_workers,
+ &plug->work);
+ return;
+ }
+ run_plug(plug);
+}
+
+/*
+ * our main entry point for writes from the rest of the FS.
+ */
+int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len)
+{
+ struct btrfs_raid_bio *rbio;
+ struct btrfs_plug_cb *plug = NULL;
+ struct blk_plug_cb *cb;
+
+ rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
+ if (IS_ERR(rbio)) {
+ kfree(raid_map);
+ kfree(bbio);
+ return PTR_ERR(rbio);
+ }
+ bio_list_add(&rbio->bio_list, bio);
+ rbio->bio_list_bytes = bio->bi_size;
+
+ /*
+ * don't plug on full rbios, just get them out the door
+ * as quickly as we can
+ */
+ if (rbio_is_full(rbio))
+ return full_stripe_write(rbio);
+
+ cb = blk_check_plugged(btrfs_raid_unplug, root->fs_info,
+ sizeof(*plug));
+ if (cb) {
+ plug = container_of(cb, struct btrfs_plug_cb, cb);
+ if (!plug->info) {
+ plug->info = root->fs_info;
+ INIT_LIST_HEAD(&plug->rbio_list);
+ }
+ list_add_tail(&rbio->plug_list, &plug->rbio_list);
+ } else {
+ return __raid56_parity_write(rbio);
+ }
+ return 0;
+}
+
+/*
+ * all parity reconstruction happens here. We've read in everything
+ * we can find from the drives and this does the heavy lifting of
+ * sorting the good from the bad.
+ */
+static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
+{
+ int pagenr, stripe;
+ void **pointers;
+ int faila = -1, failb = -1;
+ int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ struct page *page;
+ int err;
+ int i;
+
+ pointers = kzalloc(rbio->bbio->num_stripes * sizeof(void *),
+ GFP_NOFS);
+ if (!pointers) {
+ err = -ENOMEM;
+ goto cleanup_io;
+ }
+
+ faila = rbio->faila;
+ failb = rbio->failb;
+
+ if (rbio->read_rebuild) {
+ spin_lock_irq(&rbio->bio_list_lock);
+ set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
+ spin_unlock_irq(&rbio->bio_list_lock);
+ }
+
+ index_rbio_pages(rbio);
+
+ for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ /* setup our array of pointers with pages
+ * from each stripe
+ */
+ for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
+ /*
+ * if we're rebuilding a read, we have to use
+ * pages from the bio list
+ */
+ if (rbio->read_rebuild &&
+ (stripe == faila || stripe == failb)) {
+ page = page_in_rbio(rbio, stripe, pagenr, 0);
+ } else {
+ page = rbio_stripe_page(rbio, stripe, pagenr);
+ }
+ pointers[stripe] = kmap(page);
+ }
+
+ /* all raid6 handling here */
+ if (rbio->raid_map[rbio->bbio->num_stripes - 1] ==
+ RAID6_Q_STRIPE) {
+
+ /*
+ * single failure, rebuild from parity raid5
+ * style
+ */
+ if (failb < 0) {
+ if (faila == rbio->nr_data) {
+ /*
+ * Just the P stripe has failed, without
+ * a bad data or Q stripe.
+ * TODO, we should redo the xor here.
+ */
+ err = -EIO;
+ goto cleanup;
+ }
+ /*
+ * a single failure in raid6 is rebuilt
+ * in the pstripe code below
+ */
+ goto pstripe;
+ }
+
+ /* make sure our ps and qs are in order */
+ if (faila > failb) {
+ int tmp = failb;
+ failb = faila;
+ faila = tmp;
+ }
+
+ /* if the q stripe is failed, do a pstripe reconstruction
+ * from the xors.
+ * If both the q stripe and the P stripe are failed, we're
+ * here due to a crc mismatch and we can't give them the
+ * data they want
+ */
+ if (rbio->raid_map[failb] == RAID6_Q_STRIPE) {
+ if (rbio->raid_map[faila] == RAID5_P_STRIPE) {
+ err = -EIO;
+ goto cleanup;
+ }
+ /*
+ * otherwise we have one bad data stripe and
+ * a good P stripe. raid5!
+ */
+ goto pstripe;
+ }
+
+ if (rbio->raid_map[failb] == RAID5_P_STRIPE) {
+ raid6_datap_recov(rbio->bbio->num_stripes,
+ PAGE_SIZE, faila, pointers);
+ } else {
+ raid6_2data_recov(rbio->bbio->num_stripes,
+ PAGE_SIZE, faila, failb,
+ pointers);
+ }
+ } else {
+ void *p;
+
+ /* rebuild from P stripe here (raid5 or raid6) */
+ BUG_ON(failb != -1);
+pstripe:
+ /* Copy parity block into failed block to start with */
+ memcpy(pointers[faila],
+ pointers[rbio->nr_data],
+ PAGE_CACHE_SIZE);
+
+ /* rearrange the pointer array */
+ p = pointers[faila];
+ for (stripe = faila; stripe < rbio->nr_data - 1; stripe++)
+ pointers[stripe] = pointers[stripe + 1];
+ pointers[rbio->nr_data - 1] = p;
+
+ /* xor in the rest */
+ run_xor(pointers, rbio->nr_data - 1, PAGE_CACHE_SIZE);
+ }
+ /* if we're doing this rebuild as part of an rmw, go through
+ * and set all of our private rbio pages in the
+ * failed stripes as uptodate. This way finish_rmw will
+ * know they can be trusted. If this was a read reconstruction,
+ * other endio functions will fiddle the uptodate bits
+ */
+ if (!rbio->read_rebuild) {
+ for (i = 0; i < nr_pages; i++) {
+ if (faila != -1) {
+ page = rbio_stripe_page(rbio, faila, i);
+ SetPageUptodate(page);
+ }
+ if (failb != -1) {
+ page = rbio_stripe_page(rbio, failb, i);
+ SetPageUptodate(page);
+ }
+ }
+ }
+ for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
+ /*
+ * if we're rebuilding a read, we have to use
+ * pages from the bio list
+ */
+ if (rbio->read_rebuild &&
+ (stripe == faila || stripe == failb)) {
+ page = page_in_rbio(rbio, stripe, pagenr, 0);
+ } else {
+ page = rbio_stripe_page(rbio, stripe, pagenr);
+ }
+ kunmap(page);
+ }
+ }
+
+ err = 0;
+cleanup:
+ kfree(pointers);
+
+cleanup_io:
+
+ if (rbio->read_rebuild) {
+ if (err == 0)
+ cache_rbio_pages(rbio);
+ else
+ clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
+
+ rbio_orig_end_io(rbio, err, err == 0);
+ } else if (err == 0) {
+ rbio->faila = -1;
+ rbio->failb = -1;
+ finish_rmw(rbio);
+ } else {
+ rbio_orig_end_io(rbio, err, 0);
+ }
+}
+
+/*
+ * This is called only for stripes we've read from disk to
+ * reconstruct the parity.
+ */
+static void raid_recover_end_io(struct bio *bio, int err)
+{
+ struct btrfs_raid_bio *rbio = bio->bi_private;
+
+ /*
+ * we only read stripe pages off the disk, set them
+ * up to date if there were no errors
+ */
+ if (err)
+ fail_bio_stripe(rbio, bio);
+ else
+ set_bio_pages_uptodate(bio);
+ bio_put(bio);
+
+ if (!atomic_dec_and_test(&rbio->bbio->stripes_pending))
+ return;
+
+ if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
+ rbio_orig_end_io(rbio, -EIO, 0);
+ else
+ __raid_recover_end_io(rbio);
+}
+
+/*
+ * reads everything we need off the disk to reconstruct
+ * the parity. endio handlers trigger final reconstruction
+ * when the IO is done.
+ *
+ * This is used both for reads from the higher layers and for
+ * parity construction required to finish a rmw cycle.
+ */
+static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
+{
+ int bios_to_read = 0;
+ struct btrfs_bio *bbio = rbio->bbio;
+ struct bio_list bio_list;
+ int ret;
+ int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ int pagenr;
+ int stripe;
+ struct bio *bio;
+
+ bio_list_init(&bio_list);
+
+ ret = alloc_rbio_pages(rbio);
+ if (ret)
+ goto cleanup;
+
+ atomic_set(&rbio->bbio->error, 0);
+
+ /*
+ * read everything that hasn't failed. Thanks to the
+ * stripe cache, it is possible that some or all of these
+ * pages are going to be uptodate.
+ */
+ for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
+ if (rbio->faila == stripe ||
+ rbio->failb == stripe)
+ continue;
+
+ for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ struct page *p;
+
+ /*
+ * the rmw code may have already read this
+ * page in
+ */
+ p = rbio_stripe_page(rbio, stripe, pagenr);
+ if (PageUptodate(p))
+ continue;
+
+ ret = rbio_add_io_page(rbio, &bio_list,
+ rbio_stripe_page(rbio, stripe, pagenr),
+ stripe, pagenr, rbio->stripe_len);
+ if (ret < 0)
+ goto cleanup;
+ }
+ }
+
+ bios_to_read = bio_list_size(&bio_list);
+ if (!bios_to_read) {
+ /*
+ * we might have no bios to read just because the pages
+ * were up to date, or we might have no bios to read because
+ * the devices were gone.
+ */
+ if (atomic_read(&rbio->bbio->error) <= rbio->bbio->max_errors) {
+ __raid_recover_end_io(rbio);
+ goto out;
+ } else {
+ goto cleanup;
+ }
+ }
+
+ /*
+ * the bbio may be freed once we submit the last bio. Make sure
+ * not to touch it after that
+ */
+ atomic_set(&bbio->stripes_pending, bios_to_read);
+ while (1) {
+ bio = bio_list_pop(&bio_list);
+ if (!bio)
+ break;
+
+ bio->bi_private = rbio;
+ bio->bi_end_io = raid_recover_end_io;
+
+ btrfs_bio_wq_end_io(rbio->fs_info, bio,
+ BTRFS_WQ_ENDIO_RAID56);
+
+ BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
+ submit_bio(READ, bio);
+ }
+out:
+ return 0;
+
+cleanup:
+ if (rbio->read_rebuild)
+ rbio_orig_end_io(rbio, -EIO, 0);
+ return -EIO;
+}
+
+/*
+ * the main entry point for reads from the higher layers. This
+ * is really only called when the normal read path had a failure,
+ * so we assume the bio they send down corresponds to a failed part
+ * of the drive.
+ */
+int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len, int mirror_num)
+{
+ struct btrfs_raid_bio *rbio;
+ int ret;
+
+ rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
+ if (IS_ERR(rbio)) {
+ return PTR_ERR(rbio);
+ }
+
+ rbio->read_rebuild = 1;
+ bio_list_add(&rbio->bio_list, bio);
+ rbio->bio_list_bytes = bio->bi_size;
+
+ rbio->faila = find_logical_bio_stripe(rbio, bio);
+ if (rbio->faila == -1) {
+ BUG();
+ kfree(rbio);
+ return -EIO;
+ }
+
+ /*
+ * reconstruct from the q stripe if they are
+ * asking for mirror 3
+ */
+ if (mirror_num == 3)
+ rbio->failb = bbio->num_stripes - 2;
+
+ ret = lock_stripe_add(rbio);
+
+ /*
+ * __raid56_parity_recover will end the bio with
+ * any errors it hits. We don't want to return
+ * its error value up the stack because our caller
+ * will end up calling bio_endio with any nonzero
+ * return
+ */
+ if (ret == 0)
+ __raid56_parity_recover(rbio);
+ /*
+ * our rbio has been added to the list of
+ * rbios that will be handled after the
+ * currently lock owner is done
+ */
+ return 0;
+
+}
+
+static void rmw_work(struct btrfs_work *work)
+{
+ struct btrfs_raid_bio *rbio;
+
+ rbio = container_of(work, struct btrfs_raid_bio, work);
+ raid56_rmw_stripe(rbio);
+}
+
+static void read_rebuild_work(struct btrfs_work *work)
+{
+ struct btrfs_raid_bio *rbio;
+
+ rbio = container_of(work, struct btrfs_raid_bio, work);
+ __raid56_parity_recover(rbio);
+}
diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
new file mode 100644
index 0000000..ea5d73b
--- /dev/null
+++ b/fs/btrfs/raid56.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (C) 2012 Fusion-io All rights reserved.
+ * Copyright (C) 2012 Intel Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_RAID56__
+#define __BTRFS_RAID56__
+static inline int nr_parity_stripes(struct map_lookup *map)
+{
+ if (map->type & BTRFS_BLOCK_GROUP_RAID5)
+ return 1;
+ else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
+ return 2;
+ else
+ return 0;
+}
+
+static inline int nr_data_stripes(struct map_lookup *map)
+{
+ return map->num_stripes - nr_parity_stripes(map);
+}
+#define RAID5_P_STRIPE ((u64)-2)
+#define RAID6_Q_STRIPE ((u64)-1)
+
+#define is_parity_stripe(x) (((x) == RAID5_P_STRIPE) || \
+ ((x) == RAID6_Q_STRIPE))
+
+int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len, int mirror_num);
+int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 *raid_map,
+ u64 stripe_len);
+
+int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info);
+void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info);
+#endif
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 300e09a..b67171e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1269,6 +1269,8 @@
}
spin_unlock(&rc->reloc_root_tree.lock);
+ if (!node)
+ return 0;
BUG_ON((struct btrfs_root *)node->data != root);
if (!del) {
@@ -2238,13 +2240,28 @@
}
static noinline_for_stack
+void free_reloc_roots(struct list_head *list)
+{
+ struct btrfs_root *reloc_root;
+
+ while (!list_empty(list)) {
+ reloc_root = list_entry(list->next, struct btrfs_root,
+ root_list);
+ __update_reloc_root(reloc_root, 1);
+ free_extent_buffer(reloc_root->node);
+ free_extent_buffer(reloc_root->commit_root);
+ kfree(reloc_root);
+ }
+}
+
+static noinline_for_stack
int merge_reloc_roots(struct reloc_control *rc)
{
struct btrfs_root *root;
struct btrfs_root *reloc_root;
LIST_HEAD(reloc_roots);
int found = 0;
- int ret;
+ int ret = 0;
again:
root = rc->extent_root;
@@ -2270,20 +2287,33 @@
BUG_ON(root->reloc_root != reloc_root);
ret = merge_reloc_root(rc, root);
- BUG_ON(ret);
+ if (ret)
+ goto out;
} else {
list_del_init(&reloc_root->root_list);
}
ret = btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1);
- BUG_ON(ret < 0);
+ if (ret < 0) {
+ if (list_empty(&reloc_root->root_list))
+ list_add_tail(&reloc_root->root_list,
+ &reloc_roots);
+ goto out;
+ }
}
if (found) {
found = 0;
goto again;
}
+out:
+ if (ret) {
+ btrfs_std_error(root->fs_info, ret);
+ if (!list_empty(&reloc_roots))
+ free_reloc_roots(&reloc_roots);
+ }
+
BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
- return 0;
+ return ret;
}
static void free_block_list(struct rb_root *blocks)
@@ -2818,8 +2848,10 @@
int err = 0;
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ err = -ENOMEM;
+ goto out_path;
+ }
rb_node = rb_first(blocks);
while (rb_node) {
@@ -2858,10 +2890,11 @@
rb_node = rb_next(rb_node);
}
out:
- free_block_list(blocks);
err = finish_pending_nodes(trans, rc, path, err);
btrfs_free_path(path);
+out_path:
+ free_block_list(blocks);
return err;
}
@@ -3017,7 +3050,7 @@
}
}
- page_start = (u64)page->index << PAGE_CACHE_SHIFT;
+ page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
@@ -3472,7 +3505,7 @@
}
/*
- * hepler to find all tree blocks that reference a given data extent
+ * helper to find all tree blocks that reference a given data extent
*/
static noinline_for_stack
int add_data_references(struct reloc_control *rc,
@@ -3566,7 +3599,7 @@
}
/*
- * hepler to find next unprocessed extent
+ * helper to find next unprocessed extent
*/
static noinline_for_stack
int find_next_extent(struct btrfs_trans_handle *trans,
@@ -3698,7 +3731,15 @@
set_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans)) {
+ unset_reloc_control(rc);
+ /*
+ * extent tree is not a ref_cow tree and has no reloc_root to
+ * cleanup. And callers are responsible to free the above
+ * block rsv.
+ */
+ return PTR_ERR(trans);
+ }
btrfs_commit_transaction(trans, rc->extent_root);
return 0;
}
@@ -3730,7 +3771,11 @@
while (1) {
progress++;
trans = btrfs_start_transaction(rc->extent_root, 0);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ trans = NULL;
+ break;
+ }
restart:
if (update_backref_cache(trans, &rc->backref_cache)) {
btrfs_end_transaction(trans, rc->extent_root);
@@ -4264,14 +4309,9 @@
out_free:
kfree(rc);
out:
- while (!list_empty(&reloc_roots)) {
- reloc_root = list_entry(reloc_roots.next,
- struct btrfs_root, root_list);
- list_del(&reloc_root->root_list);
- free_extent_buffer(reloc_root->node);
- free_extent_buffer(reloc_root->commit_root);
- kfree(reloc_root);
- }
+ if (!list_empty(&reloc_roots))
+ free_reloc_roots(&reloc_roots);
+
btrfs_free_path(path);
if (err == 0) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index bdbb94f..85e072b 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -28,6 +28,7 @@
#include "dev-replace.h"
#include "check-integrity.h"
#include "rcu-string.h"
+#include "raid56.h"
/*
* This is only the first step towards a full-features scrub. It reads all
@@ -541,7 +542,6 @@
eb = path->nodes[0];
ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
item_size = btrfs_item_size_nr(eb, path->slots[0]);
- btrfs_release_path(path);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
do {
@@ -557,7 +557,9 @@
ret < 0 ? -1 : ref_level,
ret < 0 ? -1 : ref_root);
} while (ret != 1);
+ btrfs_release_path(path);
} else {
+ btrfs_release_path(path);
swarn.path = path;
swarn.dev = dev;
iterate_extent_inodes(fs_info, found_key.objectid,
@@ -580,20 +582,29 @@
int corrected = 0;
struct btrfs_key key;
struct inode *inode = NULL;
+ struct btrfs_fs_info *fs_info;
u64 end = offset + PAGE_SIZE - 1;
struct btrfs_root *local_root;
+ int srcu_index;
key.objectid = root;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = (u64)-1;
- local_root = btrfs_read_fs_root_no_name(fixup->root->fs_info, &key);
- if (IS_ERR(local_root))
+
+ fs_info = fixup->root->fs_info;
+ srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
+ local_root = btrfs_read_fs_root_no_name(fs_info, &key);
+ if (IS_ERR(local_root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
return PTR_ERR(local_root);
+ }
key.type = BTRFS_INODE_ITEM_KEY;
key.objectid = inum;
key.offset = 0;
- inode = btrfs_iget(fixup->root->fs_info->sb, &key, local_root, NULL);
+ inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+ srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -606,7 +617,6 @@
}
if (PageUptodate(page)) {
- struct btrfs_fs_info *fs_info;
if (PageDirty(page)) {
/*
* we need to write the data to the defect sector. the
@@ -2246,6 +2256,13 @@
struct btrfs_device *extent_dev;
int extent_mirror_num;
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6)) {
+ if (num >= nr_data_stripes(map)) {
+ return 0;
+ }
+ }
+
nstripes = length;
offset = 0;
do_div(nstripes, map->stripe_len);
@@ -2700,7 +2717,7 @@
int ret;
struct btrfs_root *root = sctx->dev_root;
- if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return -EIO;
gen = root->fs_info->last_trans_committed;
@@ -3180,18 +3197,25 @@
u64 physical_for_dev_replace;
u64 len;
struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info;
+ int srcu_index;
key.objectid = root;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = (u64)-1;
+
+ srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
+
local_root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(local_root))
+ if (IS_ERR(local_root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
return PTR_ERR(local_root);
+ }
key.type = BTRFS_INODE_ITEM_KEY;
key.objectid = inum;
key.offset = 0;
inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
+ srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
if (IS_ERR(inode))
return PTR_ERR(inode);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 321b7fb..c85e7c6 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -85,6 +85,7 @@
u32 send_max_size;
u64 total_send_size;
u64 cmd_send_size[BTRFS_SEND_C_MAX + 1];
+ u64 flags; /* 'flags' member of btrfs_ioctl_send_args is u64 */
struct vfsmount *mnt;
@@ -3709,6 +3710,39 @@
return ret;
}
+/*
+ * Send an update extent command to user space.
+ */
+static int send_update_extent(struct send_ctx *sctx,
+ u64 offset, u32 len)
+{
+ int ret = 0;
+ struct fs_path *p;
+
+ p = fs_path_alloc(sctx);
+ if (!p)
+ return -ENOMEM;
+
+ ret = begin_cmd(sctx, BTRFS_SEND_C_UPDATE_EXTENT);
+ if (ret < 0)
+ goto out;
+
+ ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
+ if (ret < 0)
+ goto out;
+
+ TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
+ TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
+ TLV_PUT_U64(sctx, BTRFS_SEND_A_SIZE, len);
+
+ ret = send_cmd(sctx);
+
+tlv_put_failure:
+out:
+ fs_path_free(sctx, p);
+ return ret;
+}
+
static int send_write_or_clone(struct send_ctx *sctx,
struct btrfs_path *path,
struct btrfs_key *key,
@@ -3744,7 +3778,11 @@
goto out;
}
- if (!clone_root) {
+ if (clone_root) {
+ ret = send_clone(sctx, offset, len, clone_root);
+ } else if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) {
+ ret = send_update_extent(sctx, offset, len);
+ } else {
while (pos < len) {
l = len - pos;
if (l > BTRFS_SEND_READ_SIZE)
@@ -3757,10 +3795,7 @@
pos += ret;
}
ret = 0;
- } else {
- ret = send_clone(sctx, offset, len, clone_root);
}
-
out:
return ret;
}
@@ -3910,12 +3945,10 @@
found_key.type != key.type) {
key.offset += right_len;
break;
- } else {
- if (found_key.offset != key.offset + right_len) {
- /* Should really not happen */
- ret = -EIO;
- goto out;
- }
+ }
+ if (found_key.offset != key.offset + right_len) {
+ ret = 0;
+ goto out;
}
key = found_key;
}
@@ -4536,7 +4569,6 @@
struct btrfs_fs_info *fs_info;
struct btrfs_ioctl_send_args *arg = NULL;
struct btrfs_key key;
- struct file *filp = NULL;
struct send_ctx *sctx = NULL;
u32 i;
u64 *clone_sources_tmp = NULL;
@@ -4544,7 +4576,7 @@
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- send_root = BTRFS_I(fdentry(mnt_file)->d_inode)->root;
+ send_root = BTRFS_I(file_inode(mnt_file))->root;
fs_info = send_root->fs_info;
arg = memdup_user(arg_, sizeof(*arg));
@@ -4561,6 +4593,11 @@
goto out;
}
+ if (arg->flags & ~BTRFS_SEND_FLAG_NO_FILE_DATA) {
+ ret = -EINVAL;
+ goto out;
+ }
+
sctx = kzalloc(sizeof(struct send_ctx), GFP_NOFS);
if (!sctx) {
ret = -ENOMEM;
@@ -4572,6 +4609,8 @@
INIT_RADIX_TREE(&sctx->name_cache, GFP_NOFS);
INIT_LIST_HEAD(&sctx->name_cache_list);
+ sctx->flags = arg->flags;
+
sctx->send_filp = fget(arg->send_fd);
if (IS_ERR(sctx->send_filp)) {
ret = PTR_ERR(sctx->send_filp);
@@ -4673,8 +4712,6 @@
goto out;
out:
- if (filp)
- fput(filp);
kfree(arg);
vfree(clone_sources_tmp);
diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h
index 1bf4f32..8bb18f7 100644
--- a/fs/btrfs/send.h
+++ b/fs/btrfs/send.h
@@ -86,6 +86,7 @@
BTRFS_SEND_C_UTIMES,
BTRFS_SEND_C_END,
+ BTRFS_SEND_C_UPDATE_EXTENT,
__BTRFS_SEND_C_MAX,
};
#define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d8982e9..f6b8859 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -41,13 +41,13 @@
#include <linux/slab.h>
#include <linux/cleancache.h>
#include <linux/ratelimit.h>
+#include <linux/btrfs.h>
#include "compat.h"
#include "delayed-inode.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
-#include "ioctl.h"
#include "print-tree.h"
#include "xattr.h"
#include "volumes.h"
@@ -63,8 +63,7 @@
static const struct super_operations btrfs_super_ops;
static struct file_system_type btrfs_fs_type;
-static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
- char nbuf[16])
+static const char *btrfs_decode_error(int errno, char nbuf[16])
{
char *errstr = NULL;
@@ -98,7 +97,7 @@
* today we only save the error info into ram. Long term we'll
* also send it down to the disk
*/
- fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
+ set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
}
static void save_error_info(struct btrfs_fs_info *fs_info)
@@ -114,7 +113,7 @@
if (sb->s_flags & MS_RDONLY)
return;
- if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
sb->s_flags |= MS_RDONLY;
printk(KERN_INFO "btrfs is forced readonly\n");
/*
@@ -142,8 +141,6 @@
struct super_block *sb = fs_info->sb;
char nbuf[16];
const char *errstr;
- va_list args;
- va_start(args, fmt);
/*
* Special case: if the error is EROFS, and we're already
@@ -152,15 +149,18 @@
if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
return;
- errstr = btrfs_decode_error(fs_info, errno, nbuf);
+ errstr = btrfs_decode_error(errno, nbuf);
if (fmt) {
- struct va_format vaf = {
- .fmt = fmt,
- .va = &args,
- };
+ struct va_format vaf;
+ va_list args;
+
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s (%pV)\n",
sb->s_id, function, line, errstr, &vaf);
+ va_end(args);
} else {
printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
sb->s_id, function, line, errstr);
@@ -171,7 +171,6 @@
save_error_info(fs_info);
btrfs_handle_error(fs_info);
}
- va_end(args);
}
static const char * const logtypes[] = {
@@ -261,7 +260,7 @@
char nbuf[16];
const char *errstr;
- errstr = btrfs_decode_error(root->fs_info, errno, nbuf);
+ errstr = btrfs_decode_error(errno, nbuf);
btrfs_printk(root->fs_info,
"%s:%d: Aborting unused transaction(%s).\n",
function, line, errstr);
@@ -289,8 +288,8 @@
va_start(args, fmt);
vaf.va = &args;
- errstr = btrfs_decode_error(fs_info, errno, nbuf);
- if (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR)
+ errstr = btrfs_decode_error(errno, nbuf);
+ if (fs_info && (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR))
panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (%s)\n",
s_id, function, line, &vaf, errstr);
@@ -438,6 +437,7 @@
case Opt_compress_force:
case Opt_compress_force_type:
compress_force = true;
+ /* Fallthrough */
case Opt_compress:
case Opt_compress_type:
if (token == Opt_compress ||
@@ -519,7 +519,9 @@
case Opt_alloc_start:
num = match_strdup(&args[0]);
if (num) {
+ mutex_lock(&info->chunk_mutex);
info->alloc_start = memparse(num, NULL);
+ mutex_unlock(&info->chunk_mutex);
kfree(num);
printk(KERN_INFO
"btrfs: allocations start at %llu\n",
@@ -876,7 +878,7 @@
btrfs_wait_ordered_extents(root, 0);
- trans = btrfs_attach_transaction(root);
+ trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
if (PTR_ERR(trans) == -ENOENT)
@@ -1200,6 +1202,38 @@
new_pool_size);
}
+static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info,
+ unsigned long old_opts, int flags)
+{
+ set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+
+ if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
+ (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
+ (flags & MS_RDONLY))) {
+ /* wait for any defraggers to finish */
+ wait_event(fs_info->transaction_wait,
+ (atomic_read(&fs_info->defrag_running) == 0));
+ if (flags & MS_RDONLY)
+ sync_filesystem(fs_info->sb);
+ }
+}
+
+static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
+ unsigned long old_opts)
+{
+ /*
+ * We need cleanup all defragable inodes if the autodefragment is
+ * close or the fs is R/O.
+ */
+ if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
+ (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
+ (fs_info->sb->s_flags & MS_RDONLY))) {
+ btrfs_cleanup_defrag_inodes(fs_info);
+ }
+
+ clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
+}
+
static int btrfs_remount(struct super_block *sb, int *flags, char *data)
{
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
@@ -1213,6 +1247,8 @@
unsigned int old_metadata_ratio = fs_info->metadata_ratio;
int ret;
+ btrfs_remount_prepare(fs_info, old_opts, *flags);
+
ret = btrfs_parse_options(root, data);
if (ret) {
ret = -EINVAL;
@@ -1223,7 +1259,7 @@
fs_info->thread_pool_size, old_thread_pool_size);
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
- return 0;
+ goto out;
if (*flags & MS_RDONLY) {
/*
@@ -1278,7 +1314,8 @@
}
sb->s_flags &= ~MS_RDONLY;
}
-
+out:
+ btrfs_remount_cleanup(fs_info, old_opts);
return 0;
restore:
@@ -1289,10 +1326,13 @@
fs_info->mount_opt = old_opts;
fs_info->compress_type = old_compress_type;
fs_info->max_inline = old_max_inline;
+ mutex_lock(&fs_info->chunk_mutex);
fs_info->alloc_start = old_alloc_start;
+ mutex_unlock(&fs_info->chunk_mutex);
btrfs_resize_thread_pool(fs_info,
old_thread_pool_size, fs_info->thread_pool_size);
fs_info->metadata_ratio = old_metadata_ratio;
+ btrfs_remount_cleanup(fs_info, old_opts);
return ret;
}
@@ -1518,6 +1558,7 @@
.kill_sb = btrfs_kill_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("btrfs");
/*
* used by btrfsctl to scan devices when no FS is mounted
@@ -1559,7 +1600,7 @@
struct btrfs_trans_handle *trans;
struct btrfs_root *root = btrfs_sb(sb)->tree_root;
- trans = btrfs_attach_transaction(root);
+ trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
if (PTR_ERR(trans) == -ENOENT)
@@ -1684,10 +1725,14 @@
if (err)
goto free_delayed_inode;
- err = btrfs_interface_init();
+ err = btrfs_delayed_ref_init();
if (err)
goto free_auto_defrag;
+ err = btrfs_interface_init();
+ if (err)
+ goto free_delayed_ref;
+
err = register_filesystem(&btrfs_fs_type);
if (err)
goto unregister_ioctl;
@@ -1699,6 +1744,8 @@
unregister_ioctl:
btrfs_interface_exit();
+free_delayed_ref:
+ btrfs_delayed_ref_exit();
free_auto_defrag:
btrfs_auto_defrag_exit();
free_delayed_inode:
@@ -1720,6 +1767,7 @@
static void __exit exit_btrfs_fs(void)
{
btrfs_destroy_cachep();
+ btrfs_delayed_ref_exit();
btrfs_auto_defrag_exit();
btrfs_delayed_inode_exit();
ordered_data_exit();
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index daac9ae..5b326cd 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -21,7 +21,6 @@
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
-#include <linux/module.h>
#include <linux/kobject.h>
#include "ctree.h"
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f154946..50767bb 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -40,7 +40,6 @@
if (atomic_dec_and_test(&transaction->use_count)) {
BUG_ON(!list_empty(&transaction->list));
WARN_ON(transaction->delayed_refs.root.rb_node);
- memset(transaction, 0, sizeof(*transaction));
kmem_cache_free(btrfs_transaction_cachep, transaction);
}
}
@@ -51,6 +50,14 @@
root->commit_root = btrfs_root_node(root);
}
+static inline int can_join_transaction(struct btrfs_transaction *trans,
+ int type)
+{
+ return !(trans->in_commit &&
+ type != TRANS_JOIN &&
+ type != TRANS_JOIN_NOLOCK);
+}
+
/*
* either allocate a new transaction or hop into the existing one
*/
@@ -62,7 +69,7 @@
spin_lock(&fs_info->trans_lock);
loop:
/* The file system has been taken offline. No new transactions. */
- if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
spin_unlock(&fs_info->trans_lock);
return -EROFS;
}
@@ -86,6 +93,10 @@
spin_unlock(&fs_info->trans_lock);
return cur_trans->aborted;
}
+ if (!can_join_transaction(cur_trans, type)) {
+ spin_unlock(&fs_info->trans_lock);
+ return -EBUSY;
+ }
atomic_inc(&cur_trans->use_count);
atomic_inc(&cur_trans->num_writers);
cur_trans->num_joined++;
@@ -112,9 +123,8 @@
* to redo the trans_no_join checks above
*/
kmem_cache_free(btrfs_transaction_cachep, cur_trans);
- cur_trans = fs_info->running_transaction;
goto loop;
- } else if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ } else if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
spin_unlock(&fs_info->trans_lock);
kmem_cache_free(btrfs_transaction_cachep, cur_trans);
return -EROFS;
@@ -156,8 +166,12 @@
spin_lock_init(&cur_trans->commit_lock);
spin_lock_init(&cur_trans->delayed_refs.lock);
+ atomic_set(&cur_trans->delayed_refs.procs_running_refs, 0);
+ atomic_set(&cur_trans->delayed_refs.ref_seq, 0);
+ init_waitqueue_head(&cur_trans->delayed_refs.wait);
INIT_LIST_HEAD(&cur_trans->pending_snapshots);
+ INIT_LIST_HEAD(&cur_trans->ordered_operations);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(&cur_trans->dirty_pages,
fs_info->btree_inode->i_mapping);
@@ -302,7 +316,7 @@
int ret;
u64 qgroup_reserved = 0;
- if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return ERR_PTR(-EROFS);
if (current->journal_info) {
@@ -333,12 +347,14 @@
&root->fs_info->trans_block_rsv,
num_bytes, flush);
if (ret)
- return ERR_PTR(ret);
+ goto reserve_fail;
}
again:
h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
- if (!h)
- return ERR_PTR(-ENOMEM);
+ if (!h) {
+ ret = -ENOMEM;
+ goto alloc_fail;
+ }
/*
* If we are JOIN_NOLOCK we're already committing a transaction and
@@ -358,18 +374,17 @@
do {
ret = join_transaction(root, type);
- if (ret == -EBUSY)
+ if (ret == -EBUSY) {
wait_current_trans(root);
+ if (unlikely(type == TRANS_ATTACH))
+ ret = -ENOENT;
+ }
} while (ret == -EBUSY);
if (ret < 0) {
/* We must get the transaction if we are JOIN_NOLOCK. */
BUG_ON(type == TRANS_JOIN_NOLOCK);
-
- if (type < TRANS_JOIN_NOLOCK)
- sb_end_intwrite(root->fs_info->sb);
- kmem_cache_free(btrfs_trans_handle_cachep, h);
- return ERR_PTR(ret);
+ goto join_fail;
}
cur_trans = root->fs_info->running_transaction;
@@ -385,9 +400,10 @@
h->block_rsv = NULL;
h->orig_rsv = NULL;
h->aborted = 0;
- h->qgroup_reserved = qgroup_reserved;
+ h->qgroup_reserved = 0;
h->delayed_ref_elem.seq = 0;
h->type = type;
+ h->allocating_chunk = false;
INIT_LIST_HEAD(&h->qgroup_ref_list);
INIT_LIST_HEAD(&h->new_bgs);
@@ -403,6 +419,7 @@
h->block_rsv = &root->fs_info->trans_block_rsv;
h->bytes_reserved = num_bytes;
}
+ h->qgroup_reserved = qgroup_reserved;
got_it:
btrfs_record_root_in_trans(h, root);
@@ -410,6 +427,19 @@
if (!current->journal_info && type != TRANS_USERSPACE)
current->journal_info = h;
return h;
+
+join_fail:
+ if (type < TRANS_JOIN_NOLOCK)
+ sb_end_intwrite(root->fs_info->sb);
+ kmem_cache_free(btrfs_trans_handle_cachep, h);
+alloc_fail:
+ if (num_bytes)
+ btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
+ num_bytes);
+reserve_fail:
+ if (qgroup_reserved)
+ btrfs_qgroup_free(root, qgroup_reserved);
+ return ERR_PTR(ret);
}
struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
@@ -441,11 +471,43 @@
return start_transaction(root, 0, TRANS_USERSPACE, 0);
}
+/*
+ * btrfs_attach_transaction() - catch the running transaction
+ *
+ * It is used when we want to commit the current the transaction, but
+ * don't want to start a new one.
+ *
+ * Note: If this function return -ENOENT, it just means there is no
+ * running transaction. But it is possible that the inactive transaction
+ * is still in the memory, not fully on disk. If you hope there is no
+ * inactive transaction in the fs when -ENOENT is returned, you should
+ * invoke
+ * btrfs_attach_transaction_barrier()
+ */
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root)
{
return start_transaction(root, 0, TRANS_ATTACH, 0);
}
+/*
+ * btrfs_attach_transaction() - catch the running transaction
+ *
+ * It is similar to the above function, the differentia is this one
+ * will wait for all the inactive transactions until they fully
+ * complete.
+ */
+struct btrfs_trans_handle *
+btrfs_attach_transaction_barrier(struct btrfs_root *root)
+{
+ struct btrfs_trans_handle *trans;
+
+ trans = start_transaction(root, 0, TRANS_ATTACH, 0);
+ if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT)
+ btrfs_wait_for_commit(root, 0);
+
+ return trans;
+}
+
/* wait for a transaction commit to be fully complete */
static noinline void wait_for_commit(struct btrfs_root *root,
struct btrfs_transaction *commit)
@@ -563,21 +625,20 @@
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
- /*
- * the same root has to be passed to start_transaction and
- * end_transaction. Subvolume quota depends on this.
- */
- WARN_ON(trans->root != root);
if (trans->qgroup_reserved) {
- btrfs_qgroup_free(root, trans->qgroup_reserved);
+ /*
+ * the same root has to be passed here between start_transaction
+ * and end_transaction. Subvolume quota depends on this.
+ */
+ btrfs_qgroup_free(trans->root, trans->qgroup_reserved);
trans->qgroup_reserved = 0;
}
if (!list_empty(&trans->new_bgs))
btrfs_create_pending_block_groups(trans, root);
- while (count < 2) {
+ while (count < 1) {
unsigned long cur = trans->delayed_ref_updates;
trans->delayed_ref_updates = 0;
if (cur &&
@@ -589,6 +650,7 @@
}
count++;
}
+
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
@@ -634,12 +696,10 @@
btrfs_run_delayed_iputs(root);
if (trans->aborted ||
- root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
err = -EIO;
- }
assert_qgroups_uptodate(trans);
- memset(trans, 0, sizeof(*trans));
kmem_cache_free(btrfs_trans_handle_cachep, trans);
return err;
}
@@ -686,7 +746,9 @@
struct extent_state *cached_state = NULL;
u64 start = 0;
u64 end;
+ struct blk_plug plug;
+ blk_start_plug(&plug);
while (!find_first_extent_bit(dirty_pages, start, &start, &end,
mark, &cached_state)) {
convert_extent_bit(dirty_pages, start, end, EXTENT_NEED_WAIT,
@@ -700,6 +762,7 @@
}
if (err)
werr = err;
+ blk_finish_plug(&plug);
return werr;
}
@@ -950,10 +1013,10 @@
}
/*
- * defrag a given btree. If cacheonly == 1, this won't read from the disk,
- * otherwise every leaf in the btree is read and defragged.
+ * defrag a given btree.
+ * Every leaf in the btree is read and defragged.
*/
-int btrfs_defrag_root(struct btrfs_root *root, int cacheonly)
+int btrfs_defrag_root(struct btrfs_root *root)
{
struct btrfs_fs_info *info = root->fs_info;
struct btrfs_trans_handle *trans;
@@ -967,7 +1030,7 @@
if (IS_ERR(trans))
return PTR_ERR(trans);
- ret = btrfs_defrag_leaves(trans, root, cacheonly);
+ ret = btrfs_defrag_leaves(trans, root);
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(info->tree_root);
@@ -975,6 +1038,12 @@
if (btrfs_fs_closing(root->fs_info) || ret != -EAGAIN)
break;
+
+ if (btrfs_defrag_cancelled(root->fs_info)) {
+ printk(KERN_DEBUG "btrfs: defrag_root cancelled\n");
+ ret = -EAGAIN;
+ break;
+ }
}
root->defrag_running = 0;
return ret;
@@ -982,7 +1051,12 @@
/*
* new snapshots need to be created at a very specific time in the
- * transaction commit. This does the actual creation
+ * transaction commit. This does the actual creation.
+ *
+ * Note:
+ * If the error which may affect the commitment of the current transaction
+ * happens, we should return the error number. If the error which just affect
+ * the creation of the pending snapshots, just return 0.
*/
static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
@@ -997,12 +1071,11 @@
struct inode *parent_inode;
struct btrfs_path *path;
struct btrfs_dir_item *dir_item;
- struct dentry *parent;
struct dentry *dentry;
struct extent_buffer *tmp;
struct extent_buffer *old;
struct timespec cur_time = CURRENT_TIME;
- int ret;
+ int ret = 0;
u64 to_reserve = 0;
u64 index = 0;
u64 objectid;
@@ -1011,40 +1084,36 @@
path = btrfs_alloc_path();
if (!path) {
- ret = pending->error = -ENOMEM;
- goto path_alloc_fail;
+ pending->error = -ENOMEM;
+ return 0;
}
new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
if (!new_root_item) {
- ret = pending->error = -ENOMEM;
+ pending->error = -ENOMEM;
goto root_item_alloc_fail;
}
- ret = btrfs_find_free_objectid(tree_root, &objectid);
- if (ret) {
- pending->error = ret;
+ pending->error = btrfs_find_free_objectid(tree_root, &objectid);
+ if (pending->error)
goto no_free_objectid;
- }
btrfs_reloc_pre_snapshot(trans, pending, &to_reserve);
if (to_reserve > 0) {
- ret = btrfs_block_rsv_add(root, &pending->block_rsv,
- to_reserve,
- BTRFS_RESERVE_NO_FLUSH);
- if (ret) {
- pending->error = ret;
+ pending->error = btrfs_block_rsv_add(root,
+ &pending->block_rsv,
+ to_reserve,
+ BTRFS_RESERVE_NO_FLUSH);
+ if (pending->error)
goto no_free_objectid;
- }
}
- ret = btrfs_qgroup_inherit(trans, fs_info, root->root_key.objectid,
- objectid, pending->inherit);
- if (ret) {
- pending->error = ret;
+ pending->error = btrfs_qgroup_inherit(trans, fs_info,
+ root->root_key.objectid,
+ objectid, pending->inherit);
+ if (pending->error)
goto no_free_objectid;
- }
key.objectid = objectid;
key.offset = (u64)-1;
@@ -1052,10 +1121,10 @@
rsv = trans->block_rsv;
trans->block_rsv = &pending->block_rsv;
+ trans->bytes_reserved = trans->block_rsv->reserved;
dentry = pending->dentry;
- parent = dget_parent(dentry);
- parent_inode = parent->d_inode;
+ parent_inode = pending->dir;
parent_root = BTRFS_I(parent_inode)->root;
record_root_in_trans(trans, parent_root);
@@ -1072,7 +1141,7 @@
dentry->d_name.len, 0);
if (dir_item != NULL && !IS_ERR(dir_item)) {
pending->error = -EEXIST;
- goto fail;
+ goto dir_item_existed;
} else if (IS_ERR(dir_item)) {
ret = PTR_ERR(dir_item);
btrfs_abort_transaction(trans, root, ret);
@@ -1203,14 +1272,14 @@
if (ret)
btrfs_abort_transaction(trans, root, ret);
fail:
- dput(parent);
+ pending->error = ret;
+dir_item_existed:
trans->block_rsv = rsv;
+ trans->bytes_reserved = 0;
no_free_objectid:
kfree(new_root_item);
root_item_alloc_fail:
btrfs_free_path(path);
-path_alloc_fail:
- btrfs_block_rsv_release(root, &pending->block_rsv, (u64)-1);
return ret;
}
@@ -1220,12 +1289,17 @@
static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info)
{
- struct btrfs_pending_snapshot *pending;
+ struct btrfs_pending_snapshot *pending, *next;
struct list_head *head = &trans->transaction->pending_snapshots;
+ int ret = 0;
- list_for_each_entry(pending, head, list)
- create_pending_snapshot(trans, fs_info, pending);
- return 0;
+ list_for_each_entry_safe(pending, next, head, list) {
+ list_del(&pending->list);
+ ret = create_pending_snapshot(trans, fs_info, pending);
+ if (ret)
+ break;
+ }
+ return ret;
}
static void update_super_roots(struct btrfs_root *root)
@@ -1296,13 +1370,13 @@
struct btrfs_async_commit {
struct btrfs_trans_handle *newtrans;
struct btrfs_root *root;
- struct delayed_work work;
+ struct work_struct work;
};
static void do_async_commit(struct work_struct *work)
{
struct btrfs_async_commit *ac =
- container_of(work, struct btrfs_async_commit, work.work);
+ container_of(work, struct btrfs_async_commit, work);
/*
* We've got freeze protection passed with the transaction.
@@ -1330,7 +1404,7 @@
if (!ac)
return -ENOMEM;
- INIT_DELAYED_WORK(&ac->work, do_async_commit);
+ INIT_WORK(&ac->work, do_async_commit);
ac->root = root;
ac->newtrans = btrfs_join_transaction(root);
if (IS_ERR(ac->newtrans)) {
@@ -1354,7 +1428,7 @@
&root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
1, _THIS_IP_);
- schedule_delayed_work(&ac->work, 0);
+ schedule_work(&ac->work);
/* wait for transaction to start and unblock */
if (wait_for_unblock)
@@ -1374,16 +1448,29 @@
struct btrfs_root *root, int err)
{
struct btrfs_transaction *cur_trans = trans->transaction;
+ DEFINE_WAIT(wait);
WARN_ON(trans->use_count > 1);
btrfs_abort_transaction(trans, root, err);
spin_lock(&root->fs_info->trans_lock);
+
+ if (list_empty(&cur_trans->list)) {
+ spin_unlock(&root->fs_info->trans_lock);
+ btrfs_end_transaction(trans, root);
+ return;
+ }
+
list_del_init(&cur_trans->list);
if (cur_trans == root->fs_info->running_transaction) {
+ root->fs_info->trans_no_join = 1;
+ spin_unlock(&root->fs_info->trans_lock);
+ wait_event(cur_trans->writer_wait,
+ atomic_read(&cur_trans->num_writers) == 1);
+
+ spin_lock(&root->fs_info->trans_lock);
root->fs_info->running_transaction = NULL;
- root->fs_info->trans_no_join = 0;
}
spin_unlock(&root->fs_info->trans_lock);
@@ -1417,7 +1504,9 @@
}
if (flush_on_commit || snap_pending) {
- btrfs_start_delalloc_inodes(root, 1);
+ ret = btrfs_start_delalloc_inodes(root, 1);
+ if (ret)
+ return ret;
btrfs_wait_ordered_extents(root, 1);
}
@@ -1439,9 +1528,9 @@
* it here and no for sure that nothing new will be added
* to the list
*/
- btrfs_run_ordered_operations(root, 1);
+ ret = btrfs_run_ordered_operations(trans, root, 1);
- return 0;
+ return ret;
}
/*
@@ -1462,27 +1551,35 @@
int should_grow = 0;
unsigned long now = get_seconds();
- ret = btrfs_run_ordered_operations(root, 0);
+ ret = btrfs_run_ordered_operations(trans, root, 0);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
- goto cleanup_transaction;
+ btrfs_end_transaction(trans, root);
+ return ret;
}
/* Stop the commit early if ->aborted is set */
if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
ret = cur_trans->aborted;
- goto cleanup_transaction;
+ btrfs_end_transaction(trans, root);
+ return ret;
}
/* make a pass through all the delayed refs we have so far
* any runnings procs may add more while we are here
*/
ret = btrfs_run_delayed_refs(trans, root, 0);
- if (ret)
- goto cleanup_transaction;
+ if (ret) {
+ btrfs_end_transaction(trans, root);
+ return ret;
+ }
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
+ if (trans->qgroup_reserved) {
+ btrfs_qgroup_free(root, trans->qgroup_reserved);
+ trans->qgroup_reserved = 0;
+ }
cur_trans = trans->transaction;
@@ -1496,8 +1593,10 @@
btrfs_create_pending_block_groups(trans, root);
ret = btrfs_run_delayed_refs(trans, root, 0);
- if (ret)
- goto cleanup_transaction;
+ if (ret) {
+ btrfs_end_transaction(trans, root);
+ return ret;
+ }
spin_lock(&cur_trans->commit_lock);
if (cur_trans->in_commit) {
@@ -1761,6 +1860,10 @@
cleanup_transaction:
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
+ if (trans->qgroup_reserved) {
+ btrfs_qgroup_free(root, trans->qgroup_reserved);
+ trans->qgroup_reserved = 0;
+ }
btrfs_printk(root->fs_info, "Skipping commit of aborted transaction.\n");
// WARN_ON(1);
if (current->journal_info == trans)
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 0e8aa1e..3c8e0d2 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -43,6 +43,7 @@
wait_queue_head_t writer_wait;
wait_queue_head_t commit_wait;
struct list_head pending_snapshots;
+ struct list_head ordered_operations;
struct btrfs_delayed_ref_root delayed_refs;
int aborted;
};
@@ -68,6 +69,7 @@
struct btrfs_block_rsv *orig_rsv;
short aborted;
short adding_csums;
+ bool allocating_chunk;
enum btrfs_trans_type type;
/*
* this root is only needed to validate that the root passed to
@@ -82,11 +84,13 @@
struct btrfs_pending_snapshot {
struct dentry *dentry;
+ struct inode *dir;
struct btrfs_root *root;
struct btrfs_root *snap;
struct btrfs_qgroup_inherit *inherit;
/* block reservation for the operation */
struct btrfs_block_rsv block_rsv;
+ u64 qgroup_reserved;
/* extra metadata reseration for relocation */
int error;
bool readonly;
@@ -110,13 +114,15 @@
struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
+ struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root);
int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_add_dead_root(struct btrfs_root *root);
-int btrfs_defrag_root(struct btrfs_root *root, int cacheonly);
+int btrfs_defrag_root(struct btrfs_root *root);
int btrfs_clean_old_snapshots(struct btrfs_root *root);
int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c
index 3b580ee..94e05c1 100644
--- a/fs/btrfs/tree-defrag.c
+++ b/fs/btrfs/tree-defrag.c
@@ -23,13 +23,14 @@
#include "transaction.h"
#include "locking.h"
-/* defrag all the leaves in a given btree. If cache_only == 1, don't read
- * things from disk, otherwise read all the leaves and try to get key order to
+/*
+ * Defrag all the leaves in a given btree.
+ * Read all the leaves and try to get key order to
* better reflect disk order
*/
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, int cache_only)
+ struct btrfs_root *root)
{
struct btrfs_path *path = NULL;
struct btrfs_key key;
@@ -41,9 +42,6 @@
u64 last_ret = 0;
u64 min_trans = 0;
- if (cache_only)
- goto out;
-
if (root->fs_info->extent_root == root) {
/*
* there's recursion here right now in the tree locking,
@@ -86,11 +84,8 @@
}
path->keep_locks = 1;
- if (cache_only)
- min_trans = root->defrag_trans_start;
- ret = btrfs_search_forward(root, &key, NULL, path,
- cache_only, min_trans);
+ ret = btrfs_search_forward(root, &key, NULL, path, min_trans);
if (ret < 0)
goto out;
if (ret > 0) {
@@ -109,11 +104,11 @@
goto out;
}
path->slots[1] = btrfs_header_nritems(path->nodes[1]);
- next_key_ret = btrfs_find_next_key(root, path, &key, 1, cache_only,
+ next_key_ret = btrfs_find_next_key(root, path, &key, 1,
min_trans);
ret = btrfs_realloc_node(trans, root,
path->nodes[1], 0,
- cache_only, &last_ret,
+ &last_ret,
&root->defrag_progress);
if (ret) {
WARN_ON(ret == -EAGAIN);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9027bb1..451fad9 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -278,8 +278,7 @@
struct walk_control *wc, u64 gen)
{
if (wc->pin)
- btrfs_pin_extent_for_log_replay(wc->trans,
- log->fs_info->extent_root,
+ btrfs_pin_extent_for_log_replay(log->fs_info->extent_root,
eb->start, eb->len);
if (btrfs_buffer_uptodate(eb, gen, 0)) {
@@ -485,7 +484,6 @@
struct btrfs_key *key)
{
int found_type;
- u64 mask = root->sectorsize - 1;
u64 extent_end;
u64 start = key->offset;
u64 saved_nbytes;
@@ -502,7 +500,7 @@
extent_end = start + btrfs_file_extent_num_bytes(eb, item);
else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size = btrfs_file_extent_inline_len(eb, item);
- extent_end = (start + size + mask) & ~mask;
+ extent_end = ALIGN(start + size, root->sectorsize);
} else {
ret = 0;
goto out;
@@ -1384,7 +1382,10 @@
btrfs_release_path(path);
if (ret == 0) {
- btrfs_inc_nlink(inode);
+ if (!inode->i_nlink)
+ set_nlink(inode, 1);
+ else
+ btrfs_inc_nlink(inode);
ret = btrfs_update_inode(trans, root, inode);
} else if (ret == -EEXIST) {
ret = 0;
@@ -2281,6 +2282,7 @@
unsigned long log_transid = 0;
mutex_lock(&root->log_mutex);
+ log_transid = root->log_transid;
index1 = root->log_transid % 2;
if (atomic_read(&root->log_commit[index1])) {
wait_log_commit(trans, root, root->log_transid);
@@ -2308,11 +2310,11 @@
/* bail out if we need to do a full commit */
if (root->fs_info->last_trans_log_full_commit == trans->transid) {
ret = -EAGAIN;
+ btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&root->log_mutex);
goto out;
}
- log_transid = root->log_transid;
if (log_transid % 2 == 0)
mark = EXTENT_DIRTY;
else
@@ -2324,6 +2326,7 @@
ret = btrfs_write_marked_extents(log, &log->dirty_log_pages, mark);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
+ btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&root->log_mutex);
goto out;
}
@@ -2363,6 +2366,7 @@
}
root->fs_info->last_trans_log_full_commit = trans->transid;
btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
+ btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&log_root_tree->log_mutex);
ret = -EAGAIN;
goto out;
@@ -2373,6 +2377,7 @@
btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
wait_log_commit(trans, log_root_tree,
log_root_tree->log_transid);
+ btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&log_root_tree->log_mutex);
ret = 0;
goto out;
@@ -2392,6 +2397,7 @@
*/
if (root->fs_info->last_trans_log_full_commit == trans->transid) {
btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
+ btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&log_root_tree->log_mutex);
ret = -EAGAIN;
goto out_wake_log_root;
@@ -2402,10 +2408,12 @@
EXTENT_DIRTY | EXTENT_NEW);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
+ btrfs_free_logged_extents(log, log_transid);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
+ btrfs_wait_logged_extents(log, log_transid);
btrfs_set_super_log_root(root->fs_info->super_for_commit,
log_root_tree->node->start);
@@ -2461,8 +2469,10 @@
.process_func = process_one_buffer
};
- ret = walk_log_tree(trans, log, &wc);
- BUG_ON(ret);
+ if (trans) {
+ ret = walk_log_tree(trans, log, &wc);
+ BUG_ON(ret);
+ }
while (1) {
ret = find_first_extent_bit(&log->dirty_log_pages,
@@ -2475,6 +2485,14 @@
EXTENT_DIRTY | EXTENT_NEW, GFP_NOFS);
}
+ /*
+ * We may have short-circuited the log tree with the full commit logic
+ * and left ordered extents on our list, so clear these out to keep us
+ * from leaking inodes and memory.
+ */
+ btrfs_free_logged_extents(log, 0);
+ btrfs_free_logged_extents(log, 1);
+
free_extent_buffer(log->node);
kfree(log);
}
@@ -2724,7 +2742,7 @@
path->keep_locks = 1;
ret = btrfs_search_forward(root, &min_key, &max_key,
- path, 0, trans->transid);
+ path, trans->transid);
/*
* we didn't find anything from this transaction, see if there
@@ -3271,16 +3289,21 @@
struct btrfs_root *log = root->log_root;
struct btrfs_file_extent_item *fi;
struct extent_buffer *leaf;
+ struct btrfs_ordered_extent *ordered;
struct list_head ordered_sums;
struct btrfs_map_token token;
struct btrfs_key key;
- u64 csum_offset = em->mod_start - em->start;
- u64 csum_len = em->mod_len;
+ u64 mod_start = em->mod_start;
+ u64 mod_len = em->mod_len;
+ u64 csum_offset;
+ u64 csum_len;
u64 extent_offset = em->start - em->orig_start;
u64 block_len;
int ret;
+ int index = log->log_transid % 2;
bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
+insert:
INIT_LIST_HEAD(&ordered_sums);
btrfs_init_map_token(&token);
key.objectid = btrfs_ino(inode);
@@ -3296,6 +3319,23 @@
leaf = path->nodes[0];
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
+
+ /*
+ * If we are overwriting an inline extent with a real one then we need
+ * to just delete the inline extent as it may not be large enough to
+ * have the entire file_extent_item.
+ */
+ if (ret && btrfs_token_file_extent_type(leaf, fi, &token) ==
+ BTRFS_FILE_EXTENT_INLINE) {
+ ret = btrfs_del_item(trans, log, path);
+ btrfs_release_path(path);
+ if (ret) {
+ path->really_keep_locks = 0;
+ return ret;
+ }
+ goto insert;
+ }
+
btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
&token);
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
@@ -3362,6 +3402,92 @@
csum_len = block_len;
}
+ /*
+ * First check and see if our csums are on our outstanding ordered
+ * extents.
+ */
+again:
+ spin_lock_irq(&log->log_extents_lock[index]);
+ list_for_each_entry(ordered, &log->logged_list[index], log_list) {
+ struct btrfs_ordered_sum *sum;
+
+ if (!mod_len)
+ break;
+
+ if (ordered->inode != inode)
+ continue;
+
+ if (ordered->file_offset + ordered->len <= mod_start ||
+ mod_start + mod_len <= ordered->file_offset)
+ continue;
+
+ /*
+ * We are going to copy all the csums on this ordered extent, so
+ * go ahead and adjust mod_start and mod_len in case this
+ * ordered extent has already been logged.
+ */
+ if (ordered->file_offset > mod_start) {
+ if (ordered->file_offset + ordered->len >=
+ mod_start + mod_len)
+ mod_len = ordered->file_offset - mod_start;
+ /*
+ * If we have this case
+ *
+ * |--------- logged extent ---------|
+ * |----- ordered extent ----|
+ *
+ * Just don't mess with mod_start and mod_len, we'll
+ * just end up logging more csums than we need and it
+ * will be ok.
+ */
+ } else {
+ if (ordered->file_offset + ordered->len <
+ mod_start + mod_len) {
+ mod_len = (mod_start + mod_len) -
+ (ordered->file_offset + ordered->len);
+ mod_start = ordered->file_offset +
+ ordered->len;
+ } else {
+ mod_len = 0;
+ }
+ }
+
+ /*
+ * To keep us from looping for the above case of an ordered
+ * extent that falls inside of the logged extent.
+ */
+ if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM,
+ &ordered->flags))
+ continue;
+ atomic_inc(&ordered->refs);
+ spin_unlock_irq(&log->log_extents_lock[index]);
+ /*
+ * we've dropped the lock, we must either break or
+ * start over after this.
+ */
+
+ wait_event(ordered->wait, ordered->csum_bytes_left == 0);
+
+ list_for_each_entry(sum, &ordered->list, list) {
+ ret = btrfs_csum_file_blocks(trans, log, sum);
+ if (ret) {
+ btrfs_put_ordered_extent(ordered);
+ goto unlocked;
+ }
+ }
+ btrfs_put_ordered_extent(ordered);
+ goto again;
+
+ }
+ spin_unlock_irq(&log->log_extents_lock[index]);
+unlocked:
+
+ if (!mod_len || ret)
+ return ret;
+
+ csum_offset = mod_start - em->start;
+ csum_len = mod_len;
+
/* block start is already adjusted for the file extent offset. */
ret = btrfs_lookup_csums_range(log->fs_info->csum_root,
em->block_start + csum_offset,
@@ -3393,6 +3519,7 @@
struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree;
u64 test_gen;
int ret = 0;
+ int num = 0;
INIT_LIST_HEAD(&extents);
@@ -3401,16 +3528,31 @@
list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
list_del_init(&em->list);
+
+ /*
+ * Just an arbitrary number, this can be really CPU intensive
+ * once we start getting a lot of extents, and really once we
+ * have a bunch of extents we just want to commit since it will
+ * be faster.
+ */
+ if (++num > 32768) {
+ list_del_init(&tree->modified_extents);
+ ret = -EFBIG;
+ goto process;
+ }
+
if (em->generation <= test_gen)
continue;
/* Need a ref to keep it from getting evicted from cache */
atomic_inc(&em->refs);
set_bit(EXTENT_FLAG_LOGGING, &em->flags);
list_add_tail(&em->list, &extents);
+ num++;
}
list_sort(NULL, &extents, extent_cmp);
+process:
while (!list_empty(&extents)) {
em = list_entry(extents.next, struct extent_map, list);
@@ -3513,6 +3655,8 @@
mutex_lock(&BTRFS_I(inode)->log_mutex);
+ btrfs_get_logged_extents(log, inode);
+
/*
* a brute force approach to making sure we get the most uptodate
* copies of everything.
@@ -3558,7 +3702,7 @@
while (1) {
ins_nr = 0;
ret = btrfs_search_forward(root, &min_key, &max_key,
- path, 0, trans->transid);
+ path, trans->transid);
if (ret != 0)
break;
again:
@@ -3656,6 +3800,8 @@
BTRFS_I(inode)->logged_trans = trans->transid;
BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans;
out_unlock:
+ if (err)
+ btrfs_free_logged_extents(log, log->log_transid);
mutex_unlock(&BTRFS_I(inode)->log_mutex);
btrfs_free_path(path);
@@ -3822,7 +3968,6 @@
end_trans:
dput(old_parent);
if (ret < 0) {
- WARN_ON(ret != -ENOSPC);
root->fs_info->last_trans_log_full_commit = trans->transid;
ret = 1;
}
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index 99be4c1..ddc61ca 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -5,7 +5,7 @@
*/
#include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include "ulist.h"
/*
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 15f6efd..2854c82 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -25,6 +25,8 @@
#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
+#include <linux/raid/pq.h>
+#include <asm/div64.h>
#include "compat.h"
#include "ctree.h"
#include "extent_map.h"
@@ -32,6 +34,7 @@
#include "transaction.h"
#include "print-tree.h"
#include "volumes.h"
+#include "raid56.h"
#include "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"
@@ -647,6 +650,7 @@
new_device->writeable = 0;
new_device->in_fs_metadata = 0;
new_device->can_discard = 0;
+ spin_lock_init(&new_device->io_lock);
list_replace_rcu(&device->dev_list, &new_device->dev_list);
call_rcu(&device->rcu, free_device);
@@ -680,6 +684,12 @@
__btrfs_close_devices(fs_devices);
free_fs_devices(fs_devices);
}
+ /*
+ * Wait for rcu kworkers under __btrfs_close_devices
+ * to finish all blkdev_puts so device is really
+ * free when umount is done.
+ */
+ rcu_barrier();
return ret;
}
@@ -792,26 +802,75 @@
return ret;
}
+/*
+ * Look for a btrfs signature on a device. This may be called out of the mount path
+ * and we are not allowed to call set_blocksize during the scan. The superblock
+ * is read via pagecache
+ */
int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
struct btrfs_fs_devices **fs_devices_ret)
{
struct btrfs_super_block *disk_super;
struct block_device *bdev;
- struct buffer_head *bh;
- int ret;
+ struct page *page;
+ void *p;
+ int ret = -EINVAL;
u64 devid;
u64 transid;
u64 total_devices;
+ u64 bytenr;
+ pgoff_t index;
+ /*
+ * we would like to check all the supers, but that would make
+ * a btrfs mount succeed after a mkfs from a different FS.
+ * So, we need to add a special mount option to scan for
+ * later supers, using BTRFS_SUPER_MIRROR_MAX instead
+ */
+ bytenr = btrfs_sb_offset(0);
flags |= FMODE_EXCL;
mutex_lock(&uuid_mutex);
- ret = btrfs_get_bdev_and_sb(path, flags, holder, 0, &bdev, &bh);
- if (ret)
+
+ bdev = blkdev_get_by_path(path, flags, holder);
+
+ if (IS_ERR(bdev)) {
+ ret = PTR_ERR(bdev);
goto error;
- disk_super = (struct btrfs_super_block *)bh->b_data;
+ }
+
+ /* make sure our super fits in the device */
+ if (bytenr + PAGE_CACHE_SIZE >= i_size_read(bdev->bd_inode))
+ goto error_bdev_put;
+
+ /* make sure our super fits in the page */
+ if (sizeof(*disk_super) > PAGE_CACHE_SIZE)
+ goto error_bdev_put;
+
+ /* make sure our super doesn't straddle pages on disk */
+ index = bytenr >> PAGE_CACHE_SHIFT;
+ if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_CACHE_SHIFT != index)
+ goto error_bdev_put;
+
+ /* pull in the page with our super */
+ page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
+ index, GFP_NOFS);
+
+ if (IS_ERR_OR_NULL(page))
+ goto error_bdev_put;
+
+ p = kmap(page);
+
+ /* align our pointer to the offset of the super block */
+ disk_super = p + (bytenr & ~PAGE_CACHE_MASK);
+
+ if (btrfs_super_bytenr(disk_super) != bytenr ||
+ disk_super->magic != cpu_to_le64(BTRFS_MAGIC))
+ goto error_unmap;
+
devid = btrfs_stack_device_id(&disk_super->dev_item);
transid = btrfs_super_generation(disk_super);
total_devices = btrfs_super_num_devices(disk_super);
+
if (disk_super->label[0]) {
if (disk_super->label[BTRFS_LABEL_SIZE - 1])
disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
@@ -819,12 +878,19 @@
} else {
printk(KERN_INFO "device fsid %pU ", disk_super->fsid);
}
+
printk(KERN_CONT "devid %llu transid %llu %s\n",
(unsigned long long)devid, (unsigned long long)transid, path);
+
ret = device_list_add(path, disk_super, devid, fs_devices_ret);
if (!ret && fs_devices_ret)
(*fs_devices_ret)->total_devices = total_devices;
- brelse(bh);
+
+error_unmap:
+ kunmap(page);
+ page_cache_release(page);
+
+error_bdev_put:
blkdev_put(bdev, flags);
error:
mutex_unlock(&uuid_mutex);
@@ -1372,14 +1438,19 @@
u64 devid;
u64 num_devices;
u8 *dev_uuid;
+ unsigned seq;
int ret = 0;
bool clear_super = false;
mutex_lock(&uuid_mutex);
- all_avail = root->fs_info->avail_data_alloc_bits |
- root->fs_info->avail_system_alloc_bits |
- root->fs_info->avail_metadata_alloc_bits;
+ do {
+ seq = read_seqbegin(&root->fs_info->profiles_lock);
+
+ all_avail = root->fs_info->avail_data_alloc_bits |
+ root->fs_info->avail_system_alloc_bits |
+ root->fs_info->avail_metadata_alloc_bits;
+ } while (read_seqretry(&root->fs_info->profiles_lock, seq));
num_devices = root->fs_info->fs_devices->num_devices;
btrfs_dev_replace_lock(&root->fs_info->dev_replace);
@@ -1403,6 +1474,21 @@
goto out;
}
+ if ((all_avail & BTRFS_BLOCK_GROUP_RAID5) &&
+ root->fs_info->fs_devices->rw_devices <= 2) {
+ printk(KERN_ERR "btrfs: unable to go below two "
+ "devices on raid5\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if ((all_avail & BTRFS_BLOCK_GROUP_RAID6) &&
+ root->fs_info->fs_devices->rw_devices <= 3) {
+ printk(KERN_ERR "btrfs: unable to go below three "
+ "devices on raid6\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
if (strcmp(device_path, "missing") == 0) {
struct list_head *devices;
struct btrfs_device *tmp;
@@ -1556,7 +1642,8 @@
ret = 0;
/* Notify udev that device has changed */
- btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+ if (bdev)
+ btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
error_brelse:
brelse(bh);
@@ -2298,7 +2385,11 @@
return ret;
trans = btrfs_start_transaction(root, 0);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ btrfs_std_error(root->fs_info, ret);
+ return ret;
+ }
lock_chunks(root);
@@ -2615,7 +2706,7 @@
chunk_used = btrfs_block_group_used(&cache->item);
if (bargs->usage == 0)
- user_thresh = 0;
+ user_thresh = 1;
else if (bargs->usage > 100)
user_thresh = cache->key.offset;
else
@@ -2663,11 +2754,15 @@
return 0;
if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP |
- BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10))
- factor = 2;
- else
- factor = 1;
- factor = num_stripes / factor;
+ BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10)) {
+ factor = num_stripes / 2;
+ } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID5) {
+ factor = num_stripes - 1;
+ } else if (btrfs_chunk_type(leaf, chunk) & BTRFS_BLOCK_GROUP_RAID6) {
+ factor = num_stripes - 2;
+ } else {
+ factor = num_stripes;
+ }
for (i = 0; i < num_stripes; i++) {
stripe = btrfs_stripe_nr(chunk, i);
@@ -2965,7 +3060,8 @@
unset_balance_control(fs_info);
ret = del_balance_item(fs_info->tree_root);
- BUG_ON(ret);
+ if (ret)
+ btrfs_std_error(fs_info, ret);
atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
}
@@ -2984,6 +3080,7 @@
int mixed = 0;
int ret;
u64 num_devices;
+ unsigned seq;
if (btrfs_fs_closing(fs_info) ||
atomic_read(&fs_info->balance_pause_req) ||
@@ -3026,7 +3123,9 @@
allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
else
allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10);
+ BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6);
if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->data.target, 1) ||
@@ -3066,23 +3165,29 @@
/* allow to reduce meta or sys integrity only if force set */
allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10;
- if (((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (fs_info->avail_system_alloc_bits & allowed) &&
- !(bctl->sys.target & allowed)) ||
- ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
- (fs_info->avail_metadata_alloc_bits & allowed) &&
- !(bctl->meta.target & allowed))) {
- if (bctl->flags & BTRFS_BALANCE_FORCE) {
- printk(KERN_INFO "btrfs: force reducing metadata "
- "integrity\n");
- } else {
- printk(KERN_ERR "btrfs: balance will reduce metadata "
- "integrity, use force if you want this\n");
- ret = -EINVAL;
- goto out;
+ BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6;
+ do {
+ seq = read_seqbegin(&fs_info->profiles_lock);
+
+ if (((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (fs_info->avail_system_alloc_bits & allowed) &&
+ !(bctl->sys.target & allowed)) ||
+ ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (fs_info->avail_metadata_alloc_bits & allowed) &&
+ !(bctl->meta.target & allowed))) {
+ if (bctl->flags & BTRFS_BALANCE_FORCE) {
+ printk(KERN_INFO "btrfs: force reducing metadata "
+ "integrity\n");
+ } else {
+ printk(KERN_ERR "btrfs: balance will reduce metadata "
+ "integrity, use force if you want this\n");
+ ret = -EINVAL;
+ goto out;
+ }
}
- }
+ } while (read_seqretry(&fs_info->profiles_lock, seq));
if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
int num_tolerated_disk_barrier_failures;
@@ -3126,6 +3231,11 @@
mutex_lock(&fs_info->balance_mutex);
atomic_dec(&fs_info->balance_running);
+ if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ fs_info->num_tolerated_disk_barrier_failures =
+ btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
+ }
+
if (bargs) {
memset(bargs, 0, sizeof(*bargs));
update_ioctl_balance_args(fs_info, 0, bargs);
@@ -3136,11 +3246,6 @@
__cancel_balance(fs_info);
}
- if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
- fs_info->num_tolerated_disk_barrier_failures =
- btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
- }
-
wake_up(&fs_info->balance_wait_q);
return ret;
@@ -3503,13 +3608,86 @@
}
struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
- { 2, 1, 0, 4, 2, 2 /* raid10 */ },
- { 1, 1, 2, 2, 2, 2 /* raid1 */ },
- { 1, 2, 1, 1, 1, 2 /* dup */ },
- { 1, 1, 0, 2, 1, 1 /* raid0 */ },
- { 1, 1, 1, 1, 1, 1 /* single */ },
+ [BTRFS_RAID_RAID10] = {
+ .sub_stripes = 2,
+ .dev_stripes = 1,
+ .devs_max = 0, /* 0 == as many as possible */
+ .devs_min = 4,
+ .devs_increment = 2,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_RAID1] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 2,
+ .devs_min = 2,
+ .devs_increment = 2,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_DUP] = {
+ .sub_stripes = 1,
+ .dev_stripes = 2,
+ .devs_max = 1,
+ .devs_min = 1,
+ .devs_increment = 1,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_RAID0] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 2,
+ .devs_increment = 1,
+ .ncopies = 1,
+ },
+ [BTRFS_RAID_SINGLE] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 1,
+ .devs_min = 1,
+ .devs_increment = 1,
+ .ncopies = 1,
+ },
+ [BTRFS_RAID_RAID5] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 2,
+ .devs_increment = 1,
+ .ncopies = 2,
+ },
+ [BTRFS_RAID_RAID6] = {
+ .sub_stripes = 1,
+ .dev_stripes = 1,
+ .devs_max = 0,
+ .devs_min = 3,
+ .devs_increment = 1,
+ .ncopies = 3,
+ },
};
+static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target)
+{
+ /* TODO allow them to set a preferred stripe size */
+ return 64 * 1024;
+}
+
+static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
+{
+ u64 features;
+
+ if (!(type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)))
+ return;
+
+ features = btrfs_super_incompat_flags(info->super_copy);
+ if (features & BTRFS_FEATURE_INCOMPAT_RAID56)
+ return;
+
+ features |= BTRFS_FEATURE_INCOMPAT_RAID56;
+ btrfs_set_super_incompat_flags(info->super_copy, features);
+ printk(KERN_INFO "btrfs: setting RAID5/6 feature flag\n");
+}
+
static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
struct btrfs_root *extent_root,
struct map_lookup **map_ret,
@@ -3525,6 +3703,8 @@
struct btrfs_device_info *devices_info = NULL;
u64 total_avail;
int num_stripes; /* total number of stripes to allocate */
+ int data_stripes; /* number of stripes that count for
+ block group size */
int sub_stripes; /* sub_stripes info for map */
int dev_stripes; /* stripes per dev */
int devs_max; /* max devs to use */
@@ -3536,6 +3716,7 @@
u64 max_chunk_size;
u64 stripe_size;
u64 num_bytes;
+ u64 raid_stripe_len = BTRFS_STRIPE_LEN;
int ndevs;
int i;
int j;
@@ -3630,12 +3811,16 @@
if (max_avail < BTRFS_STRIPE_LEN * dev_stripes)
continue;
+ if (ndevs == fs_devices->rw_devices) {
+ WARN(1, "%s: found more than %llu devices\n",
+ __func__, fs_devices->rw_devices);
+ break;
+ }
devices_info[ndevs].dev_offset = dev_offset;
devices_info[ndevs].max_avail = max_avail;
devices_info[ndevs].total_avail = total_avail;
devices_info[ndevs].dev = device;
++ndevs;
- WARN_ON(ndevs > fs_devices->rw_devices);
}
/*
@@ -3661,16 +3846,48 @@
stripe_size = devices_info[ndevs-1].max_avail;
num_stripes = ndevs * dev_stripes;
- if (stripe_size * ndevs > max_chunk_size * ncopies) {
- stripe_size = max_chunk_size * ncopies;
- do_div(stripe_size, ndevs);
+ /*
+ * this will have to be fixed for RAID1 and RAID10 over
+ * more drives
+ */
+ data_stripes = num_stripes / ncopies;
+
+ if (type & BTRFS_BLOCK_GROUP_RAID5) {
+ raid_stripe_len = find_raid56_stripe_len(ndevs - 1,
+ btrfs_super_stripesize(info->super_copy));
+ data_stripes = num_stripes - 1;
+ }
+ if (type & BTRFS_BLOCK_GROUP_RAID6) {
+ raid_stripe_len = find_raid56_stripe_len(ndevs - 2,
+ btrfs_super_stripesize(info->super_copy));
+ data_stripes = num_stripes - 2;
+ }
+
+ /*
+ * Use the number of data stripes to figure out how big this chunk
+ * is really going to be in terms of logical address space,
+ * and compare that answer with the max chunk size
+ */
+ if (stripe_size * data_stripes > max_chunk_size) {
+ u64 mask = (1ULL << 24) - 1;
+ stripe_size = max_chunk_size;
+ do_div(stripe_size, data_stripes);
+
+ /* bump the answer up to a 16MB boundary */
+ stripe_size = (stripe_size + mask) & ~mask;
+
+ /* but don't go higher than the limits we found
+ * while searching for free extents
+ */
+ if (stripe_size > devices_info[ndevs-1].max_avail)
+ stripe_size = devices_info[ndevs-1].max_avail;
}
do_div(stripe_size, dev_stripes);
/* align to BTRFS_STRIPE_LEN */
- do_div(stripe_size, BTRFS_STRIPE_LEN);
- stripe_size *= BTRFS_STRIPE_LEN;
+ do_div(stripe_size, raid_stripe_len);
+ stripe_size *= raid_stripe_len;
map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
if (!map) {
@@ -3688,14 +3905,14 @@
}
}
map->sector_size = extent_root->sectorsize;
- map->stripe_len = BTRFS_STRIPE_LEN;
- map->io_align = BTRFS_STRIPE_LEN;
- map->io_width = BTRFS_STRIPE_LEN;
+ map->stripe_len = raid_stripe_len;
+ map->io_align = raid_stripe_len;
+ map->io_width = raid_stripe_len;
map->type = type;
map->sub_stripes = sub_stripes;
*map_ret = map;
- num_bytes = stripe_size * (num_stripes / ncopies);
+ num_bytes = stripe_size * data_stripes;
*stripe_size_out = stripe_size;
*num_bytes_out = num_bytes;
@@ -3717,15 +3934,10 @@
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em);
write_unlock(&em_tree->lock);
- free_extent_map(em);
- if (ret)
+ if (ret) {
+ free_extent_map(em);
goto error;
-
- ret = btrfs_make_block_group(trans, extent_root, 0, type,
- BTRFS_FIRST_CHUNK_TREE_OBJECTID,
- start, num_bytes);
- if (ret)
- goto error;
+ }
for (i = 0; i < map->num_stripes; ++i) {
struct btrfs_device *device;
@@ -3738,15 +3950,44 @@
info->chunk_root->root_key.objectid,
BTRFS_FIRST_CHUNK_TREE_OBJECTID,
start, dev_offset, stripe_size);
- if (ret) {
- btrfs_abort_transaction(trans, extent_root, ret);
- goto error;
- }
+ if (ret)
+ goto error_dev_extent;
}
+ ret = btrfs_make_block_group(trans, extent_root, 0, type,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID,
+ start, num_bytes);
+ if (ret) {
+ i = map->num_stripes - 1;
+ goto error_dev_extent;
+ }
+
+ free_extent_map(em);
+ check_raid56_incompat_flag(extent_root->fs_info, type);
+
kfree(devices_info);
return 0;
+error_dev_extent:
+ for (; i >= 0; i--) {
+ struct btrfs_device *device;
+ int err;
+
+ device = map->stripes[i].dev;
+ err = btrfs_free_dev_extent(trans, device, start);
+ if (err) {
+ btrfs_abort_transaction(trans, extent_root, err);
+ break;
+ }
+ }
+ write_lock(&em_tree->lock);
+ remove_extent_mapping(em_tree, em);
+ write_unlock(&em_tree->lock);
+
+ /* One for our allocation */
+ free_extent_map(em);
+ /* One for the tree reference */
+ free_extent_map(em);
error:
kfree(map);
kfree(devices_info);
@@ -3886,10 +4127,7 @@
if (ret)
return ret;
- alloc_profile = BTRFS_BLOCK_GROUP_METADATA |
- fs_info->avail_metadata_alloc_bits;
- alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile);
-
+ alloc_profile = btrfs_get_alloc_profile(extent_root, 0);
ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size,
&stripe_size, chunk_offset, alloc_profile);
if (ret)
@@ -3897,10 +4135,7 @@
sys_chunk_offset = chunk_offset + chunk_size;
- alloc_profile = BTRFS_BLOCK_GROUP_SYSTEM |
- fs_info->avail_system_alloc_bits;
- alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile);
-
+ alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0);
ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map,
&sys_chunk_size, &sys_stripe_size,
sys_chunk_offset, alloc_profile);
@@ -4013,6 +4248,10 @@
ret = map->num_stripes;
else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
ret = map->sub_stripes;
+ else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
+ ret = 2;
+ else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
+ ret = 3;
else
ret = 1;
free_extent_map(em);
@@ -4025,6 +4264,52 @@
return ret;
}
+unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
+ struct btrfs_mapping_tree *map_tree,
+ u64 logical)
+{
+ struct extent_map *em;
+ struct map_lookup *map;
+ struct extent_map_tree *em_tree = &map_tree->map_tree;
+ unsigned long len = root->sectorsize;
+
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, logical, len);
+ read_unlock(&em_tree->lock);
+ BUG_ON(!em);
+
+ BUG_ON(em->start > logical || em->start + em->len < logical);
+ map = (struct map_lookup *)em->bdev;
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6)) {
+ len = map->stripe_len * nr_data_stripes(map);
+ }
+ free_extent_map(em);
+ return len;
+}
+
+int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
+ u64 logical, u64 len, int mirror_num)
+{
+ struct extent_map *em;
+ struct map_lookup *map;
+ struct extent_map_tree *em_tree = &map_tree->map_tree;
+ int ret = 0;
+
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, logical, len);
+ read_unlock(&em_tree->lock);
+ BUG_ON(!em);
+
+ BUG_ON(em->start > logical || em->start + em->len < logical);
+ map = (struct map_lookup *)em->bdev;
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6))
+ ret = 1;
+ free_extent_map(em);
+ return ret;
+}
+
static int find_live_mirror(struct btrfs_fs_info *fs_info,
struct map_lookup *map, int first, int num,
int optimal, int dev_replace_is_ongoing)
@@ -4062,10 +4347,39 @@
return optimal;
}
+static inline int parity_smaller(u64 a, u64 b)
+{
+ return a > b;
+}
+
+/* Bubble-sort the stripe set to put the parity/syndrome stripes last */
+static void sort_parity_stripes(struct btrfs_bio *bbio, u64 *raid_map)
+{
+ struct btrfs_bio_stripe s;
+ int i;
+ u64 l;
+ int again = 1;
+
+ while (again) {
+ again = 0;
+ for (i = 0; i < bbio->num_stripes - 1; i++) {
+ if (parity_smaller(raid_map[i], raid_map[i+1])) {
+ s = bbio->stripes[i];
+ l = raid_map[i];
+ bbio->stripes[i] = bbio->stripes[i+1];
+ raid_map[i] = raid_map[i+1];
+ bbio->stripes[i+1] = s;
+ raid_map[i+1] = l;
+ again = 1;
+ }
+ }
+ }
+}
+
static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret,
- int mirror_num)
+ int mirror_num, u64 **raid_map_ret)
{
struct extent_map *em;
struct map_lookup *map;
@@ -4077,6 +4391,8 @@
u64 stripe_nr;
u64 stripe_nr_orig;
u64 stripe_nr_end;
+ u64 stripe_len;
+ u64 *raid_map = NULL;
int stripe_index;
int i;
int ret = 0;
@@ -4088,6 +4404,7 @@
int num_alloc_stripes;
int patch_the_first_stripe_for_dev_replace = 0;
u64 physical_to_patch_in_first_stripe = 0;
+ u64 raid56_full_stripe_start = (u64)-1;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, logical, *length);
@@ -4104,29 +4421,63 @@
map = (struct map_lookup *)em->bdev;
offset = logical - em->start;
+ if (mirror_num > map->num_stripes)
+ mirror_num = 0;
+
+ stripe_len = map->stripe_len;
stripe_nr = offset;
/*
* stripe_nr counts the total number of stripes we have to stride
* to get to this block
*/
- do_div(stripe_nr, map->stripe_len);
+ do_div(stripe_nr, stripe_len);
- stripe_offset = stripe_nr * map->stripe_len;
+ stripe_offset = stripe_nr * stripe_len;
BUG_ON(offset < stripe_offset);
/* stripe_offset is the offset of this block in its stripe*/
stripe_offset = offset - stripe_offset;
- if (rw & REQ_DISCARD)
+ /* if we're here for raid56, we need to know the stripe aligned start */
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) {
+ unsigned long full_stripe_len = stripe_len * nr_data_stripes(map);
+ raid56_full_stripe_start = offset;
+
+ /* allow a write of a full stripe, but make sure we don't
+ * allow straddling of stripes
+ */
+ do_div(raid56_full_stripe_start, full_stripe_len);
+ raid56_full_stripe_start *= full_stripe_len;
+ }
+
+ if (rw & REQ_DISCARD) {
+ /* we don't discard raid56 yet */
+ if (map->type &
+ (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6)) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
*length = min_t(u64, em->len - offset, *length);
- else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
- /* we limit the length of each bio to what fits in a stripe */
- *length = min_t(u64, em->len - offset,
- map->stripe_len - stripe_offset);
+ } else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ u64 max_len;
+ /* For writes to RAID[56], allow a full stripeset across all disks.
+ For other RAID types and for RAID[56] reads, just allow a single
+ stripe (on a single disk). */
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6) &&
+ (rw & REQ_WRITE)) {
+ max_len = stripe_len * nr_data_stripes(map) -
+ (offset - raid56_full_stripe_start);
+ } else {
+ /* we limit the length of each bio to what fits in a stripe */
+ max_len = stripe_len - stripe_offset;
+ }
+ *length = min_t(u64, em->len - offset, max_len);
} else {
*length = em->len - offset;
}
+ /* This is for when we're called from btrfs_merge_bio_hook() and all
+ it cares about is the length */
if (!bbio_ret)
goto out;
@@ -4159,7 +4510,7 @@
u64 physical_of_found = 0;
ret = __btrfs_map_block(fs_info, REQ_GET_READ_MIRRORS,
- logical, &tmp_length, &tmp_bbio, 0);
+ logical, &tmp_length, &tmp_bbio, 0, NULL);
if (ret) {
WARN_ON(tmp_bbio != NULL);
goto out;
@@ -4220,11 +4571,11 @@
num_stripes = 1;
stripe_index = 0;
stripe_nr_orig = stripe_nr;
- stripe_nr_end = (offset + *length + map->stripe_len - 1) &
- (~(map->stripe_len - 1));
+ stripe_nr_end = ALIGN(offset + *length, map->stripe_len);
do_div(stripe_nr_end, map->stripe_len);
stripe_end_offset = stripe_nr_end * map->stripe_len -
(offset + *length);
+
if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
if (rw & REQ_DISCARD)
num_stripes = min_t(u64, map->num_stripes,
@@ -4275,6 +4626,65 @@
dev_replace_is_ongoing);
mirror_num = stripe_index - old_stripe_index + 1;
}
+
+ } else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6)) {
+ u64 tmp;
+
+ if (bbio_ret && ((rw & REQ_WRITE) || mirror_num > 1)
+ && raid_map_ret) {
+ int i, rot;
+
+ /* push stripe_nr back to the start of the full stripe */
+ stripe_nr = raid56_full_stripe_start;
+ do_div(stripe_nr, stripe_len);
+
+ stripe_index = do_div(stripe_nr, nr_data_stripes(map));
+
+ /* RAID[56] write or recovery. Return all stripes */
+ num_stripes = map->num_stripes;
+ max_errors = nr_parity_stripes(map);
+
+ raid_map = kmalloc(sizeof(u64) * num_stripes,
+ GFP_NOFS);
+ if (!raid_map) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* Work out the disk rotation on this stripe-set */
+ tmp = stripe_nr;
+ rot = do_div(tmp, num_stripes);
+
+ /* Fill in the logical address of each stripe */
+ tmp = stripe_nr * nr_data_stripes(map);
+ for (i = 0; i < nr_data_stripes(map); i++)
+ raid_map[(i+rot) % num_stripes] =
+ em->start + (tmp + i) * map->stripe_len;
+
+ raid_map[(i+rot) % map->num_stripes] = RAID5_P_STRIPE;
+ if (map->type & BTRFS_BLOCK_GROUP_RAID6)
+ raid_map[(i+rot+1) % num_stripes] =
+ RAID6_Q_STRIPE;
+
+ *length = map->stripe_len;
+ stripe_index = 0;
+ stripe_offset = 0;
+ } else {
+ /*
+ * Mirror #0 or #1 means the original data block.
+ * Mirror #2 is RAID5 parity block.
+ * Mirror #3 is RAID6 Q block.
+ */
+ stripe_index = do_div(stripe_nr, nr_data_stripes(map));
+ if (mirror_num > 1)
+ stripe_index = nr_data_stripes(map) +
+ mirror_num - 2;
+
+ /* We distribute the parity blocks across stripes */
+ tmp = stripe_nr + stripe_index;
+ stripe_index = do_div(tmp, map->num_stripes);
+ }
} else {
/*
* after this do_div call, stripe_nr is the number of stripes
@@ -4383,8 +4793,11 @@
if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) {
if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_RAID5 |
BTRFS_BLOCK_GROUP_DUP)) {
max_errors = 1;
+ } else if (map->type & BTRFS_BLOCK_GROUP_RAID6) {
+ max_errors = 2;
}
}
@@ -4485,6 +4898,10 @@
bbio->stripes[0].physical = physical_to_patch_in_first_stripe;
bbio->mirror_num = map->num_stripes + 1;
}
+ if (raid_map) {
+ sort_parity_stripes(bbio, raid_map);
+ *raid_map_ret = raid_map;
+ }
out:
if (dev_replace_is_ongoing)
btrfs_dev_replace_unlock(dev_replace);
@@ -4497,7 +4914,7 @@
struct btrfs_bio **bbio_ret, int mirror_num)
{
return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
- mirror_num);
+ mirror_num, NULL);
}
int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
@@ -4511,20 +4928,39 @@
u64 bytenr;
u64 length;
u64 stripe_nr;
+ u64 rmap_len;
int i, j, nr = 0;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, chunk_start, 1);
read_unlock(&em_tree->lock);
- BUG_ON(!em || em->start != chunk_start);
+ if (!em) {
+ printk(KERN_ERR "btrfs: couldn't find em for chunk %Lu\n",
+ chunk_start);
+ return -EIO;
+ }
+
+ if (em->start != chunk_start) {
+ printk(KERN_ERR "btrfs: bad chunk start, em=%Lu, wanted=%Lu\n",
+ em->start, chunk_start);
+ free_extent_map(em);
+ return -EIO;
+ }
map = (struct map_lookup *)em->bdev;
length = em->len;
+ rmap_len = map->stripe_len;
+
if (map->type & BTRFS_BLOCK_GROUP_RAID10)
do_div(length, map->num_stripes / map->sub_stripes);
else if (map->type & BTRFS_BLOCK_GROUP_RAID0)
do_div(length, map->num_stripes);
+ else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID6)) {
+ do_div(length, nr_data_stripes(map));
+ rmap_len = map->stripe_len * nr_data_stripes(map);
+ }
buf = kzalloc(sizeof(u64) * map->num_stripes, GFP_NOFS);
BUG_ON(!buf); /* -ENOMEM */
@@ -4544,8 +4980,11 @@
do_div(stripe_nr, map->sub_stripes);
} else if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
stripe_nr = stripe_nr * map->num_stripes + i;
- }
- bytenr = chunk_start + stripe_nr * map->stripe_len;
+ } /* else if RAID[56], multiply by nr_data_stripes().
+ * Alternatively, just use rmap_len below instead of
+ * map->stripe_len */
+
+ bytenr = chunk_start + stripe_nr * rmap_len;
WARN_ON(nr >= map->num_stripes);
for (j = 0; j < nr; j++) {
if (buf[j] == bytenr)
@@ -4559,7 +4998,7 @@
*logical = buf;
*naddrs = nr;
- *stripe_len = map->stripe_len;
+ *stripe_len = rmap_len;
free_extent_map(em);
return 0;
@@ -4633,7 +5072,7 @@
bio->bi_bdev = (struct block_device *)
(unsigned long)bbio->mirror_num;
/* only send an error to the higher layers if it is
- * beyond the tolerance of the multi-bio
+ * beyond the tolerance of the btrfs bio
*/
if (atomic_read(&bbio->error) > bbio->max_errors) {
err = -EIO;
@@ -4667,13 +5106,18 @@
* This will add one bio to the pending list for a device and make sure
* the work struct is scheduled.
*/
-static noinline void schedule_bio(struct btrfs_root *root,
+noinline void btrfs_schedule_bio(struct btrfs_root *root,
struct btrfs_device *device,
int rw, struct bio *bio)
{
int should_queue = 1;
struct btrfs_pending_bios *pending_bios;
+ if (device->missing || !device->bdev) {
+ bio_endio(bio, -EIO);
+ return;
+ }
+
/* don't bother with additional async steps for reads, right now */
if (!(rw & REQ_WRITE)) {
bio_get(bio);
@@ -4771,7 +5215,7 @@
#endif
bio->bi_bdev = dev->bdev;
if (async)
- schedule_bio(root, dev, rw, bio);
+ btrfs_schedule_bio(root, dev, rw, bio);
else
btrfsic_submit_bio(rw, bio);
}
@@ -4830,6 +5274,7 @@
u64 logical = (u64)bio->bi_sector << 9;
u64 length = 0;
u64 map_length;
+ u64 *raid_map = NULL;
int ret;
int dev_nr = 0;
int total_devs = 1;
@@ -4838,12 +5283,30 @@
length = bio->bi_size;
map_length = length;
- ret = btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
- mirror_num);
- if (ret)
+ ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
+ mirror_num, &raid_map);
+ if (ret) /* -ENOMEM */
return ret;
total_devs = bbio->num_stripes;
+ bbio->orig_bio = first_bio;
+ bbio->private = first_bio->bi_private;
+ bbio->end_io = first_bio->bi_end_io;
+ atomic_set(&bbio->stripes_pending, bbio->num_stripes);
+
+ if (raid_map) {
+ /* In this case, map_length has been set to the length of
+ a single stripe; not the whole write */
+ if (rw & WRITE) {
+ return raid56_parity_write(root, bio, bbio,
+ raid_map, map_length);
+ } else {
+ return raid56_parity_recover(root, bio, bbio,
+ raid_map, map_length,
+ mirror_num);
+ }
+ }
+
if (map_length < length) {
printk(KERN_CRIT "btrfs: mapping failed logical %llu bio len %llu "
"len %llu\n", (unsigned long long)logical,
@@ -4852,11 +5315,6 @@
BUG();
}
- bbio->orig_bio = first_bio;
- bbio->private = first_bio->bi_private;
- bbio->end_io = first_bio->bi_end_io;
- atomic_set(&bbio->stripes_pending, bbio->num_stripes);
-
while (dev_nr < total_devs) {
dev = bbio->stripes[dev_nr].dev;
if (!dev || !dev->bdev || (rw & WRITE && !dev->writeable)) {
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index d3c3939..062d860 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -21,8 +21,8 @@
#include <linux/bio.h>
#include <linux/sort.h>
+#include <linux/btrfs.h>
#include "async-thread.h"
-#include "ioctl.h"
#define BTRFS_STRIPE_LEN (64 * 1024)
@@ -321,7 +321,14 @@
void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
struct btrfs_device *tgtdev);
int btrfs_scratch_superblock(struct btrfs_device *device);
-
+void btrfs_schedule_bio(struct btrfs_root *root,
+ struct btrfs_device *device,
+ int rw, struct bio *bio);
+int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
+ u64 logical, u64 len, int mirror_num);
+unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
+ struct btrfs_mapping_tree *map_tree,
+ u64 logical);
static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
int index)
{
diff --git a/fs/buffer.c b/fs/buffer.c
index 7a75c3e..b4dcb34 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -41,6 +41,7 @@
#include <linux/bitops.h>
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
+#include <trace/events/block.h>
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@@ -53,6 +54,13 @@
}
EXPORT_SYMBOL(init_buffer);
+inline void touch_buffer(struct buffer_head *bh)
+{
+ trace_block_touch_buffer(bh);
+ mark_page_accessed(bh->b_page);
+}
+EXPORT_SYMBOL(touch_buffer);
+
static int sleep_on_buffer(void *word)
{
io_schedule();
@@ -1113,6 +1121,8 @@
{
WARN_ON_ONCE(!buffer_uptodate(bh));
+ trace_block_dirty_buffer(bh);
+
/*
* Very *carefully* optimize the it-is-already-dirty case.
*
@@ -2332,7 +2342,7 @@
get_block_t get_block)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
unsigned long end;
loff_t size;
int ret;
@@ -2359,7 +2369,7 @@
if (unlikely(ret < 0))
goto out_unlock;
set_page_dirty(page);
- wait_on_page_writeback(page);
+ wait_for_stable_page(page);
return 0;
out_unlock:
unlock_page(page);
@@ -2371,7 +2381,7 @@
get_block_t get_block)
{
int ret;
- struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
+ struct super_block *sb = file_inode(vma->vm_file)->i_sb;
sb_start_pagefault(sb);
@@ -3227,7 +3237,7 @@
* Once the number of bh's in the machine exceeds this level, we start
* stripping them in writeback.
*/
-static int max_buffer_heads;
+static unsigned long max_buffer_heads;
int buffer_heads_over_limit;
@@ -3343,7 +3353,7 @@
void __init buffer_init(void)
{
- int nrpages;
+ unsigned long nrpages;
bh_cachep = kmem_cache_create("buffer_head",
sizeof(struct buffer_head), 0,
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 9eb134e..49bc782 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -1,6 +1,6 @@
config CEPH_FS
- tristate "Ceph distributed file system (EXPERIMENTAL)"
- depends on INET && EXPERIMENTAL
+ tristate "Ceph distributed file system"
+ depends on INET
select CEPH_LIB
select LIBCRC32C
select CRYPTO_AES
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 064d1a6..a60ea97 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -195,7 +195,7 @@
*/
static int readpage_nounlock(struct file *filp, struct page *page)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_inode_to_client(inode)->client->osdc;
@@ -236,16 +236,10 @@
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
- struct ceph_osd_reply_head *replyhead;
- int rc, bytes;
+ int rc = req->r_result;
+ int bytes = le32_to_cpu(msg->hdr.data_len);
int i;
- /* parse reply */
- replyhead = msg->front.iov_base;
- WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
- rc = le32_to_cpu(replyhead->result);
- bytes = le32_to_cpu(msg->hdr.data_len);
-
dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);
/* unlock all pages, zeroing any data we didn't read */
@@ -315,7 +309,7 @@
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, 0,
ci->i_truncate_seq, ci->i_truncate_size,
- NULL, false, 1, 0);
+ NULL, false, 0);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -370,7 +364,7 @@
static int ceph_readpages(struct file *file, struct address_space *mapping,
struct list_head *page_list, unsigned nr_pages)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
int rc = 0;
int max = 0;
@@ -492,8 +486,7 @@
&ci->i_layout, snapc,
page_off, len,
ci->i_truncate_seq, ci->i_truncate_size,
- &inode->i_mtime,
- &page, 1, 0, 0, true);
+ &inode->i_mtime, &page, 1);
if (err < 0) {
dout("writepage setting page/mapping error %d %p\n", err, page);
SetPageError(page);
@@ -554,27 +547,18 @@
struct ceph_msg *msg)
{
struct inode *inode = req->r_inode;
- struct ceph_osd_reply_head *replyhead;
- struct ceph_osd_op *op;
struct ceph_inode_info *ci = ceph_inode(inode);
unsigned wrote;
struct page *page;
int i;
struct ceph_snap_context *snapc = req->r_snapc;
struct address_space *mapping = inode->i_mapping;
- __s32 rc = -EIO;
- u64 bytes = 0;
+ int rc = req->r_result;
+ u64 bytes = le64_to_cpu(req->r_request_ops[0].extent.length);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
long writeback_stat;
unsigned issued = ceph_caps_issued(ci);
- /* parse reply */
- replyhead = msg->front.iov_base;
- WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
- op = (void *)(replyhead + 1);
- rc = le32_to_cpu(replyhead->result);
- bytes = le64_to_cpu(op->extent.length);
-
if (rc >= 0) {
/*
* Assume we wrote the pages we originally sent. The
@@ -741,8 +725,6 @@
struct page *page;
int want;
u64 offset, len;
- struct ceph_osd_request_head *reqhead;
- struct ceph_osd_op *op;
long writeback_stat;
next = 0;
@@ -838,7 +820,7 @@
snapc, do_sync,
ci->i_truncate_seq,
ci->i_truncate_size,
- &inode->i_mtime, true, 1, 0);
+ &inode->i_mtime, true, 0);
if (IS_ERR(req)) {
rc = PTR_ERR(req);
@@ -906,10 +888,8 @@
/* revise final length, page count */
req->r_num_pages = locked_pages;
- reqhead = req->r_request->front.iov_base;
- op = (void *)(reqhead + 1);
- op->extent.length = cpu_to_le64(len);
- op->payload_len = cpu_to_le32(len);
+ req->r_request_ops[0].extent.length = cpu_to_le64(len);
+ req->r_request_ops[0].payload_len = cpu_to_le32(len);
req->r_request->hdr.data_len = cpu_to_le32(len);
rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
@@ -977,7 +957,7 @@
loff_t pos, unsigned len,
struct page *page)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
loff_t page_off = pos & PAGE_CACHE_MASK;
@@ -1086,7 +1066,7 @@
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_file_info *fi = file->private_data;
struct page *page;
@@ -1144,7 +1124,7 @@
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1228,7 +1208,7 @@
*/
static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct page *page = vmf->page;
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
loff_t off = page_offset(page);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a1d9bb3..78e2f57 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -611,8 +611,16 @@
if (flags & CEPH_CAP_FLAG_AUTH)
ci->i_auth_cap = cap;
- else if (ci->i_auth_cap == cap)
+ else if (ci->i_auth_cap == cap) {
ci->i_auth_cap = NULL;
+ spin_lock(&mdsc->cap_dirty_lock);
+ if (!list_empty(&ci->i_dirty_item)) {
+ dout(" moving %p to cap_dirty_migrating\n", inode);
+ list_move(&ci->i_dirty_item,
+ &mdsc->cap_dirty_migrating);
+ }
+ spin_unlock(&mdsc->cap_dirty_lock);
+ }
dout("add_cap inode %p (%llx.%llx) cap %p %s now %s seq %d mds%d\n",
inode, ceph_vinop(inode), cap, ceph_cap_string(issued),
@@ -930,7 +938,7 @@
u64 size, u64 max_size,
struct timespec *mtime, struct timespec *atime,
u64 time_warp_seq,
- uid_t uid, gid_t gid, umode_t mode,
+ kuid_t uid, kgid_t gid, umode_t mode,
u64 xattr_version,
struct ceph_buffer *xattrs_buf,
u64 follows)
@@ -974,8 +982,8 @@
ceph_encode_timespec(&fc->atime, atime);
fc->time_warp_seq = cpu_to_le32(time_warp_seq);
- fc->uid = cpu_to_le32(uid);
- fc->gid = cpu_to_le32(gid);
+ fc->uid = cpu_to_le32(from_kuid(&init_user_ns, uid));
+ fc->gid = cpu_to_le32(from_kgid(&init_user_ns, gid));
fc->mode = cpu_to_le32(mode);
fc->xattr_version = cpu_to_le64(xattr_version);
@@ -1081,8 +1089,8 @@
struct timespec mtime, atime;
int wake = 0;
umode_t mode;
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
struct ceph_mds_session *session;
u64 xattr_version = 0;
struct ceph_buffer *xattr_blob = NULL;
@@ -1460,7 +1468,7 @@
struct ceph_mds_client *mdsc = fsc->mdsc;
struct inode *inode = &ci->vfs_inode;
struct ceph_cap *cap;
- int file_wanted, used;
+ int file_wanted, used, cap_used;
int took_snap_rwsem = 0; /* true if mdsc->snap_rwsem held */
int issued, implemented, want, retain, revoking, flushing = 0;
int mds = -1; /* keep track of how far we've gone through i_caps list
@@ -1563,9 +1571,14 @@
/* NOTE: no side-effects allowed, until we take s_mutex */
+ cap_used = used;
+ if (ci->i_auth_cap && cap != ci->i_auth_cap)
+ cap_used &= ~ci->i_auth_cap->issued;
+
revoking = cap->implemented & ~cap->issued;
- dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
+ dout(" mds%d cap %p used %s issued %s implemented %s revoking %s\n",
cap->mds, cap, ceph_cap_string(cap->issued),
+ ceph_cap_string(cap_used),
ceph_cap_string(cap->implemented),
ceph_cap_string(revoking));
@@ -1593,7 +1606,7 @@
}
/* completed revocation? going down and there are no caps? */
- if (revoking && (revoking & used) == 0) {
+ if (revoking && (revoking & cap_used) == 0) {
dout("completed revocation of %s\n",
ceph_cap_string(cap->implemented & ~cap->issued));
goto ack;
@@ -1670,8 +1683,8 @@
sent++;
/* __send_cap drops i_ceph_lock */
- delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, used, want,
- retain, flushing, NULL);
+ delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, cap_used,
+ want, retain, flushing, NULL);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
@@ -2359,10 +2372,11 @@
if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
- inode->i_uid = le32_to_cpu(grant->uid);
- inode->i_gid = le32_to_cpu(grant->gid);
+ inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
+ inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
- inode->i_uid, inode->i_gid);
+ from_kuid(&init_user_ns, inode->i_uid),
+ from_kgid(&init_user_ns, inode->i_gid));
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
@@ -2416,7 +2430,9 @@
dout("mds wanted %s -> %s\n",
ceph_cap_string(le32_to_cpu(grant->wanted)),
ceph_cap_string(wanted));
- grant->wanted = cpu_to_le32(wanted);
+ /* imported cap may not have correct mds_wanted */
+ if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT)
+ check_caps = 1;
}
cap->seq = seq;
@@ -2820,6 +2836,9 @@
dout(" mds%d seq %lld cap seq %u\n", session->s_mds, session->s_seq,
(unsigned)seq);
+ if (op == CEPH_CAP_OP_IMPORT)
+ ceph_add_cap_releases(mdsc, session);
+
/* lookup ino */
inode = ceph_find_inode(sb, vino);
ci = ceph_inode(inode);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8c1aabe..6d797f4 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -238,7 +238,7 @@
static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
struct ceph_file_info *fi = filp->private_data;
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -1138,7 +1138,7 @@
loff_t *ppos)
{
struct ceph_file_info *cf = file->private_data;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
int left;
const int bufsize = 1024;
@@ -1188,7 +1188,7 @@
static int ceph_dir_fsync(struct file *file, loff_t start, loff_t end,
int datasync)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct list_head *head = &ci->i_unsafe_dirops;
struct ceph_mds_request *req;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index ca3ab3f..16796be 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -81,7 +81,7 @@
if (parent_inode) {
/* nfsd wants connectable */
*max_len = connected_handle_length;
- type = 255;
+ type = FILEID_INVALID;
} else {
dout("encode_fh %p\n", dentry);
fh->ino = ceph_ino(inode);
@@ -90,7 +90,7 @@
}
} else {
*max_len = handle_length;
- type = 255;
+ type = FILEID_INVALID;
}
if (dentry)
dput(dentry);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index e51558f..bf338d9 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -243,6 +243,9 @@
err = ceph_mdsc_do_request(mdsc,
(flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
req);
+ if (err)
+ goto out_err;
+
err = ceph_handle_snapdir(req, dentry, err);
if (err == 0 && (flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
@@ -263,6 +266,9 @@
err = finish_no_open(file, dn);
} else {
dout("atomic_open finish_open on dn %p\n", dn);
+ if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+ *opened |= FILE_CREATED;
+ }
err = finish_open(file, dentry, ceph_open, opened);
}
@@ -393,7 +399,7 @@
static ssize_t ceph_sync_read(struct file *file, char __user *data,
unsigned len, loff_t *poff, int *checkeof)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct page **pages;
u64 off = *poff;
int num_pages, ret;
@@ -466,7 +472,7 @@
static ssize_t ceph_sync_write(struct file *file, const char __user *data,
size_t left, loff_t *offset)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_osd_request *req;
@@ -483,7 +489,7 @@
int ret;
struct timespec mtime = CURRENT_TIME;
- if (ceph_snap(file->f_dentry->d_inode) != CEPH_NOSNAP)
+ if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
return -EROFS;
dout("sync_write on file %p %lld~%u %s\n", file, *offset,
@@ -535,7 +541,7 @@
ci->i_snap_realm->cached_context,
do_sync,
ci->i_truncate_seq, ci->i_truncate_size,
- &mtime, false, 2, page_align);
+ &mtime, false, page_align);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -637,7 +643,7 @@
struct ceph_file_info *fi = filp->private_data;
loff_t *ppos = &iocb->ki_pos;
size_t len = iov->iov_len;
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ceph_inode_info *ci = ceph_inode(inode);
void __user *base = iov->iov_base;
ssize_t ret;
@@ -707,7 +713,7 @@
{
struct file *file = iocb->ki_filp;
struct ceph_file_info *fi = file->private_data;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2971eaa..851814d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -612,10 +612,11 @@
if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(info->mode);
- inode->i_uid = le32_to_cpu(info->uid);
- inode->i_gid = le32_to_cpu(info->gid);
+ inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
+ inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
- inode->i_uid, inode->i_gid);
+ from_kuid(&init_user_ns, inode->i_uid),
+ from_kgid(&init_user_ns, inode->i_gid));
}
if ((issued & CEPH_CAP_LINK_EXCL) == 0)
@@ -1130,8 +1131,8 @@
req->r_request_started);
dout(" final dn %p\n", dn);
i++;
- } else if (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
- req->r_op == CEPH_MDS_OP_MKSNAP) {
+ } else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+ req->r_op == CEPH_MDS_OP_MKSNAP) && !req->r_aborted) {
struct dentry *dn = req->r_dentry;
/* fill out a snapdir LOOKUPSNAP dentry */
@@ -1195,6 +1196,39 @@
/*
* Prepopulate our cache with readdir results, leases, etc.
*/
+static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req,
+ struct ceph_mds_session *session)
+{
+ struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+ int i, err = 0;
+
+ for (i = 0; i < rinfo->dir_nr; i++) {
+ struct ceph_vino vino;
+ struct inode *in;
+ int rc;
+
+ vino.ino = le64_to_cpu(rinfo->dir_in[i].in->ino);
+ vino.snap = le64_to_cpu(rinfo->dir_in[i].in->snapid);
+
+ in = ceph_get_inode(req->r_dentry->d_sb, vino);
+ if (IS_ERR(in)) {
+ err = PTR_ERR(in);
+ dout("new_inode badness got %d\n", err);
+ continue;
+ }
+ rc = fill_inode(in, &rinfo->dir_in[i], NULL, session,
+ req->r_request_started, -1,
+ &req->r_caps_reservation);
+ if (rc < 0) {
+ pr_err("fill_inode badness on %p got %d\n", in, rc);
+ err = rc;
+ continue;
+ }
+ }
+
+ return err;
+}
+
int ceph_readdir_prepopulate(struct ceph_mds_request *req,
struct ceph_mds_session *session)
{
@@ -1209,6 +1243,9 @@
u64 frag = le32_to_cpu(rhead->args.readdir.frag);
struct ceph_dentry_info *di;
+ if (req->r_aborted)
+ return readdir_prepopulate_inodes_only(req, session);
+
if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) {
snapdir = ceph_get_snapdir(parent->d_inode);
parent = d_find_alias(snapdir);
@@ -1565,26 +1602,30 @@
if (ia_valid & ATTR_UID) {
dout("setattr %p uid %d -> %d\n", inode,
- inode->i_uid, attr->ia_uid);
+ from_kuid(&init_user_ns, inode->i_uid),
+ from_kuid(&init_user_ns, attr->ia_uid));
if (issued & CEPH_CAP_AUTH_EXCL) {
inode->i_uid = attr->ia_uid;
dirtied |= CEPH_CAP_AUTH_EXCL;
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
- attr->ia_uid != inode->i_uid) {
- req->r_args.setattr.uid = cpu_to_le32(attr->ia_uid);
+ !uid_eq(attr->ia_uid, inode->i_uid)) {
+ req->r_args.setattr.uid = cpu_to_le32(
+ from_kuid(&init_user_ns, attr->ia_uid));
mask |= CEPH_SETATTR_UID;
release |= CEPH_CAP_AUTH_SHARED;
}
}
if (ia_valid & ATTR_GID) {
dout("setattr %p gid %d -> %d\n", inode,
- inode->i_gid, attr->ia_gid);
+ from_kgid(&init_user_ns, inode->i_gid),
+ from_kgid(&init_user_ns, attr->ia_gid));
if (issued & CEPH_CAP_AUTH_EXCL) {
inode->i_gid = attr->ia_gid;
dirtied |= CEPH_CAP_AUTH_EXCL;
} else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 ||
- attr->ia_gid != inode->i_gid) {
- req->r_args.setattr.gid = cpu_to_le32(attr->ia_gid);
+ !gid_eq(attr->ia_gid, inode->i_gid)) {
+ req->r_args.setattr.gid = cpu_to_le32(
+ from_kgid(&init_user_ns, attr->ia_gid));
mask |= CEPH_SETATTR_GID;
release |= CEPH_CAP_AUTH_SHARED;
}
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 36549a4..4a98934 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -16,11 +16,11 @@
*/
static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
{
- struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
+ struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout l;
int err;
- err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
+ err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
if (!err) {
l.stripe_unit = ceph_file_layout_su(ci->i_layout);
l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
@@ -63,12 +63,12 @@
static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct inode *parent_inode;
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
- struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
+ struct ceph_inode_info *ci = ceph_inode(file_inode(file));
struct ceph_ioctl_layout nl;
int err;
@@ -76,7 +76,7 @@
return -EFAULT;
/* validate changed params against current layout */
- err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
+ err = ceph_do_getattr(file_inode(file), CEPH_STAT_CAP_LAYOUT);
if (err)
return err;
@@ -136,7 +136,7 @@
*/
static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_mds_request *req;
struct ceph_ioctl_layout l;
int err;
@@ -179,13 +179,12 @@
static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
{
struct ceph_ioctl_dataloc dl;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_osd_client *osdc =
&ceph_sb_to_client(inode->i_sb)->client->osdc;
u64 len = 1, olen;
u64 tmp;
- struct ceph_object_layout ol;
struct ceph_pg pgid;
int r;
@@ -194,7 +193,7 @@
return -EFAULT;
down_read(&osdc->map_sem);
- r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
+ r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
&dl.object_no, &dl.object_offset,
&olen);
if (r < 0)
@@ -209,10 +208,9 @@
snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
ceph_ino(inode), dl.object_no);
- ceph_calc_object_layout(&ol, dl.object_name, &ci->i_layout,
+ ceph_calc_object_layout(&pgid, dl.object_name, &ci->i_layout,
osdc->osdmap);
- pgid = ol.ol_pgid;
dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
if (dl.osd >= 0) {
struct ceph_entity_addr *a =
@@ -234,7 +232,7 @@
static long ceph_ioctl_lazyio(struct file *file)
{
struct ceph_file_info *fi = file->private_data;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_inode_info *ci = ceph_inode(inode);
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 80576d05..202dd3d 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -13,7 +13,7 @@
static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
int cmd, u8 wait, struct file_lock *fl)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ceph_mds_client *mdsc =
ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_mds_request *req;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9165eb8..442880d 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -233,6 +233,30 @@
}
/*
+ * parse create results
+ */
+static int parse_reply_info_create(void **p, void *end,
+ struct ceph_mds_reply_info_parsed *info,
+ int features)
+{
+ if (features & CEPH_FEATURE_REPLY_CREATE_INODE) {
+ if (*p == end) {
+ info->has_create_ino = false;
+ } else {
+ info->has_create_ino = true;
+ info->ino = ceph_decode_64(p);
+ }
+ }
+
+ if (unlikely(*p != end))
+ goto bad;
+ return 0;
+
+bad:
+ return -EIO;
+}
+
+/*
* parse extra results
*/
static int parse_reply_info_extra(void **p, void *end,
@@ -241,8 +265,12 @@
{
if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
return parse_reply_info_filelock(p, end, info, features);
- else
+ else if (info->head->op == CEPH_MDS_OP_READDIR)
return parse_reply_info_dir(p, end, info, features);
+ else if (info->head->op == CEPH_MDS_OP_CREATE)
+ return parse_reply_info_create(p, end, info, features);
+ else
+ return -EIO;
}
/*
@@ -1658,8 +1686,8 @@
head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch);
head->op = cpu_to_le32(req->r_op);
- head->caller_uid = cpu_to_le32(req->r_uid);
- head->caller_gid = cpu_to_le32(req->r_gid);
+ head->caller_uid = cpu_to_le32(from_kuid(&init_user_ns, req->r_uid));
+ head->caller_gid = cpu_to_le32(from_kgid(&init_user_ns, req->r_gid));
head->args = req->r_args;
ceph_encode_filepath(&p, end, ino1, path1);
@@ -2170,7 +2198,8 @@
mutex_lock(&req->r_fill_mutex);
err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
if (err == 0) {
- if (result == 0 && req->r_op != CEPH_MDS_OP_GETFILELOCK &&
+ if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
+ req->r_op == CEPH_MDS_OP_LSSNAP) &&
rinfo->dir_nr)
ceph_readdir_prepopulate(req, req->r_session);
ceph_unreserve_caps(mdsc, &req->r_caps_reservation);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index dd26846..c2a19fb 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -74,6 +74,12 @@
struct ceph_mds_reply_info_in *dir_in;
u8 dir_complete, dir_end;
};
+
+ /* for create results */
+ struct {
+ bool has_create_ino;
+ u64 ino;
+ };
};
/* encoded blob describing snapshot contexts for certain
@@ -184,8 +190,8 @@
union ceph_mds_request_args r_args;
int r_fmode; /* file mode, if expecting cap */
- uid_t r_uid;
- gid_t r_gid;
+ kuid_t r_uid;
+ kgid_t r_gid;
/* for choosing which mds to send this request to */
int r_direct_mode;
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 73b7d44..0d3c924 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -59,6 +59,10 @@
return ERR_PTR(-ENOMEM);
ceph_decode_16_safe(p, end, version, bad);
+ if (version > 3) {
+ pr_warning("got mdsmap version %d > 3, failing", version);
+ goto bad;
+ }
ceph_decode_need(p, end, 8*sizeof(u32) + sizeof(u64), bad);
m->m_epoch = ceph_decode_32(p);
@@ -144,13 +148,13 @@
/* pg_pools */
ceph_decode_32_safe(p, end, n, bad);
m->m_num_data_pg_pools = n;
- m->m_data_pg_pools = kcalloc(n, sizeof(u32), GFP_NOFS);
+ m->m_data_pg_pools = kcalloc(n, sizeof(u64), GFP_NOFS);
if (!m->m_data_pg_pools)
goto badmem;
- ceph_decode_need(p, end, sizeof(u32)*(n+1), bad);
+ ceph_decode_need(p, end, sizeof(u64)*(n+1), bad);
for (i = 0; i < n; i++)
- m->m_data_pg_pools[i] = ceph_decode_32(p);
- m->m_cas_pg_pool = ceph_decode_32(p);
+ m->m_data_pg_pools[i] = ceph_decode_64(p);
+ m->m_cas_pg_pool = ceph_decode_64(p);
/* ok, we don't care about the rest. */
dout("mdsmap_decode success epoch %u\n", m->m_epoch);
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index cd5097d..89fa4a9 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -15,6 +15,7 @@
case CEPH_MDS_STATE_BOOT: return "up:boot";
case CEPH_MDS_STATE_STANDBY: return "up:standby";
case CEPH_MDS_STATE_STANDBY_REPLAY: return "up:standby-replay";
+ case CEPH_MDS_STATE_REPLAYONCE: return "up:oneshot-replay";
case CEPH_MDS_STATE_CREATING: return "up:creating";
case CEPH_MDS_STATE_STARTING: return "up:starting";
/* up and in */
@@ -50,10 +51,13 @@
case CEPH_MDS_OP_LOOKUP: return "lookup";
case CEPH_MDS_OP_LOOKUPHASH: return "lookuphash";
case CEPH_MDS_OP_LOOKUPPARENT: return "lookupparent";
+ case CEPH_MDS_OP_LOOKUPINO: return "lookupino";
case CEPH_MDS_OP_GETATTR: return "getattr";
case CEPH_MDS_OP_SETXATTR: return "setxattr";
case CEPH_MDS_OP_SETATTR: return "setattr";
case CEPH_MDS_OP_RMXATTR: return "rmxattr";
+ case CEPH_MDS_OP_SETLAYOUT: return "setlayou";
+ case CEPH_MDS_OP_SETDIRLAYOUT: return "setdirlayout";
case CEPH_MDS_OP_READDIR: return "readdir";
case CEPH_MDS_OP_MKNOD: return "mknod";
case CEPH_MDS_OP_LINK: return "link";
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index e86aa994..6ddc0bc 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -71,8 +71,14 @@
/*
* express utilization in terms of large blocks to avoid
* overflow on 32-bit machines.
+ *
+ * NOTE: for the time being, we make bsize == frsize to humor
+ * not-yet-ancient versions of glibc that are broken.
+ * Someday, we will probably want to report a real block
+ * size... whatever that may mean for a network file system!
*/
buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
+ buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
buf->f_bfree = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
buf->f_bavail = le64_to_cpu(st.kb_avail) >> (CEPH_BLOCK_SHIFT-10);
@@ -80,7 +86,6 @@
buf->f_files = le64_to_cpu(st.num_objects);
buf->f_ffree = -1;
buf->f_namelen = NAME_MAX;
- buf->f_frsize = PAGE_CACHE_SIZE;
/* leave fsid little-endian, regardless of host endianness */
fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);
@@ -947,6 +952,7 @@
.kill_sb = ceph_kill_sb,
.fs_flags = FS_RENAME_DOES_D_MOVE,
};
+MODULE_ALIAS_FS("ceph");
#define _STRINGIFY(x) #x
#define STRINGIFY(x) _STRINGIFY(x)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 66ebe72..c7b3097 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -21,7 +21,7 @@
/* large granularity for statfs utilization stats to facilitate
* large volume sizes on 32-bit machines. */
-#define CEPH_BLOCK_SHIFT 20 /* 1 MB */
+#define CEPH_BLOCK_SHIFT 22 /* 4 MB */
#define CEPH_BLOCK (1 << CEPH_BLOCK_SHIFT)
#define CEPH_MOUNT_OPT_DIRSTAT (1<<4) /* `cat dirname` for stats */
@@ -138,8 +138,8 @@
struct ceph_snap_context *context;
umode_t mode;
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
struct ceph_buffer *xattr_blob;
u64 xattr_version;
@@ -798,13 +798,7 @@
/* file.c */
extern const struct file_operations ceph_file_fops;
extern const struct address_space_operations ceph_aops;
-extern int ceph_copy_to_page_vector(struct page **pages,
- const char *data,
- loff_t off, size_t len);
-extern int ceph_copy_from_page_vector(struct page **pages,
- char *data,
- loff_t off, size_t len);
-extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+
extern int ceph_open(struct inode *inode, struct file *file);
extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 2c2ae5b..9b6b2b6 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -29,9 +29,94 @@
size_t name_size; /* strlen(name) + 1 (for '\0') */
size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
- bool readonly;
+ bool readonly, hidden;
+ bool (*exists_cb)(struct ceph_inode_info *ci);
};
+/* layouts */
+
+static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
+{
+ size_t s;
+ char *p = (char *)&ci->i_layout;
+
+ for (s = 0; s < sizeof(ci->i_layout); s++, p++)
+ if (*p)
+ return true;
+ return false;
+}
+
+static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
+ size_t size)
+{
+ int ret;
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_osd_client *osdc = &fsc->client->osdc;
+ s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+ const char *pool_name;
+
+ dout("ceph_vxattrcb_layout %p\n", &ci->vfs_inode);
+ down_read(&osdc->map_sem);
+ pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
+ if (pool_name)
+ ret = snprintf(val, size,
+ "stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%s",
+ (unsigned long long)ceph_file_layout_su(ci->i_layout),
+ (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
+ (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
+ pool_name);
+ else
+ ret = snprintf(val, size,
+ "stripe_unit=%lld stripe_count=%lld object_size=%lld pool=%lld",
+ (unsigned long long)ceph_file_layout_su(ci->i_layout),
+ (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
+ (unsigned long long)ceph_file_layout_object_size(ci->i_layout),
+ (unsigned long long)pool);
+
+ up_read(&osdc->map_sem);
+ return ret;
+}
+
+static size_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ return snprintf(val, size, "%lld",
+ (unsigned long long)ceph_file_layout_su(ci->i_layout));
+}
+
+static size_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ return snprintf(val, size, "%lld",
+ (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout));
+}
+
+static size_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ return snprintf(val, size, "%lld",
+ (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
+}
+
+static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
+ char *val, size_t size)
+{
+ int ret;
+ struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+ struct ceph_osd_client *osdc = &fsc->client->osdc;
+ s64 pool = ceph_file_layout_pg_pool(ci->i_layout);
+ const char *pool_name;
+
+ down_read(&osdc->map_sem);
+ pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
+ if (pool_name)
+ ret = snprintf(val, size, "%s", pool_name);
+ else
+ ret = snprintf(val, size, "%lld", (unsigned long long)pool);
+ up_read(&osdc->map_sem);
+ return ret;
+}
+
/* directories */
static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
@@ -83,17 +168,43 @@
(long)ci->i_rctime.tv_nsec);
}
-#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
-#define XATTR_NAME_CEPH(_type, _name) \
- { \
- .name = CEPH_XATTR_NAME(_type, _name), \
- .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
- .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
- .readonly = true, \
- }
+#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
+#define CEPH_XATTR_NAME2(_type, _name, _name2) \
+ XATTR_CEPH_PREFIX #_type "." #_name "." #_name2
+
+#define XATTR_NAME_CEPH(_type, _name) \
+ { \
+ .name = CEPH_XATTR_NAME(_type, _name), \
+ .name_size = sizeof (CEPH_XATTR_NAME(_type, _name)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name, \
+ .readonly = true, \
+ .hidden = false, \
+ .exists_cb = NULL, \
+ }
+#define XATTR_LAYOUT_FIELD(_type, _name, _field) \
+ { \
+ .name = CEPH_XATTR_NAME2(_type, _name, _field), \
+ .name_size = sizeof (CEPH_XATTR_NAME2(_type, _name, _field)), \
+ .getxattr_cb = ceph_vxattrcb_ ## _name ## _ ## _field, \
+ .readonly = false, \
+ .hidden = true, \
+ .exists_cb = ceph_vxattrcb_layout_exists, \
+ }
static struct ceph_vxattr ceph_dir_vxattrs[] = {
+ {
+ .name = "ceph.dir.layout",
+ .name_size = sizeof("ceph.dir.layout"),
+ .getxattr_cb = ceph_vxattrcb_layout,
+ .readonly = false,
+ .hidden = false,
+ .exists_cb = ceph_vxattrcb_layout_exists,
+ },
+ XATTR_LAYOUT_FIELD(dir, layout, stripe_unit),
+ XATTR_LAYOUT_FIELD(dir, layout, stripe_count),
+ XATTR_LAYOUT_FIELD(dir, layout, object_size),
+ XATTR_LAYOUT_FIELD(dir, layout, pool),
XATTR_NAME_CEPH(dir, entries),
XATTR_NAME_CEPH(dir, files),
XATTR_NAME_CEPH(dir, subdirs),
@@ -102,35 +213,26 @@
XATTR_NAME_CEPH(dir, rsubdirs),
XATTR_NAME_CEPH(dir, rbytes),
XATTR_NAME_CEPH(dir, rctime),
- { 0 } /* Required table terminator */
+ { .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_dir_vxattrs_name_size; /* total size of all names */
/* files */
-static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val,
- size_t size)
-{
- int ret;
-
- ret = snprintf(val, size,
- "chunk_bytes=%lld\nstripe_count=%lld\nobject_size=%lld\n",
- (unsigned long long)ceph_file_layout_su(ci->i_layout),
- (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout),
- (unsigned long long)ceph_file_layout_object_size(ci->i_layout));
- return ret;
-}
-
static struct ceph_vxattr ceph_file_vxattrs[] = {
- XATTR_NAME_CEPH(file, layout),
- /* The following extended attribute name is deprecated */
{
- .name = XATTR_CEPH_PREFIX "layout",
- .name_size = sizeof (XATTR_CEPH_PREFIX "layout"),
- .getxattr_cb = ceph_vxattrcb_file_layout,
- .readonly = true,
+ .name = "ceph.file.layout",
+ .name_size = sizeof("ceph.file.layout"),
+ .getxattr_cb = ceph_vxattrcb_layout,
+ .readonly = false,
+ .hidden = false,
+ .exists_cb = ceph_vxattrcb_layout_exists,
},
- { 0 } /* Required table terminator */
+ XATTR_LAYOUT_FIELD(file, layout, stripe_unit),
+ XATTR_LAYOUT_FIELD(file, layout, stripe_count),
+ XATTR_LAYOUT_FIELD(file, layout, object_size),
+ XATTR_LAYOUT_FIELD(file, layout, pool),
+ { .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_file_vxattrs_name_size; /* total size of all names */
@@ -164,7 +266,8 @@
size_t size = 0;
for (vxattr = vxattrs; vxattr->name; vxattr++)
- size += vxattr->name_size;
+ if (!vxattr->hidden)
+ size += vxattr->name_size;
return size;
}
@@ -572,13 +675,17 @@
if (!ceph_is_valid_xattr(name))
return -ENODATA;
- /* let's see if a virtual xattr was requested */
- vxattr = ceph_match_vxattr(inode, name);
-
spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
ci->i_xattrs.version, ci->i_xattrs.index_version);
+ /* let's see if a virtual xattr was requested */
+ vxattr = ceph_match_vxattr(inode, name);
+ if (vxattr && !(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
+ err = vxattr->getxattr_cb(ci, value, size);
+ goto out;
+ }
+
if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto get_xattr;
@@ -592,11 +699,6 @@
spin_lock(&ci->i_ceph_lock);
- if (vxattr && vxattr->readonly) {
- err = vxattr->getxattr_cb(ci, value, size);
- goto out;
- }
-
err = __build_xattrs(inode);
if (err < 0)
goto out;
@@ -604,11 +706,8 @@
get_xattr:
err = -ENODATA; /* == ENOATTR */
xattr = __get_xattr(ci, name);
- if (!xattr) {
- if (vxattr)
- err = vxattr->getxattr_cb(ci, value, size);
+ if (!xattr)
goto out;
- }
err = -ERANGE;
if (size && size < xattr->val_len)
@@ -664,23 +763,30 @@
vir_namelen = ceph_vxattrs_name_size(vxattrs);
/* adding 1 byte per each variable due to the null termination */
- namelen = vir_namelen + ci->i_xattrs.names_size + ci->i_xattrs.count;
+ namelen = ci->i_xattrs.names_size + ci->i_xattrs.count;
err = -ERANGE;
- if (size && namelen > size)
+ if (size && vir_namelen + namelen > size)
goto out;
- err = namelen;
+ err = namelen + vir_namelen;
if (size == 0)
goto out;
names = __copy_xattr_names(ci, names);
/* virtual xattr names, too */
- if (vxattrs)
+ err = namelen;
+ if (vxattrs) {
for (i = 0; vxattrs[i].name; i++) {
- len = sprintf(names, "%s", vxattrs[i].name);
- names += len + 1;
+ if (!vxattrs[i].hidden &&
+ !(vxattrs[i].exists_cb &&
+ !vxattrs[i].exists_cb(ci))) {
+ len = sprintf(names, "%s", vxattrs[i].name);
+ names += len + 1;
+ err += len + 1;
+ }
}
+ }
out:
spin_unlock(&ci->i_ceph_lock);
@@ -782,6 +888,10 @@
if (vxattr && vxattr->readonly)
return -EOPNOTSUPP;
+ /* pass any unhandled ceph.* xattrs through to the MDS */
+ if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
+ goto do_sync_unlocked;
+
/* preallocate memory for xattr name, value, index node */
err = -ENOMEM;
newname = kmemdup(name, name_len + 1, GFP_NOFS);
@@ -838,6 +948,7 @@
do_sync:
spin_unlock(&ci->i_ceph_lock);
+do_sync_unlocked:
err = ceph_sync_setxattr(dentry, name, value, size, flags);
out:
kfree(newname);
@@ -892,6 +1003,10 @@
if (vxattr && vxattr->readonly)
return -EOPNOTSUPP;
+ /* pass any unhandled ceph.* xattrs through to the MDS */
+ if (!strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN))
+ goto do_sync_unlocked;
+
err = -ENOMEM;
spin_lock(&ci->i_ceph_lock);
retry:
@@ -931,6 +1046,7 @@
return err;
do_sync:
spin_unlock(&ci->i_ceph_lock);
+do_sync_unlocked:
err = ceph_send_removexattr(dentry, name);
out:
return err;
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 21ff76c..2906ee2 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -155,14 +155,14 @@
points. If unsure, say N.
config CIFS_NFSD_EXPORT
- bool "Allow nfsd to export CIFS file system (EXPERIMENTAL)"
- depends on CIFS && EXPERIMENTAL && BROKEN
+ bool "Allow nfsd to export CIFS file system"
+ depends on CIFS && BROKEN
help
Allows NFS server to export a CIFS mounted share (nfsd over cifs)
config CIFS_SMB2
- bool "SMB2 network file system support (EXPERIMENTAL)"
- depends on CIFS && EXPERIMENTAL && INET
+ bool "SMB2 network file system support"
+ depends on CIFS && INET
select NLS
select KEYS
select FSCACHE
diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c
index cfd1ce3..1d36db1 100644
--- a/fs/cifs/asn1.c
+++ b/fs/cifs/asn1.c
@@ -614,53 +614,10 @@
}
}
- /* mechlistMIC */
- if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
- /* Check if we have reached the end of the blob, but with
- no mechListMic (e.g. NTLMSSP instead of KRB5) */
- if (ctx.error == ASN1_ERR_DEC_EMPTY)
- goto decode_negtoken_exit;
- cFYI(1, "Error decoding last part negTokenInit exit3");
- return 0;
- } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
- /* tag = 3 indicating mechListMIC */
- cFYI(1, "Exit 4 cls = %d con = %d tag = %d end = %p (%d)",
- cls, con, tag, end, *end);
- return 0;
- }
-
- /* sequence */
- if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
- cFYI(1, "Error decoding last part negTokenInit exit5");
- return 0;
- } else if ((cls != ASN1_UNI) || (con != ASN1_CON)
- || (tag != ASN1_SEQ)) {
- cFYI(1, "cls = %d con = %d tag = %d end = %p (%d)",
- cls, con, tag, end, *end);
- }
-
- /* sequence of */
- if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
- cFYI(1, "Error decoding last part negTokenInit exit 7");
- return 0;
- } else if ((cls != ASN1_CTX) || (con != ASN1_CON)) {
- cFYI(1, "Exit 8 cls = %d con = %d tag = %d end = %p (%d)",
- cls, con, tag, end, *end);
- return 0;
- }
-
- /* general string */
- if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) {
- cFYI(1, "Error decoding last part negTokenInit exit9");
- return 0;
- } else if ((cls != ASN1_UNI) || (con != ASN1_PRI)
- || (tag != ASN1_GENSTR)) {
- cFYI(1, "Exit10 cls = %d con = %d tag = %d end = %p (%d)",
- cls, con, tag, end, *end);
- return 0;
- }
- cFYI(1, "Need to call asn1_octets_decode() function for %s",
- ctx.pointer); /* is this UTF-8 or ASCII? */
-decode_negtoken_exit:
+ /*
+ * We currently ignore anything at the end of the SPNEGO blob after
+ * the mechTypes have been parsed, since none of that info is
+ * used at the moment.
+ */
return 1;
}
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index c865bfd..37e4a72 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -55,10 +55,10 @@
unsigned int wsize;
unsigned long actimeo; /* attribute cache timeout (jiffies) */
atomic_t active;
- uid_t mnt_uid;
- gid_t mnt_gid;
- uid_t mnt_backupuid;
- gid_t mnt_backupgid;
+ kuid_t mnt_uid;
+ kgid_t mnt_gid;
+ kuid_t mnt_backupuid;
+ kgid_t mnt_backupgid;
umode_t mnt_file_mode;
umode_t mnt_dir_mode;
unsigned int mnt_cifs_flags;
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 086f381..10e7747 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -149,10 +149,12 @@
goto out;
dp = description + strlen(description);
- sprintf(dp, ";uid=0x%x", sesInfo->linux_uid);
+ sprintf(dp, ";uid=0x%x",
+ from_kuid_munged(&init_user_ns, sesInfo->linux_uid));
dp = description + strlen(description);
- sprintf(dp, ";creduid=0x%x", sesInfo->cred_uid);
+ sprintf(dp, ";creduid=0x%x",
+ from_kuid_munged(&init_user_ns, sesInfo->cred_uid));
if (sesInfo->user_name) {
dp = description + strlen(description);
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 5cbd00e..f1e3f25 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -266,8 +266,8 @@
struct key *sidkey;
char *sidstr;
const struct cred *saved_cred;
- uid_t fuid = cifs_sb->mnt_uid;
- gid_t fgid = cifs_sb->mnt_gid;
+ kuid_t fuid = cifs_sb->mnt_uid;
+ kgid_t fgid = cifs_sb->mnt_gid;
/*
* If we have too many subauthorities, then something is really wrong.
@@ -297,6 +297,7 @@
* probably a safe assumption but might be better to check based on
* sidtype.
*/
+ BUILD_BUG_ON(sizeof(uid_t) != sizeof(gid_t));
if (sidkey->datalen != sizeof(uid_t)) {
rc = -EIO;
cFYI(1, "%s: Downcall contained malformed key "
@@ -305,10 +306,21 @@
goto out_key_put;
}
- if (sidtype == SIDOWNER)
- memcpy(&fuid, &sidkey->payload.value, sizeof(uid_t));
- else
- memcpy(&fgid, &sidkey->payload.value, sizeof(gid_t));
+ if (sidtype == SIDOWNER) {
+ kuid_t uid;
+ uid_t id;
+ memcpy(&id, &sidkey->payload.value, sizeof(uid_t));
+ uid = make_kuid(&init_user_ns, id);
+ if (uid_valid(uid))
+ fuid = uid;
+ } else {
+ kgid_t gid;
+ gid_t id;
+ memcpy(&id, &sidkey->payload.value, sizeof(gid_t));
+ gid = make_kgid(&init_user_ns, id);
+ if (gid_valid(gid))
+ fgid = gid;
+ }
out_key_put:
key_put(sidkey);
@@ -346,7 +358,8 @@
if (!cred)
return -ENOMEM;
- keyring = keyring_alloc(".cifs_idmap", 0, 0, cred,
+ keyring = keyring_alloc(".cifs_idmap",
+ GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred,
(KEY_POS_ALL & ~KEY_POS_SETATTR) |
KEY_USR_VIEW | KEY_USR_READ,
KEY_ALLOC_NOT_IN_QUOTA, NULL);
@@ -774,7 +787,7 @@
/* Convert permission bits from mode to equivalent CIFS ACL */
static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
- __u32 secdesclen, __u64 nmode, uid_t uid, gid_t gid, int *aclflag)
+ __u32 secdesclen, __u64 nmode, kuid_t uid, kgid_t gid, int *aclflag)
{
int rc = 0;
__u32 dacloffset;
@@ -806,17 +819,19 @@
*aclflag = CIFS_ACL_DACL;
} else {
memcpy(pnntsd, pntsd, secdesclen);
- if (uid != NO_CHANGE_32) { /* chown */
+ if (uid_valid(uid)) { /* chown */
+ uid_t id;
owner_sid_ptr = (struct cifs_sid *)((char *)pnntsd +
le32_to_cpu(pnntsd->osidoffset));
nowner_sid_ptr = kmalloc(sizeof(struct cifs_sid),
GFP_KERNEL);
if (!nowner_sid_ptr)
return -ENOMEM;
- rc = id_to_sid(uid, SIDOWNER, nowner_sid_ptr);
+ id = from_kuid(&init_user_ns, uid);
+ rc = id_to_sid(id, SIDOWNER, nowner_sid_ptr);
if (rc) {
cFYI(1, "%s: Mapping error %d for owner id %d",
- __func__, rc, uid);
+ __func__, rc, id);
kfree(nowner_sid_ptr);
return rc;
}
@@ -824,17 +839,19 @@
kfree(nowner_sid_ptr);
*aclflag = CIFS_ACL_OWNER;
}
- if (gid != NO_CHANGE_32) { /* chgrp */
+ if (gid_valid(gid)) { /* chgrp */
+ gid_t id;
group_sid_ptr = (struct cifs_sid *)((char *)pnntsd +
le32_to_cpu(pnntsd->gsidoffset));
ngroup_sid_ptr = kmalloc(sizeof(struct cifs_sid),
GFP_KERNEL);
if (!ngroup_sid_ptr)
return -ENOMEM;
- rc = id_to_sid(gid, SIDGROUP, ngroup_sid_ptr);
+ id = from_kgid(&init_user_ns, gid);
+ rc = id_to_sid(id, SIDGROUP, ngroup_sid_ptr);
if (rc) {
cFYI(1, "%s: Mapping error %d for group id %d",
- __func__, rc, gid);
+ __func__, rc, id);
kfree(ngroup_sid_ptr);
return rc;
}
@@ -1002,7 +1019,7 @@
/* Convert mode bits to an ACL so we can update the ACL on the server */
int
id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
- uid_t uid, gid_t gid)
+ kuid_t uid, kgid_t gid)
{
int rc = 0;
int aclflag = CIFS_ACL_DACL; /* default flag to set */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index de7f9168..345fc89 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -91,6 +91,30 @@
__u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
#endif
+/*
+ * Bumps refcount for cifs super block.
+ * Note that it should be only called if a referece to VFS super block is
+ * already held, e.g. in open-type syscalls context. Otherwise it can race with
+ * atomic_dec_and_test in deactivate_locked_super.
+ */
+void
+cifs_sb_active(struct super_block *sb)
+{
+ struct cifs_sb_info *server = CIFS_SB(sb);
+
+ if (atomic_inc_return(&server->active) == 1)
+ atomic_inc(&sb->s_active);
+}
+
+void
+cifs_sb_deactive(struct super_block *sb)
+{
+ struct cifs_sb_info *server = CIFS_SB(sb);
+
+ if (atomic_dec_and_test(&server->active))
+ deactivate_super(sb);
+}
+
static int
cifs_read_super(struct super_block *sb)
{
@@ -375,13 +399,15 @@
(int)(srcaddr->sa_family));
}
- seq_printf(s, ",uid=%u", cifs_sb->mnt_uid);
+ seq_printf(s, ",uid=%u",
+ from_kuid_munged(&init_user_ns, cifs_sb->mnt_uid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
seq_printf(s, ",forceuid");
else
seq_printf(s, ",noforceuid");
- seq_printf(s, ",gid=%u", cifs_sb->mnt_gid);
+ seq_printf(s, ",gid=%u",
+ from_kgid_munged(&init_user_ns, cifs_sb->mnt_gid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
seq_printf(s, ",forcegid");
else
@@ -436,9 +462,13 @@
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
seq_printf(s, ",noperm");
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
- seq_printf(s, ",backupuid=%u", cifs_sb->mnt_backupuid);
+ seq_printf(s, ",backupuid=%u",
+ from_kuid_munged(&init_user_ns,
+ cifs_sb->mnt_backupuid));
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID)
- seq_printf(s, ",backupgid=%u", cifs_sb->mnt_backupgid);
+ seq_printf(s, ",backupgid=%u",
+ from_kgid_munged(&init_user_ns,
+ cifs_sb->mnt_backupgid));
seq_printf(s, ",rsize=%u", cifs_sb->rsize);
seq_printf(s, ",wsize=%u", cifs_sb->wsize);
@@ -558,6 +588,11 @@
dentry = ERR_PTR(-ENOENT);
break;
}
+ if (!S_ISDIR(dir->i_mode)) {
+ dput(dentry);
+ dentry = ERR_PTR(-ENOTDIR);
+ break;
+ }
/* skip separators */
while (*s == sep)
@@ -677,7 +712,7 @@
static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
- struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(iocb->ki_filp);
ssize_t written;
int rc;
@@ -701,7 +736,7 @@
*/
if (whence != SEEK_SET && whence != SEEK_CUR) {
int rc;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
/*
* We need to be sure that all dirty pages are written and the
@@ -733,7 +768,7 @@
{
/* note that this is called by vfs setlease with lock_flocks held
to protect *lease from going away */
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct cifsFileInfo *cfile = file->private_data;
if (!(S_ISREG(inode->i_mode)))
@@ -766,6 +801,7 @@
.kill_sb = cifs_kill_sb,
/* .fs_flags */
};
+MODULE_ALIAS_FS("cifs");
const struct inode_operations cifs_dir_inode_ops = {
.create = cifs_create,
.atomic_open = cifs_atomic_open,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 7163419..0e32c34 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -41,6 +41,10 @@
extern const struct address_space_operations cifs_addr_ops;
extern const struct address_space_operations cifs_addr_ops_smallbuf;
+/* Functions related to super block operations */
+extern void cifs_sb_active(struct super_block *sb);
+extern void cifs_sb_deactive(struct super_block *sb);
+
/* Functions related to inodes */
extern const struct inode_operations cifs_dir_inode_ops;
extern struct inode *cifs_root_iget(struct super_block *);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index e6899ce..4f07f6f 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -400,11 +400,11 @@
char *iocharset; /* local code page for mapping to and from Unicode */
char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */
char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */
- uid_t cred_uid;
- uid_t linux_uid;
- gid_t linux_gid;
- uid_t backupuid;
- gid_t backupgid;
+ kuid_t cred_uid;
+ kuid_t linux_uid;
+ kgid_t linux_gid;
+ kuid_t backupuid;
+ kgid_t backupgid;
umode_t file_mode;
umode_t dir_mode;
unsigned secFlg;
@@ -703,8 +703,8 @@
char *serverNOS; /* name of network operating system of server */
char *serverDomain; /* security realm of server */
__u64 Suid; /* remote smb uid */
- uid_t linux_uid; /* overriding owner of files on the mount */
- uid_t cred_uid; /* owner of credentials */
+ kuid_t linux_uid; /* overriding owner of files on the mount */
+ kuid_t cred_uid; /* owner of credentials */
unsigned int capabilities;
char serverName[SERVER_NAME_LEN_WITH_NULL * 2]; /* BB make bigger for
TCP names - will ipv6 and sctp addresses fit? */
@@ -838,7 +838,7 @@
*/
struct tcon_link {
struct rb_node tl_rbnode;
- uid_t tl_uid;
+ kuid_t tl_uid;
unsigned long tl_flags;
#define TCON_LINK_MASTER 0
#define TCON_LINK_PENDING 1
@@ -931,7 +931,7 @@
struct list_head tlist; /* pointer to next fid owned by tcon */
struct list_head flist; /* next fid (file instance) for this inode */
struct cifs_fid_locks *llist; /* brlocks held by this fid */
- unsigned int uid; /* allows finding which FileInfo structure */
+ kuid_t uid; /* allows finding which FileInfo structure */
__u32 pid; /* process id who opened file */
struct cifs_fid fid; /* file id from remote */
/* BB add lock scope info here if needed */ ;
@@ -1245,8 +1245,8 @@
u64 cf_eof;
u64 cf_bytes;
u64 cf_createtime;
- uid_t cf_uid;
- gid_t cf_gid;
+ kuid_t cf_uid;
+ kgid_t cf_gid;
umode_t cf_mode;
dev_t cf_rdev;
unsigned int cf_nlink;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index b9d59a9..e996ff6 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -277,7 +277,6 @@
#define CIFS_NO_HANDLE 0xFFFF
#define NO_CHANGE_64 0xFFFFFFFFFFFFFFFFULL
-#define NO_CHANGE_32 0xFFFFFFFFUL
/* IPC$ in ASCII */
#define CIFS_IPC_RESOURCE "\x49\x50\x43\x24"
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 1988c1b..f450f06 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -46,7 +46,8 @@
({ \
unsigned int __xid = _get_xid(); \
cFYI(1, "CIFS VFS: in %s as Xid: %u with uid: %d", \
- __func__, __xid, current_fsuid()); \
+ __func__, __xid, \
+ from_kuid(&init_user_ns, current_fsuid())); \
__xid; \
})
@@ -161,7 +162,7 @@
struct cifs_fattr *fattr, struct inode *inode,
const char *path, const __u16 *pfid);
extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64,
- uid_t, gid_t);
+ kuid_t, kgid_t);
extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *,
const char *, u32 *);
extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
@@ -304,8 +305,8 @@
__u64 atime;
__u64 mtime;
__u64 mode;
- __u64 uid;
- __u64 gid;
+ kuid_t uid;
+ kgid_t gid;
dev_t device;
};
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 76d0d29..8e2e799 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1909,9 +1909,12 @@
} while (rc == -EAGAIN);
for (i = 0; i < wdata->nr_pages; i++) {
- if (rc != 0)
- SetPageError(wdata->pages[i]);
unlock_page(wdata->pages[i]);
+ if (rc != 0) {
+ SetPageError(wdata->pages[i]);
+ end_page_writeback(wdata->pages[i]);
+ page_cache_release(wdata->pages[i]);
+ }
}
mapping_set_error(inode->i_mapping, rc);
@@ -5819,8 +5822,14 @@
cifs_fill_unix_set_info(FILE_UNIX_BASIC_INFO *data_offset,
const struct cifs_unix_set_info_args *args)
{
+ u64 uid = NO_CHANGE_64, gid = NO_CHANGE_64;
u64 mode = args->mode;
+ if (uid_valid(args->uid))
+ uid = from_kuid(&init_user_ns, args->uid);
+ if (gid_valid(args->gid))
+ gid = from_kgid(&init_user_ns, args->gid);
+
/*
* Samba server ignores set of file size to zero due to bugs in some
* older clients, but we should be precise - we use SetFileSize to
@@ -5833,8 +5842,8 @@
data_offset->LastStatusChange = cpu_to_le64(args->ctime);
data_offset->LastAccessTime = cpu_to_le64(args->atime);
data_offset->LastModificationTime = cpu_to_le64(args->mtime);
- data_offset->Uid = cpu_to_le64(args->uid);
- data_offset->Gid = cpu_to_le64(args->gid);
+ data_offset->Uid = cpu_to_le64(uid);
+ data_offset->Gid = cpu_to_le64(gid);
/* better to leave device as zero when it is */
data_offset->DevMajor = cpu_to_le64(MAJOR(args->device));
data_offset->DevMinor = cpu_to_le64(MINOR(args->device));
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 12b3da3..991c63c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -97,7 +97,7 @@
Opt_user, Opt_pass, Opt_ip,
Opt_unc, Opt_domain,
Opt_srcaddr, Opt_prefixpath,
- Opt_iocharset, Opt_sockopt,
+ Opt_iocharset,
Opt_netbiosname, Opt_servern,
Opt_ver, Opt_vers, Opt_sec, Opt_cache,
@@ -202,7 +202,6 @@
{ Opt_srcaddr, "srcaddr=%s" },
{ Opt_prefixpath, "prefixpath=%s" },
{ Opt_iocharset, "iocharset=%s" },
- { Opt_sockopt, "sockopt=%s" },
{ Opt_netbiosname, "netbiosname=%s" },
{ Opt_servern, "servern=%s" },
{ Opt_ver, "ver=%s" },
@@ -987,6 +986,41 @@
return rc;
}
+static int get_option_uid(substring_t args[], kuid_t *result)
+{
+ unsigned long value;
+ kuid_t uid;
+ int rc;
+
+ rc = get_option_ul(args, &value);
+ if (rc)
+ return rc;
+
+ uid = make_kuid(current_user_ns(), value);
+ if (!uid_valid(uid))
+ return -EINVAL;
+
+ *result = uid;
+ return 0;
+}
+
+static int get_option_gid(substring_t args[], kgid_t *result)
+{
+ unsigned long value;
+ kgid_t gid;
+ int rc;
+
+ rc = get_option_ul(args, &value);
+ if (rc)
+ return rc;
+
+ gid = make_kgid(current_user_ns(), value);
+ if (!gid_valid(gid))
+ return -EINVAL;
+
+ *result = gid;
+ return 0;
+}
static int cifs_parse_security_flavors(char *value,
struct smb_vol *vol)
@@ -996,7 +1030,7 @@
switch (match_token(value, cifs_secflavor_tokens, args)) {
case Opt_sec_krb5:
- vol->secFlg |= CIFSSEC_MAY_KRB5;
+ vol->secFlg |= CIFSSEC_MAY_KRB5 | CIFSSEC_MAY_SIGN;
break;
case Opt_sec_krb5i:
vol->secFlg |= CIFSSEC_MAY_KRB5 | CIFSSEC_MUST_SIGN;
@@ -1424,47 +1458,42 @@
/* Numeric Values */
case Opt_backupuid:
- if (get_option_ul(args, &option)) {
+ if (get_option_uid(args, &vol->backupuid)) {
cERROR(1, "%s: Invalid backupuid value",
__func__);
goto cifs_parse_mount_err;
}
- vol->backupuid = option;
vol->backupuid_specified = true;
break;
case Opt_backupgid:
- if (get_option_ul(args, &option)) {
+ if (get_option_gid(args, &vol->backupgid)) {
cERROR(1, "%s: Invalid backupgid value",
__func__);
goto cifs_parse_mount_err;
}
- vol->backupgid = option;
vol->backupgid_specified = true;
break;
case Opt_uid:
- if (get_option_ul(args, &option)) {
+ if (get_option_uid(args, &vol->linux_uid)) {
cERROR(1, "%s: Invalid uid value",
__func__);
goto cifs_parse_mount_err;
}
- vol->linux_uid = option;
uid_specified = true;
break;
case Opt_cruid:
- if (get_option_ul(args, &option)) {
+ if (get_option_uid(args, &vol->cred_uid)) {
cERROR(1, "%s: Invalid cruid value",
__func__);
goto cifs_parse_mount_err;
}
- vol->cred_uid = option;
break;
case Opt_gid:
- if (get_option_ul(args, &option)) {
+ if (get_option_gid(args, &vol->linux_gid)) {
cERROR(1, "%s: Invalid gid value",
__func__);
goto cifs_parse_mount_err;
}
- vol->linux_gid = option;
gid_specified = true;
break;
case Opt_file_mode:
@@ -1722,19 +1751,6 @@
*/
cFYI(1, "iocharset set to %s", string);
break;
- case Opt_sockopt:
- string = match_strdup(args);
- if (string == NULL)
- goto out_nomem;
-
- if (strnicmp(string, "TCP_NODELAY", 11) == 0) {
- printk(KERN_WARNING "CIFS: the "
- "sockopt=TCP_NODELAY option has been "
- "deprecated and will be removed "
- "in 3.9\n");
- vol->sockopt_tcp_nodelay = 1;
- }
- break;
case Opt_netbiosname:
string = match_strdup(args);
if (string == NULL)
@@ -2241,7 +2257,7 @@
{
switch (ses->server->secType) {
case Kerberos:
- if (vol->cred_uid != ses->cred_uid)
+ if (!uid_eq(vol->cred_uid, ses->cred_uid))
return 0;
break;
default:
@@ -2713,7 +2729,7 @@
if (new->rsize && new->rsize < old->rsize)
return 0;
- if (old->mnt_uid != new->mnt_uid || old->mnt_gid != new->mnt_gid)
+ if (!uid_eq(old->mnt_uid, new->mnt_uid) || !gid_eq(old->mnt_gid, new->mnt_gid))
return 0;
if (old->mnt_file_mode != new->mnt_file_mode ||
@@ -3919,7 +3935,7 @@
}
static struct cifs_tcon *
-cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid)
+cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
{
int rc;
struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb);
@@ -3989,7 +4005,7 @@
/* find and return a tlink with given uid */
static struct tcon_link *
-tlink_rb_search(struct rb_root *root, uid_t uid)
+tlink_rb_search(struct rb_root *root, kuid_t uid)
{
struct rb_node *node = root->rb_node;
struct tcon_link *tlink;
@@ -3997,9 +4013,9 @@
while (node) {
tlink = rb_entry(node, struct tcon_link, tl_rbnode);
- if (tlink->tl_uid > uid)
+ if (uid_gt(tlink->tl_uid, uid))
node = node->rb_left;
- else if (tlink->tl_uid < uid)
+ else if (uid_lt(tlink->tl_uid, uid))
node = node->rb_right;
else
return tlink;
@@ -4018,7 +4034,7 @@
tlink = rb_entry(*new, struct tcon_link, tl_rbnode);
parent = *new;
- if (tlink->tl_uid > new_tlink->tl_uid)
+ if (uid_gt(tlink->tl_uid, new_tlink->tl_uid))
new = &((*new)->rb_left);
else
new = &((*new)->rb_right);
@@ -4048,7 +4064,7 @@
cifs_sb_tlink(struct cifs_sb_info *cifs_sb)
{
int ret;
- uid_t fsuid = current_fsuid();
+ kuid_t fsuid = current_fsuid();
struct tcon_link *tlink, *newtlink;
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 8719bbe..1cd0162 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -342,14 +342,14 @@
*created |= FILE_CREATED;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
- args.uid = (__u64) current_fsuid();
+ args.uid = current_fsuid();
if (inode->i_mode & S_ISGID)
- args.gid = (__u64) inode->i_gid;
+ args.gid = inode->i_gid;
else
- args.gid = (__u64) current_fsgid();
+ args.gid = current_fsgid();
} else {
- args.uid = NO_CHANGE_64;
- args.gid = NO_CHANGE_64;
+ args.uid = INVALID_UID; /* no change */
+ args.gid = INVALID_GID; /* no change */
}
CIFSSMBUnixSetFileInfo(xid, tcon, &args, fid->netfid,
current->tgid);
@@ -588,11 +588,11 @@
.device = device_number,
};
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
- args.uid = (__u64) current_fsuid();
- args.gid = (__u64) current_fsgid();
+ args.uid = current_fsuid();
+ args.gid = current_fsgid();
} else {
- args.uid = NO_CHANGE_64;
- args.gid = NO_CHANGE_64;
+ args.uid = INVALID_UID; /* no change */
+ args.gid = INVALID_GID; /* no change */
}
rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, &args,
cifs_sb->local_nls,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 8ea6ca5..7a0dd99 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -43,6 +43,7 @@
#include "cifs_fs_sb.h"
#include "fscache.h"
+
static inline int cifs_convert_flags(unsigned int flags)
{
if ((flags & O_ACCMODE) == O_RDONLY)
@@ -72,10 +73,15 @@
else if ((flags & O_ACCMODE) == O_RDWR)
posix_flags = SMB_O_RDWR;
- if (flags & O_CREAT)
+ if (flags & O_CREAT) {
posix_flags |= SMB_O_CREAT;
- if (flags & O_EXCL)
- posix_flags |= SMB_O_EXCL;
+ if (flags & O_EXCL)
+ posix_flags |= SMB_O_EXCL;
+ } else if (flags & O_EXCL)
+ cFYI(1, "Application %s pid %d has incorrectly set O_EXCL flag"
+ "but not O_CREAT on file open. Ignoring O_EXCL",
+ current->comm, current->tgid);
+
if (flags & O_TRUNC)
posix_flags |= SMB_O_TRUNC;
/* be safe and imply O_SYNC for O_DSYNC */
@@ -294,6 +300,8 @@
INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
mutex_init(&cfile->fh_mutex);
+ cifs_sb_active(inode->i_sb);
+
/*
* If the server returned a read oplock and we have mandatory brlocks,
* set oplock level to None.
@@ -343,7 +351,8 @@
struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
struct cifsInodeInfo *cifsi = CIFS_I(inode);
- struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct super_block *sb = inode->i_sb;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifsLockInfo *li, *tmp;
struct cifs_fid fid;
struct cifs_pending_open open;
@@ -408,6 +417,7 @@
cifs_put_tlink(cifs_file->tlink);
dput(cifs_file->dentry);
+ cifs_sb_deactive(sb);
kfree(cifs_file);
}
@@ -515,8 +525,8 @@
*/
struct cifs_unix_set_info_args args = {
.mode = inode->i_mode,
- .uid = NO_CHANGE_64,
- .gid = NO_CHANGE_64,
+ .uid = INVALID_UID, /* no change */
+ .gid = INVALID_GID, /* no change */
.ctime = NO_CHANGE_64,
.atime = NO_CHANGE_64,
.mtime = NO_CHANGE_64,
@@ -947,7 +957,7 @@
cifs_posix_lock_test(struct file *file, struct file_lock *flock)
{
int rc = 0;
- struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
unsigned char saved_type = flock->fl_type;
if ((flock->fl_flags & FL_POSIX) == 0)
@@ -974,7 +984,7 @@
static int
cifs_posix_lock_set(struct file *file, struct file_lock *flock)
{
- struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode);
+ struct cifsInodeInfo *cinode = CIFS_I(file_inode(file));
int rc = 1;
if ((flock->fl_flags & FL_POSIX) == 0)
@@ -1548,7 +1558,7 @@
cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
netfid = cfile->fid.netfid;
- cinode = CIFS_I(file->f_path.dentry->d_inode);
+ cinode = CIFS_I(file_inode(file));
if (cap_unix(tcon->ses) &&
(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
@@ -1693,7 +1703,7 @@
are always at the end of the list but since the first entry might
have a close pending, we go through the whole list */
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
- if (fsuid_only && open_file->uid != current_fsuid())
+ if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
continue;
if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) {
if (!open_file->invalidHandle) {
@@ -1746,7 +1756,7 @@
list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
if (!any_available && open_file->pid != current->tgid)
continue;
- if (fsuid_only && open_file->uid != current_fsuid())
+ if (fsuid_only && !uid_eq(open_file->uid, current_fsuid()))
continue;
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
if (!open_file->invalidHandle) {
@@ -2171,7 +2181,7 @@
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifsFileInfo *smbfile = file->private_data;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
@@ -2246,7 +2256,7 @@
*/
int cifs_flush(struct file *file, fl_owner_t id)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
int rc = 0;
if (file->f_mode & FMODE_WRITE)
@@ -2480,7 +2490,7 @@
ssize_t written;
struct inode *inode;
- inode = iocb->ki_filp->f_path.dentry->d_inode;
+ inode = file_inode(iocb->ki_filp);
/*
* BB - optimize the way when signing is disabled. We can drop this
@@ -2543,7 +2553,7 @@
cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
- struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = (struct cifsFileInfo *)
@@ -2915,7 +2925,7 @@
cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
- struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(iocb->ki_filp);
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = (struct cifsFileInfo *)
@@ -3063,7 +3073,7 @@
int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
{
int rc, xid;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
xid = get_xid();
@@ -3356,7 +3366,7 @@
int rc;
/* Is the page cached? */
- rc = cifs_readpage_from_fscache(file->f_path.dentry->d_inode, page);
+ rc = cifs_readpage_from_fscache(file_inode(file), page);
if (rc == 0)
goto read_complete;
@@ -3371,8 +3381,8 @@
else
cFYI(1, "Bytes read %d", rc);
- file->f_path.dentry->d_inode->i_atime =
- current_fs_time(file->f_path.dentry->d_inode->i_sb);
+ file_inode(file)->i_atime =
+ current_fs_time(file_inode(file)->i_sb);
if (PAGE_CACHE_SIZE > rc)
memset(read_data + rc, 0, PAGE_CACHE_SIZE - rc);
@@ -3381,7 +3391,7 @@
SetPageUptodate(page);
/* send this page to the cache */
- cifs_readpage_to_fscache(file->f_path.dentry->d_inode, page);
+ cifs_readpage_to_fscache(file_inode(file), page);
rc = 0;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index ed6208f..20887bf 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -244,15 +244,25 @@
break;
}
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
- fattr->cf_uid = cifs_sb->mnt_uid;
- else
- fattr->cf_uid = le64_to_cpu(info->Uid);
-
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
- fattr->cf_gid = cifs_sb->mnt_gid;
- else
- fattr->cf_gid = le64_to_cpu(info->Gid);
+ fattr->cf_uid = cifs_sb->mnt_uid;
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) {
+ u64 id = le64_to_cpu(info->Uid);
+ if (id < ((uid_t)-1)) {
+ kuid_t uid = make_kuid(&init_user_ns, id);
+ if (uid_valid(uid))
+ fattr->cf_uid = uid;
+ }
+ }
+
+ fattr->cf_gid = cifs_sb->mnt_gid;
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) {
+ u64 id = le64_to_cpu(info->Gid);
+ if (id < ((gid_t)-1)) {
+ kgid_t gid = make_kgid(&init_user_ns, id);
+ if (gid_valid(gid))
+ fattr->cf_gid = gid;
+ }
+ }
fattr->cf_nlink = le64_to_cpu(info->Nlinks);
}
@@ -289,7 +299,7 @@
unsigned int xid;
FILE_UNIX_BASIC_INFO find_data;
struct cifs_fattr fattr;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = filp->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
@@ -558,7 +568,7 @@
unsigned int xid;
FILE_ALL_INFO find_data;
struct cifs_fattr fattr;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = filp->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
@@ -806,10 +816,9 @@
inode_has_hashed_dentries(struct inode *inode)
{
struct dentry *dentry;
- struct hlist_node *p;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
spin_unlock(&inode->i_lock);
return true;
@@ -986,6 +995,15 @@
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
+ /*
+ * We cannot rename the file if the server doesn't support
+ * CAP_INFOLEVEL_PASSTHRU
+ */
+ if (!(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) {
+ rc = -EBUSY;
+ goto out;
+ }
+
rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
DELETE|FILE_WRITE_ATTRIBUTES, CREATE_NOT_DIR,
&netfid, &oplock, NULL, cifs_sb->local_nls,
@@ -1014,7 +1032,7 @@
current->tgid);
/* although we would like to mark the file hidden
if that fails we will still try to rename it */
- if (rc != 0)
+ if (!rc)
cifsInode->cifsAttrs = dosattr;
else
dosattr = origattr; /* since not able to change them */
@@ -1025,7 +1043,7 @@
cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
if (rc != 0) {
- rc = -ETXTBSY;
+ rc = -EBUSY;
goto undo_setattr;
}
@@ -1044,7 +1062,7 @@
if (rc == -ENOENT)
rc = 0;
else if (rc != 0) {
- rc = -ETXTBSY;
+ rc = -EBUSY;
goto undo_rename;
}
cifsInode->delete_pending = true;
@@ -1151,15 +1169,13 @@
cifs_drop_nlink(inode);
} else if (rc == -ENOENT) {
d_drop(dentry);
- } else if (rc == -ETXTBSY) {
+ } else if (rc == -EBUSY) {
if (server->ops->rename_pending_delete) {
rc = server->ops->rename_pending_delete(full_path,
dentry, xid);
if (rc == 0)
cifs_drop_nlink(inode);
}
- if (rc == -ETXTBSY)
- rc = -EBUSY;
} else if ((rc == -EACCES) && (dosattr == 0) && inode) {
attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
if (attrs == NULL) {
@@ -1245,14 +1261,14 @@
.device = 0,
};
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
- args.uid = (__u64)current_fsuid();
+ args.uid = current_fsuid();
if (parent->i_mode & S_ISGID)
- args.gid = (__u64)parent->i_gid;
+ args.gid = parent->i_gid;
else
- args.gid = (__u64)current_fsgid();
+ args.gid = current_fsgid();
} else {
- args.uid = NO_CHANGE_64;
- args.gid = NO_CHANGE_64;
+ args.uid = INVALID_UID; /* no change */
+ args.gid = INVALID_GID; /* no change */
}
CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
cifs_sb->local_nls,
@@ -1500,7 +1516,7 @@
* source. Note that cross directory moves do not work with
* rename by filehandle to various Windows servers.
*/
- if (rc == 0 || rc != -ETXTBSY)
+ if (rc == 0 || rc != -EBUSY)
goto do_rename_exit;
/* open-file renames don't work across directories */
@@ -1678,7 +1694,7 @@
int cifs_revalidate_file_attr(struct file *filp)
{
int rc = 0;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct cifsFileInfo *cfile = (struct cifsFileInfo *) filp->private_data;
if (!cifs_inode_needs_reval(inode))
@@ -1735,7 +1751,7 @@
int cifs_revalidate_file(struct file *filp)
{
int rc;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
rc = cifs_revalidate_file_attr(filp);
if (rc)
@@ -2013,12 +2029,12 @@
if (attrs->ia_valid & ATTR_UID)
args->uid = attrs->ia_uid;
else
- args->uid = NO_CHANGE_64;
+ args->uid = INVALID_UID; /* no change */
if (attrs->ia_valid & ATTR_GID)
args->gid = attrs->ia_gid;
else
- args->gid = NO_CHANGE_64;
+ args->gid = INVALID_GID; /* no change */
if (attrs->ia_valid & ATTR_ATIME)
args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
@@ -2086,8 +2102,8 @@
cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
{
unsigned int xid;
- uid_t uid = NO_CHANGE_32;
- gid_t gid = NO_CHANGE_32;
+ kuid_t uid = INVALID_UID;
+ kgid_t gid = INVALID_GID;
struct inode *inode = direntry->d_inode;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
@@ -2146,7 +2162,7 @@
#ifdef CONFIG_CIFS_ACL
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
- if (uid != NO_CHANGE_32 || gid != NO_CHANGE_32) {
+ if (uid_valid(uid) || gid_valid(gid)) {
rc = id_mode_to_cifs_acl(inode, full_path, NO_CHANGE_64,
uid, gid);
if (rc) {
@@ -2170,7 +2186,7 @@
#ifdef CONFIG_CIFS_ACL
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
rc = id_mode_to_cifs_acl(inode, full_path, mode,
- NO_CHANGE_32, NO_CHANGE_32);
+ INVALID_UID, INVALID_GID);
if (rc) {
cFYI(1, "%s: Setting ACL failed with error: %d",
__func__, rc);
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index fd5009d..6c9f121 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -30,7 +30,7 @@
long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
{
- struct inode *inode = filep->f_dentry->d_inode;
+ struct inode *inode = file_inode(filep);
int rc = -ENOTTY; /* strange error - but the precedent */
unsigned int xid;
struct cifs_sb_info *cifs_sb;
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 51dc2fb..9f6c4c4 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -76,7 +76,7 @@
}
rc = crypto_shash_update(&sdescmd5->shash, link_str, link_len);
if (rc) {
- cERROR(1, "%s: Could not update iwth link_str", __func__);
+ cERROR(1, "%s: Could not update with link_str", __func__);
goto symlink_hash_err;
}
rc = crypto_shash_final(&sdescmd5->shash, md5_hash);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 3a00c0d..1b15bf8 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -569,7 +569,7 @@
backup_cred(struct cifs_sb_info *cifs_sb)
{
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) {
- if (cifs_sb->mnt_backupuid == current_fsuid())
+ if (uid_eq(cifs_sb->mnt_backupuid, current_fsuid()))
return true;
}
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) {
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index a82bc51..c0b25b2 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -62,7 +62,7 @@
{ERRdiffdevice, -EXDEV},
{ERRnofiles, -ENOENT},
{ERRwriteprot, -EROFS},
- {ERRbadshare, -ETXTBSY},
+ {ERRbadshare, -EBUSY},
{ERRlock, -EACCES},
{ERRunsup, -EINVAL},
{ERRnosuchshare, -ENXIO},
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index cdd6ff4..df40cc5 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -82,12 +82,10 @@
cFYI(1, "%s: for %s", __func__, name->name);
- if (parent->d_op && parent->d_op->d_hash)
- parent->d_op->d_hash(parent, parent->d_inode, name);
- else
- name->hash = full_name_hash(name->name, name->len);
+ dentry = d_hash_and_lookup(parent, name);
+ if (unlikely(IS_ERR(dentry)))
+ return;
- dentry = d_lookup(parent, name);
if (dentry) {
int err;
@@ -505,7 +503,7 @@
whether we can use the cached search results from the previous search */
static int is_dir_changed(struct file *file)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct cifsInodeInfo *cifsInfo = CIFS_I(inode);
if (cifsInfo->time == 0)
@@ -778,7 +776,7 @@
switch ((int) file->f_pos) {
case 0:
if (filldir(direntry, ".", 1, file->f_pos,
- file->f_path.dentry->d_inode->i_ino, DT_DIR) < 0) {
+ file_inode(file)->i_ino, DT_DIR) < 0) {
cERROR(1, "Filldir for current dir failed");
rc = -ENOMEM;
break;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index c9c7aa7..bceffe7 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -744,4 +744,5 @@
.cap_unix = 0,
.cap_nt_find = SMB2_NT_FIND,
.cap_large_files = SMB2_LARGE_FILES,
+ .oplock_read = SMB2_OPLOCK_LEVEL_II,
};
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 958ae0e..1da168c 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -33,7 +33,7 @@
spin_lock(&cii->c_lock);
cii->c_cached_epoch = atomic_read(&permission_epoch);
- if (cii->c_uid != current_fsuid()) {
+ if (!uid_eq(cii->c_uid, current_fsuid())) {
cii->c_uid = current_fsuid();
cii->c_cached_perm = mask;
} else
@@ -65,7 +65,7 @@
spin_lock(&cii->c_lock);
hit = (mask & cii->c_cached_perm) == mask &&
- cii->c_uid == current_fsuid() &&
+ uid_eq(cii->c_uid, current_fsuid()) &&
cii->c_cached_epoch == atomic_read(&permission_epoch);
spin_unlock(&cii->c_lock);
diff --git a/fs/coda/coda_fs_i.h b/fs/coda/coda_fs_i.h
index b24fdfd..c640752 100644
--- a/fs/coda/coda_fs_i.h
+++ b/fs/coda/coda_fs_i.h
@@ -25,7 +25,7 @@
u_short c_flags; /* flags (see below) */
unsigned int c_mapcount; /* nr of times this inode is mapped */
unsigned int c_cached_epoch; /* epoch for cached permissions */
- vuid_t c_uid; /* fsuid for cached permissions */
+ kuid_t c_uid; /* fsuid for cached permissions */
unsigned int c_cached_perm; /* cached access permissions */
spinlock_t c_lock;
struct inode vfs_inode;
diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c
index 854ace7..2849f41 100644
--- a/fs/coda/coda_linux.c
+++ b/fs/coda/coda_linux.c
@@ -100,9 +100,9 @@
if (attr->va_mode != (u_short) -1)
inode->i_mode = attr->va_mode | inode_type;
if (attr->va_uid != -1)
- inode->i_uid = (uid_t) attr->va_uid;
+ inode->i_uid = make_kuid(&init_user_ns, (uid_t) attr->va_uid);
if (attr->va_gid != -1)
- inode->i_gid = (gid_t) attr->va_gid;
+ inode->i_gid = make_kgid(&init_user_ns, (gid_t) attr->va_gid);
if (attr->va_nlink != -1)
set_nlink(inode, attr->va_nlink);
if (attr->va_size != -1)
@@ -171,10 +171,10 @@
vattr->va_mode = iattr->ia_mode;
}
if ( valid & ATTR_UID ) {
- vattr->va_uid = (vuid_t) iattr->ia_uid;
+ vattr->va_uid = (vuid_t) from_kuid(&init_user_ns, iattr->ia_uid);
}
if ( valid & ATTR_GID ) {
- vattr->va_gid = (vgid_t) iattr->ia_gid;
+ vattr->va_gid = (vgid_t) from_kgid(&init_user_ns, iattr->ia_gid);
}
if ( valid & ATTR_SIZE ) {
vattr->va_size = iattr->ia_size;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 49fe52d..b7d3a05 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -397,7 +397,7 @@
* We can't use vfs_readdir because we have to keep the file
* position in sync between the coda_file and the host_file.
* and as such we need grab the inode mutex. */
- struct inode *host_inode = host_file->f_path.dentry->d_inode;
+ struct inode *host_inode = file_inode(host_file);
mutex_lock(&host_inode->i_mutex);
host_file->f_pos = coda_file->f_pos;
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 8edd404..fa4c100 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -66,7 +66,7 @@
static ssize_t
coda_file_write(struct file *coda_file, const char __user *buf, size_t count, loff_t *ppos)
{
- struct inode *host_inode, *coda_inode = coda_file->f_path.dentry->d_inode;
+ struct inode *host_inode, *coda_inode = file_inode(coda_file);
struct coda_file_info *cfi;
struct file *host_file;
ssize_t ret;
@@ -78,7 +78,7 @@
if (!host_file->f_op || !host_file->f_op->write)
return -EINVAL;
- host_inode = host_file->f_path.dentry->d_inode;
+ host_inode = file_inode(host_file);
mutex_lock(&coda_inode->i_mutex);
ret = host_file->f_op->write(host_file, buf, count, ppos);
@@ -106,8 +106,8 @@
if (!host_file->f_op || !host_file->f_op->mmap)
return -ENODEV;
- coda_inode = coda_file->f_path.dentry->d_inode;
- host_inode = host_file->f_path.dentry->d_inode;
+ coda_inode = file_inode(coda_file);
+ host_inode = file_inode(host_file);
cii = ITOC(coda_inode);
spin_lock(&cii->c_lock);
@@ -178,7 +178,7 @@
err = venus_close(coda_inode->i_sb, coda_i2f(coda_inode),
coda_flags, coda_file->f_cred->fsuid);
- host_inode = cfi->cfi_container->f_path.dentry->d_inode;
+ host_inode = file_inode(cfi->cfi_container);
cii = ITOC(coda_inode);
/* did we mmap this file? */
@@ -202,7 +202,7 @@
int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync)
{
struct file *host_file;
- struct inode *coda_inode = coda_file->f_path.dentry->d_inode;
+ struct inode *coda_inode = file_inode(coda_file);
struct coda_file_info *cfi;
int err;
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index be2aa49..4dcc0d8 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -20,6 +20,7 @@
#include <linux/file.h>
#include <linux/vfs.h>
#include <linux/slab.h>
+#include <linux/pid_namespace.h>
#include <asm/uaccess.h>
@@ -48,7 +49,7 @@
return NULL;
memset(&ei->c_fid, 0, sizeof(struct CodaFid));
ei->c_flags = 0;
- ei->c_uid = 0;
+ ei->c_uid = GLOBAL_ROOT_UID;
ei->c_cached_perm = 0;
spin_lock_init(&ei->c_lock);
return &ei->vfs_inode;
@@ -129,7 +130,7 @@
f = fdget(data->fd);
if (!f.file)
goto Ebadf;
- inode = f.file->f_path.dentry->d_inode;
+ inode = file_inode(f.file);
if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) {
fdput(f);
goto Ebadf;
@@ -157,6 +158,9 @@
int error;
int idx;
+ if (task_active_pid_ns(current) != &init_pid_ns)
+ return -EINVAL;
+
idx = get_device_index((struct coda_mount_data *) data);
/* Ignore errors in data, for backward compatibility */
@@ -325,4 +329,5 @@
.kill_sb = kill_anon_super,
.fs_flags = FS_BINARY_MOUNTDATA,
};
+MODULE_ALIAS_FS("coda");
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index ee0981f..3f5de96 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -52,7 +52,7 @@
struct path path;
int error;
struct PioctlData data;
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct inode *target_inode = NULL;
struct coda_inode_info *cnp;
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 761d5b3..ebc2bae 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -37,6 +37,7 @@
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/device.h>
+#include <linux/pid_namespace.h>
#include <asm/io.h>
#include <asm/poll.h>
#include <asm/uaccess.h>
@@ -266,6 +267,12 @@
struct venus_comm *vcp;
int idx, err;
+ if (task_active_pid_ns(current) != &init_pid_ns)
+ return -EINVAL;
+
+ if (current_user_ns() != &init_user_ns)
+ return -EINVAL;
+
idx = iminor(inode);
if (idx < 0 || idx >= MAX_CODADEVS)
return -ENODEV;
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index 0c68fd3..3a73197 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -50,9 +50,9 @@
return ERR_PTR(-ENOMEM);
inp->ih.opcode = opcode;
- inp->ih.pid = current->pid;
- inp->ih.pgid = task_pgrp_nr(current);
- inp->ih.uid = current_fsuid();
+ inp->ih.pid = task_pid_nr_ns(current, &init_pid_ns);
+ inp->ih.pgid = task_pgrp_nr_ns(current, &init_pid_ns);
+ inp->ih.uid = from_kuid(&init_user_ns, current_fsuid());
return (void*)inp;
}
@@ -157,7 +157,7 @@
}
int venus_close(struct super_block *sb, struct CodaFid *fid, int flags,
- vuid_t uid)
+ kuid_t uid)
{
union inputArgs *inp;
union outputArgs *outp;
@@ -166,7 +166,7 @@
insize = SIZE(release);
UPARG(CODA_CLOSE);
- inp->ih.uid = uid;
+ inp->ih.uid = from_kuid(&init_user_ns, uid);
inp->coda_close.VFid = *fid;
inp->coda_close.flags = flags;
diff --git a/fs/compat.c b/fs/compat.c
index 015e1e1..d487985 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -558,6 +558,10 @@
}
*ret_pointer = iov;
+ ret = -EFAULT;
+ if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+ goto out;
+
/*
* Single unix specification:
* We should -EINVAL if an element length is not >= 0 and fitting an
@@ -1080,17 +1084,12 @@
if (!file->f_op)
goto out;
- ret = -EFAULT;
- if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
- goto out;
-
- tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs,
+ ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
UIO_FASTIOV, iovstack, &iov);
- if (tot_len == 0) {
- ret = 0;
+ if (ret <= 0)
goto out;
- }
+ tot_len = ret;
ret = rw_verify_area(type, file, pos, tot_len);
if (ret < 0)
goto out;
@@ -1278,8 +1277,7 @@
* Exactly like fs/open.c:sys_open(), except that it doesn't set the
* O_LARGEFILE flag.
*/
-asmlinkage long
-compat_sys_open(const char __user *filename, int flags, umode_t mode)
+COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
return do_sys_open(AT_FDCWD, filename, flags, mode);
}
@@ -1288,8 +1286,7 @@
* Exactly like fs/open.c:sys_openat(), except that it doesn't set the
* O_LARGEFILE flag.
*/
-asmlinkage long
-compat_sys_openat(unsigned int dfd, const char __user *filename, int flags, umode_t mode)
+COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
{
return do_sys_open(dfd, filename, flags, mode);
}
@@ -1739,55 +1736,13 @@
}
#endif /* CONFIG_SIGNALFD */
-#ifdef CONFIG_TIMERFD
-
-asmlinkage long compat_sys_timerfd_settime(int ufd, int flags,
- const struct compat_itimerspec __user *utmr,
- struct compat_itimerspec __user *otmr)
-{
- int error;
- struct itimerspec t;
- struct itimerspec __user *ut;
-
- if (get_compat_itimerspec(&t, utmr))
- return -EFAULT;
- ut = compat_alloc_user_space(2 * sizeof(struct itimerspec));
- if (copy_to_user(&ut[0], &t, sizeof(t)))
- return -EFAULT;
- error = sys_timerfd_settime(ufd, flags, &ut[0], &ut[1]);
- if (!error && otmr)
- error = (copy_from_user(&t, &ut[1], sizeof(struct itimerspec)) ||
- put_compat_itimerspec(otmr, &t)) ? -EFAULT: 0;
-
- return error;
-}
-
-asmlinkage long compat_sys_timerfd_gettime(int ufd,
- struct compat_itimerspec __user *otmr)
-{
- int error;
- struct itimerspec t;
- struct itimerspec __user *ut;
-
- ut = compat_alloc_user_space(sizeof(struct itimerspec));
- error = sys_timerfd_gettime(ufd, ut);
- if (!error)
- error = (copy_from_user(&t, ut, sizeof(struct itimerspec)) ||
- put_compat_itimerspec(otmr, &t)) ? -EFAULT: 0;
-
- return error;
-}
-
-#endif /* CONFIG_TIMERFD */
-
#ifdef CONFIG_FHANDLE
/*
* Exactly like fs/open.c:sys_open_by_handle_at(), except that it
* doesn't set the O_LARGEFILE flag.
*/
-asmlinkage long
-compat_sys_open_by_handle_at(int mountdirfd,
- struct file_handle __user *handle, int flags)
+COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+ struct file_handle __user *, handle, int, flags)
{
return do_handle_open(mountdirfd, handle, flags);
}
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index e2f57a0..3ced75f 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1582,7 +1582,7 @@
case FIBMAP:
case FIGETBSZ:
case FIONREAD:
- if (S_ISREG(f.file->f_path.dentry->d_inode->i_mode))
+ if (S_ISREG(file_inode(f.file)->i_mode))
break;
/*FALL THROUGH*/
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 712b10f..7aabc6a 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1037,10 +1037,11 @@
static int configfs_depend_prep(struct dentry *origin,
struct config_item *target)
{
- struct configfs_dirent *child_sd, *sd = origin->d_fsdata;
+ struct configfs_dirent *child_sd, *sd;
int ret = 0;
- BUG_ON(!origin || !sd);
+ BUG_ON(!origin || !origin->d_fsdata);
+ sd = origin->d_fsdata;
if (sd->s_element == target) /* Boo-yah */
goto out;
@@ -1625,7 +1626,7 @@
if (offset >= 0)
break;
default:
- mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
+ mutex_unlock(&file_inode(file)->i_mutex);
return -EINVAL;
}
if (offset != file->f_pos) {
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index aee0a7e..7f26c3c 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -114,6 +114,7 @@
.mount = configfs_do_mount,
.kill_sb = kill_litter_super,
};
+MODULE_ALIAS_FS("configfs");
struct dentry *configfs_pin_fs(void)
{
diff --git a/fs/coredump.c b/fs/coredump.c
index 1774932..c647965 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -411,7 +411,7 @@
{
struct pipe_inode_info *pipe;
- pipe = file->f_path.dentry->d_inode->i_pipe;
+ pipe = file_inode(file)->i_pipe;
pipe_lock(pipe);
pipe->readers++;
@@ -501,7 +501,7 @@
* so we dump it as root in mode 2, and only into a controlled
* environment (pipe handler or fully qualified path).
*/
- if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
+ if (__get_dumpable(cprm.mm_flags) == SUID_DUMP_ROOT) {
/* Setuid core dump mode */
flag = O_EXCL; /* Stop rewrite attacks */
cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */
@@ -600,7 +600,7 @@
if (IS_ERR(cprm.file))
goto fail_unlock;
- inode = cprm.file->f_path.dentry->d_inode;
+ inode = file_inode(cprm.file);
if (inode->i_nlink > 1)
goto close_fail;
if (d_unhashed(cprm.file->f_path.dentry))
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index c6c3f91..35b1c7b 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -351,7 +351,7 @@
*/
static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
char *buf;
unsigned int offset;
@@ -573,6 +573,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("cramfs");
static int __init init_cramfs_fs(void)
{
diff --git a/fs/dcache.c b/fs/dcache.c
index 19153a0..e8bc342 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -675,11 +675,10 @@
static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
struct dentry *alias, *discon_alias;
- struct hlist_node *p;
again:
discon_alias = NULL;
- hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
@@ -730,10 +729,9 @@
void d_prune_aliases(struct inode *inode)
{
struct dentry *dentry;
- struct hlist_node *p;
restart:
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_dlock(dentry);
@@ -1358,6 +1356,7 @@
WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH |
DCACHE_OP_COMPARE |
DCACHE_OP_REVALIDATE |
+ DCACHE_OP_WEAK_REVALIDATE |
DCACHE_OP_DELETE ));
dentry->d_op = op;
if (!op)
@@ -1368,6 +1367,8 @@
dentry->d_flags |= DCACHE_OP_COMPARE;
if (op->d_revalidate)
dentry->d_flags |= DCACHE_OP_REVALIDATE;
+ if (op->d_weak_revalidate)
+ dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE;
if (op->d_delete)
dentry->d_flags |= DCACHE_OP_DELETE;
if (op->d_prune)
@@ -1440,14 +1441,13 @@
int len = entry->d_name.len;
const char *name = entry->d_name.name;
unsigned int hash = entry->d_name.hash;
- struct hlist_node *p;
if (!inode) {
__d_instantiate(entry, NULL);
return NULL;
}
- hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
@@ -1672,7 +1672,6 @@
struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
struct qstr *name)
{
- int error;
struct dentry *found;
struct dentry *new;
@@ -1681,10 +1680,12 @@
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
+ if (unlikely(IS_ERR(found)))
+ goto err_out;
if (!found) {
new = d_alloc(dentry->d_parent, name);
if (!new) {
- error = -ENOMEM;
+ found = ERR_PTR(-ENOMEM);
goto err_out;
}
@@ -1725,7 +1726,7 @@
err_out:
iput(inode);
- return ERR_PTR(error);
+ return found;
}
EXPORT_SYMBOL(d_add_ci);
@@ -1889,7 +1890,7 @@
* dentry is returned. The caller must use dput to free the entry when it has
* finished using it. %NULL is returned if the dentry does not exist.
*/
-struct dentry *d_lookup(struct dentry *parent, struct qstr *name)
+struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
{
struct dentry *dentry;
unsigned seq;
@@ -1919,7 +1920,7 @@
*
* __d_lookup callers must be commented.
*/
-struct dentry *__d_lookup(struct dentry *parent, struct qstr *name)
+struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
{
unsigned int len = name->len;
unsigned int hash = name->hash;
@@ -1997,12 +1998,10 @@
* @dir: Directory to search in
* @name: qstr of name we wish to find
*
- * On hash failure or on lookup failure NULL is returned.
+ * On lookup failure NULL is returned; on bad name - ERR_PTR(-error)
*/
struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
{
- struct dentry *dentry = NULL;
-
/*
* Check for a fs-specific hash function. Note that we must
* calculate the standard hash first, as the d_op->d_hash()
@@ -2010,13 +2009,13 @@
*/
name->hash = full_name_hash(name->name, name->len);
if (dir->d_flags & DCACHE_OP_HASH) {
- if (dir->d_op->d_hash(dir, dir->d_inode, name) < 0)
- goto out;
+ int err = dir->d_op->d_hash(dir, dir->d_inode, name);
+ if (unlikely(err < 0))
+ return ERR_PTR(err);
}
- dentry = d_lookup(dir, name);
-out:
- return dentry;
+ return d_lookup(dir, name);
}
+EXPORT_SYMBOL(d_hash_and_lookup);
/**
* d_validate - verify dentry provided from insecure source (deprecated)
@@ -2394,7 +2393,7 @@
*/
static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
{
- struct dentry *dparent, *aparent;
+ struct dentry *dparent;
dentry_lock_for_move(anon, dentry);
@@ -2402,24 +2401,15 @@
write_seqcount_begin(&anon->d_seq);
dparent = dentry->d_parent;
- aparent = anon->d_parent;
switch_names(dentry, anon);
swap(dentry->d_name.hash, anon->d_name.hash);
- dentry->d_parent = (aparent == anon) ? dentry : aparent;
- list_del(&dentry->d_u.d_child);
- if (!IS_ROOT(dentry))
- list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
- else
- INIT_LIST_HEAD(&dentry->d_u.d_child);
-
- anon->d_parent = (dparent == dentry) ? anon : dparent;
+ dentry->d_parent = dentry;
+ list_del_init(&dentry->d_u.d_child);
+ anon->d_parent = dparent;
list_del(&anon->d_u.d_child);
- if (!IS_ROOT(anon))
- list_add(&anon->d_u.d_child, &anon->d_parent->d_subdirs);
- else
- INIT_LIST_HEAD(&anon->d_u.d_child);
+ list_add(&anon->d_u.d_child, &dparent->d_subdirs);
write_seqcount_end(&dentry->d_seq);
write_seqcount_end(&anon->d_seq);
@@ -2552,7 +2542,6 @@
bool slash = false;
int error = 0;
- br_read_lock(&vfsmount_lock);
while (dentry != root->dentry || vfsmnt != root->mnt) {
struct dentry * parent;
@@ -2582,8 +2571,6 @@
if (!error && !slash)
error = prepend(buffer, buflen, "/", 1);
-out:
- br_read_unlock(&vfsmount_lock);
return error;
global_root:
@@ -2600,7 +2587,7 @@
error = prepend(buffer, buflen, "/", 1);
if (!error)
error = is_mounted(vfsmnt) ? 1 : 2;
- goto out;
+ return error;
}
/**
@@ -2627,9 +2614,11 @@
int error;
prepend(&res, &buflen, "\0", 1);
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
error = prepend_path(path, root, &res, &buflen);
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
if (error < 0)
return ERR_PTR(error);
@@ -2646,9 +2635,11 @@
int error;
prepend(&res, &buflen, "\0", 1);
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
error = prepend_path(path, &root, &res, &buflen);
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
if (error > 1)
error = -EINVAL;
@@ -2712,47 +2703,18 @@
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
get_fs_root(current->fs, &root);
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
error = path_with_deleted(path, &root, &res, &buflen);
+ write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
if (error < 0)
res = ERR_PTR(error);
- write_sequnlock(&rename_lock);
path_put(&root);
return res;
}
EXPORT_SYMBOL(d_path);
-/**
- * d_path_with_unreachable - return the path of a dentry
- * @path: path to report
- * @buf: buffer to return value in
- * @buflen: buffer length
- *
- * The difference from d_path() is that this prepends "(unreachable)"
- * to paths which are unreachable from the current process' root.
- */
-char *d_path_with_unreachable(const struct path *path, char *buf, int buflen)
-{
- char *res = buf + buflen;
- struct path root;
- int error;
-
- if (path->dentry->d_op && path->dentry->d_op->d_dname)
- return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
-
- get_fs_root(current->fs, &root);
- write_seqlock(&rename_lock);
- error = path_with_deleted(path, &root, &res, &buflen);
- if (error > 0)
- error = prepend_unreachable(&res, &buflen);
- write_sequnlock(&rename_lock);
- path_put(&root);
- if (error)
- res = ERR_PTR(error);
-
- return res;
-}
-
/*
* Helper function for dentry_operations.d_dname() members
*/
@@ -2871,6 +2833,7 @@
get_fs_root_and_pwd(current->fs, &root, &pwd);
error = -ENOENT;
+ br_read_lock(&vfsmount_lock);
write_seqlock(&rename_lock);
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
@@ -2880,6 +2843,7 @@
prepend(&cwd, &buflen, "\0", 1);
error = prepend_path(&pwd, &root, &cwd, &buflen);
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
if (error < 0)
goto out;
@@ -2900,6 +2864,7 @@
}
} else {
write_sequnlock(&rename_lock);
+ br_read_unlock(&vfsmount_lock);
}
out:
@@ -3035,7 +3000,7 @@
ino_t ino = 0;
dentry = d_hash_and_lookup(dir, name);
- if (dentry) {
+ if (!IS_ERR_OR_NULL(dentry)) {
if (dentry->d_inode)
ino = dentry->d_inode->i_ino;
dput(dentry);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index a5f12b7..4888cb3 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -299,6 +299,7 @@
.mount = debug_mount,
.kill_sb = kill_litter_super,
};
+MODULE_ALIAS_FS("debugfs");
static struct dentry *__create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
@@ -322,7 +323,6 @@
if (!parent)
parent = debugfs_mount->mnt_root;
- dentry = NULL;
mutex_lock(&parent->d_inode->i_mutex);
dentry = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(dentry)) {
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 472e6be..073d30b 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -243,6 +243,13 @@
struct dentry *root = sb->s_root;
struct pts_fs_info *fsi = DEVPTS_SB(sb);
struct pts_mount_opts *opts = &fsi->mount_opts;
+ kuid_t root_uid;
+ kgid_t root_gid;
+
+ root_uid = make_kuid(current_user_ns(), 0);
+ root_gid = make_kgid(current_user_ns(), 0);
+ if (!uid_valid(root_uid) || !gid_valid(root_gid))
+ return -EINVAL;
mutex_lock(&root->d_inode->i_mutex);
@@ -273,6 +280,8 @@
mode = S_IFCHR|opts->ptmxmode;
init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2));
+ inode->i_uid = root_uid;
+ inode->i_gid = root_gid;
d_add(dentry, inode);
@@ -438,6 +447,12 @@
if (error)
return ERR_PTR(error);
+ /* Require newinstance for all user namespace mounts to ensure
+ * the mount options are not changed.
+ */
+ if ((current_user_ns() != &init_user_ns) && !opts.newinstance)
+ return ERR_PTR(-EINVAL);
+
if (opts.newinstance)
s = sget(fs_type, NULL, set_anon_super, flags, NULL);
else
@@ -491,6 +506,9 @@
.name = "devpts",
.mount = devpts_mount,
.kill_sb = devpts_kill_sb,
+#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES
+ .fs_flags = FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT,
+#endif
};
/*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index cf5b44b..f853263 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -261,9 +261,9 @@
dio->end_io(dio->iocb, offset, transferred,
dio->private, ret, is_async);
} else {
+ inode_dio_done(dio->inode);
if (is_async)
aio_complete(dio->iocb, ret, 0);
- inode_dio_done(dio->inode);
}
return ret;
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index a0387dd..7d58d5b 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -158,7 +158,7 @@
unsigned int x;
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
x = simple_strtoul(buf, NULL, 0);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 77c0f70..e7665c3 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -96,10 +96,13 @@
}
+#define DLM_RTF_SHRINK 0x00000001
+
struct dlm_rsbtable {
struct rb_root keep;
struct rb_root toss;
spinlock_t lock;
+ uint32_t flags;
};
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index a579f30..1b11466 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1132,6 +1132,7 @@
rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[r->res_bucket].keep);
rsb_insert(r, &ls->ls_rsbtbl[r->res_bucket].toss);
r->res_toss_time = jiffies;
+ ls->ls_rsbtbl[r->res_bucket].flags |= DLM_RTF_SHRINK;
if (r->res_lvbptr) {
dlm_free_lvb(r->res_lvbptr);
r->res_lvbptr = NULL;
@@ -1182,7 +1183,7 @@
static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
{
struct dlm_lkb *lkb;
- int rv, id;
+ int rv;
lkb = dlm_allocate_lkb(ls);
if (!lkb)
@@ -1198,19 +1199,13 @@
mutex_init(&lkb->lkb_cb_mutex);
INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);
- retry:
- rv = idr_pre_get(&ls->ls_lkbidr, GFP_NOFS);
- if (!rv)
- return -ENOMEM;
-
+ idr_preload(GFP_NOFS);
spin_lock(&ls->ls_lkbidr_spin);
- rv = idr_get_new_above(&ls->ls_lkbidr, lkb, 1, &id);
- if (!rv)
- lkb->lkb_id = id;
+ rv = idr_alloc(&ls->ls_lkbidr, lkb, 1, 0, GFP_NOWAIT);
+ if (rv >= 0)
+ lkb->lkb_id = rv;
spin_unlock(&ls->ls_lkbidr_spin);
-
- if (rv == -EAGAIN)
- goto retry;
+ idr_preload_end();
if (rv < 0) {
log_error(ls, "create_lkb idr error %d", rv);
@@ -1659,11 +1654,18 @@
char *name;
int our_nodeid = dlm_our_nodeid();
int remote_count = 0;
+ int need_shrink = 0;
int i, len, rv;
memset(&ls->ls_remove_lens, 0, sizeof(int) * DLM_REMOVE_NAMES_MAX);
spin_lock(&ls->ls_rsbtbl[b].lock);
+
+ if (!(ls->ls_rsbtbl[b].flags & DLM_RTF_SHRINK)) {
+ spin_unlock(&ls->ls_rsbtbl[b].lock);
+ return;
+ }
+
for (n = rb_first(&ls->ls_rsbtbl[b].toss); n; n = next) {
next = rb_next(n);
r = rb_entry(n, struct dlm_rsb, res_hashnode);
@@ -1679,6 +1681,8 @@
continue;
}
+ need_shrink = 1;
+
if (!time_after_eq(jiffies, r->res_toss_time +
dlm_config.ci_toss_secs * HZ)) {
continue;
@@ -1710,6 +1714,11 @@
rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);
dlm_free_rsb(r);
}
+
+ if (need_shrink)
+ ls->ls_rsbtbl[b].flags |= DLM_RTF_SHRINK;
+ else
+ ls->ls_rsbtbl[b].flags &= ~DLM_RTF_SHRINK;
spin_unlock(&ls->ls_rsbtbl[b].lock);
/*
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 2e99fb0..3ca79d3 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -796,7 +796,6 @@
*/
idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls);
- idr_remove_all(&ls->ls_lkbidr);
idr_destroy(&ls->ls_lkbidr);
/*
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index dd87a31..4f5ad24 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -177,12 +177,11 @@
static struct connection *__find_con(int nodeid)
{
int r;
- struct hlist_node *h;
struct connection *con;
r = nodeid_hash(nodeid);
- hlist_for_each_entry(con, h, &connection_hash[r], list) {
+ hlist_for_each_entry(con, &connection_hash[r], list) {
if (con->nodeid == nodeid)
return con;
}
@@ -232,13 +231,12 @@
static void foreach_conn(void (*conn_func)(struct connection *c))
{
int i;
- struct hlist_node *h, *n;
+ struct hlist_node *n;
struct connection *con;
for (i = 0; i < CONN_HASH_SIZE; i++) {
- hlist_for_each_entry_safe(con, h, n, &connection_hash[i], list){
+ hlist_for_each_entry_safe(con, n, &connection_hash[i], list)
conn_func(con);
- }
}
}
@@ -257,13 +255,12 @@
static struct connection *assoc2con(int assoc_id)
{
int i;
- struct hlist_node *h;
struct connection *con;
mutex_lock(&connections_lock);
for (i = 0 ; i < CONN_HASH_SIZE; i++) {
- hlist_for_each_entry(con, h, &connection_hash[i], list) {
+ hlist_for_each_entry(con, &connection_hash[i], list) {
if (con->sctp_assoc == assoc_id) {
mutex_unlock(&connections_lock);
return con;
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index aedea28..a6bc63f 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -305,27 +305,26 @@
static int recover_idr_add(struct dlm_rsb *r)
{
struct dlm_ls *ls = r->res_ls;
- int rv, id;
+ int rv;
- rv = idr_pre_get(&ls->ls_recover_idr, GFP_NOFS);
- if (!rv)
- return -ENOMEM;
-
+ idr_preload(GFP_NOFS);
spin_lock(&ls->ls_recover_idr_lock);
if (r->res_id) {
- spin_unlock(&ls->ls_recover_idr_lock);
- return -1;
+ rv = -1;
+ goto out_unlock;
}
- rv = idr_get_new_above(&ls->ls_recover_idr, r, 1, &id);
- if (rv) {
- spin_unlock(&ls->ls_recover_idr_lock);
- return rv;
- }
- r->res_id = id;
+ rv = idr_alloc(&ls->ls_recover_idr, r, 1, 0, GFP_NOWAIT);
+ if (rv < 0)
+ goto out_unlock;
+
+ r->res_id = rv;
ls->ls_recover_list_count++;
dlm_hold_rsb(r);
+ rv = 0;
+out_unlock:
spin_unlock(&ls->ls_recover_idr_lock);
- return 0;
+ idr_preload_end();
+ return rv;
}
static void recover_idr_del(struct dlm_rsb *r)
@@ -351,24 +350,21 @@
return r;
}
-static int recover_idr_clear_rsb(int id, void *p, void *data)
-{
- struct dlm_ls *ls = data;
- struct dlm_rsb *r = p;
-
- r->res_id = 0;
- r->res_recover_locks_count = 0;
- ls->ls_recover_list_count--;
-
- dlm_put_rsb(r);
- return 0;
-}
-
static void recover_idr_clear(struct dlm_ls *ls)
{
+ struct dlm_rsb *r;
+ int id;
+
spin_lock(&ls->ls_recover_idr_lock);
- idr_for_each(&ls->ls_recover_idr, recover_idr_clear_rsb, ls);
- idr_remove_all(&ls->ls_recover_idr);
+
+ idr_for_each_entry(&ls->ls_recover_idr, r, id) {
+ idr_remove(&ls->ls_recover_idr, id);
+ r->res_id = 0;
+ r->res_recover_locks_count = 0;
+ ls->ls_recover_list_count--;
+
+ dlm_put_rsb(r);
+ }
if (ls->ls_recover_list_count != 0) {
log_error(ls, "warning: recover_list_count %d",
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 7ff4985..911649a 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -503,11 +503,11 @@
#endif
return -EINVAL;
-#ifdef CONFIG_COMPAT
- if (count > sizeof(struct dlm_write_request32) + DLM_RESNAME_MAXLEN)
-#else
+ /*
+ * can't compare against COMPAT/dlm_write_request32 because
+ * we don't yet know if is64bit is zero
+ */
if (count > sizeof(struct dlm_write_request) + DLM_RESNAME_MAXLEN)
-#endif
return -EINVAL;
kbuf = kzalloc(count + 1, GFP_NOFS);
diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig
index cc16562..434aa31 100644
--- a/fs/ecryptfs/Kconfig
+++ b/fs/ecryptfs/Kconfig
@@ -1,6 +1,6 @@
config ECRYPT_FS
- tristate "eCrypt filesystem layer support (EXPERIMENTAL)"
- depends on EXPERIMENTAL && KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
+ tristate "eCrypt filesystem layer support"
+ depends on KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n)
select CRYPTO_ECB
select CRYPTO_CBC
select CRYPTO_MD5
@@ -12,3 +12,11 @@
To compile this file system support as a module, choose M here: the
module will be called ecryptfs.
+
+config ECRYPT_FS_MESSAGING
+ bool "Enable notifications for userspace key wrap/unwrap"
+ depends on ECRYPT_FS
+ help
+ Enables the /dev/ecryptfs entry for use by ecryptfsd. This allows
+ for userspace to wrap/unwrap file encryption keys by other
+ backends, like OpenSSL.
diff --git a/fs/ecryptfs/Makefile b/fs/ecryptfs/Makefile
index 2cc9ee4..49678a6 100644
--- a/fs/ecryptfs/Makefile
+++ b/fs/ecryptfs/Makefile
@@ -1,7 +1,10 @@
#
-# Makefile for the Linux 2.6 eCryptfs
+# Makefile for the Linux eCryptfs
#
obj-$(CONFIG_ECRYPT_FS) += ecryptfs.o
-ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o miscdev.o kthread.o debug.o
+ecryptfs-y := dentry.o file.o inode.o main.o super.o mmap.o read_write.o \
+ crypto.o keystore.o kthread.o debug.o
+
+ecryptfs-$(CONFIG_ECRYPT_FS_MESSAGING) += messaging.o miscdev.o
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index a7b0c2d..d5c25db 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -301,17 +301,14 @@
while (size > 0 && i < sg_size) {
pg = virt_to_page(addr);
offset = offset_in_page(addr);
- if (sg)
- sg_set_page(&sg[i], pg, 0, offset);
+ sg_set_page(&sg[i], pg, 0, offset);
remainder_of_page = PAGE_CACHE_SIZE - offset;
if (size >= remainder_of_page) {
- if (sg)
- sg[i].length = remainder_of_page;
+ sg[i].length = remainder_of_page;
addr += remainder_of_page;
size -= remainder_of_page;
} else {
- if (sg)
- sg[i].length = size;
+ sg[i].length = size;
addr += size;
size = 0;
}
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 1b5d9af..bf12ba5 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -45,14 +45,12 @@
static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *lower_dentry;
- struct vfsmount *lower_mnt;
int rc = 1;
if (flags & LOOKUP_RCU)
return -ECHILD;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
goto out;
rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index cfb4b9f..dd299b3 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -172,6 +172,19 @@
#define ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE 24
#define ECRYPTFS_ENCRYPTED_DENTRY_NAME_LEN (18 + 1 + 4 + 1 + 32)
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
+# define ECRYPTFS_VERSIONING_MASK_MESSAGING (ECRYPTFS_VERSIONING_DEVMISC \
+ | ECRYPTFS_VERSIONING_PUBKEY)
+#else
+# define ECRYPTFS_VERSIONING_MASK_MESSAGING 0
+#endif
+
+#define ECRYPTFS_VERSIONING_MASK (ECRYPTFS_VERSIONING_PASSPHRASE \
+ | ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH \
+ | ECRYPTFS_VERSIONING_XATTR \
+ | ECRYPTFS_VERSIONING_MULTKEY \
+ | ECRYPTFS_VERSIONING_MASK_MESSAGING \
+ | ECRYPTFS_VERSIONING_FILENAME_ENCRYPTION)
struct ecryptfs_key_sig {
struct list_head crypt_stat_list;
char keysig[ECRYPTFS_SIG_SIZE_HEX + 1];
@@ -399,7 +412,9 @@
struct hlist_node euid_chain;
};
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
extern struct mutex ecryptfs_daemon_hash_mux;
+#endif
static inline size_t
ecryptfs_lower_header_size(struct ecryptfs_crypt_stat *crypt_stat)
@@ -509,6 +524,12 @@
return ((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path.mnt;
}
+static inline struct path *
+ecryptfs_dentry_to_lower_path(struct dentry *dentry)
+{
+ return &((struct ecryptfs_dentry_info *)dentry->d_fsdata)->lower_path;
+}
+
static inline void
ecryptfs_set_dentry_lower_mnt(struct dentry *dentry, struct vfsmount *lower_mnt)
{
@@ -604,6 +625,7 @@
ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags);
int ecryptfs_read_xattr_region(char *page_virt, struct inode *ecryptfs_inode);
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
int ecryptfs_process_response(struct ecryptfs_daemon *daemon,
struct ecryptfs_message *msg, u32 seq);
int ecryptfs_send_message(char *data, int data_len,
@@ -612,6 +634,24 @@
struct ecryptfs_message **emsg);
int ecryptfs_init_messaging(void);
void ecryptfs_release_messaging(void);
+#else
+static inline int ecryptfs_init_messaging(void)
+{
+ return 0;
+}
+static inline void ecryptfs_release_messaging(void)
+{ }
+static inline int ecryptfs_send_message(char *data, int data_len,
+ struct ecryptfs_msg_ctx **msg_ctx)
+{
+ return -ENOTCONN;
+}
+static inline int ecryptfs_wait_for_response(struct ecryptfs_msg_ctx *msg_ctx,
+ struct ecryptfs_message **emsg)
+{
+ return -ENOMSG;
+}
+#endif
void
ecryptfs_write_header_metadata(char *virt,
@@ -649,12 +689,11 @@
size_t offset_in_page, size_t size,
struct inode *ecryptfs_inode);
struct page *ecryptfs_get_locked_page(struct inode *inode, loff_t index);
-int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon);
-int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon);
int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
size_t *length_size);
int ecryptfs_write_packet_length(char *dest, size_t size,
size_t *packet_size_length);
+#ifdef CONFIG_ECRYPT_FS_MESSAGING
int ecryptfs_init_ecryptfs_miscdev(void);
void ecryptfs_destroy_ecryptfs_miscdev(void);
int ecryptfs_send_miscdev(char *data, size_t data_size,
@@ -663,6 +702,9 @@
void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx);
int
ecryptfs_spawn_daemon(struct ecryptfs_daemon **daemon, struct file *file);
+int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon);
+int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon);
+#endif
int ecryptfs_init_kthread(void);
void ecryptfs_destroy_kthread(void);
int ecryptfs_privileged_open(struct file **lower_file,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index d45ba45..63b1f54 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -118,7 +118,7 @@
lower_file = ecryptfs_file_to_lower(file);
lower_file->f_pos = file->f_pos;
- inode = file->f_path.dentry->d_inode;
+ inode = file_inode(file);
memset(&buf, 0, sizeof(buf));
buf.dirent = dirent;
buf.dentry = file->f_path.dentry;
@@ -133,7 +133,7 @@
goto out;
if (rc >= 0)
fsstack_copy_attr_atime(inode,
- lower_file->f_path.dentry->d_inode);
+ file_inode(lower_file));
out:
return rc;
}
@@ -199,7 +199,6 @@
struct dentry *ecryptfs_dentry = file->f_path.dentry;
/* Private value of ecryptfs_dentry allocated in
* ecryptfs_lookup() */
- struct dentry *lower_dentry;
struct ecryptfs_file_info *file_info;
mount_crypt_stat = &ecryptfs_superblock_to_private(
@@ -222,7 +221,6 @@
rc = -ENOMEM;
goto out;
}
- lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
mutex_lock(&crypt_stat->cs_mutex);
if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index cc7709e..5eab400 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -999,8 +999,8 @@
return rc;
}
-int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
- struct kstat *stat)
+static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
{
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
int rc = 0;
@@ -1021,14 +1021,13 @@
return rc;
}
-int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
- struct kstat *stat)
+static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
{
struct kstat lower_stat;
int rc;
- rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry),
- ecryptfs_dentry_to_lower(dentry), &lower_stat);
+ rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat);
if (!rc) {
fsstack_copy_attr_all(dentry->d_inode,
ecryptfs_inode_to_lower(dentry->d_inode));
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 2333203..7d52806 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1150,7 +1150,7 @@
struct ecryptfs_message *msg = NULL;
char *auth_tok_sig;
char *payload;
- size_t payload_len;
+ size_t payload_len = 0;
int rc;
rc = ecryptfs_get_auth_tok_sig(&auth_tok_sig, auth_tok);
@@ -1168,7 +1168,7 @@
rc = ecryptfs_send_message(payload, payload_len, &msg_ctx);
if (rc) {
ecryptfs_printk(KERN_ERR, "Error sending message to "
- "ecryptfsd\n");
+ "ecryptfsd: %d\n", rc);
goto out;
}
rc = ecryptfs_wait_for_response(msg_ctx, &msg);
@@ -1202,8 +1202,7 @@
crypt_stat->key_size);
}
out:
- if (msg)
- kfree(msg);
+ kfree(msg);
return rc;
}
@@ -1989,7 +1988,7 @@
rc = ecryptfs_send_message(payload, payload_len, &msg_ctx);
if (rc) {
ecryptfs_printk(KERN_ERR, "Error sending message to "
- "ecryptfsd\n");
+ "ecryptfsd: %d\n", rc);
goto out;
}
rc = ecryptfs_wait_for_response(msg_ctx, &msg);
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 4e0886c..e924cf4 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -629,6 +629,7 @@
.kill_sb = ecryptfs_kill_block_super,
.fs_flags = 0
};
+MODULE_ALIAS_FS("ecryptfs");
/**
* inode_info_init_once
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 5fa2471..49ff8ea0 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -97,8 +97,7 @@
void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx)
{
list_move(&(msg_ctx->node), &ecryptfs_msg_ctx_free_list);
- if (msg_ctx->msg)
- kfree(msg_ctx->msg);
+ kfree(msg_ctx->msg);
msg_ctx->msg = NULL;
msg_ctx->state = ECRYPTFS_MSG_CTX_STATE_FREE;
}
@@ -115,10 +114,9 @@
*/
int ecryptfs_find_daemon_by_euid(struct ecryptfs_daemon **daemon)
{
- struct hlist_node *elem;
int rc;
- hlist_for_each_entry(*daemon, elem,
+ hlist_for_each_entry(*daemon,
&ecryptfs_daemon_hash[ecryptfs_current_euid_hash()],
euid_chain) {
if (uid_eq((*daemon)->file->f_cred->euid, current_euid())) {
@@ -284,7 +282,7 @@
int rc;
rc = ecryptfs_find_daemon_by_euid(&daemon);
- if (rc || !daemon) {
+ if (rc) {
rc = -ENOTCONN;
goto out;
}
@@ -445,7 +443,6 @@
mutex_unlock(&ecryptfs_msg_ctx_lists_mux);
}
if (ecryptfs_daemon_hash) {
- struct hlist_node *elem;
struct ecryptfs_daemon *daemon;
int i;
@@ -453,7 +450,7 @@
for (i = 0; i < (1 << ecryptfs_hash_bits); i++) {
int rc;
- hlist_for_each_entry(daemon, elem,
+ hlist_for_each_entry(daemon,
&ecryptfs_daemon_hash[i],
euid_chain) {
rc = ecryptfs_exorcise_daemon(daemon);
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index b2a34a1..6a16053 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -40,16 +40,12 @@
loff_t offset, size_t size)
{
struct file *lower_file;
- mm_segment_t fs_save;
ssize_t rc;
lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file;
if (!lower_file)
return -EIO;
- fs_save = get_fs();
- set_fs(get_ds());
- rc = vfs_write(lower_file, data, size, &offset);
- set_fs(fs_save);
+ rc = kernel_write(lower_file, data, size, offset);
mark_inode_dirty_sync(ecryptfs_inode);
return rc;
}
diff --git a/fs/efivarfs/Kconfig b/fs/efivarfs/Kconfig
new file mode 100644
index 0000000..367bbb1
--- /dev/null
+++ b/fs/efivarfs/Kconfig
@@ -0,0 +1,12 @@
+config EFIVAR_FS
+ tristate "EFI Variable filesystem"
+ depends on EFI
+ help
+ efivarfs is a replacement filesystem for the old EFI
+ variable support via sysfs, as it doesn't suffer from the
+ same 1024-byte variable size limit.
+
+ To compile this file system support as a module, choose M
+ here. The module will be called efivarfs.
+
+ If unsure, say N.
diff --git a/fs/efivarfs/Makefile b/fs/efivarfs/Makefile
new file mode 100644
index 0000000..955d478
--- /dev/null
+++ b/fs/efivarfs/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the efivarfs filesystem
+#
+
+obj-$(CONFIG_EFIVAR_FS) += efivarfs.o
+
+efivarfs-objs := inode.o file.o super.o
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
new file mode 100644
index 0000000..ede07fc
--- /dev/null
+++ b/fs/efivarfs/file.c
@@ -0,0 +1,105 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com>
+ *
+ * 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/efi.h>
+#include <linux/fs.h>
+
+#include "internal.h"
+
+static ssize_t efivarfs_file_write(struct file *file,
+ const char __user *userbuf, size_t count, loff_t *ppos)
+{
+ struct efivar_entry *var = file->private_data;
+ void *data;
+ u32 attributes;
+ struct inode *inode = file->f_mapping->host;
+ unsigned long datasize = count - sizeof(attributes);
+ ssize_t bytes = 0;
+ bool set = false;
+
+ if (count < sizeof(attributes))
+ return -EINVAL;
+
+ if (copy_from_user(&attributes, userbuf, sizeof(attributes)))
+ return -EFAULT;
+
+ if (attributes & ~(EFI_VARIABLE_MASK))
+ return -EINVAL;
+
+ data = kmalloc(datasize, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) {
+ bytes = -EFAULT;
+ goto out;
+ }
+
+ bytes = efivar_entry_set_get_size(var, attributes, &datasize,
+ data, &set);
+ if (!set && bytes)
+ goto out;
+
+ if (bytes == -ENOENT) {
+ drop_nlink(inode);
+ d_delete(file->f_dentry);
+ dput(file->f_dentry);
+ } else {
+ mutex_lock(&inode->i_mutex);
+ i_size_write(inode, datasize + sizeof(attributes));
+ mutex_unlock(&inode->i_mutex);
+ }
+
+ bytes = count;
+
+out:
+ kfree(data);
+
+ return bytes;
+}
+
+static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ struct efivar_entry *var = file->private_data;
+ unsigned long datasize = 0;
+ u32 attributes;
+ void *data;
+ ssize_t size = 0;
+ int err;
+
+ err = efivar_entry_size(var, &datasize);
+ if (err)
+ return err;
+
+ data = kmalloc(datasize + sizeof(attributes), GFP_KERNEL);
+
+ if (!data)
+ return -ENOMEM;
+
+ size = efivar_entry_get(var, &attributes, &datasize,
+ data + sizeof(attributes));
+ if (size)
+ goto out_free;
+
+ memcpy(data, &attributes, sizeof(attributes));
+ size = simple_read_from_buffer(userbuf, count, ppos,
+ data, datasize + sizeof(attributes));
+out_free:
+ kfree(data);
+
+ return size;
+}
+
+const struct file_operations efivarfs_file_operations = {
+ .open = simple_open,
+ .read = efivarfs_file_read,
+ .write = efivarfs_file_write,
+ .llseek = no_llseek,
+};
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
new file mode 100644
index 0000000..640e289
--- /dev/null
+++ b/fs/efivarfs/inode.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com>
+ *
+ * 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/efi.h>
+#include <linux/fs.h>
+#include <linux/ctype.h>
+
+#include "internal.h"
+
+struct inode *efivarfs_get_inode(struct super_block *sb,
+ const struct inode *dir, int mode, dev_t dev)
+{
+ struct inode *inode = new_inode(sb);
+
+ if (inode) {
+ inode->i_ino = get_next_ino();
+ inode->i_mode = mode;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ switch (mode & S_IFMT) {
+ case S_IFREG:
+ inode->i_fop = &efivarfs_file_operations;
+ break;
+ case S_IFDIR:
+ inode->i_op = &efivarfs_dir_inode_operations;
+ inode->i_fop = &simple_dir_operations;
+ inc_nlink(inode);
+ break;
+ }
+ }
+ return inode;
+}
+
+/*
+ * Return true if 'str' is a valid efivarfs filename of the form,
+ *
+ * VariableName-12345678-1234-1234-1234-1234567891bc
+ */
+bool efivarfs_valid_name(const char *str, int len)
+{
+ static const char dashes[EFI_VARIABLE_GUID_LEN] = {
+ [8] = 1, [13] = 1, [18] = 1, [23] = 1
+ };
+ const char *s = str + len - EFI_VARIABLE_GUID_LEN;
+ int i;
+
+ /*
+ * We need a GUID, plus at least one letter for the variable name,
+ * plus the '-' separator
+ */
+ if (len < EFI_VARIABLE_GUID_LEN + 2)
+ return false;
+
+ /* GUID must be preceded by a '-' */
+ if (*(s - 1) != '-')
+ return false;
+
+ /*
+ * Validate that 's' is of the correct format, e.g.
+ *
+ * 12345678-1234-1234-1234-123456789abc
+ */
+ for (i = 0; i < EFI_VARIABLE_GUID_LEN; i++) {
+ if (dashes[i]) {
+ if (*s++ != '-')
+ return false;
+ } else {
+ if (!isxdigit(*s++))
+ return false;
+ }
+ }
+
+ return true;
+}
+
+static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
+{
+ guid->b[0] = hex_to_bin(str[6]) << 4 | hex_to_bin(str[7]);
+ guid->b[1] = hex_to_bin(str[4]) << 4 | hex_to_bin(str[5]);
+ guid->b[2] = hex_to_bin(str[2]) << 4 | hex_to_bin(str[3]);
+ guid->b[3] = hex_to_bin(str[0]) << 4 | hex_to_bin(str[1]);
+ guid->b[4] = hex_to_bin(str[11]) << 4 | hex_to_bin(str[12]);
+ guid->b[5] = hex_to_bin(str[9]) << 4 | hex_to_bin(str[10]);
+ guid->b[6] = hex_to_bin(str[16]) << 4 | hex_to_bin(str[17]);
+ guid->b[7] = hex_to_bin(str[14]) << 4 | hex_to_bin(str[15]);
+ guid->b[8] = hex_to_bin(str[19]) << 4 | hex_to_bin(str[20]);
+ guid->b[9] = hex_to_bin(str[21]) << 4 | hex_to_bin(str[22]);
+ guid->b[10] = hex_to_bin(str[24]) << 4 | hex_to_bin(str[25]);
+ guid->b[11] = hex_to_bin(str[26]) << 4 | hex_to_bin(str[27]);
+ guid->b[12] = hex_to_bin(str[28]) << 4 | hex_to_bin(str[29]);
+ guid->b[13] = hex_to_bin(str[30]) << 4 | hex_to_bin(str[31]);
+ guid->b[14] = hex_to_bin(str[32]) << 4 | hex_to_bin(str[33]);
+ guid->b[15] = hex_to_bin(str[34]) << 4 | hex_to_bin(str[35]);
+}
+
+static int efivarfs_create(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool excl)
+{
+ struct inode *inode;
+ struct efivar_entry *var;
+ int namelen, i = 0, err = 0;
+
+ if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
+ return -EINVAL;
+
+ inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
+ if (!inode)
+ return -ENOMEM;
+
+ var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
+ if (!var) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ /* length of the variable name itself: remove GUID and separator */
+ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
+
+ efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
+ &var->var.VendorGuid);
+
+ for (i = 0; i < namelen; i++)
+ var->var.VariableName[i] = dentry->d_name.name[i];
+
+ var->var.VariableName[i] = '\0';
+
+ inode->i_private = var;
+
+ efivar_entry_add(var, &efivarfs_list);
+ d_instantiate(dentry, inode);
+ dget(dentry);
+out:
+ if (err) {
+ kfree(var);
+ iput(inode);
+ }
+ return err;
+}
+
+static int efivarfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ struct efivar_entry *var = dentry->d_inode->i_private;
+
+ if (efivar_entry_delete(var))
+ return -EINVAL;
+
+ drop_nlink(dentry->d_inode);
+ dput(dentry);
+ return 0;
+};
+
+/*
+ * Handle negative dentry.
+ */
+static struct dentry *efivarfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ if (dentry->d_name.len > NAME_MAX)
+ return ERR_PTR(-ENAMETOOLONG);
+ d_add(dentry, NULL);
+ return NULL;
+}
+
+const struct inode_operations efivarfs_dir_inode_operations = {
+ .lookup = efivarfs_lookup,
+ .unlink = efivarfs_unlink,
+ .create = efivarfs_create,
+};
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
new file mode 100644
index 0000000..b5ff16a
--- /dev/null
+++ b/fs/efivarfs/internal.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com>
+ *
+ * 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.
+ */
+#ifndef EFIVAR_FS_INTERNAL_H
+#define EFIVAR_FS_INTERNAL_H
+
+#include <linux/list.h>
+
+extern const struct file_operations efivarfs_file_operations;
+extern const struct inode_operations efivarfs_dir_inode_operations;
+extern bool efivarfs_valid_name(const char *str, int len);
+extern struct inode *efivarfs_get_inode(struct super_block *sb,
+ const struct inode *dir, int mode, dev_t dev);
+
+extern struct list_head efivarfs_list;
+
+#endif /* EFIVAR_FS_INTERNAL_H */
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
new file mode 100644
index 0000000..34c48f1
--- /dev/null
+++ b/fs/efivarfs/super.c
@@ -0,0 +1,267 @@
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com>
+ *
+ * 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/ctype.h>
+#include <linux/efi.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/pagemap.h>
+
+#include "internal.h"
+
+LIST_HEAD(efivarfs_list);
+
+static void efivarfs_evict_inode(struct inode *inode)
+{
+ clear_inode(inode);
+}
+
+static const struct super_operations efivarfs_ops = {
+ .statfs = simple_statfs,
+ .drop_inode = generic_delete_inode,
+ .evict_inode = efivarfs_evict_inode,
+ .show_options = generic_show_options,
+};
+
+static struct super_block *efivarfs_sb;
+
+/*
+ * Compare two efivarfs file names.
+ *
+ * An efivarfs filename is composed of two parts,
+ *
+ * 1. A case-sensitive variable name
+ * 2. A case-insensitive GUID
+ *
+ * So we need to perform a case-sensitive match on part 1 and a
+ * case-insensitive match on part 2.
+ */
+static int efivarfs_d_compare(const struct dentry *parent, const struct inode *pinode,
+ const struct dentry *dentry, const struct inode *inode,
+ unsigned int len, const char *str,
+ const struct qstr *name)
+{
+ int guid = len - EFI_VARIABLE_GUID_LEN;
+
+ if (name->len != len)
+ return 1;
+
+ /* Case-sensitive compare for the variable name */
+ if (memcmp(str, name->name, guid))
+ return 1;
+
+ /* Case-insensitive compare for the GUID */
+ return strncasecmp(name->name + guid, str + guid, EFI_VARIABLE_GUID_LEN);
+}
+
+static int efivarfs_d_hash(const struct dentry *dentry,
+ const struct inode *inode, struct qstr *qstr)
+{
+ unsigned long hash = init_name_hash();
+ const unsigned char *s = qstr->name;
+ unsigned int len = qstr->len;
+
+ if (!efivarfs_valid_name(s, len))
+ return -EINVAL;
+
+ while (len-- > EFI_VARIABLE_GUID_LEN)
+ hash = partial_name_hash(*s++, hash);
+
+ /* GUID is case-insensitive. */
+ while (len--)
+ hash = partial_name_hash(tolower(*s++), hash);
+
+ qstr->hash = end_name_hash(hash);
+ return 0;
+}
+
+/*
+ * Retaining negative dentries for an in-memory filesystem just wastes
+ * memory and lookup time: arrange for them to be deleted immediately.
+ */
+static int efivarfs_delete_dentry(const struct dentry *dentry)
+{
+ return 1;
+}
+
+static struct dentry_operations efivarfs_d_ops = {
+ .d_compare = efivarfs_d_compare,
+ .d_hash = efivarfs_d_hash,
+ .d_delete = efivarfs_delete_dentry,
+};
+
+static struct dentry *efivarfs_alloc_dentry(struct dentry *parent, char *name)
+{
+ struct dentry *d;
+ struct qstr q;
+ int err;
+
+ q.name = name;
+ q.len = strlen(name);
+
+ err = efivarfs_d_hash(NULL, NULL, &q);
+ if (err)
+ return ERR_PTR(err);
+
+ d = d_alloc(parent, &q);
+ if (d)
+ return d;
+
+ return ERR_PTR(-ENOMEM);
+}
+
+static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
+ unsigned long name_size, void *data)
+{
+ struct super_block *sb = (struct super_block *)data;
+ struct efivar_entry *entry;
+ struct inode *inode = NULL;
+ struct dentry *dentry, *root = sb->s_root;
+ unsigned long size = 0;
+ char *name;
+ int len, i;
+ int err = -ENOMEM;
+
+ entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return err;
+
+ memcpy(entry->var.VariableName, name16, name_size);
+ memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
+
+ len = utf16_strlen(entry->var.VariableName);
+
+ /* name, plus '-', plus GUID, plus NUL*/
+ name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
+ if (!name)
+ goto fail;
+
+ for (i = 0; i < len; i++)
+ name[i] = entry->var.VariableName[i] & 0xFF;
+
+ name[len] = '-';
+
+ efi_guid_unparse(&entry->var.VendorGuid, name + len + 1);
+
+ name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
+
+ inode = efivarfs_get_inode(sb, root->d_inode, S_IFREG | 0644, 0);
+ if (!inode)
+ goto fail_name;
+
+ dentry = efivarfs_alloc_dentry(root, name);
+ if (IS_ERR(dentry)) {
+ err = PTR_ERR(dentry);
+ goto fail_inode;
+ }
+
+ /* copied by the above to local storage in the dentry. */
+ kfree(name);
+
+ efivar_entry_size(entry, &size);
+ efivar_entry_add(entry, &efivarfs_list);
+
+ mutex_lock(&inode->i_mutex);
+ inode->i_private = entry;
+ i_size_write(inode, size + sizeof(entry->var.Attributes));
+ mutex_unlock(&inode->i_mutex);
+ d_add(dentry, inode);
+
+ return 0;
+
+fail_inode:
+ iput(inode);
+fail_name:
+ kfree(name);
+fail:
+ kfree(entry);
+ return err;
+}
+
+static int efivarfs_destroy(struct efivar_entry *entry, void *data)
+{
+ efivar_entry_remove(entry);
+ kfree(entry);
+ return 0;
+}
+
+static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+ struct inode *inode = NULL;
+ struct dentry *root;
+ int err;
+
+ efivarfs_sb = sb;
+
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
+ sb->s_blocksize = PAGE_CACHE_SIZE;
+ sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ sb->s_magic = EFIVARFS_MAGIC;
+ sb->s_op = &efivarfs_ops;
+ sb->s_d_op = &efivarfs_d_ops;
+ sb->s_time_gran = 1;
+
+ inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+ if (!inode)
+ return -ENOMEM;
+ inode->i_op = &efivarfs_dir_inode_operations;
+
+ root = d_make_root(inode);
+ sb->s_root = root;
+ if (!root)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&efivarfs_list);
+
+ err = efivar_init(efivarfs_callback, (void *)sb, false,
+ true, &efivarfs_list);
+ if (err)
+ __efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL);
+
+ return err;
+}
+
+static struct dentry *efivarfs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ return mount_single(fs_type, flags, data, efivarfs_fill_super);
+}
+
+static void efivarfs_kill_sb(struct super_block *sb)
+{
+ kill_litter_super(sb);
+ efivarfs_sb = NULL;
+
+ /* Remove all entries and destroy */
+ __efivar_entry_iter(efivarfs_destroy, &efivarfs_list, NULL, NULL);
+}
+
+static struct file_system_type efivarfs_type = {
+ .name = "efivarfs",
+ .mount = efivarfs_mount,
+ .kill_sb = efivarfs_kill_sb,
+};
+
+static __init int efivarfs_init(void)
+{
+ if (!efi_enabled(EFI_RUNTIME_SERVICES))
+ return 0;
+
+ if (!efivars_kobject())
+ return 0;
+
+ return register_filesystem(&efivarfs_type);
+}
+
+MODULE_AUTHOR("Matthew Garrett, Jeremy Kerr");
+MODULE_DESCRIPTION("EFI Variable Filesystem");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_FS("efivarfs");
+
+module_init(efivarfs_init);
diff --git a/fs/efs/Kconfig b/fs/efs/Kconfig
index 6ebfc1c..d020e3c 100644
--- a/fs/efs/Kconfig
+++ b/fs/efs/Kconfig
@@ -1,6 +1,6 @@
config EFS_FS
- tristate "EFS file system support (read only) (EXPERIMENTAL)"
- depends on BLOCK && EXPERIMENTAL
+ tristate "EFS file system support (read only)"
+ depends on BLOCK
help
EFS is an older file system used for non-ISO9660 CD-ROMs and hard
disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer
diff --git a/fs/efs/dir.c b/fs/efs/dir.c
index 7ee6f7e3..055a9e9 100644
--- a/fs/efs/dir.c
+++ b/fs/efs/dir.c
@@ -20,7 +20,7 @@
};
static int efs_readdir(struct file *filp, void *dirent, filldir_t filldir) {
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct buffer_head *bh;
struct efs_dir *dirblock;
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 2002431..c6f57a7 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -33,6 +33,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("efs");
static struct pt_types sgi_pt_types[] = {
{0x00, "SGI vh"},
diff --git a/fs/exec.c b/fs/exec.c
index 20df02c..a96a488 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -123,7 +123,7 @@
goto out;
error = -EINVAL;
- if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ if (!S_ISREG(file_inode(file)->i_mode))
goto exit;
error = -EACCES;
@@ -355,7 +355,7 @@
* flags, permissions, and offset, so we use temporary values. We'll update
* them later in setup_arg_pages().
*/
-int bprm_mm_init(struct linux_binprm *bprm)
+static int bprm_mm_init(struct linux_binprm *bprm)
{
int err;
struct mm_struct *mm = NULL;
@@ -764,7 +764,7 @@
goto out;
err = -EACCES;
- if (!S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ if (!S_ISREG(file_inode(file)->i_mode))
goto exit;
if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
@@ -1098,7 +1098,7 @@
void would_dump(struct linux_binprm *bprm, struct file *file)
{
- if (inode_permission(file->f_path.dentry->d_inode, MAY_READ) < 0)
+ if (inode_permission(file_inode(file), MAY_READ) < 0)
bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
}
EXPORT_SYMBOL(would_dump);
@@ -1111,7 +1111,7 @@
current->sas_ss_sp = current->sas_ss_size = 0;
if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))
- set_dumpable(current->mm, SUID_DUMPABLE_ENABLED);
+ set_dumpable(current->mm, SUID_DUMP_USER);
else
set_dumpable(current->mm, suid_dumpable);
@@ -1270,7 +1270,7 @@
int prepare_binprm(struct linux_binprm *bprm)
{
umode_t mode;
- struct inode * inode = bprm->file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(bprm->file);
int retval;
mode = inode->i_mode;
@@ -1639,17 +1639,17 @@
void set_dumpable(struct mm_struct *mm, int value)
{
switch (value) {
- case SUID_DUMPABLE_DISABLED:
+ case SUID_DUMP_DISABLE:
clear_bit(MMF_DUMPABLE, &mm->flags);
smp_wmb();
clear_bit(MMF_DUMP_SECURELY, &mm->flags);
break;
- case SUID_DUMPABLE_ENABLED:
+ case SUID_DUMP_USER:
set_bit(MMF_DUMPABLE, &mm->flags);
smp_wmb();
clear_bit(MMF_DUMP_SECURELY, &mm->flags);
break;
- case SUID_DUMPABLE_SAFE:
+ case SUID_DUMP_ROOT:
set_bit(MMF_DUMP_SECURELY, &mm->flags);
smp_wmb();
set_bit(MMF_DUMPABLE, &mm->flags);
@@ -1662,7 +1662,7 @@
int ret;
ret = mm_flags & MMF_DUMPABLE_MASK;
- return (ret > SUID_DUMPABLE_ENABLED) ? SUID_DUMPABLE_SAFE : ret;
+ return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret;
}
int get_dumpable(struct mm_struct *mm)
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index c61e62a..4637589 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -242,7 +242,7 @@
exofs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
loff_t pos = filp->f_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
unsigned int offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
unsigned long npages = dir_pages(inode);
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 5e59280..9d97633 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -1010,6 +1010,7 @@
.mount = exofs_mount,
.kill_sb = generic_shutdown_super,
};
+MODULE_ALIAS_FS("exofs");
static int __init init_exofs(void)
{
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 5df4bb4..262fc99 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -44,14 +44,13 @@
{
struct dentry *dentry, *toput = NULL;
struct inode *inode;
- struct hlist_node *p;
if (acceptable(context, result))
return result;
inode = result->d_inode;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
dget(dentry);
spin_unlock(&inode->i_lock);
if (toput)
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 2616d0e..9f9992b 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -159,15 +159,6 @@
return bh;
}
-static void release_blocks(struct super_block *sb, int count)
-{
- if (count) {
- struct ext2_sb_info *sbi = EXT2_SB(sb);
-
- percpu_counter_add(&sbi->s_freeblocks_counter, count);
- }
-}
-
static void group_adjust_blocks(struct super_block *sb, int group_no,
struct ext2_group_desc *desc, struct buffer_head *bh, int count)
{
@@ -568,8 +559,11 @@
}
error_return:
brelse(bitmap_bh);
- release_blocks(sb, freed);
- dquot_free_block_nodirty(inode, freed);
+ if (freed) {
+ percpu_counter_add(&sbi->s_freeblocks_counter, freed);
+ dquot_free_block_nodirty(inode, freed);
+ mark_inode_dirty(inode);
+ }
}
/**
@@ -1239,10 +1233,6 @@
*errp = -ENOSPC;
sb = inode->i_sb;
- if (!sb) {
- printk("ext2_new_blocks: nonexistent device");
- return 0;
- }
/*
* Check quota for allocation of this block.
@@ -1416,9 +1406,11 @@
*errp = 0;
brelse(bitmap_bh);
- dquot_free_block_nodirty(inode, *count-num);
- mark_inode_dirty(inode);
- *count = num;
+ if (num < *count) {
+ dquot_free_block_nodirty(inode, *count-num);
+ mark_inode_dirty(inode);
+ *count = num;
+ }
return ret_block;
io_error:
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 0f4f5c9..4237722bf 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -290,7 +290,7 @@
ext2_readdir (struct file * filp, void * dirent, filldir_t filldir)
{
loff_t pos = filp->f_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
unsigned int offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 8f370e01..7cadd82 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -118,7 +118,6 @@
* as writing the quota to disk may need the lock as well.
*/
/* Quota is already initialized in iput() */
- ext2_xattr_delete_inode(inode);
dquot_free_inode(inode);
dquot_drop(inode);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 6363ac6..fe60cc1 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -34,6 +34,7 @@
#include "ext2.h"
#include "acl.h"
#include "xip.h"
+#include "xattr.h"
static int __ext2_write_inode(struct inode *inode, int do_sync);
@@ -88,6 +89,7 @@
inode->i_size = 0;
if (inode->i_blocks)
ext2_truncate_blocks(inode, 0);
+ ext2_xattr_delete_inode(inode);
}
invalidate_inode_buffers(inode);
@@ -495,6 +497,10 @@
* parent to disk.
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
+ goto failed;
+ }
branch[n].bh = bh;
lock_buffer(bh);
memset(bh->b_data, 0, blocksize);
@@ -523,6 +529,14 @@
}
*blks = num;
return err;
+
+failed:
+ for (i = 1; i < n; i++)
+ bforget(branch[i].bh);
+ for (i = 0; i < indirect_blks; i++)
+ ext2_free_blocks(inode, new_blocks[i], 1);
+ ext2_free_blocks(inode, new_blocks[i], num);
+ return err;
}
/**
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 2de655f..5d46c09 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -19,7 +19,7 @@
long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ext2_inode_info *ei = EXT2_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index fa04d02..2885349 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1500,7 +1500,7 @@
bh = sb_bread(sb, tmp_bh.b_blocknr);
else
bh = sb_getblk(sb, tmp_bh.b_blocknr);
- if (!bh) {
+ if (unlikely(!bh)) {
err = -EIO;
goto out;
}
@@ -1536,6 +1536,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ext2");
static int __init init_ext2_fs(void)
{
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index b6754db..2d7557d 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -662,10 +662,10 @@
ea_idebug(inode, "creating block %d", block);
new_bh = sb_getblk(sb, block);
- if (!new_bh) {
+ if (unlikely(!new_bh)) {
ext2_free_blocks(inode, block, 1);
mark_inode_dirty(inode);
- error = -EIO;
+ error = -ENOMEM;
goto cleanup;
}
lock_buffer(new_bh);
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index dd91264..87eccbb 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -99,7 +99,7 @@
int i, stored;
struct ext3_dir_entry_2 *de;
int err;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
int ret = 0;
int dir_has_error = 0;
@@ -114,7 +114,7 @@
* We don't set the inode dirty flag since it's not
* critical that it get flushed back to the disk.
*/
- EXT3_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT3_INDEX_FL;
+ EXT3_I(file_inode(filp))->i_flags &= ~EXT3_INDEX_FL;
}
stored = 0;
offset = filp->f_pos & (sb->s_blocksize - 1);
@@ -457,7 +457,7 @@
{
struct dir_private_info *info = filp->private_data;
loff_t curr_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block * sb;
int error;
@@ -487,7 +487,7 @@
void * dirent, filldir_t filldir)
{
struct dir_private_info *info = filp->private_data;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct fname *fname;
int ret;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index b176d42..d512c4b 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -676,6 +676,10 @@
* parent to disk.
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
+ goto failed;
+ }
branch[n].bh = bh;
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
@@ -717,7 +721,7 @@
BUFFER_TRACE(branch[i].bh, "call journal_forget");
ext3_journal_forget(handle, branch[i].bh);
}
- for (i = 0; i <indirect_blks; i++)
+ for (i = 0; i < indirect_blks; i++)
ext3_free_blocks(handle, inode, new_blocks[i], 1);
ext3_free_blocks(handle, inode, new_blocks[i], num);
@@ -1078,8 +1082,8 @@
if (!err && buffer_mapped(&dummy)) {
struct buffer_head *bh;
bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
- if (!bh) {
- *errp = -EIO;
+ if (unlikely(!bh)) {
+ *errp = -ENOMEM;
goto err;
}
if (buffer_new(&dummy)) {
@@ -2729,12 +2733,12 @@
return -EIO;
bh = sb_getblk(inode->i_sb, block);
- if (!bh) {
+ if (unlikely(!bh)) {
ext3_error (inode->i_sb, "ext3_get_inode_loc",
"unable to read inode block - "
"inode=%lu, block="E3FSBLK,
inode->i_ino, block);
- return -EIO;
+ return -ENOMEM;
}
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
@@ -2783,7 +2787,7 @@
bitmap_bh = sb_getblk(inode->i_sb,
le32_to_cpu(desc->bg_inode_bitmap));
- if (!bitmap_bh)
+ if (unlikely(!bitmap_bh))
goto make_io;
/*
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 677a5c2..4d96e9a 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -14,7 +14,7 @@
long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ext3_inode_info *ei = EXT3_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 890b894..692de13 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -36,7 +36,6 @@
#define NAMEI_RA_CHUNKS 2
#define NAMEI_RA_BLOCKS 4
#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
-#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
static struct buffer_head *ext3_append(handle_t *handle,
struct inode *inode,
@@ -624,7 +623,7 @@
dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
start_minor_hash));
- dir = dir_file->f_path.dentry->d_inode;
+ dir = file_inode(dir_file);
if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
if (hinfo.hash_version <= DX_HASH_TEA)
@@ -638,7 +637,7 @@
}
hinfo.hash = start_hash;
hinfo.minor_hash = 0;
- frame = dx_probe(NULL, dir_file->f_path.dentry->d_inode, &hinfo, frames, &err);
+ frame = dx_probe(NULL, file_inode(dir_file), &hinfo, frames, &err);
if (!frame)
return err;
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 0f814f3..2710565 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -116,8 +116,8 @@
int err;
bh = sb_getblk(sb, blk);
- if (!bh)
- return ERR_PTR(-EIO);
+ if (unlikely(!bh))
+ return ERR_PTR(-ENOMEM);
if ((err = ext3_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
@@ -234,8 +234,8 @@
goto exit_bh;
gdb = sb_getblk(sb, block);
- if (!gdb) {
- err = -EIO;
+ if (unlikely(!gdb)) {
+ err = -ENOMEM;
goto exit_bh;
}
if ((err = ext3_journal_get_write_access(handle, gdb))) {
@@ -722,8 +722,8 @@
break;
bh = sb_getblk(sb, group * bpg + blk_off);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
break;
}
ext3_debug("update metadata backup %#04lx\n",
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 6e50223..fb5120a 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -353,7 +353,7 @@
return bdev;
fail:
- ext3_msg(sb, "error: failed to open journal device %s: %ld",
+ ext3_msg(sb, KERN_ERR, "error: failed to open journal device %s: %ld",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
@@ -887,7 +887,7 @@
/*todo: use simple_strtoll with >32bit ext3 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
- ext3_msg(sb, "error: invalid sb specification: %s",
+ ext3_msg(sb, KERN_ERR, "error: invalid sb specification: %s",
(char *) *data);
return 1;
}
@@ -916,21 +916,24 @@
"Not enough memory for storing quotafile name");
return 0;
}
- if (sbi->s_qf_names[qtype] &&
- strcmp(sbi->s_qf_names[qtype], qname)) {
+ if (sbi->s_qf_names[qtype]) {
+ int same = !strcmp(sbi->s_qf_names[qtype], qname);
+
+ kfree(qname);
+ if (!same) {
+ ext3_msg(sb, KERN_ERR,
+ "%s quota file already specified",
+ QTYPE2NAME(qtype));
+ }
+ return same;
+ }
+ if (strchr(qname, '/')) {
ext3_msg(sb, KERN_ERR,
- "%s quota file already specified", QTYPE2NAME(qtype));
+ "quotafile must be on filesystem root");
kfree(qname);
return 0;
}
sbi->s_qf_names[qtype] = qname;
- if (strchr(sbi->s_qf_names[qtype], '/')) {
- ext3_msg(sb, KERN_ERR,
- "quotafile must be on filesystem root");
- kfree(sbi->s_qf_names[qtype]);
- sbi->s_qf_names[qtype] = NULL;
- return 0;
- }
set_opt(sbi->s_mount_opt, QUOTA);
return 1;
}
@@ -945,11 +948,10 @@
" when quota turned on");
return 0;
}
- /*
- * The space will be released later when all options are confirmed
- * to be correct
- */
- sbi->s_qf_names[qtype] = NULL;
+ if (sbi->s_qf_names[qtype]) {
+ kfree(sbi->s_qf_names[qtype]);
+ sbi->s_qf_names[qtype] = NULL;
+ }
return 1;
}
#endif
@@ -2065,6 +2067,7 @@
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
"writeback");
+ sb->s_flags |= MS_SNAP_STABLE;
return 0;
@@ -2605,7 +2608,18 @@
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++)
- old_opts.s_qf_names[i] = sbi->s_qf_names[i];
+ if (sbi->s_qf_names[i]) {
+ old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
+ GFP_KERNEL);
+ if (!old_opts.s_qf_names[i]) {
+ int j;
+
+ for (j = 0; j < i; j++)
+ kfree(old_opts.s_qf_names[j]);
+ return -ENOMEM;
+ }
+ } else
+ old_opts.s_qf_names[i] = NULL;
#endif
/*
@@ -2698,9 +2712,7 @@
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
- if (old_opts.s_qf_names[i] &&
- old_opts.s_qf_names[i] != sbi->s_qf_names[i])
- kfree(old_opts.s_qf_names[i]);
+ kfree(old_opts.s_qf_names[i]);
#endif
if (enable_quota)
dquot_resume(sb, -1);
@@ -2714,9 +2726,7 @@
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
- if (sbi->s_qf_names[i] &&
- old_opts.s_qf_names[i] != sbi->s_qf_names[i])
- kfree(sbi->s_qf_names[i]);
+ kfree(sbi->s_qf_names[i]);
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
@@ -3058,6 +3068,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ext3");
static int __init init_ext3_fs(void)
{
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index d22ebb7..b1fc963 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -813,10 +813,10 @@
ea_idebug(inode, "creating block %d", block);
new_bh = sb_getblk(sb, block);
- if (!new_bh) {
+ if (unlikely(!new_bh)) {
getblk_failed:
ext3_free_blocks(handle, inode, block, 1);
- error = -EIO;
+ error = -ENOMEM;
goto cleanup;
}
lock_buffer(new_bh);
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index e6e0d98..39a54a0 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -324,8 +324,8 @@
if (error)
return error;
retry:
- handle = ext4_journal_start(inode,
- EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ handle = ext4_journal_start(inode, EXT4_HT_XATTR,
+ ext4_jbd2_credits_xattr(inode));
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
ext4_std_error(inode->i_sb, error);
@@ -422,7 +422,8 @@
acl = NULL;
retry:
- handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
+ handle = ext4_journal_start(inode, EXT4_HT_XATTR,
+ ext4_jbd2_credits_xattr(inode));
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto release_and_out;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index cf18217..92e68b3 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -358,7 +358,7 @@
}
/**
- * ext4_read_block_bitmap()
+ * ext4_read_block_bitmap_nowait()
* @sb: super block
* @block_group: given block group
*
@@ -457,6 +457,8 @@
struct buffer_head *bh;
bh = ext4_read_block_bitmap_nowait(sb, block_group);
+ if (!bh)
+ return NULL;
if (ext4_wait_block_bitmap(sb, block_group, bh)) {
put_bh(bh);
return NULL;
@@ -482,11 +484,16 @@
free_clusters = percpu_counter_read_positive(fcc);
dirty_clusters = percpu_counter_read_positive(dcc);
- root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es));
+
+ /*
+ * r_blocks_count should always be multiple of the cluster ratio so
+ * we are safe to do a plane bit shift only.
+ */
+ root_clusters = ext4_r_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
if (free_clusters - (nclusters + root_clusters + dirty_clusters) <
EXT4_FREECLUSTERS_WATERMARK) {
- free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc));
+ free_clusters = percpu_counter_sum_positive(fcc);
dirty_clusters = percpu_counter_sum_positive(dcc);
}
/* Check whether we have space after accounting for current
@@ -628,7 +635,7 @@
brelse(bitmap_bh);
printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
", computed = %llu, %llu\n",
- EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
+ EXT4_NUM_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
desc_count, bitmap_count);
return bitmap_count;
#else
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 80a28b2..d8cd1f0 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -110,7 +110,7 @@
int i, stored;
struct ext4_dir_entry_2 *de;
int err;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
int ret = 0;
int dir_has_error = 0;
@@ -133,7 +133,7 @@
* We don't set the inode dirty flag since it's not
* critical that it get flushed back to the disk.
*/
- ext4_clear_inode_flag(filp->f_path.dentry->d_inode,
+ ext4_clear_inode_flag(file_inode(filp),
EXT4_INODE_INDEX);
}
stored = 0;
@@ -185,6 +185,7 @@
"at offset %llu",
(unsigned long long)filp->f_pos);
filp->f_pos += sb->s_blocksize - offset;
+ brelse(bh);
continue;
}
set_buffer_verified(bh);
@@ -333,7 +334,7 @@
*
* For non-htree, ext4_llseek already chooses the proper max offset.
*/
-loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
+static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
int dx_dir = is_dx_dir(inode);
@@ -494,7 +495,7 @@
{
struct dir_private_info *info = filp->private_data;
loff_t curr_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb;
int error;
@@ -526,7 +527,7 @@
void *dirent, filldir_t filldir)
{
struct dir_private_info *info = filp->private_data;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct fname *fname;
int ret;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8462eb3..3b83cd6 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -194,8 +194,7 @@
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
-#define EXT4_IO_END_QUEUED 0x0004
-#define EXT4_IO_END_DIRECT 0x0008
+#define EXT4_IO_END_DIRECT 0x0004
struct ext4_io_page {
struct page *p_page;
@@ -215,10 +214,8 @@
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; /* for writepage() path */
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 */
int num_io_pages; /* for writepages() */
@@ -338,9 +335,9 @@
*/
struct flex_groups {
- atomic_t free_inodes;
- atomic_t free_clusters;
- atomic_t used_dirs;
+ atomic64_t free_clusters;
+ atomic_t free_inodes;
+ atomic_t used_dirs;
};
#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
@@ -582,6 +579,8 @@
#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080
/* Do not take i_data_sem locking in ext4_map_blocks */
#define EXT4_GET_BLOCKS_NO_LOCK 0x0100
+ /* Do not put hole in extent cache */
+#define EXT4_GET_BLOCKS_NO_PUT_HOLE 0x0200
/*
* Flags used by ext4_free_blocks
@@ -810,17 +809,6 @@
#endif /* defined(__KERNEL__) || defined(__linux__) */
-/*
- * storage for cached extent
- * If ec_len == 0, then the cache is invalid.
- * If ec_start == 0, then the cache represents a gap (null mapping)
- */
-struct ext4_ext_cache {
- ext4_fsblk_t ec_start;
- ext4_lblk_t ec_block;
- __u32 ec_len; /* must be 32bit to return holes */
-};
-
#include "extents_status.h"
/*
@@ -887,7 +875,6 @@
struct inode vfs_inode;
struct jbd2_inode *jinode;
- struct ext4_ext_cache i_cached_extent;
/*
* File creation time. Its function is same as that of
* struct timespec i_{a,c,m}time in the generic inode.
@@ -901,6 +888,8 @@
/* extents status tree */
struct ext4_es_tree i_es_tree;
rwlock_t i_es_lock;
+ struct list_head i_es_lru;
+ unsigned int i_es_lru_nr; /* protected by i_es_lock */
/* ialloc */
ext4_group_t i_last_alloc_group;
@@ -930,6 +919,7 @@
spinlock_t i_completed_io_lock;
atomic_t i_ioend_count; /* Number of outstanding io_end structs */
atomic_t i_unwritten; /* Nr. of inflight conversions pending */
+ struct work_struct i_unwritten_work; /* deferred extent conversion */
spinlock_t i_block_reservation_lock;
@@ -985,7 +975,6 @@
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
-#define EXT4_MOUNT_MBLK_IO_SUBMIT 0x4000000 /* multi-block io submits */
#define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */
#define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */
#define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */
@@ -1316,6 +1305,12 @@
/* Precomputed FS UUID checksum for seeding other checksums */
__u32 s_csum_seed;
+
+ /* Reclaim extents from extent status tree */
+ struct shrinker s_es_shrinker;
+ struct list_head s_es_lru;
+ struct percpu_counter s_extent_cache_cnt;
+ spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -2007,9 +2002,20 @@
dx_hash_info *hinfo);
/* ialloc.c */
-extern struct inode *ext4_new_inode(handle_t *, struct inode *, umode_t,
- const struct qstr *qstr, __u32 goal,
- uid_t *owner);
+extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
+ const struct qstr *qstr, __u32 goal,
+ uid_t *owner, int handle_type,
+ unsigned int line_no, int nblocks);
+
+#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \
+ __ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
+ 0, 0, 0)
+#define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
+ type, nblocks) \
+ __ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
+ (type), __LINE__, (nblocks))
+
+
extern void ext4_free_inode(handle_t *, struct inode *);
extern struct inode * ext4_orphan_get(struct super_block *, unsigned long);
extern unsigned long ext4_count_free_inodes(struct super_block *);
@@ -2103,6 +2109,7 @@
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks, int chunk);
extern void ext4_ind_truncate(struct inode *inode);
+extern int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length);
/* ioctl.c */
extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
@@ -2151,6 +2158,8 @@
extern void ext4_kvfree(void *ptr);
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
+extern const char *ext4_decode_error(struct super_block *sb, int errno,
+ char nbuf[16]);
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
const char *, ...);
@@ -2227,6 +2236,8 @@
struct ext4_group_desc *gdp);
extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
struct ext4_group_desc *gdp);
+extern int ext4_register_li_request(struct super_block *sb,
+ ext4_group_t first_not_zeroed);
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
@@ -2454,6 +2465,75 @@
extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
extern void ext4_unwritten_wait(struct inode *inode);
+/* inline.c */
+extern int ext4_has_inline_data(struct inode *inode);
+extern int ext4_get_inline_size(struct inode *inode);
+extern int ext4_get_max_inline_size(struct inode *inode);
+extern int ext4_find_inline_data_nolock(struct inode *inode);
+extern void ext4_write_inline_data(struct inode *inode,
+ struct ext4_iloc *iloc,
+ void *buffer, loff_t pos,
+ unsigned int len);
+extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len);
+extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
+ unsigned int len);
+extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
+
+extern int ext4_readpage_inline(struct inode *inode, struct page *page);
+extern int ext4_try_to_write_inline_data(struct address_space *mapping,
+ struct inode *inode,
+ loff_t pos, unsigned len,
+ unsigned flags,
+ struct page **pagep);
+extern int ext4_write_inline_data_end(struct inode *inode,
+ loff_t pos, unsigned len,
+ unsigned copied,
+ struct page *page);
+extern struct buffer_head *
+ext4_journalled_write_inline_data(struct inode *inode,
+ unsigned len,
+ struct page *page);
+extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
+ struct inode *inode,
+ loff_t pos, unsigned len,
+ unsigned flags,
+ struct page **pagep,
+ void **fsdata);
+extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
+ unsigned len, unsigned copied,
+ struct page *page);
+extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
+ struct inode *inode);
+extern int ext4_try_create_inline_dir(handle_t *handle,
+ struct inode *parent,
+ struct inode *inode);
+extern int ext4_read_inline_dir(struct file *filp,
+ void *dirent, filldir_t filldir,
+ int *has_inline_data);
+extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+ const struct qstr *d_name,
+ struct ext4_dir_entry_2 **res_dir,
+ int *has_inline_data);
+extern int ext4_delete_inline_entry(handle_t *handle,
+ struct inode *dir,
+ struct ext4_dir_entry_2 *de_del,
+ struct buffer_head *bh,
+ int *has_inline_data);
+extern int empty_inline_dir(struct inode *dir, int *has_inline_data);
+extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
+ struct ext4_dir_entry_2 **parent_de,
+ int *retval);
+extern int ext4_inline_data_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo,
+ int *has_inline);
+extern int ext4_try_to_evict_inline_data(handle_t *handle,
+ struct inode *inode,
+ int needed);
+extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+
+extern int ext4_convert_inline_data(struct inode *inode);
+
/* namei.c */
extern const struct inode_operations ext4_dir_inode_operations;
extern const struct inode_operations ext4_special_inode_operations;
@@ -2520,6 +2600,9 @@
struct ext4_ext_path *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
+extern int ext4_find_delalloc_range(struct inode *inode,
+ ext4_lblk_t lblk_start,
+ ext4_lblk_t lblk_end);
extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
@@ -2534,9 +2617,10 @@
extern int __init ext4_init_pageio(void);
extern void ext4_add_complete_io(ext4_io_end_t *io_end);
extern void ext4_exit_pageio(void);
-extern void ext4_ioend_wait(struct inode *);
+extern void ext4_ioend_shutdown(struct inode *);
extern void ext4_free_io_end(ext4_io_end_t *io);
extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags);
+extern void ext4_end_io_work(struct work_struct *work);
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 487fda1..8643ff5 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -193,12 +193,6 @@
return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
}
-static inline void
-ext4_ext_invalidate_cache(struct inode *inode)
-{
- EXT4_I(inode)->i_cached_extent.ec_len = 0;
-}
-
static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
{
/* We can not have an uninitialized extent of zero length! */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index b4323ba..7058975 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -6,6 +6,108 @@
#include <trace/events/ext4.h>
+/* Just increment the non-pointer handle value */
+static handle_t *ext4_get_nojournal(void)
+{
+ handle_t *handle = current->journal_info;
+ unsigned long ref_cnt = (unsigned long)handle;
+
+ BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
+
+ ref_cnt++;
+ handle = (handle_t *)ref_cnt;
+
+ current->journal_info = handle;
+ return handle;
+}
+
+
+/* Decrement the non-pointer handle value */
+static void ext4_put_nojournal(handle_t *handle)
+{
+ unsigned long ref_cnt = (unsigned long)handle;
+
+ BUG_ON(ref_cnt == 0);
+
+ ref_cnt--;
+ handle = (handle_t *)ref_cnt;
+
+ current->journal_info = handle;
+}
+
+/*
+ * Wrappers for jbd2_journal_start/end.
+ */
+handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
+ int type, int nblocks)
+{
+ journal_t *journal;
+
+ trace_ext4_journal_start(sb, nblocks, _RET_IP_);
+ if (sb->s_flags & MS_RDONLY)
+ return ERR_PTR(-EROFS);
+
+ WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
+ journal = EXT4_SB(sb)->s_journal;
+ if (!journal)
+ return ext4_get_nojournal();
+ /*
+ * 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.
+ */
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, "Detected aborted journal");
+ return ERR_PTR(-EROFS);
+ }
+ return jbd2__journal_start(journal, nblocks, GFP_NOFS, type, line);
+}
+
+int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
+{
+ struct super_block *sb;
+ int err;
+ int rc;
+
+ if (!ext4_handle_valid(handle)) {
+ ext4_put_nojournal(handle);
+ return 0;
+ }
+ sb = handle->h_transaction->t_journal->j_private;
+ err = handle->h_err;
+ rc = jbd2_journal_stop(handle);
+
+ if (!err)
+ err = rc;
+ if (err)
+ __ext4_std_error(sb, where, line, err);
+ return 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);
+
+ BUG_ON(!ext4_handle_valid(handle));
+
+ if (bh)
+ BUFFER_TRACE(bh, "abort");
+
+ if (!handle->h_err)
+ handle->h_err = err;
+
+ if (is_handle_aborted(handle))
+ return;
+
+ printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
+ caller, line, errstr, err_fn);
+
+ jbd2_journal_abort_handle(handle);
+}
+
int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle_t *handle, struct buffer_head *bh)
{
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 7177f9b..4c216b1 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -59,12 +59,6 @@
#define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \
EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
-/* Delete operations potentially hit one directory's namespace plus an
- * entire inode, plus arbitrary amounts of bitmap/indirection data. Be
- * generous. We can grow the delete transaction later if necessary. */
-
-#define EXT4_DELETE_TRANS_BLOCKS(sb) (2 * EXT4_DATA_TRANS_BLOCKS(sb) + 64)
-
/* Define an arbitrary limit for the amount of data we will anticipate
* writing to any given transaction. For unbounded transactions such as
* write(2) and truncate(2) we can write more than this, but we always
@@ -110,6 +104,36 @@
#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
+static inline int ext4_jbd2_credits_xattr(struct inode *inode)
+{
+ int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
+
+ /*
+ * In case of inline data, we may push out the data to a block,
+ * so we need to reserve credits for this eventuality
+ */
+ if (ext4_has_inline_data(inode))
+ credits += ext4_writepage_trans_blocks(inode) + 1;
+ return credits;
+}
+
+
+/*
+ * Ext4 handle operation types -- for logging purposes
+ */
+#define EXT4_HT_MISC 0
+#define EXT4_HT_INODE 1
+#define EXT4_HT_WRITE_PAGE 2
+#define EXT4_HT_MAP_BLOCKS 3
+#define EXT4_HT_DIR 4
+#define EXT4_HT_TRUNCATE 5
+#define EXT4_HT_QUOTA 6
+#define EXT4_HT_RESIZE 7
+#define EXT4_HT_MIGRATE 8
+#define EXT4_HT_MOVE_EXTENTS 9
+#define EXT4_HT_XATTR 10
+#define EXT4_HT_MAX 11
+
/**
* struct ext4_journal_cb_entry - Base structure for callback information.
*
@@ -234,7 +258,8 @@
#define ext4_handle_dirty_super(handle, sb) \
__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
-handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
+handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
+ int type, int nblocks);
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
#define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
@@ -268,9 +293,17 @@
return 1;
}
-static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
+#define ext4_journal_start_sb(sb, type, nblocks) \
+ __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks))
+
+#define ext4_journal_start(inode, type, nblocks) \
+ __ext4_journal_start((inode), __LINE__, (type), (nblocks))
+
+static inline handle_t *__ext4_journal_start(struct inode *inode,
+ unsigned int line, int type,
+ int nblocks)
{
- return ext4_journal_start_sb(inode->i_sb, nblocks);
+ return __ext4_journal_start_sb(inode->i_sb, line, type, nblocks);
}
#define ext4_journal_stop(handle) \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 5ae1674..56efcaa 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -112,7 +112,7 @@
int flags);
static int ext4_find_delayed_extent(struct inode *inode,
- struct ext4_ext_cache *newex);
+ struct extent_status *newes);
static int ext4_ext_truncate_extend_restart(handle_t *handle,
struct inode *inode,
@@ -714,7 +714,6 @@
eh->eh_magic = EXT4_EXT_MAGIC;
eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0));
ext4_mark_inode_dirty(handle, inode);
- ext4_ext_invalidate_cache(inode);
return 0;
}
@@ -725,6 +724,7 @@
struct ext4_extent_header *eh;
struct buffer_head *bh;
short int depth, i, ppos = 0, alloc = 0;
+ int ret;
eh = ext_inode_hdr(inode);
depth = ext_depth(inode);
@@ -752,12 +752,15 @@
path[ppos].p_ext = NULL;
bh = sb_getblk(inode->i_sb, path[ppos].p_block);
- if (unlikely(!bh))
+ if (unlikely(!bh)) {
+ ret = -ENOMEM;
goto err;
+ }
if (!bh_uptodate_or_lock(bh)) {
trace_ext4_ext_load_extent(inode, block,
path[ppos].p_block);
- if (bh_submit_read(bh) < 0) {
+ ret = bh_submit_read(bh);
+ if (ret < 0) {
put_bh(bh);
goto err;
}
@@ -768,13 +771,15 @@
put_bh(bh);
EXT4_ERROR_INODE(inode,
"ppos %d > depth %d", ppos, depth);
+ ret = -EIO;
goto err;
}
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
i--;
- if (ext4_ext_check_block(inode, eh, i, bh))
+ ret = ext4_ext_check_block(inode, eh, i, bh);
+ if (ret < 0)
goto err;
}
@@ -796,7 +801,7 @@
ext4_ext_drop_refs(path);
if (alloc)
kfree(path);
- return ERR_PTR(-EIO);
+ return ERR_PTR(ret);
}
/*
@@ -950,8 +955,8 @@
goto cleanup;
}
bh = sb_getblk(inode->i_sb, newblock);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
goto cleanup;
}
lock_buffer(bh);
@@ -1023,8 +1028,8 @@
oldblock = newblock;
newblock = ablocks[--a];
bh = sb_getblk(inode->i_sb, newblock);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
goto cleanup;
}
lock_buffer(bh);
@@ -1136,11 +1141,8 @@
return err;
bh = sb_getblk(inode->i_sb, newblock);
- if (!bh) {
- err = -EIO;
- ext4_std_error(inode->i_sb, err);
- return err;
- }
+ if (unlikely(!bh))
+ return -ENOMEM;
lock_buffer(bh);
err = ext4_journal_get_create_access(handle, bh);
@@ -1582,10 +1584,12 @@
unsigned short ext1_ee_len, ext2_ee_len, max_len;
/*
- * Make sure that either both extents are uninitialized, or
- * both are _not_.
+ * Make sure that both extents are initialized. We don't merge
+ * uninitialized extents so that we can be sure that end_io code has
+ * the extent that was written properly split out and conversion to
+ * initialized is trivial.
*/
- if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
+ if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
return 0;
if (ext4_ext_is_uninitialized(ex1))
@@ -1960,7 +1964,6 @@
ext4_ext_drop_refs(npath);
kfree(npath);
}
- ext4_ext_invalidate_cache(inode);
return err;
}
@@ -1969,8 +1972,8 @@
struct fiemap_extent_info *fieinfo)
{
struct ext4_ext_path *path = NULL;
- struct ext4_ext_cache newex;
struct ext4_extent *ex;
+ struct extent_status es;
ext4_lblk_t next, next_del, start = 0, end = 0;
ext4_lblk_t last = block + num;
int exists, depth = 0, err = 0;
@@ -2044,37 +2047,47 @@
BUG_ON(end <= start);
if (!exists) {
- newex.ec_block = start;
- newex.ec_len = end - start;
- newex.ec_start = 0;
+ es.es_lblk = start;
+ es.es_len = end - start;
+ es.es_pblk = 0;
} else {
- newex.ec_block = le32_to_cpu(ex->ee_block);
- newex.ec_len = ext4_ext_get_actual_len(ex);
- newex.ec_start = ext4_ext_pblock(ex);
+ es.es_lblk = le32_to_cpu(ex->ee_block);
+ es.es_len = ext4_ext_get_actual_len(ex);
+ es.es_pblk = ext4_ext_pblock(ex);
if (ext4_ext_is_uninitialized(ex))
flags |= FIEMAP_EXTENT_UNWRITTEN;
}
/*
- * Find delayed extent and update newex accordingly. We call
- * it even in !exists case to find out whether newex is the
+ * Find delayed extent and update es accordingly. We call
+ * it even in !exists case to find out whether es is the
* last existing extent or not.
*/
- next_del = ext4_find_delayed_extent(inode, &newex);
+ next_del = ext4_find_delayed_extent(inode, &es);
if (!exists && next_del) {
exists = 1;
flags |= FIEMAP_EXTENT_DELALLOC;
}
up_read(&EXT4_I(inode)->i_data_sem);
- if (unlikely(newex.ec_len == 0)) {
- EXT4_ERROR_INODE(inode, "newex.ec_len == 0");
+ if (unlikely(es.es_len == 0)) {
+ EXT4_ERROR_INODE(inode, "es.es_len == 0");
err = -EIO;
break;
}
- /* This is possible iff next == next_del == EXT_MAX_BLOCKS */
- if (next == next_del) {
+ /*
+ * This is possible iff next == next_del == EXT_MAX_BLOCKS.
+ * we need to check next == EXT_MAX_BLOCKS because it is
+ * possible that an extent is with unwritten and delayed
+ * status due to when an extent is delayed allocated and
+ * is allocated by fallocate status tree will track both of
+ * them in a extent.
+ *
+ * So we could return a unwritten and delayed extent, and
+ * its block is equal to 'next'.
+ */
+ if (next == next_del && next == EXT_MAX_BLOCKS) {
flags |= FIEMAP_EXTENT_LAST;
if (unlikely(next_del != EXT_MAX_BLOCKS ||
next != EXT_MAX_BLOCKS)) {
@@ -2089,9 +2102,9 @@
if (exists) {
err = fiemap_fill_next_extent(fieinfo,
- (__u64)newex.ec_block << blksize_bits,
- (__u64)newex.ec_start << blksize_bits,
- (__u64)newex.ec_len << blksize_bits,
+ (__u64)es.es_lblk << blksize_bits,
+ (__u64)es.es_pblk << blksize_bits,
+ (__u64)es.es_len << blksize_bits,
flags);
if (err < 0)
break;
@@ -2101,7 +2114,7 @@
}
}
- block = newex.ec_block + newex.ec_len;
+ block = es.es_lblk + es.es_len;
}
if (path) {
@@ -2112,21 +2125,6 @@
return err;
}
-static void
-ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block,
- __u32 len, ext4_fsblk_t start)
-{
- struct ext4_ext_cache *cex;
- BUG_ON(len == 0);
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- trace_ext4_ext_put_in_cache(inode, block, len, start);
- cex = &EXT4_I(inode)->i_cached_extent;
- cex->ec_block = block;
- cex->ec_len = len;
- cex->ec_start = start;
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-}
-
/*
* ext4_ext_put_gap_in_cache:
* calculate boundaries of the gap that the requested block fits into
@@ -2143,9 +2141,10 @@
ex = path[depth].p_ext;
if (ex == NULL) {
- /* there is no extent yet, so gap is [0;-] */
- lblock = 0;
- len = EXT_MAX_BLOCKS;
+ /*
+ * there is no extent yet, so gap is [0;-] and we
+ * don't cache it
+ */
ext_debug("cache gap(whole file):");
} else if (block < le32_to_cpu(ex->ee_block)) {
lblock = block;
@@ -2154,6 +2153,9 @@
block,
le32_to_cpu(ex->ee_block),
ext4_ext_get_actual_len(ex));
+ if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
+ ext4_es_insert_extent(inode, lblock, len, ~0,
+ EXTENT_STATUS_HOLE);
} else if (block >= le32_to_cpu(ex->ee_block)
+ ext4_ext_get_actual_len(ex)) {
ext4_lblk_t next;
@@ -2167,58 +2169,15 @@
block);
BUG_ON(next == lblock);
len = next - lblock;
+ if (!ext4_find_delalloc_range(inode, lblock, lblock + len - 1))
+ ext4_es_insert_extent(inode, lblock, len, ~0,
+ EXTENT_STATUS_HOLE);
} else {
lblock = len = 0;
BUG();
}
ext_debug(" -> %u:%lu\n", lblock, len);
- ext4_ext_put_in_cache(inode, lblock, len, 0);
-}
-
-/*
- * ext4_ext_in_cache()
- * Checks to see if the given block is in the cache.
- * If it is, the cached extent is stored in the given
- * cache extent pointer.
- *
- * @inode: The files inode
- * @block: The block to look for in the cache
- * @ex: Pointer where the cached extent will be stored
- * if it contains block
- *
- * Return 0 if cache is invalid; 1 if the cache is valid
- */
-static int
-ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block,
- struct ext4_extent *ex)
-{
- struct ext4_ext_cache *cex;
- int ret = 0;
-
- /*
- * We borrow i_block_reservation_lock to protect i_cached_extent
- */
- spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
- cex = &EXT4_I(inode)->i_cached_extent;
-
- /* has cache valid data? */
- if (cex->ec_len == 0)
- goto errout;
-
- if (in_range(block, cex->ec_block, cex->ec_len)) {
- ex->ee_block = cpu_to_le32(cex->ec_block);
- ext4_ext_store_pblock(ex, cex->ec_start);
- ex->ee_len = cpu_to_le16(cex->ec_len);
- ext_debug("%u cached by %u:%u:%llu\n",
- block,
- cex->ec_block, cex->ec_len, cex->ec_start);
- ret = 1;
- }
-errout:
- trace_ext4_ext_in_cache(inode, block, ret);
- spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- return ret;
}
/*
@@ -2653,13 +2612,11 @@
ext_debug("truncate since %u to %u\n", start, end);
/* probably first extent we're gonna free will be last in block */
- handle = ext4_journal_start(inode, depth + 1);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, depth + 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
again:
- ext4_ext_invalidate_cache(inode);
-
trace_ext4_ext_remove_space(inode, start, depth);
/*
@@ -2968,7 +2925,7 @@
{
ext4_fsblk_t newblock;
ext4_lblk_t ee_block;
- struct ext4_extent *ex, newex, orig_ex;
+ struct ext4_extent *ex, newex, orig_ex, zero_ex;
struct ext4_extent *ex2 = NULL;
unsigned int ee_len, depth;
int err = 0;
@@ -2988,6 +2945,10 @@
newblock = split - ee_block + ext4_ext_pblock(ex);
BUG_ON(split < ee_block || split >= (ee_block + ee_len));
+ BUG_ON(!ext4_ext_is_uninitialized(ex) &&
+ split_flag & (EXT4_EXT_MAY_ZEROOUT |
+ EXT4_EXT_MARK_UNINIT1 |
+ EXT4_EXT_MARK_UNINIT2));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -3035,12 +2996,26 @@
err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
- if (split_flag & EXT4_EXT_DATA_VALID1)
+ if (split_flag & EXT4_EXT_DATA_VALID1) {
err = ext4_ext_zeroout(inode, ex2);
- else
+ zero_ex.ee_block = ex2->ee_block;
+ zero_ex.ee_len = ext4_ext_get_actual_len(ex2);
+ ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_pblock(ex2));
+ } else {
err = ext4_ext_zeroout(inode, ex);
- } else
+ zero_ex.ee_block = ex->ee_block;
+ zero_ex.ee_len = ext4_ext_get_actual_len(ex);
+ ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_pblock(ex));
+ }
+ } else {
err = ext4_ext_zeroout(inode, &orig_ex);
+ zero_ex.ee_block = orig_ex.ee_block;
+ zero_ex.ee_len = ext4_ext_get_actual_len(&orig_ex);
+ ext4_ext_store_pblock(&zero_ex,
+ ext4_ext_pblock(&orig_ex));
+ }
if (err)
goto fix_extent_len;
@@ -3048,6 +3023,12 @@
ex->ee_len = cpu_to_le16(ee_len);
ext4_ext_try_to_merge(handle, inode, path, ex);
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+ if (err)
+ goto fix_extent_len;
+
+ /* update extent status tree */
+ err = ext4_es_zeroout(inode, &zero_ex);
+
goto out;
} else if (err)
goto fix_extent_len;
@@ -3086,6 +3067,7 @@
int err = 0;
int uninitialized;
int split_flag1, flags1;
+ int allocated = map->m_len;
depth = ext_depth(inode);
ex = path[depth].p_ext;
@@ -3105,20 +3087,29 @@
map->m_lblk + map->m_len, split_flag1, flags1);
if (err)
goto out;
+ } else {
+ allocated = ee_len - (map->m_lblk - ee_block);
}
-
+ /*
+ * Update path is required because previous ext4_split_extent_at() may
+ * result in split of original leaf or extent zeroout.
+ */
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode, map->m_lblk, path);
if (IS_ERR(path))
return PTR_ERR(path);
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+ uninitialized = ext4_ext_is_uninitialized(ex);
+ split_flag1 = 0;
if (map->m_lblk >= ee_block) {
- split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT |
- EXT4_EXT_DATA_VALID2);
- if (uninitialized)
+ split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
+ if (uninitialized) {
split_flag1 |= EXT4_EXT_MARK_UNINIT1;
- if (split_flag & EXT4_EXT_MARK_UNINIT2)
- split_flag1 |= EXT4_EXT_MARK_UNINIT2;
+ split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
+ EXT4_EXT_MARK_UNINIT2);
+ }
err = ext4_split_extent_at(handle, inode, path,
map->m_lblk, split_flag1, flags);
if (err)
@@ -3127,7 +3118,7 @@
ext4_ext_show_leaf(inode, path);
out:
- return err ? err : map->m_len;
+ return err ? err : allocated;
}
/*
@@ -3182,6 +3173,7 @@
ee_block = le32_to_cpu(ex->ee_block);
ee_len = ext4_ext_get_actual_len(ex);
allocated = ee_len - (map->m_lblk - ee_block);
+ zero_ex.ee_len = 0;
trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
@@ -3272,13 +3264,16 @@
if (EXT4_EXT_MAY_ZEROOUT & split_flag)
max_zeroout = sbi->s_extent_max_zeroout_kb >>
- inode->i_sb->s_blocksize_bits;
+ (inode->i_sb->s_blocksize_bits - 10);
/* If extent is less than s_max_zeroout_kb, zeroout directly */
if (max_zeroout && (ee_len <= max_zeroout)) {
err = ext4_ext_zeroout(inode, ex);
if (err)
goto out;
+ zero_ex.ee_block = ex->ee_block;
+ zero_ex.ee_len = ext4_ext_get_actual_len(ex);
+ ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
err = ext4_ext_get_access(handle, inode, path + depth);
if (err)
@@ -3337,6 +3332,9 @@
err = allocated;
out:
+ /* If we have gotten a failure, don't zero out status tree */
+ if (!err)
+ err = ext4_es_zeroout(inode, &zero_ex);
return err ? err : allocated;
}
@@ -3419,8 +3417,19 @@
"block %llu, max_blocks %u\n", inode->i_ino,
(unsigned long long)ee_block, ee_len);
- /* If extent is larger than requested then split is required */
+ /* If extent is larger than requested it is a clear sign that we still
+ * have some extent state machine issues left. So extent_split is still
+ * required.
+ * TODO: Once all related issues will be fixed this situation should be
+ * illegal.
+ */
if (ee_block != map->m_lblk || ee_len > map->m_len) {
+#ifdef EXT4_DEBUG
+ ext4_warning("Inode (%ld) finished: extent logical block %llu,"
+ " len %u; IO logical block %llu, len %u\n",
+ inode->i_ino, (unsigned long long)ee_block, ee_len,
+ (unsigned long long)map->m_lblk, map->m_len);
+#endif
err = ext4_split_unwritten_extents(handle, inode, map, path,
EXT4_GET_BLOCKS_CONVERT);
if (err < 0)
@@ -3519,19 +3528,19 @@
*
* Return 1 if there is a delalloc block in the range, otherwise 0.
*/
-static int ext4_find_delalloc_range(struct inode *inode,
- ext4_lblk_t lblk_start,
- ext4_lblk_t lblk_end)
+int ext4_find_delalloc_range(struct inode *inode,
+ ext4_lblk_t lblk_start,
+ ext4_lblk_t lblk_end)
{
struct extent_status es;
- es.start = lblk_start;
- ext4_es_find_extent(inode, &es);
- if (es.len == 0)
+ ext4_es_find_delayed_extent(inode, lblk_start, &es);
+ if (es.es_len == 0)
return 0; /* there is no delay extent in this tree */
- else if (es.start <= lblk_start && lblk_start < es.start + es.len)
+ else if (es.es_lblk <= lblk_start &&
+ lblk_start < es.es_lblk + es.es_len)
return 1;
- else if (lblk_start <= es.start && es.start <= lblk_end)
+ else if (lblk_start <= es.es_lblk && es.es_lblk <= lblk_end)
return 1;
else
return 0;
@@ -3656,6 +3665,7 @@
ext4_set_io_unwritten_flag(inode, io);
else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
goto out;
@@ -3670,6 +3680,10 @@
path, map->m_len);
} else
err = ret;
+ map->m_flags |= EXT4_MAP_MAPPED;
+ if (allocated > map->m_len)
+ allocated = map->m_len;
+ map->m_len = allocated;
goto out2;
}
/* buffered IO case */
@@ -3677,8 +3691,10 @@
* repeat fallocate creation request
* we already have an unwritten extent
*/
- if (flags & EXT4_GET_BLOCKS_UNINIT_EXT)
+ if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
goto map_out;
+ }
/* buffered READ or buffered write_begin() lookup */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
@@ -3717,6 +3733,7 @@
allocated - map->m_len);
allocated = map->m_len;
}
+ map->m_len = allocated;
/*
* If we have done fallocate with the offset that is already
@@ -3898,35 +3915,6 @@
map->m_lblk, map->m_len, inode->i_ino);
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
- /* check in cache */
- if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
- if (!newex.ee_start_lo && !newex.ee_start_hi) {
- if ((sbi->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk))
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
-
- if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
- /*
- * block isn't allocated yet and
- * user doesn't want to allocate it
- */
- goto out2;
- }
- /* we should allocate requested block */
- } else {
- /* block is already allocated */
- if (sbi->s_cluster_ratio > 1)
- map->m_flags |= EXT4_MAP_FROM_CLUSTER;
- newblock = map->m_lblk
- - le32_to_cpu(newex.ee_block)
- + ext4_ext_pblock(&newex);
- /* number of remaining blocks in the extent */
- allocated = ext4_ext_get_actual_len(&newex) -
- (map->m_lblk - le32_to_cpu(newex.ee_block));
- goto out;
- }
- }
-
/* find extent for this block */
path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
if (IS_ERR(path)) {
@@ -3973,15 +3961,9 @@
ext_debug("%u fit into %u:%d -> %llu\n", map->m_lblk,
ee_block, ee_len, newblock);
- /*
- * Do not put uninitialized extent
- * in the cache
- */
- if (!ext4_ext_is_uninitialized(ex)) {
- ext4_ext_put_in_cache(inode, ee_block,
- ee_len, ee_start);
+ if (!ext4_ext_is_uninitialized(ex))
goto out;
- }
+
allocated = ext4_ext_handle_uninitialized_extents(
handle, inode, map, path, flags,
allocated, newblock);
@@ -4002,7 +3984,8 @@
* put just found gap into cache to speed up
* subsequent requests
*/
- ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
+ if ((flags & EXT4_GET_BLOCKS_NO_PUT_HOLE) == 0)
+ ext4_ext_put_gap_in_cache(inode, path, map->m_lblk);
goto out2;
}
@@ -4108,6 +4091,7 @@
/* Mark uninitialized */
if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
ext4_ext_mark_uninitialized(&newex);
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
/*
* io_end structure was created for every IO write to an
* uninitialized extent. To avoid unnecessary conversion,
@@ -4181,9 +4165,6 @@
}
} else {
BUG_ON(allocated_clusters < reserved_clusters);
- /* We will claim quota for all newly allocated blocks.*/
- ext4_da_update_reserve_space(inode, allocated_clusters,
- 1);
if (reserved_clusters < allocated_clusters) {
struct ext4_inode_info *ei = EXT4_I(inode);
int reservation = allocated_clusters -
@@ -4234,6 +4215,15 @@
ei->i_reserved_data_blocks += reservation;
spin_unlock(&ei->i_block_reservation_lock);
}
+ /*
+ * We will claim quota for all newly allocated blocks.
+ * We're updating the reserved space *after* the
+ * correction above so we do not accidentally free
+ * all the metadata reservation because we might
+ * actually need it later on.
+ */
+ ext4_da_update_reserve_space(inode, allocated_clusters,
+ 1);
}
}
@@ -4241,10 +4231,9 @@
* Cache the extent and update transaction to commit on fdatasync only
* when it is _not_ an uninitialized extent.
*/
- if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
- ext4_ext_put_in_cache(inode, map->m_lblk, allocated, newblock);
+ if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
- } else
+ else
ext4_update_inode_fsync_trans(handle, inode, 0);
out:
if (allocated > map->m_len)
@@ -4284,7 +4273,7 @@
* probably first extent we're gonna free will be last in block
*/
err = ext4_writepage_trans_blocks(inode);
- handle = ext4_journal_start(inode, err);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, err);
if (IS_ERR(handle))
return;
@@ -4303,7 +4292,6 @@
goto out_stop;
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_ext_invalidate_cache(inode);
ext4_discard_preallocations(inode);
@@ -4386,7 +4374,7 @@
*/
long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
handle_t *handle;
loff_t new_size;
unsigned int max_blocks;
@@ -4397,13 +4385,6 @@
struct ext4_map_blocks map;
unsigned int credits, blkbits = inode->i_blkbits;
- /*
- * currently supporting (pre)allocate mode for extent-based
- * files _only_
- */
- if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return -EOPNOTSUPP;
-
/* Return error if mode is not supported */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
@@ -4415,6 +4396,13 @@
if (ret)
return ret;
+ /*
+ * currently supporting (pre)allocate mode for extent-based
+ * files _only_
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+ return -EOPNOTSUPP;
+
trace_ext4_fallocate_enter(inode, offset, len, mode);
map.m_lblk = offset >> blkbits;
/*
@@ -4445,13 +4433,12 @@
if (len <= EXT_UNINIT_MAX_LEN << blkbits)
flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
- /* Prevent race condition between unwritten */
- ext4_flush_unwritten_io(inode);
retry:
while (ret >= 0 && ret < max_blocks) {
map.m_lblk = map.m_lblk + ret;
map.m_len = max_blocks = max_blocks - ret;
- handle = ext4_journal_start(inode, credits);
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
break;
@@ -4459,11 +4446,11 @@
ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret <= 0) {
#ifdef EXT4FS_DEBUG
- WARN_ON(ret <= 0);
- printk(KERN_ERR "%s: ext4_ext_map_blocks "
- "returned error inode#%lu, block=%u, "
- "max_blocks=%u", __func__,
- inode->i_ino, map.m_lblk, max_blocks);
+ ext4_warning(inode->i_sb,
+ "inode #%lu: block %u: len %u: "
+ "ext4_ext_map_blocks returned %d",
+ inode->i_ino, map.m_lblk,
+ map.m_len, ret);
#endif
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
@@ -4529,21 +4516,19 @@
while (ret >= 0 && ret < max_blocks) {
map.m_lblk += ret;
map.m_len = (max_blocks -= ret);
- handle = ext4_journal_start(inode, credits);
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
break;
}
ret = ext4_map_blocks(handle, inode, &map,
EXT4_GET_BLOCKS_IO_CONVERT_EXT);
- if (ret <= 0) {
- WARN_ON(ret <= 0);
- ext4_msg(inode->i_sb, KERN_ERR,
- "%s:%d: inode #%lu: block %u: len %u: "
- "ext4_ext_map_blocks returned %d",
- __func__, __LINE__, inode->i_ino, map.m_lblk,
- map.m_len, ret);
- }
+ if (ret <= 0)
+ ext4_warning(inode->i_sb,
+ "inode #%lu: block %u: len %u: "
+ "ext4_ext_map_blocks returned %d",
+ inode->i_ino, map.m_lblk,
+ map.m_len, ret);
ext4_mark_inode_dirty(handle, inode);
ret2 = ext4_journal_stop(handle);
if (ret <= 0 || ret2 )
@@ -4553,42 +4538,48 @@
}
/*
- * If newex is not existing extent (newex->ec_start equals zero) find
- * delayed extent at start of newex and update newex accordingly and
+ * If newes is not existing extent (newes->ec_pblk equals zero) find
+ * delayed extent at start of newes and update newes accordingly and
* return start of the next delayed extent.
*
- * If newex is existing extent (newex->ec_start is not equal zero)
+ * If newes is existing extent (newes->ec_pblk is not equal zero)
* return start of next delayed extent or EXT_MAX_BLOCKS if no delayed
- * extent found. Leave newex unmodified.
+ * extent found. Leave newes unmodified.
*/
static int ext4_find_delayed_extent(struct inode *inode,
- struct ext4_ext_cache *newex)
+ struct extent_status *newes)
{
struct extent_status es;
- ext4_lblk_t next_del;
+ ext4_lblk_t block, next_del;
- es.start = newex->ec_block;
- next_del = ext4_es_find_extent(inode, &es);
+ ext4_es_find_delayed_extent(inode, newes->es_lblk, &es);
- if (newex->ec_start == 0) {
+ if (newes->es_pblk == 0) {
/*
- * No extent in extent-tree contains block @newex->ec_start,
+ * No extent in extent-tree contains block @newes->es_pblk,
* then the block may stay in 1)a hole or 2)delayed-extent.
*/
- if (es.len == 0)
+ if (es.es_len == 0)
/* A hole found. */
return 0;
- if (es.start > newex->ec_block) {
+ if (es.es_lblk > newes->es_lblk) {
/* A hole found. */
- newex->ec_len = min(es.start - newex->ec_block,
- newex->ec_len);
+ newes->es_len = min(es.es_lblk - newes->es_lblk,
+ newes->es_len);
return 0;
}
- newex->ec_len = es.start + es.len - newex->ec_block;
+ newes->es_len = es.es_lblk + es.es_len - newes->es_lblk;
}
+ block = newes->es_lblk + newes->es_len;
+ ext4_es_find_delayed_extent(inode, block, &es);
+ if (es.es_len == 0)
+ next_del = EXT_MAX_BLOCKS;
+ else
+ next_del = es.es_lblk;
+
return next_del;
}
/* fiemap flags we can handle specified here */
@@ -4643,7 +4634,7 @@
*/
int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
ext4_lblk_t first_block, stop_block;
struct address_space *mapping = inode->i_mapping;
@@ -4709,7 +4700,7 @@
inode_dio_wait(inode);
credits = ext4_writepage_trans_blocks(inode);
- handle = ext4_journal_start(inode, credits);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out_dio;
@@ -4786,14 +4777,12 @@
goto out;
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_ext_invalidate_cache(inode);
ext4_discard_preallocations(inode);
err = ext4_es_remove_extent(inode, first_block,
stop_block - first_block);
err = ext4_ext_remove_space(inode, first_block, stop_block - 1);
- ext4_ext_invalidate_cache(inode);
ext4_discard_preallocations(inode);
if (IS_SYNC(inode))
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 564d981..fe3337a 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -23,40 +23,53 @@
* (e.g. Reservation space warning), and provide extent-level locking.
* Delay extent tree is the first step to achieve this goal. It is
* original built by Yongqiang Yang. At that time it is called delay
- * extent tree, whose goal is only track delay extent in memory to
+ * extent tree, whose goal is only track delayed extents in memory to
* simplify the implementation of fiemap and bigalloc, and introduce
* lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called
- * delay extent tree at the following comment. But for better
- * understand what it does, it has been rename to extent status tree.
+ * delay extent tree at the first commit. But for better understand
+ * what it does, it has been rename to extent status tree.
*
- * Currently the first step has been done. All delay extents are
- * tracked in the tree. It maintains the delay extent when a delay
- * allocation is issued, and the delay extent is written out or
+ * Step1:
+ * Currently the first step has been done. All delayed extents are
+ * tracked in the tree. It maintains the delayed extent when a delayed
+ * allocation is issued, and the delayed extent is written out or
* invalidated. Therefore the implementation of fiemap and bigalloc
* are simplified, and SEEK_DATA/SEEK_HOLE are introduced.
*
* The following comment describes the implemenmtation of extent
* status tree and future works.
+ *
+ * Step2:
+ * In this step all extent status are tracked by extent status tree.
+ * Thus, we can first try to lookup a block mapping in this tree before
+ * finding it in extent tree. Hence, single extent cache can be removed
+ * because extent status tree can do a better job. Extents in status
+ * tree are loaded on-demand. Therefore, the extent status tree may not
+ * contain all of the extents in a file. Meanwhile we define a shrinker
+ * to reclaim memory from extent status tree because fragmented extent
+ * tree will make status tree cost too much memory. written/unwritten/-
+ * hole extents in the tree will be reclaimed by this shrinker when we
+ * are under high memory pressure. Delayed extents will not be
+ * reclimed because fiemap, bigalloc, and seek_data/hole need it.
*/
/*
- * extents status tree implementation for ext4.
+ * Extent status tree implementation for ext4.
*
*
* ==========================================================================
- * Extents status encompass delayed extents and extent locks
+ * Extent status tree tracks all extent status.
*
- * 1. Why delayed extent implementation ?
+ * 1. Why we need to implement extent status tree?
*
- * Without delayed extent, ext4 identifies a delayed extent by looking
+ * Without extent status tree, ext4 identifies a delayed extent by looking
* up page cache, this has several deficiencies - complicated, buggy,
* and inefficient code.
*
- * FIEMAP, SEEK_HOLE/DATA, bigalloc, punch hole and writeout all need
- * to know if a block or a range of blocks are belonged to a delayed
- * extent.
+ * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a
+ * block or a range of blocks are belonged to a delayed extent.
*
- * Let us have a look at how they do without delayed extents implementation.
+ * Let us have a look at how they do without extent status tree.
* -- FIEMAP
* FIEMAP looks up page cache to identify delayed allocations from holes.
*
@@ -68,47 +81,48 @@
* already under delayed allocation or not to determine whether
* quota reserving is needed for the cluster.
*
- * -- punch hole
- * punch hole looks up page cache to identify a delayed extent.
- *
* -- writeout
* Writeout looks up whole page cache to see if a buffer is
* mapped, If there are not very many delayed buffers, then it is
* time comsuming.
*
- * With delayed extents implementation, FIEMAP, SEEK_HOLE/DATA,
+ * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA,
* bigalloc and writeout can figure out if a block or a range of
* blocks is under delayed allocation(belonged to a delayed extent) or
- * not by searching the delayed extent tree.
+ * not by searching the extent tree.
*
*
* ==========================================================================
- * 2. ext4 delayed extents impelmentation
+ * 2. Ext4 extent status tree impelmentation
*
- * -- delayed extent
- * A delayed extent is a range of blocks which are contiguous
- * logically and under delayed allocation. Unlike extent in
- * ext4, delayed extent in ext4 is a in-memory struct, there is
- * no corresponding on-disk data. There is no limit on length of
- * delayed extent, so a delayed extent can contain as many blocks
- * as they are contiguous logically.
+ * -- extent
+ * A extent is a range of blocks which are contiguous logically and
+ * physically. Unlike extent in extent tree, this extent in ext4 is
+ * a in-memory struct, there is no corresponding on-disk data. There
+ * is no limit on length of extent, so an extent can contain as many
+ * blocks as they are contiguous logically and physically.
*
- * -- delayed extent tree
- * Every inode has a delayed extent tree and all under delayed
- * allocation blocks are added to the tree as delayed extents.
- * Delayed extents in the tree are ordered by logical block no.
+ * -- extent status tree
+ * Every inode has an extent status tree and all allocation blocks
+ * are added to the tree with different status. The extent in the
+ * tree are ordered by logical block no.
*
- * -- operations on a delayed extent tree
- * There are three operations on a delayed extent tree: find next
- * delayed extent, adding a space(a range of blocks) and removing
- * a space.
+ * -- operations on a extent status tree
+ * There are three important operations on a delayed extent tree: find
+ * next extent, adding a extent(a range of blocks) and removing a extent.
*
- * -- race on a delayed extent tree
- * Delayed extent tree is protected inode->i_es_lock.
+ * -- race on a extent status tree
+ * Extent status tree is protected by inode->i_es_lock.
+ *
+ * -- memory consumption
+ * Fragmented extent tree will make extent status tree cost too much
+ * memory. Hence, we will reclaim written/unwritten/hole extents from
+ * the tree under a heavy memory pressure.
*
*
* ==========================================================================
- * 3. performance analysis
+ * 3. Performance analysis
+ *
* -- overhead
* 1. There is a cache extent for write access, so if writes are
* not very random, adding space operaions are in O(1) time.
@@ -120,18 +134,25 @@
*
* ==========================================================================
* 4. TODO list
- * -- Track all extent status
*
- * -- Improve get block process
+ * -- Refactor delayed space reservation
*
* -- Extent-level locking
*/
static struct kmem_cache *ext4_es_cachep;
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes);
+static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t end);
+static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
+ int nr_to_scan);
+
int __init ext4_init_es(void)
{
- ext4_es_cachep = KMEM_CACHE(extent_status, SLAB_RECLAIM_ACCOUNT);
+ ext4_es_cachep = kmem_cache_create("ext4_extent_status",
+ sizeof(struct extent_status),
+ 0, (SLAB_RECLAIM_ACCOUNT), NULL);
if (ext4_es_cachep == NULL)
return -ENOMEM;
return 0;
@@ -161,7 +182,9 @@
while (node) {
struct extent_status *es;
es = rb_entry(node, struct extent_status, rb_node);
- printk(KERN_DEBUG " [%u/%u)", es->start, es->len);
+ printk(KERN_DEBUG " [%u/%u) %llu %llx",
+ es->es_lblk, es->es_len,
+ ext4_es_pblock(es), ext4_es_status(es));
node = rb_next(node);
}
printk(KERN_DEBUG "\n");
@@ -170,10 +193,10 @@
#define ext4_es_print_tree(inode)
#endif
-static inline ext4_lblk_t extent_status_end(struct extent_status *es)
+static inline ext4_lblk_t ext4_es_end(struct extent_status *es)
{
- BUG_ON(es->start + es->len < es->start);
- return es->start + es->len - 1;
+ BUG_ON(es->es_lblk + es->es_len < es->es_lblk);
+ return es->es_lblk + es->es_len - 1;
}
/*
@@ -181,25 +204,25 @@
* it can't be found, try to find next extent.
*/
static struct extent_status *__es_tree_search(struct rb_root *root,
- ext4_lblk_t offset)
+ ext4_lblk_t lblk)
{
struct rb_node *node = root->rb_node;
struct extent_status *es = NULL;
while (node) {
es = rb_entry(node, struct extent_status, rb_node);
- if (offset < es->start)
+ if (lblk < es->es_lblk)
node = node->rb_left;
- else if (offset > extent_status_end(es))
+ else if (lblk > ext4_es_end(es))
node = node->rb_right;
else
return es;
}
- if (es && offset < es->start)
+ if (es && lblk < es->es_lblk)
return es;
- if (es && offset > extent_status_end(es)) {
+ if (es && lblk > ext4_es_end(es)) {
node = rb_next(&es->rb_node);
return node ? rb_entry(node, struct extent_status, rb_node) :
NULL;
@@ -209,79 +232,134 @@
}
/*
- * ext4_es_find_extent: find the 1st delayed extent covering @es->start
- * if it exists, otherwise, the next extent after @es->start.
+ * ext4_es_find_delayed_extent: find the 1st delayed extent covering @es->lblk
+ * if it exists, otherwise, the next extent after @es->lblk.
*
* @inode: the inode which owns delayed extents
+ * @lblk: the offset where we start to search
* @es: delayed extent that we found
- *
- * Returns the first block of the next extent after es, otherwise
- * EXT_MAX_BLOCKS if no delay extent is found.
- * Delayed extent is returned via @es.
*/
-ext4_lblk_t ext4_es_find_extent(struct inode *inode, struct extent_status *es)
+void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+ struct extent_status *es)
{
struct ext4_es_tree *tree = NULL;
struct extent_status *es1 = NULL;
struct rb_node *node;
- ext4_lblk_t ret = EXT_MAX_BLOCKS;
- trace_ext4_es_find_extent_enter(inode, es->start);
+ BUG_ON(es == NULL);
+ trace_ext4_es_find_delayed_extent_enter(inode, lblk);
read_lock(&EXT4_I(inode)->i_es_lock);
tree = &EXT4_I(inode)->i_es_tree;
- /* find delay extent in cache firstly */
+ /* find extent in cache firstly */
+ es->es_lblk = es->es_len = es->es_pblk = 0;
if (tree->cache_es) {
es1 = tree->cache_es;
- if (in_range(es->start, es1->start, es1->len)) {
- es_debug("%u cached by [%u/%u)\n",
- es->start, es1->start, es1->len);
+ if (in_range(lblk, es1->es_lblk, es1->es_len)) {
+ es_debug("%u cached by [%u/%u) %llu %llx\n",
+ lblk, es1->es_lblk, es1->es_len,
+ ext4_es_pblock(es1), ext4_es_status(es1));
goto out;
}
}
- es->len = 0;
- es1 = __es_tree_search(&tree->root, es->start);
+ es1 = __es_tree_search(&tree->root, lblk);
out:
- if (es1) {
- tree->cache_es = es1;
- es->start = es1->start;
- es->len = es1->len;
- node = rb_next(&es1->rb_node);
- if (node) {
+ if (es1 && !ext4_es_is_delayed(es1)) {
+ while ((node = rb_next(&es1->rb_node)) != NULL) {
es1 = rb_entry(node, struct extent_status, rb_node);
- ret = es1->start;
+ if (ext4_es_is_delayed(es1))
+ break;
}
}
+ if (es1 && ext4_es_is_delayed(es1)) {
+ tree->cache_es = es1;
+ es->es_lblk = es1->es_lblk;
+ es->es_len = es1->es_len;
+ es->es_pblk = es1->es_pblk;
+ }
+
read_unlock(&EXT4_I(inode)->i_es_lock);
- trace_ext4_es_find_extent_exit(inode, es, ret);
- return ret;
+ ext4_es_lru_add(inode);
+ trace_ext4_es_find_delayed_extent_exit(inode, es);
}
static struct extent_status *
-ext4_es_alloc_extent(ext4_lblk_t start, ext4_lblk_t len)
+ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
+ ext4_fsblk_t pblk)
{
struct extent_status *es;
es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
if (es == NULL)
return NULL;
- es->start = start;
- es->len = len;
+ es->es_lblk = lblk;
+ es->es_len = len;
+ es->es_pblk = pblk;
+
+ /*
+ * We don't count delayed extent because we never try to reclaim them
+ */
+ if (!ext4_es_is_delayed(es)) {
+ EXT4_I(inode)->i_es_lru_nr++;
+ percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+ }
+
return es;
}
-static void ext4_es_free_extent(struct extent_status *es)
+static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
{
+ /* Decrease the lru counter when this es is not delayed */
+ if (!ext4_es_is_delayed(es)) {
+ BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
+ EXT4_I(inode)->i_es_lru_nr--;
+ percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
+ }
+
kmem_cache_free(ext4_es_cachep, es);
}
-static struct extent_status *
-ext4_es_try_to_merge_left(struct ext4_es_tree *tree, struct extent_status *es)
+/*
+ * Check whether or not two extents can be merged
+ * Condition:
+ * - logical block number is contiguous
+ * - physical block number is contiguous
+ * - status is equal
+ */
+static int ext4_es_can_be_merged(struct extent_status *es1,
+ struct extent_status *es2)
{
+ if (ext4_es_status(es1) != ext4_es_status(es2))
+ return 0;
+
+ if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
+ return 0;
+
+ if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
+ return 0;
+
+ if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) &&
+ (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2)))
+ return 1;
+
+ if (ext4_es_is_hole(es1))
+ return 1;
+
+ /* we need to check delayed extent is without unwritten status */
+ if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1))
+ return 1;
+
+ return 0;
+}
+
+static struct extent_status *
+ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es)
+{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct extent_status *es1;
struct rb_node *node;
@@ -290,10 +368,10 @@
return es;
es1 = rb_entry(node, struct extent_status, rb_node);
- if (es->start == extent_status_end(es1) + 1) {
- es1->len += es->len;
+ if (ext4_es_can_be_merged(es1, es)) {
+ es1->es_len += es->es_len;
rb_erase(&es->rb_node, &tree->root);
- ext4_es_free_extent(es);
+ ext4_es_free_extent(inode, es);
es = es1;
}
@@ -301,8 +379,9 @@
}
static struct extent_status *
-ext4_es_try_to_merge_right(struct ext4_es_tree *tree, struct extent_status *es)
+ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct extent_status *es1;
struct rb_node *node;
@@ -311,69 +390,230 @@
return es;
es1 = rb_entry(node, struct extent_status, rb_node);
- if (es1->start == extent_status_end(es) + 1) {
- es->len += es1->len;
+ if (ext4_es_can_be_merged(es, es1)) {
+ es->es_len += es1->es_len;
rb_erase(node, &tree->root);
- ext4_es_free_extent(es1);
+ ext4_es_free_extent(inode, es1);
}
return es;
}
-static int __es_insert_extent(struct ext4_es_tree *tree, ext4_lblk_t offset,
- ext4_lblk_t len)
+#ifdef ES_AGGRESSIVE_TEST
+static void ext4_es_insert_extent_ext_check(struct inode *inode,
+ struct extent_status *es)
{
+ struct ext4_ext_path *path = NULL;
+ struct ext4_extent *ex;
+ ext4_lblk_t ee_block;
+ ext4_fsblk_t ee_start;
+ unsigned short ee_len;
+ int depth, ee_status, es_status;
+
+ path = ext4_ext_find_extent(inode, es->es_lblk, NULL);
+ if (IS_ERR(path))
+ return;
+
+ depth = ext_depth(inode);
+ ex = path[depth].p_ext;
+
+ if (ex) {
+
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_start = ext4_ext_pblock(ex);
+ ee_len = ext4_ext_get_actual_len(ex);
+
+ ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
+ es_status = ext4_es_is_unwritten(es) ? 1 : 0;
+
+ /*
+ * Make sure ex and es are not overlap when we try to insert
+ * a delayed/hole extent.
+ */
+ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) {
+ if (in_range(es->es_lblk, ee_block, ee_len)) {
+ pr_warn("ES insert assertation failed for "
+ "inode: %lu we can find an extent "
+ "at block [%d/%d/%llu/%c], but we "
+ "want to add an delayed/hole extent "
+ "[%d/%d/%llu/%llx]\n",
+ inode->i_ino, ee_block, ee_len,
+ ee_start, ee_status ? 'u' : 'w',
+ es->es_lblk, es->es_len,
+ ext4_es_pblock(es), ext4_es_status(es));
+ }
+ goto out;
+ }
+
+ /*
+ * We don't check ee_block == es->es_lblk, etc. because es
+ * might be a part of whole extent, vice versa.
+ */
+ if (es->es_lblk < ee_block ||
+ ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) {
+ pr_warn("ES insert assertation failed for inode: %lu "
+ "ex_status [%d/%d/%llu/%c] != "
+ "es_status [%d/%d/%llu/%c]\n", inode->i_ino,
+ ee_block, ee_len, ee_start,
+ ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
+ ext4_es_pblock(es), es_status ? 'u' : 'w');
+ goto out;
+ }
+
+ if (ee_status ^ es_status) {
+ pr_warn("ES insert assertation failed for inode: %lu "
+ "ex_status [%d/%d/%llu/%c] != "
+ "es_status [%d/%d/%llu/%c]\n", inode->i_ino,
+ ee_block, ee_len, ee_start,
+ ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
+ ext4_es_pblock(es), es_status ? 'u' : 'w');
+ }
+ } else {
+ /*
+ * We can't find an extent on disk. So we need to make sure
+ * that we don't want to add an written/unwritten extent.
+ */
+ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
+ pr_warn("ES insert assertation failed for inode: %lu "
+ "can't find an extent at block %d but we want "
+ "to add an written/unwritten extent "
+ "[%d/%d/%llu/%llx]\n", inode->i_ino,
+ es->es_lblk, es->es_lblk, es->es_len,
+ ext4_es_pblock(es), ext4_es_status(es));
+ }
+ }
+out:
+ if (path) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+}
+
+static void ext4_es_insert_extent_ind_check(struct inode *inode,
+ struct extent_status *es)
+{
+ struct ext4_map_blocks map;
+ int retval;
+
+ /*
+ * Here we call ext4_ind_map_blocks to lookup a block mapping because
+ * 'Indirect' structure is defined in indirect.c. So we couldn't
+ * access direct/indirect tree from outside. It is too dirty to define
+ * this function in indirect.c file.
+ */
+
+ map.m_lblk = es->es_lblk;
+ map.m_len = es->es_len;
+
+ retval = ext4_ind_map_blocks(NULL, inode, &map, 0);
+ if (retval > 0) {
+ if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) {
+ /*
+ * We want to add a delayed/hole extent but this
+ * block has been allocated.
+ */
+ pr_warn("ES insert assertation failed for inode: %lu "
+ "We can find blocks but we want to add a "
+ "delayed/hole extent [%d/%d/%llu/%llx]\n",
+ inode->i_ino, es->es_lblk, es->es_len,
+ ext4_es_pblock(es), ext4_es_status(es));
+ return;
+ } else if (ext4_es_is_written(es)) {
+ if (retval != es->es_len) {
+ pr_warn("ES insert assertation failed for "
+ "inode: %lu retval %d != es_len %d\n",
+ inode->i_ino, retval, es->es_len);
+ return;
+ }
+ if (map.m_pblk != ext4_es_pblock(es)) {
+ pr_warn("ES insert assertation failed for "
+ "inode: %lu m_pblk %llu != "
+ "es_pblk %llu\n",
+ inode->i_ino, map.m_pblk,
+ ext4_es_pblock(es));
+ return;
+ }
+ } else {
+ /*
+ * We don't need to check unwritten extent because
+ * indirect-based file doesn't have it.
+ */
+ BUG_ON(1);
+ }
+ } else if (retval == 0) {
+ if (ext4_es_is_written(es)) {
+ pr_warn("ES insert assertation failed for inode: %lu "
+ "We can't find the block but we want to add "
+ "an written extent [%d/%d/%llu/%llx]\n",
+ inode->i_ino, es->es_lblk, es->es_len,
+ ext4_es_pblock(es), ext4_es_status(es));
+ return;
+ }
+ }
+}
+
+static inline void ext4_es_insert_extent_check(struct inode *inode,
+ struct extent_status *es)
+{
+ /*
+ * We don't need to worry about the race condition because
+ * caller takes i_data_sem locking.
+ */
+ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem));
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ ext4_es_insert_extent_ext_check(inode, es);
+ else
+ ext4_es_insert_extent_ind_check(inode, es);
+}
+#else
+static inline void ext4_es_insert_extent_check(struct inode *inode,
+ struct extent_status *es)
+{
+}
+#endif
+
+static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
+{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
struct rb_node **p = &tree->root.rb_node;
struct rb_node *parent = NULL;
struct extent_status *es;
- ext4_lblk_t end = offset + len - 1;
-
- BUG_ON(end < offset);
- es = tree->cache_es;
- if (es && offset == (extent_status_end(es) + 1)) {
- es_debug("cached by [%u/%u)\n", es->start, es->len);
- es->len += len;
- es = ext4_es_try_to_merge_right(tree, es);
- goto out;
- } else if (es && es->start == end + 1) {
- es_debug("cached by [%u/%u)\n", es->start, es->len);
- es->start = offset;
- es->len += len;
- es = ext4_es_try_to_merge_left(tree, es);
- goto out;
- } else if (es && es->start <= offset &&
- end <= extent_status_end(es)) {
- es_debug("cached by [%u/%u)\n", es->start, es->len);
- goto out;
- }
while (*p) {
parent = *p;
es = rb_entry(parent, struct extent_status, rb_node);
- if (offset < es->start) {
- if (es->start == end + 1) {
- es->start = offset;
- es->len += len;
- es = ext4_es_try_to_merge_left(tree, es);
+ if (newes->es_lblk < es->es_lblk) {
+ if (ext4_es_can_be_merged(newes, es)) {
+ /*
+ * Here we can modify es_lblk directly
+ * because it isn't overlapped.
+ */
+ es->es_lblk = newes->es_lblk;
+ es->es_len += newes->es_len;
+ if (ext4_es_is_written(es) ||
+ ext4_es_is_unwritten(es))
+ ext4_es_store_pblock(es,
+ newes->es_pblk);
+ es = ext4_es_try_to_merge_left(inode, es);
goto out;
}
p = &(*p)->rb_left;
- } else if (offset > extent_status_end(es)) {
- if (offset == extent_status_end(es) + 1) {
- es->len += len;
- es = ext4_es_try_to_merge_right(tree, es);
+ } else if (newes->es_lblk > ext4_es_end(es)) {
+ if (ext4_es_can_be_merged(es, newes)) {
+ es->es_len += newes->es_len;
+ es = ext4_es_try_to_merge_right(inode, es);
goto out;
}
p = &(*p)->rb_right;
} else {
- if (extent_status_end(es) <= end)
- es->len = offset - es->start + len;
- goto out;
+ BUG_ON(1);
+ return -EINVAL;
}
}
- es = ext4_es_alloc_extent(offset, len);
+ es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len,
+ newes->es_pblk);
if (!es)
return -ENOMEM;
rb_link_node(&es->rb_node, parent, p);
@@ -385,85 +625,168 @@
}
/*
- * ext4_es_insert_extent() adds a space to a delayed extent tree.
- * Caller holds inode->i_es_lock.
+ * ext4_es_insert_extent() adds a space to a extent status tree.
*
* ext4_es_insert_extent is called by ext4_da_write_begin and
* ext4_es_remove_extent.
*
* Return 0 on success, error code on failure.
*/
-int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t offset,
- ext4_lblk_t len)
+int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned long long status)
{
- struct ext4_es_tree *tree;
+ struct extent_status newes;
+ ext4_lblk_t end = lblk + len - 1;
int err = 0;
- trace_ext4_es_insert_extent(inode, offset, len);
- es_debug("add [%u/%u) to extent status tree of inode %lu\n",
- offset, len, inode->i_ino);
+ es_debug("add [%u/%u) %llu %llx to extent status tree of inode %lu\n",
+ lblk, len, pblk, status, inode->i_ino);
+
+ if (!len)
+ return 0;
+
+ BUG_ON(end < lblk);
+
+ newes.es_lblk = lblk;
+ newes.es_len = len;
+ ext4_es_store_pblock(&newes, pblk);
+ ext4_es_store_status(&newes, status);
+ trace_ext4_es_insert_extent(inode, &newes);
+
+ ext4_es_insert_extent_check(inode, &newes);
write_lock(&EXT4_I(inode)->i_es_lock);
- tree = &EXT4_I(inode)->i_es_tree;
- err = __es_insert_extent(tree, offset, len);
+ err = __es_remove_extent(inode, lblk, end);
+ if (err != 0)
+ goto error;
+ err = __es_insert_extent(inode, &newes);
+
+error:
write_unlock(&EXT4_I(inode)->i_es_lock);
+ ext4_es_lru_add(inode);
ext4_es_print_tree(inode);
return err;
}
/*
- * ext4_es_remove_extent() removes a space from a delayed extent tree.
- * Caller holds inode->i_es_lock.
+ * ext4_es_lookup_extent() looks up an extent in extent status tree.
*
- * Return 0 on success, error code on failure.
+ * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
+ *
+ * Return: 1 on found, 0 on not
*/
-int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t offset,
- ext4_lblk_t len)
+int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
+ struct extent_status *es)
{
- struct rb_node *node;
struct ext4_es_tree *tree;
+ struct extent_status *es1 = NULL;
+ struct rb_node *node;
+ int found = 0;
+
+ trace_ext4_es_lookup_extent_enter(inode, lblk);
+ es_debug("lookup extent in block %u\n", lblk);
+
+ tree = &EXT4_I(inode)->i_es_tree;
+ read_lock(&EXT4_I(inode)->i_es_lock);
+
+ /* find extent in cache firstly */
+ es->es_lblk = es->es_len = es->es_pblk = 0;
+ if (tree->cache_es) {
+ es1 = tree->cache_es;
+ if (in_range(lblk, es1->es_lblk, es1->es_len)) {
+ es_debug("%u cached by [%u/%u)\n",
+ lblk, es1->es_lblk, es1->es_len);
+ found = 1;
+ goto out;
+ }
+ }
+
+ node = tree->root.rb_node;
+ while (node) {
+ es1 = rb_entry(node, struct extent_status, rb_node);
+ if (lblk < es1->es_lblk)
+ node = node->rb_left;
+ else if (lblk > ext4_es_end(es1))
+ node = node->rb_right;
+ else {
+ found = 1;
+ break;
+ }
+ }
+
+out:
+ if (found) {
+ BUG_ON(!es1);
+ es->es_lblk = es1->es_lblk;
+ es->es_len = es1->es_len;
+ es->es_pblk = es1->es_pblk;
+ }
+
+ read_unlock(&EXT4_I(inode)->i_es_lock);
+
+ ext4_es_lru_add(inode);
+ trace_ext4_es_lookup_extent_exit(inode, es, found);
+ return found;
+}
+
+static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t end)
+{
+ struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
+ struct rb_node *node;
struct extent_status *es;
struct extent_status orig_es;
- ext4_lblk_t len1, len2, end;
+ ext4_lblk_t len1, len2;
+ ext4_fsblk_t block;
int err = 0;
- trace_ext4_es_remove_extent(inode, offset, len);
- es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
- offset, len, inode->i_ino);
-
- end = offset + len - 1;
- BUG_ON(end < offset);
- write_lock(&EXT4_I(inode)->i_es_lock);
- tree = &EXT4_I(inode)->i_es_tree;
- es = __es_tree_search(&tree->root, offset);
+ es = __es_tree_search(&tree->root, lblk);
if (!es)
goto out;
- if (es->start > end)
+ if (es->es_lblk > end)
goto out;
/* Simply invalidate cache_es. */
tree->cache_es = NULL;
- orig_es.start = es->start;
- orig_es.len = es->len;
- len1 = offset > es->start ? offset - es->start : 0;
- len2 = extent_status_end(es) > end ?
- extent_status_end(es) - end : 0;
+ orig_es.es_lblk = es->es_lblk;
+ orig_es.es_len = es->es_len;
+ orig_es.es_pblk = es->es_pblk;
+
+ len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0;
+ len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0;
if (len1 > 0)
- es->len = len1;
+ es->es_len = len1;
if (len2 > 0) {
if (len1 > 0) {
- err = __es_insert_extent(tree, end + 1, len2);
+ struct extent_status newes;
+
+ newes.es_lblk = end + 1;
+ newes.es_len = len2;
+ if (ext4_es_is_written(&orig_es) ||
+ ext4_es_is_unwritten(&orig_es)) {
+ block = ext4_es_pblock(&orig_es) +
+ orig_es.es_len - len2;
+ ext4_es_store_pblock(&newes, block);
+ }
+ ext4_es_store_status(&newes, ext4_es_status(&orig_es));
+ err = __es_insert_extent(inode, &newes);
if (err) {
- es->start = orig_es.start;
- es->len = orig_es.len;
+ es->es_lblk = orig_es.es_lblk;
+ es->es_len = orig_es.es_len;
goto out;
}
} else {
- es->start = end + 1;
- es->len = len2;
+ es->es_lblk = end + 1;
+ es->es_len = len2;
+ if (ext4_es_is_written(es) ||
+ ext4_es_is_unwritten(es)) {
+ block = orig_es.es_pblk + orig_es.es_len - len2;
+ ext4_es_store_pblock(es, block);
+ }
}
goto out;
}
@@ -476,10 +799,10 @@
es = NULL;
}
- while (es && extent_status_end(es) <= end) {
+ while (es && ext4_es_end(es) <= end) {
node = rb_next(&es->rb_node);
rb_erase(&es->rb_node, &tree->root);
- ext4_es_free_extent(es);
+ ext4_es_free_extent(inode, es);
if (!node) {
es = NULL;
break;
@@ -487,14 +810,183 @@
es = rb_entry(node, struct extent_status, rb_node);
}
- if (es && es->start < end + 1) {
- len1 = extent_status_end(es) - end;
- es->start = end + 1;
- es->len = len1;
+ if (es && es->es_lblk < end + 1) {
+ ext4_lblk_t orig_len = es->es_len;
+
+ len1 = ext4_es_end(es) - end;
+ es->es_lblk = end + 1;
+ es->es_len = len1;
+ if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) {
+ block = es->es_pblk + orig_len - len1;
+ ext4_es_store_pblock(es, block);
+ }
}
out:
+ return err;
+}
+
+/*
+ * ext4_es_remove_extent() removes a space from a extent status tree.
+ *
+ * Return 0 on success, error code on failure.
+ */
+int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len)
+{
+ ext4_lblk_t end;
+ int err = 0;
+
+ trace_ext4_es_remove_extent(inode, lblk, len);
+ es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
+ lblk, len, inode->i_ino);
+
+ if (!len)
+ return err;
+
+ end = lblk + len - 1;
+ BUG_ON(end < lblk);
+
+ write_lock(&EXT4_I(inode)->i_es_lock);
+ err = __es_remove_extent(inode, lblk, end);
write_unlock(&EXT4_I(inode)->i_es_lock);
ext4_es_print_tree(inode);
return err;
}
+
+int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
+{
+ ext4_lblk_t ee_block;
+ ext4_fsblk_t ee_pblock;
+ unsigned int ee_len;
+
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_len = ext4_ext_get_actual_len(ex);
+ ee_pblock = ext4_ext_pblock(ex);
+
+ if (ee_len == 0)
+ return 0;
+
+ return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+ EXTENT_STATUS_WRITTEN);
+}
+
+static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ struct ext4_sb_info *sbi = container_of(shrink,
+ struct ext4_sb_info, s_es_shrinker);
+ struct ext4_inode_info *ei;
+ struct list_head *cur, *tmp, scanned;
+ int nr_to_scan = sc->nr_to_scan;
+ int ret, nr_shrunk = 0;
+
+ ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);
+
+ if (!nr_to_scan)
+ return ret;
+
+ INIT_LIST_HEAD(&scanned);
+
+ spin_lock(&sbi->s_es_lru_lock);
+ list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
+ list_move_tail(cur, &scanned);
+
+ ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
+
+ read_lock(&ei->i_es_lock);
+ if (ei->i_es_lru_nr == 0) {
+ read_unlock(&ei->i_es_lock);
+ continue;
+ }
+ read_unlock(&ei->i_es_lock);
+
+ write_lock(&ei->i_es_lock);
+ ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
+ write_unlock(&ei->i_es_lock);
+
+ nr_shrunk += ret;
+ nr_to_scan -= ret;
+ if (nr_to_scan == 0)
+ break;
+ }
+ list_splice_tail(&scanned, &sbi->s_es_lru);
+ spin_unlock(&sbi->s_es_lru_lock);
+
+ ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
+ trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
+ return ret;
+}
+
+void ext4_es_register_shrinker(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi;
+
+ sbi = EXT4_SB(sb);
+ INIT_LIST_HEAD(&sbi->s_es_lru);
+ spin_lock_init(&sbi->s_es_lru_lock);
+ sbi->s_es_shrinker.shrink = ext4_es_shrink;
+ sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
+ register_shrinker(&sbi->s_es_shrinker);
+}
+
+void ext4_es_unregister_shrinker(struct super_block *sb)
+{
+ unregister_shrinker(&EXT4_SB(sb)->s_es_shrinker);
+}
+
+void ext4_es_lru_add(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ spin_lock(&sbi->s_es_lru_lock);
+ if (list_empty(&ei->i_es_lru))
+ list_add_tail(&ei->i_es_lru, &sbi->s_es_lru);
+ else
+ list_move_tail(&ei->i_es_lru, &sbi->s_es_lru);
+ spin_unlock(&sbi->s_es_lru_lock);
+}
+
+void ext4_es_lru_del(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ spin_lock(&sbi->s_es_lru_lock);
+ if (!list_empty(&ei->i_es_lru))
+ list_del_init(&ei->i_es_lru);
+ spin_unlock(&sbi->s_es_lru_lock);
+}
+
+static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
+ int nr_to_scan)
+{
+ struct inode *inode = &ei->vfs_inode;
+ struct ext4_es_tree *tree = &ei->i_es_tree;
+ struct rb_node *node;
+ struct extent_status *es;
+ int nr_shrunk = 0;
+
+ if (ei->i_es_lru_nr == 0)
+ return 0;
+
+ node = rb_first(&tree->root);
+ while (node != NULL) {
+ es = rb_entry(node, struct extent_status, rb_node);
+ node = rb_next(&es->rb_node);
+ /*
+ * We can't reclaim delayed extent from status tree because
+ * fiemap, bigallic, and seek_data/hole need to use it.
+ */
+ if (!ext4_es_is_delayed(es)) {
+ rb_erase(&es->rb_node, &tree->root);
+ ext4_es_free_extent(inode, es);
+ nr_shrunk++;
+ if (--nr_to_scan == 0)
+ break;
+ }
+ }
+ tree->cache_es = NULL;
+ return nr_shrunk;
+}
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 077f82d..d8e2d4d 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -20,10 +20,32 @@
#define es_debug(fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
+/*
+ * With ES_AGGRESSIVE_TEST defined, the result of es caching will be
+ * checked with old map_block's result.
+ */
+#define ES_AGGRESSIVE_TEST__
+
+/*
+ * These flags live in the high bits of extent_status.es_pblk
+ */
+#define EXTENT_STATUS_WRITTEN (1ULL << 63)
+#define EXTENT_STATUS_UNWRITTEN (1ULL << 62)
+#define EXTENT_STATUS_DELAYED (1ULL << 61)
+#define EXTENT_STATUS_HOLE (1ULL << 60)
+
+#define EXTENT_STATUS_FLAGS (EXTENT_STATUS_WRITTEN | \
+ EXTENT_STATUS_UNWRITTEN | \
+ EXTENT_STATUS_DELAYED | \
+ EXTENT_STATUS_HOLE)
+
+struct ext4_extent;
+
struct extent_status {
struct rb_node rb_node;
- ext4_lblk_t start; /* first block extent covers */
- ext4_lblk_t len; /* length of extent in block */
+ ext4_lblk_t es_lblk; /* first logical block extent covers */
+ ext4_lblk_t es_len; /* length of extent in block */
+ ext4_fsblk_t es_pblk; /* first physical block */
};
struct ext4_es_tree {
@@ -35,11 +57,70 @@
extern void ext4_exit_es(void);
extern void ext4_es_init_tree(struct ext4_es_tree *tree);
-extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t start,
+extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned long long status);
+extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len);
-extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t start,
- ext4_lblk_t len);
-extern ext4_lblk_t ext4_es_find_extent(struct inode *inode,
- struct extent_status *es);
+extern void ext4_es_find_delayed_extent(struct inode *inode, ext4_lblk_t lblk,
+ struct extent_status *es);
+extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
+ struct extent_status *es);
+extern int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex);
+
+static inline int ext4_es_is_written(struct extent_status *es)
+{
+ return (es->es_pblk & EXTENT_STATUS_WRITTEN) != 0;
+}
+
+static inline int ext4_es_is_unwritten(struct extent_status *es)
+{
+ return (es->es_pblk & EXTENT_STATUS_UNWRITTEN) != 0;
+}
+
+static inline int ext4_es_is_delayed(struct extent_status *es)
+{
+ return (es->es_pblk & EXTENT_STATUS_DELAYED) != 0;
+}
+
+static inline int ext4_es_is_hole(struct extent_status *es)
+{
+ return (es->es_pblk & EXTENT_STATUS_HOLE) != 0;
+}
+
+static inline ext4_fsblk_t ext4_es_status(struct extent_status *es)
+{
+ return (es->es_pblk & EXTENT_STATUS_FLAGS);
+}
+
+static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
+{
+ return (es->es_pblk & ~EXTENT_STATUS_FLAGS);
+}
+
+static inline void ext4_es_store_pblock(struct extent_status *es,
+ ext4_fsblk_t pb)
+{
+ ext4_fsblk_t block;
+
+ block = (pb & ~EXTENT_STATUS_FLAGS) |
+ (es->es_pblk & EXTENT_STATUS_FLAGS);
+ es->es_pblk = block;
+}
+
+static inline void ext4_es_store_status(struct extent_status *es,
+ unsigned long long status)
+{
+ ext4_fsblk_t block;
+
+ block = (status & EXTENT_STATUS_FLAGS) |
+ (es->es_pblk & ~EXTENT_STATUS_FLAGS);
+ es->es_pblk = block;
+}
+
+extern void ext4_es_register_shrinker(struct super_block *sb);
+extern void ext4_es_unregister_shrinker(struct super_block *sb);
+extern void ext4_es_lru_add(struct inode *inode);
+extern void ext4_es_lru_del(struct inode *inode);
#endif /* _EXT4_EXTENTS_STATUS_H */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 405565a6..64848b5 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -167,7 +167,7 @@
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
- struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
/*
@@ -240,7 +240,7 @@
handle_t *handle;
int err;
- handle = ext4_journal_start_sb(sb, 1);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
@@ -464,10 +464,8 @@
* If there is a delay extent at this offset,
* it will be as a data.
*/
- es.start = last;
- (void)ext4_es_find_extent(inode, &es);
- if (last >= es.start &&
- last < es.start + es.len) {
+ ext4_es_find_delayed_extent(inode, last, &es);
+ if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
if (last != start)
dataoff = last << blkbits;
break;
@@ -549,11 +547,9 @@
* If there is a delay extent at this offset,
* we will skip this extent.
*/
- es.start = last;
- (void)ext4_es_find_extent(inode, &es);
- if (last >= es.start &&
- last < es.start + es.len) {
- last = es.start + es.len;
+ ext4_es_find_delayed_extent(inode, last, &es);
+ if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
+ last = es.es_lblk + es.es_len;
holeoff = last << blkbits;
continue;
}
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index fa8e491..3d586f0 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -155,11 +155,11 @@
/* Check to see if the seed is all zero's */
if (hinfo->seed) {
for (i = 0; i < 4; i++) {
- if (hinfo->seed[i])
+ if (hinfo->seed[i]) {
+ memcpy(buf, hinfo->seed, sizeof(buf));
break;
+ }
}
- if (i < 4)
- memcpy(buf, hinfo->seed, sizeof(buf));
}
switch (hinfo->hash_version) {
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 3f32c80..6c5bb8d 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -324,8 +324,8 @@
}
struct orlov_stats {
+ __u64 free_clusters;
__u32 free_inodes;
- __u32 free_clusters;
__u32 used_dirs;
};
@@ -342,7 +342,7 @@
if (flex_size > 1) {
stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
- stats->free_clusters = atomic_read(&flex_group[g].free_clusters);
+ stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
return;
}
@@ -634,8 +634,10 @@
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
-struct inode *ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode,
- const struct qstr *qstr, __u32 goal, uid_t *owner)
+struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
+ umode_t mode, const struct qstr *qstr,
+ __u32 goal, uid_t *owner, int handle_type,
+ unsigned int line_no, int nblocks)
{
struct super_block *sb;
struct buffer_head *inode_bitmap_bh = NULL;
@@ -725,6 +727,15 @@
"inode=%lu", ino + 1);
continue;
}
+ if (!handle) {
+ BUG_ON(nblocks <= 0);
+ handle = __ext4_journal_start_sb(dir->i_sb, line_no,
+ handle_type, nblocks);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto fail;
+ }
+ }
BUFFER_TRACE(inode_bitmap_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, inode_bitmap_bh);
if (err)
@@ -1017,17 +1028,17 @@
inode = NULL;
bad_orphan:
ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino);
- printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+ printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n",
bit, (unsigned long long)bitmap_bh->b_blocknr,
ext4_test_bit(bit, bitmap_bh->b_data));
- printk(KERN_NOTICE "inode=%p\n", inode);
+ printk(KERN_WARNING "inode=%p\n", inode);
if (inode) {
- printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
+ printk(KERN_WARNING "is_bad_inode(inode)=%d\n",
is_bad_inode(inode));
- printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
+ printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n",
NEXT_ORPHAN(inode));
- printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
- printk(KERN_NOTICE "i_nlink=%u\n", inode->i_nlink);
+ printk(KERN_WARNING "max_ino=%lu\n", max_ino);
+ printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink);
/* Avoid freeing blocks if we got a bad deleted inode */
if (inode->i_nlink == 0)
inode->i_blocks = 0;
@@ -1137,7 +1148,7 @@
if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))
goto out;
- handle = ext4_journal_start_sb(sb, 1);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 20862f9..b505a14 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -146,6 +146,7 @@
struct super_block *sb = inode->i_sb;
Indirect *p = chain;
struct buffer_head *bh;
+ int ret = -EIO;
*err = 0;
/* i_data is not going away, no lock needed */
@@ -154,8 +155,10 @@
goto no_block;
while (--depth) {
bh = sb_getblk(sb, le32_to_cpu(p->key));
- if (unlikely(!bh))
+ if (unlikely(!bh)) {
+ ret = -ENOMEM;
goto failure;
+ }
if (!bh_uptodate_or_lock(bh)) {
if (bh_submit_read(bh) < 0) {
@@ -177,7 +180,7 @@
return NULL;
failure:
- *err = -EIO;
+ *err = ret;
no_block:
return p;
}
@@ -355,9 +358,8 @@
* for the first direct block
*/
new_blocks[index] = current_block;
- printk(KERN_INFO "%s returned more blocks than "
+ WARN(1, KERN_INFO "%s returned more blocks than "
"requested\n", __func__);
- WARN_ON(1);
break;
}
}
@@ -471,7 +473,7 @@
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
if (unlikely(!bh)) {
- err = -EIO;
+ err = -ENOMEM;
goto failed;
}
@@ -789,7 +791,7 @@
if (final_size > inode->i_size) {
/* Credits for sb + inode write */
- handle = ext4_journal_start(inode, 2);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
@@ -849,7 +851,7 @@
int err;
/* Credits for sb + inode write */
- handle = ext4_journal_start(inode, 2);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle)) {
/* This is really bad luck. We've written the data
* but cannot extend i_size. Bail out and pretend
@@ -948,7 +950,8 @@
{
handle_t *result;
- result = ext4_journal_start(inode, ext4_blocks_for_truncate(inode));
+ result = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
+ ext4_blocks_for_truncate(inode));
if (!IS_ERR(result))
return result;
@@ -1515,3 +1518,243 @@
trace_ext4_truncate_exit(inode);
}
+static int free_hole_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *parent_bh, __le32 *i_data,
+ int level, ext4_lblk_t first,
+ ext4_lblk_t count, int max)
+{
+ struct buffer_head *bh = NULL;
+ int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ int ret = 0;
+ int i, inc;
+ ext4_lblk_t offset;
+ __le32 blk;
+
+ inc = 1 << ((EXT4_BLOCK_SIZE_BITS(inode->i_sb) - 2) * level);
+ for (i = 0, offset = 0; i < max; i++, i_data++, offset += inc) {
+ if (offset >= count + first)
+ break;
+ if (*i_data == 0 || (offset + inc) <= first)
+ continue;
+ blk = *i_data;
+ if (level > 0) {
+ ext4_lblk_t first2;
+ bh = sb_bread(inode->i_sb, blk);
+ if (!bh) {
+ EXT4_ERROR_INODE_BLOCK(inode, blk,
+ "Read failure");
+ return -EIO;
+ }
+ first2 = (first > offset) ? first - offset : 0;
+ ret = free_hole_blocks(handle, inode, bh,
+ (__le32 *)bh->b_data, level - 1,
+ first2, count - offset,
+ inode->i_sb->s_blocksize >> 2);
+ if (ret) {
+ brelse(bh);
+ goto err;
+ }
+ }
+ if (level == 0 ||
+ (bh && all_zeroes((__le32 *)bh->b_data,
+ (__le32 *)bh->b_data + addr_per_block))) {
+ ext4_free_data(handle, inode, parent_bh, &blk, &blk+1);
+ *i_data = 0;
+ }
+ brelse(bh);
+ bh = NULL;
+ }
+
+err:
+ return ret;
+}
+
+static int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
+ ext4_lblk_t first, ext4_lblk_t stop)
+{
+ int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
+ int level, ret = 0;
+ int num = EXT4_NDIR_BLOCKS;
+ ext4_lblk_t count, max = EXT4_NDIR_BLOCKS;
+ __le32 *i_data = EXT4_I(inode)->i_data;
+
+ count = stop - first;
+ for (level = 0; level < 4; level++, max *= addr_per_block) {
+ if (first < max) {
+ ret = free_hole_blocks(handle, inode, NULL, i_data,
+ level, first, count, num);
+ if (ret)
+ goto err;
+ if (count > max - first)
+ count -= max - first;
+ else
+ break;
+ first = 0;
+ } else {
+ first -= max;
+ }
+ i_data += num;
+ if (level == 0) {
+ num = 1;
+ max = 1;
+ }
+ }
+
+err:
+ return ret;
+}
+
+int ext4_ind_punch_hole(struct file *file, loff_t offset, loff_t length)
+{
+ struct inode *inode = file_inode(file);
+ struct super_block *sb = inode->i_sb;
+ ext4_lblk_t first_block, stop_block;
+ struct address_space *mapping = inode->i_mapping;
+ handle_t *handle = NULL;
+ loff_t first_page, last_page, page_len;
+ loff_t first_page_offset, last_page_offset;
+ int err = 0;
+
+ /*
+ * Write out all dirty pages to avoid race conditions
+ * Then release them.
+ */
+ if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ err = filemap_write_and_wait_range(mapping,
+ offset, offset + length - 1);
+ if (err)
+ return err;
+ }
+
+ mutex_lock(&inode->i_mutex);
+ /* It's not possible punch hole on append only file */
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) {
+ err = -EPERM;
+ goto out_mutex;
+ }
+ if (IS_SWAPFILE(inode)) {
+ err = -ETXTBSY;
+ goto out_mutex;
+ }
+
+ /* No need to punch hole beyond i_size */
+ if (offset >= inode->i_size)
+ goto out_mutex;
+
+ /*
+ * If the hole extents beyond i_size, set the hole
+ * to end after the page that contains i_size
+ */
+ if (offset + length > inode->i_size) {
+ length = inode->i_size +
+ PAGE_CACHE_SIZE - (inode->i_size & (PAGE_CACHE_SIZE - 1)) -
+ offset;
+ }
+
+ first_page = (offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ last_page = (offset + length) >> PAGE_CACHE_SHIFT;
+
+ first_page_offset = first_page << PAGE_CACHE_SHIFT;
+ last_page_offset = last_page << PAGE_CACHE_SHIFT;
+
+ /* Now release the pages */
+ if (last_page_offset > first_page_offset) {
+ truncate_pagecache_range(inode, first_page_offset,
+ last_page_offset - 1);
+ }
+
+ /* Wait all existing dio works, newcomers will block on i_mutex */
+ inode_dio_wait(inode);
+
+ handle = start_transaction(inode);
+ if (IS_ERR(handle))
+ goto out_mutex;
+
+ /*
+ * Now we need to zero out the non-page-aligned data in the
+ * pages at the start and tail of the hole, and unmap the buffer
+ * heads for the block aligned regions of the page that were
+ * completely zerod.
+ */
+ if (first_page > last_page) {
+ /*
+ * If the file space being truncated is contained within a page
+ * just zero out and unmap the middle of that page
+ */
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, offset, length, 0);
+ if (err)
+ goto out;
+ } else {
+ /*
+ * Zero out and unmap the paritial page that contains
+ * the start of the hole
+ */
+ page_len = first_page_offset - offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+
+ /*
+ * Zero out and unmap the partial page that contains
+ * the end of the hole
+ */
+ page_len = offset + length - last_page_offset;
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle, mapping,
+ last_page_offset, page_len, 0);
+ if (err)
+ goto out;
+ }
+ }
+
+ /*
+ * If i_size contained in the last page, we need to
+ * unmap and zero the paritial page after i_size
+ */
+ if (inode->i_size >> PAGE_CACHE_SHIFT == last_page &&
+ inode->i_size % PAGE_CACHE_SIZE != 0) {
+ page_len = PAGE_CACHE_SIZE -
+ (inode->i_size & (PAGE_CACHE_SIZE - 1));
+ if (page_len > 0) {
+ err = ext4_discard_partial_page_buffers(handle,
+ mapping, inode->i_size, page_len, 0);
+ if (err)
+ goto out;
+ }
+ }
+
+ first_block = (offset + sb->s_blocksize - 1) >>
+ EXT4_BLOCK_SIZE_BITS(sb);
+ stop_block = (offset + length) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+ if (first_block >= stop_block)
+ goto out;
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_discard_preallocations(inode);
+
+ err = ext4_es_remove_extent(inode, first_block,
+ stop_block - first_block);
+ err = ext4_free_hole_blocks(handle, inode, first_block, stop_block);
+
+ ext4_discard_preallocations(inode);
+
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+
+ up_write(&EXT4_I(inode)->i_data_sem);
+
+out:
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+out_mutex:
+ mutex_unlock(&inode->i_mutex);
+
+ return err;
+}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 387c47c..c0fd1a1 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -545,7 +545,7 @@
return ret;
retry:
- handle = ext4_journal_start(inode, needed_blocks);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
@@ -657,7 +657,7 @@
* The possible write could happen in the inode,
* so try to reserve the space in inode first.
*/
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
@@ -853,7 +853,7 @@
if (ret)
return ret;
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
@@ -1188,7 +1188,7 @@
data_bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!data_bh) {
- error = -EIO;
+ error = -ENOMEM;
goto out_restore;
}
@@ -1298,7 +1298,7 @@
int i, stored;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int ret, inline_size = 0;
struct ext4_iloc iloc;
void *dir_buf = NULL;
@@ -1770,7 +1770,7 @@
needed_blocks = ext4_writepage_trans_blocks(inode);
- handle = ext4_journal_start(inode, needed_blocks);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
if (IS_ERR(handle))
return;
@@ -1862,7 +1862,7 @@
if (error)
return error;
- handle = ext4_journal_start(inode, needed_blocks);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto out_free;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cbfe13b..b3a5213 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -132,10 +132,6 @@
}
static void ext4_invalidatepage(struct page *page, unsigned long offset);
-static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create);
-static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
-static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
static int __ext4_journalled_writepage(struct page *page, unsigned int len);
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
static int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
@@ -189,8 +185,6 @@
trace_ext4_evict_inode(inode);
- ext4_ioend_wait(inode);
-
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
@@ -211,7 +205,8 @@
* don't use page cache.
*/
if (ext4_should_journal_data(inode) &&
- (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+ inode->i_ino != EXT4_JOURNAL_INO) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
@@ -220,6 +215,7 @@
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
+ ext4_ioend_shutdown(inode);
goto no_delete;
}
@@ -229,6 +225,7 @@
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages(&inode->i_data, 0);
+ ext4_ioend_shutdown(inode);
if (is_bad_inode(inode))
goto no_delete;
@@ -238,7 +235,8 @@
* protection against it
*/
sb_start_intwrite(inode->i_sb);
- handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
+ ext4_blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -346,7 +344,7 @@
spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used, quota_claim);
if (unlikely(used > ei->i_reserved_data_blocks)) {
- ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+ ext4_warning(inode->i_sb, "%s: ino %lu, used %d "
"with only %d reserved data blocks",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
@@ -355,10 +353,12 @@
}
if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
- ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
- "with only %d reserved metadata blocks\n", __func__,
- inode->i_ino, ei->i_allocated_meta_blocks,
- ei->i_reserved_meta_blocks);
+ ext4_warning(inode->i_sb, "ino %lu, allocated %d "
+ "with only %d reserved metadata blocks "
+ "(releasing %d blocks with reserved %d data blocks)",
+ inode->i_ino, ei->i_allocated_meta_blocks,
+ ei->i_reserved_meta_blocks, used,
+ ei->i_reserved_data_blocks);
WARN_ON(1);
ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
}
@@ -483,6 +483,58 @@
return num;
}
+#ifdef ES_AGGRESSIVE_TEST
+static void ext4_map_blocks_es_recheck(handle_t *handle,
+ struct inode *inode,
+ struct ext4_map_blocks *es_map,
+ struct ext4_map_blocks *map,
+ int flags)
+{
+ int retval;
+
+ map->m_flags = 0;
+ /*
+ * There is a race window that the result is not the same.
+ * e.g. xfstests #223 when dioread_nolock enables. The reason
+ * is that we lookup a block mapping in extent status tree with
+ * out taking i_data_sem. So at the time the unwritten extent
+ * could be converted.
+ */
+ if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+ down_read((&EXT4_I(inode)->i_data_sem));
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ retval = ext4_ext_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
+ } else {
+ retval = ext4_ind_map_blocks(handle, inode, map, flags &
+ EXT4_GET_BLOCKS_KEEP_SIZE);
+ }
+ if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
+ up_read((&EXT4_I(inode)->i_data_sem));
+ /*
+ * Clear EXT4_MAP_FROM_CLUSTER and EXT4_MAP_BOUNDARY flag
+ * because it shouldn't be marked in es_map->m_flags.
+ */
+ map->m_flags &= ~(EXT4_MAP_FROM_CLUSTER | EXT4_MAP_BOUNDARY);
+
+ /*
+ * We don't check m_len because extent will be collpased in status
+ * tree. So the m_len might not equal.
+ */
+ if (es_map->m_lblk != map->m_lblk ||
+ es_map->m_flags != map->m_flags ||
+ es_map->m_pblk != map->m_pblk) {
+ printk("ES cache assertation failed for inode: %lu "
+ "es_cached ex [%d/%d/%llu/%x] != "
+ "found ex [%d/%d/%llu/%x] retval %d flags %x\n",
+ inode->i_ino, es_map->m_lblk, es_map->m_len,
+ es_map->m_pblk, es_map->m_flags, map->m_lblk,
+ map->m_len, map->m_pblk, map->m_flags,
+ retval, flags);
+ }
+}
+#endif /* ES_AGGRESSIVE_TEST */
+
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
@@ -508,12 +560,42 @@
int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
+ struct extent_status es;
int retval;
+#ifdef ES_AGGRESSIVE_TEST
+ struct ext4_map_blocks orig_map;
+
+ memcpy(&orig_map, map, sizeof(*map));
+#endif
map->m_flags = 0;
ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
+
+ /* Lookup extent status tree firstly */
+ if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
+ map->m_pblk = ext4_es_pblock(&es) +
+ map->m_lblk - es.es_lblk;
+ map->m_flags |= ext4_es_is_written(&es) ?
+ EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN;
+ retval = es.es_len - (map->m_lblk - es.es_lblk);
+ if (retval > map->m_len)
+ retval = map->m_len;
+ map->m_len = retval;
+ } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
+ retval = 0;
+ } else {
+ BUG_ON(1);
+ }
+#ifdef ES_AGGRESSIVE_TEST
+ ext4_map_blocks_es_recheck(handle, inode, map,
+ &orig_map, flags);
+#endif
+ goto found;
+ }
+
/*
* Try to see if we can get the block without requesting a new
* file system block.
@@ -527,20 +609,36 @@
retval = ext4_ind_map_blocks(handle, inode, map, flags &
EXT4_GET_BLOCKS_KEEP_SIZE);
}
+ if (retval > 0) {
+ int ret;
+ unsigned long long status;
+
+#ifdef ES_AGGRESSIVE_TEST
+ if (retval != map->m_len) {
+ printk("ES len assertation failed for inode: %lu "
+ "retval %d != map->m_len %d "
+ "in %s (lookup)\n", inode->i_ino, retval,
+ map->m_len, __func__);
+ }
+#endif
+
+ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+ if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
+ ext4_find_delalloc_range(inode, map->m_lblk,
+ map->m_lblk + map->m_len - 1))
+ status |= EXTENT_STATUS_DELAYED;
+ ret = ext4_es_insert_extent(inode, map->m_lblk,
+ map->m_len, map->m_pblk, status);
+ if (ret < 0)
+ retval = ret;
+ }
if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
up_read((&EXT4_I(inode)->i_data_sem));
+found:
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret;
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
- /* delayed alloc may be allocated by fallocate and
- * coverted to initialized by directIO.
- * we need to handle delayed extent here.
- */
- down_write((&EXT4_I(inode)->i_data_sem));
- goto delayed_mapped;
- }
- ret = check_block_validity(inode, map);
+ int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
@@ -560,16 +658,10 @@
return retval;
/*
- * When we call get_blocks without the create flag, the
- * BH_Unwritten flag could have gotten set if the blocks
- * requested were part of a uninitialized extent. We need to
- * clear this flag now that we are committed to convert all or
- * part of the uninitialized extent to be an initialized
- * extent. This is because we need to avoid the combination
- * of BH_Unwritten and BH_Mapped flags being simultaneously
- * set on the buffer_head.
+ * Here we clear m_flags because after allocating an new extent,
+ * it will be set again.
*/
- map->m_flags &= ~EXT4_MAP_UNWRITTEN;
+ map->m_flags &= ~EXT4_MAP_FLAGS;
/*
* New blocks allocate and/or writing to uninitialized extent
@@ -615,20 +707,44 @@
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
- if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret;
-delayed_mapped:
- /* delayed allocation blocks has been allocated */
- ret = ext4_es_remove_extent(inode, map->m_lblk,
- map->m_len);
- if (ret < 0)
- retval = ret;
+ if (retval > 0) {
+ int ret;
+ unsigned long long status;
+
+#ifdef ES_AGGRESSIVE_TEST
+ if (retval != map->m_len) {
+ printk("ES len assertation failed for inode: %lu "
+ "retval %d != map->m_len %d "
+ "in %s (allocation)\n", inode->i_ino, retval,
+ map->m_len, __func__);
}
+#endif
+
+ /*
+ * If the extent has been zeroed out, we don't need to update
+ * extent status tree.
+ */
+ if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
+ ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ if (ext4_es_is_written(&es))
+ goto has_zeroout;
+ }
+ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+ if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
+ ext4_find_delalloc_range(inode, map->m_lblk,
+ map->m_lblk + map->m_len - 1))
+ status |= EXTENT_STATUS_DELAYED;
+ ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
+ if (ret < 0)
+ retval = ret;
}
+has_zeroout:
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
@@ -660,7 +776,8 @@
if (map.m_len > DIO_MAX_BLOCKS)
map.m_len = DIO_MAX_BLOCKS;
dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
- handle = ext4_journal_start(inode, dio_credits);
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
+ dio_credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
return ret;
@@ -707,14 +824,16 @@
/* ensure we send some value back into *errp */
*errp = 0;
+ if (create && err == 0)
+ err = -ENOSPC; /* should never happen */
if (err < 0)
*errp = err;
if (err <= 0)
return NULL;
bh = sb_getblk(inode->i_sb, map.m_pblk);
- if (!bh) {
- *errp = -EIO;
+ if (unlikely(!bh)) {
+ *errp = -ENOMEM;
return NULL;
}
if (map.m_flags & EXT4_MAP_NEW) {
@@ -808,11 +927,10 @@
* and the commit_write(). So doing the jbd2_journal_start at the start of
* prepare_write() is the right place.
*
- * Also, this function can nest inside ext4_writepage() ->
- * block_write_full_page(). In that case, we *know* that ext4_writepage()
- * has generated enough buffer credits to do the whole page. So we won't
- * block on the journal in that case, which is good, because the caller may
- * be PF_MEMALLOC.
+ * Also, this function can nest inside ext4_writepage(). In that case, we
+ * *know* that ext4_writepage() has generated enough buffer credits to do the
+ * whole page. So we won't block on the journal in that case, which is good,
+ * because the caller may be PF_MEMALLOC.
*
* By accident, ext4 can be reentered when a transaction is open via
* quota file writes. If we were to commit the transaction while thus
@@ -878,32 +996,40 @@
ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
flags, pagep);
if (ret < 0)
- goto out;
- if (ret == 1) {
- ret = 0;
- goto out;
- }
+ return ret;
+ if (ret == 1)
+ return 0;
}
-retry:
- handle = ext4_journal_start(inode, needed_blocks);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
-
- /* We cannot recurse into the filesystem as the transaction is already
- * started */
- flags |= AOP_FLAG_NOFS;
-
+ /*
+ * grab_cache_page_write_begin() can take a long time if the
+ * system is thrashing due to memory pressure, or if the page
+ * is being written back. So grab it first before we start
+ * the transaction handle. This also allows us to allocate
+ * the page (if needed) without using GFP_NOFS.
+ */
+retry_grab:
page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page) {
- ext4_journal_stop(handle);
- ret = -ENOMEM;
- goto out;
+ if (!page)
+ return -ENOMEM;
+ unlock_page(page);
+
+retry_journal:
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
+ if (IS_ERR(handle)) {
+ page_cache_release(page);
+ return PTR_ERR(handle);
}
- *pagep = page;
+ lock_page(page);
+ if (page->mapping != mapping) {
+ /* The page got truncated from under us */
+ unlock_page(page);
+ page_cache_release(page);
+ ext4_journal_stop(handle);
+ goto retry_grab;
+ }
+ wait_on_page_writeback(page);
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len, ext4_get_block_write);
@@ -918,7 +1044,6 @@
if (ret) {
unlock_page(page);
- page_cache_release(page);
/*
* __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
@@ -942,11 +1067,14 @@
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
- }
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-out:
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry_journal;
+ page_cache_release(page);
+ return ret;
+ }
+ *pagep = page;
return ret;
}
@@ -1178,6 +1306,55 @@
}
/*
+ * Reserve a metadata for a single block located at lblock
+ */
+static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
+{
+ int retries = 0;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int md_needed;
+ ext4_lblk_t save_last_lblock;
+ int save_len;
+
+ /*
+ * recalculate the amount of metadata blocks to reserve
+ * in order to allocate nrblocks
+ * worse case is one extent per block
+ */
+repeat:
+ spin_lock(&ei->i_block_reservation_lock);
+ /*
+ * ext4_calc_metadata_amount() has side effects, which we have
+ * to be prepared undo if we fail to claim space.
+ */
+ save_len = ei->i_da_metadata_calc_len;
+ save_last_lblock = ei->i_da_metadata_calc_last_lblock;
+ md_needed = EXT4_NUM_B2C(sbi,
+ ext4_calc_metadata_amount(inode, lblock));
+ trace_ext4_da_reserve_space(inode, md_needed);
+
+ /*
+ * We do still charge estimated metadata to the sb though;
+ * we cannot afford to run out of free blocks.
+ */
+ if (ext4_claim_free_clusters(sbi, md_needed, 0)) {
+ ei->i_da_metadata_calc_len = save_len;
+ ei->i_da_metadata_calc_last_lblock = save_last_lblock;
+ spin_unlock(&ei->i_block_reservation_lock);
+ if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+ cond_resched();
+ goto repeat;
+ }
+ return -ENOSPC;
+ }
+ ei->i_reserved_meta_blocks += md_needed;
+ spin_unlock(&ei->i_block_reservation_lock);
+
+ return 0; /* success */
+}
+
+/*
* Reserve a single cluster located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
@@ -1225,7 +1402,7 @@
ei->i_da_metadata_calc_last_lblock = save_last_lblock;
spin_unlock(&ei->i_block_reservation_lock);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
- yield();
+ cond_resched();
goto repeat;
}
dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
@@ -1256,7 +1433,7 @@
* function is called from invalidate page, it's
* harmless to return without any action.
*/
- ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+ ext4_warning(inode->i_sb, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
@@ -1357,7 +1534,6 @@
loff_t size = i_size_read(inode);
unsigned int len, block_start;
struct buffer_head *bh, *page_bufs = NULL;
- int journal_data = ext4_should_journal_data(inode);
sector_t pblock = 0, cur_logical = 0;
struct ext4_io_submit io_submit;
@@ -1378,7 +1554,7 @@
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
- int commit_write = 0, skip_page = 0;
+ int skip_page = 0;
struct page *page = pvec.pages[i];
index = page->index;
@@ -1400,27 +1576,9 @@
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
- /*
- * If the page does not have buffers (for
- * whatever reason), try to create them using
- * __block_write_begin. If this fails,
- * skip the page and move on.
- */
- if (!page_has_buffers(page)) {
- if (__block_write_begin(page, 0, len,
- noalloc_get_block_write)) {
- skip_page:
- unlock_page(page);
- continue;
- }
- commit_write = 1;
- }
-
bh = page_bufs = page_buffers(page);
block_start = 0;
do {
- if (!bh)
- goto skip_page;
if (map && (cur_logical >= map->m_lblk) &&
(cur_logical <= (map->m_lblk +
(map->m_len - 1)))) {
@@ -1448,33 +1606,14 @@
pblock++;
} while (bh != page_bufs);
- if (skip_page)
- goto skip_page;
-
- if (commit_write)
- /* mark the buffer_heads as dirty & uptodate */
- block_commit_write(page, 0, len);
+ if (skip_page) {
+ unlock_page(page);
+ continue;
+ }
clear_page_dirty_for_io(page);
- /*
- * Delalloc doesn't support data journalling,
- * but eventually maybe we'll lift this
- * restriction.
- */
- if (unlikely(journal_data && PageChecked(page)))
- err = __ext4_journalled_writepage(page, len);
- else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
- err = ext4_bio_write_page(&io_submit, page,
- len, mpd->wbc);
- else if (buffer_uninit(page_bufs)) {
- ext4_set_bh_endio(page_bufs, inode);
- err = block_write_full_page_endio(page,
- noalloc_get_block_write,
- mpd->wbc, ext4_end_io_buffer_write);
- } else
- err = block_write_full_page(page,
- noalloc_get_block_write, mpd->wbc);
-
+ err = ext4_bio_write_page(&io_submit, page, len,
+ mpd->wbc);
if (!err)
mpd->pages_written++;
/*
@@ -1640,7 +1779,7 @@
(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");
+ "This should not happen!! Data will be lost");
if (err == -ENOSPC)
ext4_print_free_blocks(mpd->inode);
}
@@ -1690,16 +1829,16 @@
*
* @mpd->lbh - extent of blocks
* @logical - logical number of the block in the file
- * @bh - bh of the block (used to access block's state)
+ * @b_state - b_state of the buffer head added
*
* the function is used to collect contig. blocks in same state
*/
-static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
- sector_t logical, size_t b_size,
+static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, sector_t logical,
unsigned long b_state)
{
sector_t next;
- int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
+ int blkbits = mpd->inode->i_blkbits;
+ int nrblocks = mpd->b_size >> blkbits;
/*
* XXX Don't go larger than mballoc is willing to allocate
@@ -1707,11 +1846,11 @@
* mpage_da_submit_io() into this function and then call
* ext4_map_blocks() multiple times in a loop
*/
- if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
+ if (nrblocks >= (8*1024*1024 >> blkbits))
goto flush_it;
- /* check if thereserved journal credits might overflow */
- if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
+ /* check if the reserved journal credits might overflow */
+ if (!ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS)) {
if (nrblocks >= EXT4_MAX_TRANS_DATA) {
/*
* With non-extent format we are limited by the journal
@@ -1720,16 +1859,6 @@
* nrblocks. So limit nrblocks.
*/
goto flush_it;
- } else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) >
- EXT4_MAX_TRANS_DATA) {
- /*
- * Adding the new buffer_head would make it cross the
- * allowed limit for which we have journal credit
- * reserved. So limit the new bh->b_size
- */
- b_size = (EXT4_MAX_TRANS_DATA - nrblocks) <<
- mpd->inode->i_blkbits;
- /* we will do mpage_da_submit_io in the next loop */
}
}
/*
@@ -1737,7 +1866,7 @@
*/
if (mpd->b_size == 0) {
mpd->b_blocknr = logical;
- mpd->b_size = b_size;
+ mpd->b_size = 1 << blkbits;
mpd->b_state = b_state & BH_FLAGS;
return;
}
@@ -1747,7 +1876,7 @@
* Can we merge the block to our big extent?
*/
if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) {
- mpd->b_size += b_size;
+ mpd->b_size += 1 << blkbits;
return;
}
@@ -1775,8 +1904,14 @@
struct ext4_map_blocks *map,
struct buffer_head *bh)
{
+ struct extent_status es;
int retval;
sector_t invalid_block = ~((sector_t) 0xffff);
+#ifdef ES_AGGRESSIVE_TEST
+ struct ext4_map_blocks orig_map;
+
+ memcpy(&orig_map, map, sizeof(*map));
+#endif
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~0;
@@ -1785,6 +1920,45 @@
ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
"logical block %lu\n", inode->i_ino, map->m_len,
(unsigned long) map->m_lblk);
+
+ /* Lookup extent status tree firstly */
+ if (ext4_es_lookup_extent(inode, iblock, &es)) {
+
+ if (ext4_es_is_hole(&es)) {
+ retval = 0;
+ down_read((&EXT4_I(inode)->i_data_sem));
+ goto add_delayed;
+ }
+
+ /*
+ * Delayed extent could be allocated by fallocate.
+ * So we need to check it.
+ */
+ if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ return 0;
+ }
+
+ map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
+ retval = es.es_len - (iblock - es.es_lblk);
+ if (retval > map->m_len)
+ retval = map->m_len;
+ map->m_len = retval;
+ if (ext4_es_is_written(&es))
+ map->m_flags |= EXT4_MAP_MAPPED;
+ else if (ext4_es_is_unwritten(&es))
+ map->m_flags |= EXT4_MAP_UNWRITTEN;
+ else
+ BUG_ON(1);
+
+#ifdef ES_AGGRESSIVE_TEST
+ ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
+#endif
+ return retval;
+ }
+
/*
* Try to see if we can get the block without requesting a new
* file system block.
@@ -1803,27 +1977,46 @@
map->m_flags |= EXT4_MAP_FROM_CLUSTER;
retval = 0;
} else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+ retval = ext4_ext_map_blocks(NULL, inode, map,
+ EXT4_GET_BLOCKS_NO_PUT_HOLE);
else
- retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+ retval = ext4_ind_map_blocks(NULL, inode, map,
+ EXT4_GET_BLOCKS_NO_PUT_HOLE);
+add_delayed:
if (retval == 0) {
+ int ret;
/*
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
- /* If the block was allocated from previously allocated cluster,
- * then we dont need to reserve it again. */
+ /*
+ * If the block was allocated from previously allocated cluster,
+ * then we don't need to reserve it again. However we still need
+ * to reserve metadata for every block we're going to write.
+ */
if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
- retval = ext4_da_reserve_space(inode, iblock);
- if (retval)
+ ret = ext4_da_reserve_space(inode, iblock);
+ if (ret) {
/* not enough space to reserve */
+ retval = ret;
goto out_unlock;
+ }
+ } else {
+ ret = ext4_da_reserve_metadata(inode, iblock);
+ if (ret) {
+ /* not enough space to reserve */
+ retval = ret;
+ goto out_unlock;
+ }
}
- retval = ext4_es_insert_extent(inode, map->m_lblk, map->m_len);
- if (retval)
+ ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ ~0, EXTENT_STATUS_DELAYED);
+ if (ret) {
+ retval = ret;
goto out_unlock;
+ }
/* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
* and it should not appear on the bh->b_state.
@@ -1833,6 +2026,25 @@
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
+ } else if (retval > 0) {
+ int ret;
+ unsigned long long status;
+
+#ifdef ES_AGGRESSIVE_TEST
+ if (retval != map->m_len) {
+ printk("ES len assertation failed for inode: %lu "
+ "retval %d != map->m_len %d "
+ "in %s (lookup)\n", inode->i_ino, retval,
+ map->m_len, __func__);
+ }
+#endif
+
+ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+ ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
+ if (ret != 0)
+ retval = ret;
}
out_unlock:
@@ -1890,27 +2102,6 @@
return 0;
}
-/*
- * 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_write_begin() 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 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)
-{
- BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
- return _ext4_get_block(inode, iblock, bh_result, 0);
-}
-
static int bget_one(handle_t *handle, struct buffer_head *bh)
{
get_bh(bh);
@@ -1955,7 +2146,8 @@
* references to buffers so we are safe */
unlock_page(page);
- handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
@@ -2035,11 +2227,12 @@
static int ext4_writepage(struct page *page,
struct writeback_control *wbc)
{
- int ret = 0, commit_write = 0;
+ int ret = 0;
loff_t size;
unsigned int len;
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
+ struct ext4_io_submit io_submit;
trace_ext4_writepage(page);
size = i_size_read(inode);
@@ -2048,39 +2241,29 @@
else
len = PAGE_CACHE_SIZE;
+ page_bufs = page_buffers(page);
/*
- * If the page does not have buffers (for whatever reason),
- * try to create them using __block_write_begin. If this
- * fails, redirty the page and move on.
+ * We cannot do block allocation or other extent handling in this
+ * function. If there are buffers needing that, we have to redirty
+ * the page. But we may reach here when we do a journal commit via
+ * journal_submit_inode_data_buffers() and in that case we must write
+ * allocated buffers to achieve data=ordered mode guarantees.
*/
- if (!page_has_buffers(page)) {
- if (__block_write_begin(page, 0, len,
- noalloc_get_block_write)) {
- redirty_page:
- redirty_page_for_writepage(wbc, page);
+ if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL,
+ ext4_bh_delay_or_unwritten)) {
+ redirty_page_for_writepage(wbc, page);
+ if (current->flags & PF_MEMALLOC) {
+ /*
+ * For memory cleaning there's no point in writing only
+ * some buffers. So just bail out. Warn if we came here
+ * from direct reclaim.
+ */
+ WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD))
+ == PF_MEMALLOC);
unlock_page(page);
return 0;
}
- commit_write = 1;
}
- page_bufs = page_buffers(page);
- if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL,
- ext4_bh_delay_or_unwritten)) {
- /*
- * We don't want to do block allocation, so redirty
- * the page and return. We may reach here when we do
- * a journal commit via journal_submit_inode_data_buffers.
- * We can also reach here via shrink_page_list but it
- * should never be for direct reclaim so warn if that
- * happens
- */
- WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
- PF_MEMALLOC);
- goto redirty_page;
- }
- if (commit_write)
- /* now mark the buffer_heads as dirty and uptodate */
- block_commit_write(page, 0, len);
if (PageChecked(page) && ext4_should_journal_data(inode))
/*
@@ -2089,14 +2272,9 @@
*/
return __ext4_journalled_writepage(page, len);
- if (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);
- } else
- ret = block_write_full_page(page, noalloc_get_block_write,
- wbc);
-
+ memset(&io_submit, 0, sizeof(io_submit));
+ ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+ ext4_io_submit(&io_submit);
return ret;
}
@@ -2228,51 +2406,38 @@
logical = (sector_t) page->index <<
(PAGE_CACHE_SHIFT - inode->i_blkbits);
- if (!page_has_buffers(page)) {
- mpage_add_bh_to_extent(mpd, logical,
- PAGE_CACHE_SIZE,
- (1 << BH_Dirty) | (1 << BH_Uptodate));
- if (mpd->io_done)
- goto ret_extent_tail;
- } else {
+ /* Add all dirty buffers to mpd */
+ head = page_buffers(page);
+ bh = head;
+ do {
+ BUG_ON(buffer_locked(bh));
/*
- * Page with regular buffer heads,
- * just add all dirty ones
+ * We need to try to allocate unmapped blocks
+ * in the same page. Otherwise we won't make
+ * progress with the page in ext4_writepage
*/
- head = page_buffers(page);
- bh = head;
- do {
- BUG_ON(buffer_locked(bh));
+ if (ext4_bh_delay_or_unwritten(NULL, bh)) {
+ mpage_add_bh_to_extent(mpd, logical,
+ bh->b_state);
+ if (mpd->io_done)
+ goto ret_extent_tail;
+ } else if (buffer_dirty(bh) &&
+ buffer_mapped(bh)) {
/*
- * We need to try to allocate
- * unmapped blocks in the same page.
- * Otherwise we won't make progress
- * with the page in ext4_writepage
+ * mapped dirty buffer. We need to
+ * update the b_state because we look
+ * at b_state in mpage_da_map_blocks.
+ * We don't update b_size because if we
+ * find an unmapped buffer_head later
+ * we need to use the b_state flag of
+ * that buffer_head.
*/
- if (ext4_bh_delay_or_unwritten(NULL, bh)) {
- mpage_add_bh_to_extent(mpd, logical,
- bh->b_size,
- bh->b_state);
- if (mpd->io_done)
- goto ret_extent_tail;
- } else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
- /*
- * mapped dirty buffer. We need
- * to update the b_state
- * because we look at b_state
- * in mpage_da_map_blocks. We
- * don't update b_size because
- * if we find an unmapped
- * buffer_head later we need to
- * use the b_state flag of that
- * buffer_head.
- */
- if (mpd->b_size == 0)
- mpd->b_state = bh->b_state & BH_FLAGS;
- }
- logical++;
- } while ((bh = bh->b_this_page) != head);
- }
+ if (mpd->b_size == 0)
+ mpd->b_state =
+ bh->b_state & BH_FLAGS;
+ }
+ logical++;
+ } while ((bh = bh->b_this_page) != head);
if (nr_to_write > 0) {
nr_to_write--;
@@ -2413,7 +2578,8 @@
needed_blocks = ext4_da_writepages_trans_blocks(inode);
/* start a new transaction*/
- handle = ext4_journal_start(inode, needed_blocks);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
@@ -2512,12 +2678,8 @@
/*
* Start pushing delalloc when 1/2 of free blocks are dirty.
*/
- if (dirty_blocks && (free_blocks < 2 * dirty_blocks) &&
- !writeback_in_progress(sb->s_bdi) &&
- down_read_trylock(&sb->s_umount)) {
- writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
- up_read(&sb->s_umount);
- }
+ if (dirty_blocks && (free_blocks < 2 * dirty_blocks))
+ try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE);
if (2 * free_blocks < 3 * dirty_blocks ||
free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
@@ -2555,42 +2717,52 @@
pos, len, flags,
pagep, fsdata);
if (ret < 0)
- goto out;
- if (ret == 1) {
- ret = 0;
- goto out;
- }
+ return ret;
+ if (ret == 1)
+ return 0;
}
-retry:
+ /*
+ * grab_cache_page_write_begin() can take a long time if the
+ * system is thrashing due to memory pressure, or if the page
+ * is being written back. So grab it first before we start
+ * the transaction handle. This also allows us to allocate
+ * the page (if needed) without using GFP_NOFS.
+ */
+retry_grab:
+ page = grab_cache_page_write_begin(mapping, index, flags);
+ if (!page)
+ return -ENOMEM;
+ unlock_page(page);
+
/*
* With delayed allocation, we don't log the i_disksize update
* if there is delayed block allocation. But we still need
* to journalling the i_disksize update if writes to the end
* of file which has an already mapped buffer.
*/
- handle = ext4_journal_start(inode, 1);
+retry_journal:
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
+ page_cache_release(page);
+ return PTR_ERR(handle);
}
- /* We cannot recurse into the filesystem as the transaction is already
- * started */
- flags |= AOP_FLAG_NOFS;
- page = grab_cache_page_write_begin(mapping, index, flags);
- if (!page) {
+ lock_page(page);
+ if (page->mapping != mapping) {
+ /* The page got truncated from under us */
+ unlock_page(page);
+ page_cache_release(page);
ext4_journal_stop(handle);
- ret = -ENOMEM;
- goto out;
+ goto retry_grab;
}
- *pagep = page;
+ /* In case writeback began while the page was unlocked */
+ wait_on_page_writeback(page);
ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
if (ret < 0) {
unlock_page(page);
ext4_journal_stop(handle);
- page_cache_release(page);
/*
* block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
@@ -2598,11 +2770,16 @@
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
+
+ if (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry_journal;
+
+ page_cache_release(page);
+ return ret;
}
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-out:
+ *pagep = page;
return ret;
}
@@ -2858,36 +3035,10 @@
return mpage_readpages(mapping, pages, nr_pages, ext4_get_block);
}
-static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offset)
-{
- struct buffer_head *head, *bh;
- unsigned int curr_off = 0;
-
- if (!page_has_buffers(page))
- return;
- head = bh = page_buffers(page);
- do {
- if (offset <= curr_off && test_clear_buffer_uninit(bh)
- && bh->b_private) {
- ext4_free_io_end(bh->b_private);
- bh->b_private = NULL;
- bh->b_end_io = NULL;
- }
- curr_off = curr_off + bh->b_size;
- bh = bh->b_this_page;
- } while (bh != head);
-}
-
static void ext4_invalidatepage(struct page *page, unsigned long offset)
{
trace_ext4_invalidatepage(page, offset);
- /*
- * free any io_end structure allocated for buffers to be discarded
- */
- if (ext4_should_dioread_nolock(page->mapping->host))
- ext4_invalidatepage_free_endio(page, offset);
-
/* No journalling happens on data buffers when this function is used */
WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page)));
@@ -2923,8 +3074,8 @@
trace_ext4_releasepage(page);
- WARN_ON(PageChecked(page));
- if (!page_has_buffers(page))
+ /* Page has dirty journalled data -> cannot release */
+ if (PageChecked(page))
return 0;
if (journal)
return jbd2_journal_try_to_free_buffers(journal, page, wait);
@@ -2959,7 +3110,7 @@
ssize_t size, void *private, int ret,
bool is_async)
{
- struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(iocb->ki_filp);
ext4_io_end_t *io_end = iocb->private;
/* if not async direct IO or dio with 0 bytes write, just return */
@@ -2977,9 +3128,9 @@
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
out:
+ inode_dio_done(inode);
if (is_async)
aio_complete(iocb, ret, 0);
- inode_dio_done(inode);
return;
}
@@ -2993,65 +3144,6 @@
ext4_add_complete_io(io_end);
}
-static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
-{
- ext4_io_end_t *io_end = bh->b_private;
- struct inode *inode;
-
- if (!test_clear_buffer_uninit(bh) || !io_end)
- goto out;
-
- if (!(io_end->inode->i_sb->s_flags & MS_ACTIVE)) {
- ext4_msg(io_end->inode->i_sb, KERN_INFO,
- "sb umounted, discard end_io request for inode %lu",
- io_end->inode->i_ino);
- ext4_free_io_end(io_end);
- goto out;
- }
-
- /*
- * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
- * but being more careful is always safe for the future change.
- */
- inode = io_end->inode;
- ext4_set_io_unwritten_flag(inode, io_end);
- ext4_add_complete_io(io_end);
-out:
- bh->b_private = NULL;
- bh->b_end_io = NULL;
- clear_buffer_uninit(bh);
- end_buffer_async_write(bh, uptodate);
-}
-
-static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode)
-{
- ext4_io_end_t *io_end;
- struct page *page = bh->b_page;
- loff_t offset = (sector_t)page->index << PAGE_CACHE_SHIFT;
- size_t size = bh->b_size;
-
-retry:
- io_end = ext4_init_io_end(inode, GFP_ATOMIC);
- if (!io_end) {
- pr_warn_ratelimited("%s: allocation fail\n", __func__);
- schedule();
- goto retry;
- }
- io_end->offset = offset;
- io_end->size = size;
- /*
- * We need to hold a reference to the page to make sure it
- * doesn't get evicted before ext4_end_io_work() has a chance
- * to convert the extent from written to unwritten.
- */
- io_end->page = page;
- get_page(io_end->page);
-
- bh->b_private = io_end;
- bh->b_end_io = ext4_end_io_buffer_write;
- return 0;
-}
-
/*
* For ext4 extent files, ext4 will do direct-io write to holes,
* preallocated extents, and those write extend the file, no need to
@@ -3553,20 +3645,20 @@
int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
if (!S_ISREG(inode->i_mode))
return -EOPNOTSUPP;
- if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- /* TODO: Add support for non extent hole punching */
- return -EOPNOTSUPP;
- }
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return ext4_ind_punch_hole(file, offset, length);
if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
/* TODO: Add support for bigalloc file systems */
return -EOPNOTSUPP;
}
+ trace_ext4_punch_hole(inode, offset, length);
+
return ext4_ext_punch_hole(file, offset, length);
}
@@ -3660,11 +3752,8 @@
iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
bh = sb_getblk(sb, block);
- if (!bh) {
- EXT4_ERROR_INODE_BLOCK(inode, block,
- "unable to read itable block");
- return -EIO;
- }
+ if (unlikely(!bh))
+ return -ENOMEM;
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
@@ -3696,7 +3785,7 @@
/* Is the inode bitmap in cache? */
bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp));
- if (!bitmap_bh)
+ if (unlikely(!bitmap_bh))
goto make_io;
/*
@@ -4404,8 +4493,9 @@
/* (user+group)*(old+new) structure, inode write (sb,
* inode block, ? - but truncate inode update has it) */
- handle = ext4_journal_start(inode, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)+
- EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb))+3);
+ handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
+ (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) +
+ EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)) + 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
@@ -4440,7 +4530,7 @@
(attr->ia_size < inode->i_size)) {
handle_t *handle;
- handle = ext4_journal_start(inode, 3);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto err_out;
@@ -4460,7 +4550,8 @@
attr->ia_size);
if (error) {
/* Do as much error cleanup as possible */
- handle = ext4_journal_start(inode, 3);
+ handle = ext4_journal_start(inode,
+ EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
ext4_orphan_del(NULL, inode);
goto err_out;
@@ -4801,7 +4892,7 @@
{
handle_t *handle;
- handle = ext4_journal_start(inode, 2);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle))
goto out;
@@ -4902,7 +4993,7 @@
/* Finally we can mark the inode as dirty. */
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -4926,7 +5017,7 @@
unsigned long len;
int ret;
struct file *file = vma->vm_file;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
handle_t *handle;
get_block_t *get_block;
@@ -4968,7 +5059,7 @@
0, len, NULL,
ext4_bh_unmapped)) {
/* Wait so that we don't change page under IO */
- wait_on_page_writeback(page);
+ wait_for_stable_page(page);
ret = VM_FAULT_LOCKED;
goto out;
}
@@ -4980,7 +5071,8 @@
else
get_block = ext4_get_block;
retry_alloc:
- handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = VM_FAULT_SIGBUS;
goto out;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5747f52..721f4d3 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -22,7 +22,7 @@
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
@@ -104,7 +104,7 @@
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
@@ -173,7 +173,7 @@
}
mutex_lock(&inode->i_mutex);
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
@@ -313,6 +313,9 @@
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
+ if (!err && ext4_has_group_desc_csum(sb) &&
+ test_opt(sb, INIT_INODE_TABLE))
+ err = ext4_register_li_request(sb, input.group);
group_add_out:
ext4_resize_end(sb);
return err;
@@ -358,6 +361,7 @@
ext4_fsblk_t n_blocks_count;
struct super_block *sb = inode->i_sb;
int err = 0, err2 = 0;
+ ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
@@ -388,6 +392,11 @@
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
+ if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
+ ext4_has_group_desc_csum(sb) &&
+ test_opt(sb, INIT_INODE_TABLE))
+ err = ext4_register_li_request(sb, o_group);
+
resizefs_out:
ext4_resize_end(sb);
return err;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 1bf6fe7..ee6614b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -23,11 +23,18 @@
#include "ext4_jbd2.h"
#include "mballoc.h"
-#include <linux/debugfs.h>
#include <linux/log2.h>
+#include <linux/module.h>
#include <linux/slab.h>
#include <trace/events/ext4.h>
+#ifdef CONFIG_EXT4_DEBUG
+ushort ext4_mballoc_debug __read_mostly;
+
+module_param_named(mballoc_debug, ext4_mballoc_debug, ushort, 0644);
+MODULE_PARM_DESC(mballoc_debug, "Debugging level for ext4's mballoc");
+#endif
+
/*
* MUSTDO:
* - test ext4_ext_search_left() and ext4_ext_search_right()
@@ -1884,15 +1891,19 @@
case 0:
BUG_ON(ac->ac_2order == 0);
- if (grp->bb_largest_free_order < ac->ac_2order)
- return 0;
-
/* Avoid using the first bg of a flexgroup for data files */
if ((ac->ac_flags & EXT4_MB_HINT_DATA) &&
(flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) &&
((group % flex_size) == 0))
return 0;
+ if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) ||
+ (free / fragments) >= ac->ac_g_ex.fe_len)
+ return 1;
+
+ if (grp->bb_largest_free_order < ac->ac_2order)
+ return 0;
+
return 1;
case 1:
if ((free / fragments) >= ac->ac_g_ex.fe_len)
@@ -2007,7 +2018,7 @@
}
ac->ac_groups_scanned++;
- if (cr == 0)
+ if (cr == 0 && ac->ac_2order < sb->s_blocksize_bits+2)
ext4_mb_simple_scan_group(ac, &e4b);
else if (cr == 1 && sbi->s_stripe &&
!(ac->ac_g_ex.fe_len % sbi->s_stripe))
@@ -2656,40 +2667,6 @@
mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
}
-#ifdef CONFIG_EXT4_DEBUG
-u8 mb_enable_debug __read_mostly;
-
-static struct dentry *debugfs_dir;
-static struct dentry *debugfs_debug;
-
-static void __init ext4_create_debugfs_entry(void)
-{
- debugfs_dir = debugfs_create_dir("ext4", NULL);
- if (debugfs_dir)
- debugfs_debug = debugfs_create_u8("mballoc-debug",
- S_IRUGO | S_IWUSR,
- debugfs_dir,
- &mb_enable_debug);
-}
-
-static void ext4_remove_debugfs_entry(void)
-{
- debugfs_remove(debugfs_debug);
- debugfs_remove(debugfs_dir);
-}
-
-#else
-
-static void __init ext4_create_debugfs_entry(void)
-{
-}
-
-static void ext4_remove_debugfs_entry(void)
-{
-}
-
-#endif
-
int __init ext4_init_mballoc(void)
{
ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space,
@@ -2711,7 +2688,6 @@
kmem_cache_destroy(ext4_ac_cachep);
return -ENOMEM;
}
- ext4_create_debugfs_entry();
return 0;
}
@@ -2726,7 +2702,6 @@
kmem_cache_destroy(ext4_ac_cachep);
kmem_cache_destroy(ext4_free_data_cachep);
ext4_groupinfo_destroy_slabs();
- ext4_remove_debugfs_entry();
}
@@ -2829,8 +2804,8 @@
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi,
ac->ac_b_ex.fe_group);
- atomic_sub(ac->ac_b_ex.fe_len,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_sub(ac->ac_b_ex.fe_len,
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
@@ -3444,7 +3419,7 @@
win = offs;
ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
- EXT4_B2C(sbi, win);
+ EXT4_NUM_B2C(sbi, win);
BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
}
@@ -3717,11 +3692,7 @@
if (free < needed && busy) {
busy = 0;
ext4_unlock_group(sb, group);
- /*
- * Yield the CPU here so that we don't get soft lockup
- * in non preempt case.
- */
- yield();
+ cond_resched();
goto repeat;
}
@@ -3872,7 +3843,7 @@
struct super_block *sb = ac->ac_sb;
ext4_group_t ngroups, i;
- if (!mb_enable_debug ||
+ if (!ext4_mballoc_debug ||
(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
return;
@@ -4005,8 +3976,8 @@
len = ar->len;
/* just a dirty hack to filter too big requests */
- if (len >= EXT4_CLUSTERS_PER_GROUP(sb) - 10)
- len = EXT4_CLUSTERS_PER_GROUP(sb) - 10;
+ if (len >= EXT4_CLUSTERS_PER_GROUP(sb))
+ len = EXT4_CLUSTERS_PER_GROUP(sb);
/* start searching from the goal */
goal = ar->goal;
@@ -4136,7 +4107,7 @@
/* The max size of hash table is PREALLOC_TB_SIZE */
order = PREALLOC_TB_SIZE - 1;
/* Add the prealloc space to lg */
- rcu_read_lock();
+ spin_lock(&lg->lg_prealloc_lock);
list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order],
pa_inode_list) {
spin_lock(&tmp_pa->pa_lock);
@@ -4160,12 +4131,12 @@
if (!added)
list_add_tail_rcu(&pa->pa_inode_list,
&lg->lg_prealloc_list[order]);
- rcu_read_unlock();
+ spin_unlock(&lg->lg_prealloc_lock);
/* Now trim the list to be not more than 8 elements */
if (lg_prealloc_count > 8) {
ext4_mb_discard_lg_preallocations(sb, lg,
- order, lg_prealloc_count);
+ order, lg_prealloc_count);
return;
}
return ;
@@ -4271,7 +4242,7 @@
ext4_claim_free_clusters(sbi, ar->len, ar->flags)) {
/* let others to free the space */
- yield();
+ cond_resched();
ar->len = ar->len >> 1;
}
if (!ar->len) {
@@ -4489,7 +4460,6 @@
struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
struct ext4_group_desc *gdp;
- unsigned long freed = 0;
unsigned int overflow;
ext4_grpblk_t bit;
struct buffer_head *gd_bh;
@@ -4590,7 +4560,7 @@
EXT4_BLOCKS_PER_GROUP(sb);
count -= overflow;
}
- count_clusters = EXT4_B2C(sbi, count);
+ count_clusters = EXT4_NUM_B2C(sbi, count);
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh) {
err = -EIO;
@@ -4691,14 +4661,12 @@
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(count_clusters,
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(count_clusters,
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
- freed += count;
-
if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
@@ -4832,12 +4800,12 @@
ext4_group_desc_csum_set(sb, block_group, desc);
ext4_unlock_group(sb, block_group);
percpu_counter_add(&sbi->s_freeclusters_counter,
- EXT4_B2C(sbi, blocks_freed));
+ EXT4_NUM_B2C(sbi, blocks_freed));
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic_add(EXT4_B2C(sbi, blocks_freed),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(EXT4_NUM_B2C(sbi, blocks_freed),
+ &sbi->s_flex_groups[flex_group].free_clusters);
}
ext4_mb_unload_buddy(&e4b);
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 3ccd889..08481ee 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -37,11 +37,11 @@
/*
*/
#ifdef CONFIG_EXT4_DEBUG
-extern u8 mb_enable_debug;
+extern ushort ext4_mballoc_debug;
#define mb_debug(n, fmt, a...) \
do { \
- if ((n) <= mb_enable_debug) { \
+ if ((n) <= ext4_mballoc_debug) { \
printk(KERN_DEBUG "(%s, %d): %s: ", \
__FILE__, __LINE__, __func__); \
printk(fmt, ## a); \
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index db8226d..480acf4 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -456,11 +456,14 @@
*/
return retval;
- handle = ext4_journal_start(inode,
- EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
- + 1);
+ /*
+ * Worst case we can touch the allocation bitmaps, a bgd
+ * block, and a block to link in the orphan list. We do need
+ * need to worry about credits for modifying the quota inode.
+ */
+ handle = ext4_journal_start(inode, EXT4_HT_MIGRATE,
+ 4 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));
+
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
return retval;
@@ -507,7 +510,7 @@
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle)) {
/*
* It is impossible to update on-disk structures without
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index fe7c63f..f9b5515 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -80,6 +80,8 @@
* is not blocked in the elevator. */
if (!*bh)
*bh = sb_getblk(sb, mmp_block);
+ if (!*bh)
+ return -ENOMEM;
if (*bh) {
get_bh(*bh);
lock_buffer(*bh);
@@ -91,7 +93,7 @@
*bh = NULL;
}
}
- if (!*bh) {
+ if (unlikely(!*bh)) {
ext4_warning(sb, "Error while reading MMP block %llu",
mmp_block);
return -EIO;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index d9cc5ee..33e1c08 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -32,16 +32,18 @@
*/
static inline int
get_ext_path(struct inode *inode, ext4_lblk_t lblock,
- struct ext4_ext_path **path)
+ struct ext4_ext_path **orig_path)
{
int ret = 0;
+ struct ext4_ext_path *path;
- *path = ext4_ext_find_extent(inode, lblock, *path);
- if (IS_ERR(*path)) {
- ret = PTR_ERR(*path);
- *path = NULL;
- } else if ((*path)[ext_depth(inode)].p_ext == NULL)
+ path = ext4_ext_find_extent(inode, lblock, *orig_path);
+ if (IS_ERR(path))
+ ret = PTR_ERR(path);
+ else if (path[ext_depth(inode)].p_ext == NULL)
ret = -ENODATA;
+ else
+ *orig_path = path;
return ret;
}
@@ -611,24 +613,25 @@
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
+ int ret = 0;
ext4_lblk_t last = from + count;
while (from < last) {
*err = get_ext_path(inode, from, &path);
if (*err)
- return 0;
+ goto out;
ext = path[ext_depth(inode)].p_ext;
- if (!ext) {
- ext4_ext_drop_refs(path);
- return 0;
- }
- if (uninit != ext4_ext_is_uninitialized(ext)) {
- ext4_ext_drop_refs(path);
- return 0;
- }
+ if (uninit != ext4_ext_is_uninitialized(ext))
+ goto out;
from += ext4_ext_get_actual_len(ext);
ext4_ext_drop_refs(path);
}
- return 1;
+ ret = 1;
+out:
+ if (path) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ }
+ return ret;
}
/**
@@ -666,6 +669,14 @@
int replaced_count = 0;
int dext_alen;
+ *err = ext4_es_remove_extent(orig_inode, from, count);
+ if (*err)
+ goto out;
+
+ *err = ext4_es_remove_extent(donor_inode, from, count);
+ if (*err)
+ goto out;
+
/* Get the original extent for the block "orig_off" */
*err = get_ext_path(orig_inode, orig_off, &orig_path);
if (*err)
@@ -681,6 +692,8 @@
depth = ext_depth(donor_inode);
dext = donor_path[depth].p_ext;
+ if (unlikely(!dext))
+ goto missing_donor_extent;
tmp_dext = *dext;
*err = mext_calc_swap_extents(&tmp_dext, &tmp_oext, orig_off,
@@ -691,7 +704,8 @@
/* Loop for the donor extents */
while (1) {
/* The extent for donor must be found. */
- if (!dext) {
+ if (unlikely(!dext)) {
+ missing_donor_extent:
EXT4_ERROR_INODE(donor_inode,
"The extent for donor must be found");
*err = -EIO;
@@ -761,9 +775,6 @@
kfree(donor_path);
}
- ext4_ext_invalidate_cache(orig_inode);
- ext4_ext_invalidate_cache(donor_inode);
-
return replaced_count;
}
@@ -900,7 +911,7 @@
pgoff_t orig_page_offset, int data_offset_in_page,
int block_len_in_page, int uninit, int *err)
{
- struct inode *orig_inode = o_filp->f_dentry->d_inode;
+ struct inode *orig_inode = file_inode(o_filp);
struct page *pagep[2] = {NULL, NULL};
handle_t *handle;
ext4_lblk_t orig_blk_offset;
@@ -920,7 +931,7 @@
again:
*err = 0;
jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
- handle = ext4_journal_start(orig_inode, jblocks);
+ handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, jblocks);
if (IS_ERR(handle)) {
*err = PTR_ERR(handle);
return 0;
@@ -1279,8 +1290,8 @@
__u64 orig_start, __u64 donor_start, __u64 len,
__u64 *moved_len)
{
- struct inode *orig_inode = o_filp->f_dentry->d_inode;
- struct inode *donor_inode = d_filp->f_dentry->d_inode;
+ struct inode *orig_inode = file_inode(o_filp);
+ struct inode *donor_inode = file_inode(d_filp);
struct ext4_ext_path *orig_path = NULL, *holecheck_path = NULL;
struct ext4_extent *ext_prev, *ext_cur, *ext_dummy;
ext4_lblk_t block_start = orig_start;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f9ed946..3825d6a 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -47,38 +47,111 @@
#define NAMEI_RA_CHUNKS 2
#define NAMEI_RA_BLOCKS 4
#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
-#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
static struct buffer_head *ext4_append(handle_t *handle,
struct inode *inode,
- ext4_lblk_t *block, int *err)
+ ext4_lblk_t *block)
{
struct buffer_head *bh;
+ int err = 0;
if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb &&
((inode->i_size >> 10) >=
- EXT4_SB(inode->i_sb)->s_max_dir_size_kb))) {
- *err = -ENOSPC;
- return NULL;
- }
+ EXT4_SB(inode->i_sb)->s_max_dir_size_kb)))
+ return ERR_PTR(-ENOSPC);
*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
- bh = ext4_bread(handle, inode, *block, 1, err);
- if (bh) {
- inode->i_size += inode->i_sb->s_blocksize;
- EXT4_I(inode)->i_disksize = inode->i_size;
- *err = ext4_journal_get_write_access(handle, bh);
- if (*err) {
+ bh = ext4_bread(handle, inode, *block, 1, &err);
+ if (!bh)
+ return ERR_PTR(err);
+ inode->i_size += inode->i_sb->s_blocksize;
+ EXT4_I(inode)->i_disksize = inode->i_size;
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err) {
+ brelse(bh);
+ ext4_std_error(inode->i_sb, err);
+ return ERR_PTR(err);
+ }
+ return bh;
+}
+
+static int ext4_dx_csum_verify(struct inode *inode,
+ struct ext4_dir_entry *dirent);
+
+typedef enum {
+ EITHER, INDEX, DIRENT
+} dirblock_type_t;
+
+#define ext4_read_dirblock(inode, block, type) \
+ __ext4_read_dirblock((inode), (block), (type), __LINE__)
+
+static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
+ ext4_lblk_t block,
+ dirblock_type_t type,
+ unsigned int line)
+{
+ struct buffer_head *bh;
+ struct ext4_dir_entry *dirent;
+ int err = 0, is_dx_block = 0;
+
+ bh = ext4_bread(NULL, inode, block, 0, &err);
+ if (!bh) {
+ if (err == 0) {
+ ext4_error_inode(inode, __func__, line, block,
+ "Directory hole found");
+ return ERR_PTR(-EIO);
+ }
+ __ext4_warning(inode->i_sb, __func__, line,
+ "error reading directory block "
+ "(ino %lu, block %lu)", inode->i_ino,
+ (unsigned long) block);
+ return ERR_PTR(err);
+ }
+ dirent = (struct ext4_dir_entry *) bh->b_data;
+ /* Determine whether or not we have an index block */
+ if (is_dx(inode)) {
+ if (block == 0)
+ is_dx_block = 1;
+ else if (ext4_rec_len_from_disk(dirent->rec_len,
+ inode->i_sb->s_blocksize) ==
+ inode->i_sb->s_blocksize)
+ is_dx_block = 1;
+ }
+ if (!is_dx_block && type == INDEX) {
+ ext4_error_inode(inode, __func__, line, block,
+ "directory leaf block found instead of index block");
+ return ERR_PTR(-EIO);
+ }
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) ||
+ buffer_verified(bh))
+ return bh;
+
+ /*
+ * An empty leaf block can get mistaken for a index block; for
+ * this reason, we can only check the index checksum when the
+ * caller is sure it should be an index block.
+ */
+ if (is_dx_block && type == INDEX) {
+ if (ext4_dx_csum_verify(inode, dirent))
+ set_buffer_verified(bh);
+ else {
+ ext4_error_inode(inode, __func__, line, block,
+ "Directory index failed checksum");
brelse(bh);
- bh = NULL;
+ return ERR_PTR(-EIO);
}
}
- if (!bh && !(*err)) {
- *err = -EIO;
- ext4_error(inode->i_sb,
- "Directory hole detected on inode %lu\n",
- inode->i_ino);
+ if (!is_dx_block) {
+ if (ext4_dirent_csum_verify(inode, dirent))
+ set_buffer_verified(bh);
+ else {
+ ext4_error_inode(inode, __func__, line, block,
+ "Directory block failed checksum");
+ brelse(bh);
+ return ERR_PTR(-EIO);
+ }
}
return bh;
}
@@ -604,9 +677,9 @@
u32 hash;
frame->bh = NULL;
- if (!(bh = ext4_bread(NULL, dir, 0, 0, err))) {
- if (*err == 0)
- *err = ERR_BAD_DX_DIR;
+ bh = ext4_read_dirblock(dir, 0, INDEX);
+ if (IS_ERR(bh)) {
+ *err = PTR_ERR(bh);
goto fail;
}
root = (struct dx_root *) bh->b_data;
@@ -643,15 +716,6 @@
goto fail;
}
- if (!buffer_verified(bh) &&
- !ext4_dx_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) {
- ext4_warning(dir->i_sb, "Root failed checksum");
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
- goto fail;
- }
- set_buffer_verified(bh);
-
entries = (struct dx_entry *) (((char *)&root->info) +
root->info.info_length);
@@ -709,22 +773,12 @@
frame->entries = entries;
frame->at = at;
if (!indirect--) return frame;
- if (!(bh = ext4_bread(NULL, dir, dx_get_block(at), 0, err))) {
- if (!(*err))
- *err = ERR_BAD_DX_DIR;
+ bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
+ if (IS_ERR(bh)) {
+ *err = PTR_ERR(bh);
goto fail2;
}
- at = entries = ((struct dx_node *) bh->b_data)->entries;
-
- if (!buffer_verified(bh) &&
- !ext4_dx_csum_verify(dir,
- (struct ext4_dir_entry *)bh->b_data)) {
- ext4_warning(dir->i_sb, "Node failed checksum");
- brelse(bh);
- *err = ERR_BAD_DX_DIR;
- goto fail2;
- }
- set_buffer_verified(bh);
+ entries = ((struct dx_node *) bh->b_data)->entries;
if (dx_get_limit(entries) != dx_node_limit (dir)) {
ext4_warning(dir->i_sb,
@@ -783,7 +837,7 @@
{
struct dx_frame *p;
struct buffer_head *bh;
- int err, num_frames = 0;
+ int num_frames = 0;
__u32 bhash;
p = frame;
@@ -822,25 +876,9 @@
* block so no check is necessary
*/
while (num_frames--) {
- if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at),
- 0, &err))) {
- if (!err) {
- ext4_error(dir->i_sb,
- "Directory hole detected on inode %lu\n",
- dir->i_ino);
- return -EIO;
- }
- return err; /* Failure */
- }
-
- if (!buffer_verified(bh) &&
- !ext4_dx_csum_verify(dir,
- (struct ext4_dir_entry *)bh->b_data)) {
- ext4_warning(dir->i_sb, "Node failed checksum");
- return -EIO;
- }
- set_buffer_verified(bh);
-
+ bh = ext4_read_dirblock(dir, dx_get_block(p->at), INDEX);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
p++;
brelse(p->bh);
p->bh = bh;
@@ -866,20 +904,9 @@
dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
(unsigned long)block));
- if (!(bh = ext4_bread(NULL, dir, block, 0, &err))) {
- if (!err) {
- err = -EIO;
- ext4_error(dir->i_sb,
- "Directory hole detected on inode %lu\n",
- dir->i_ino);
- }
- return err;
- }
-
- if (!buffer_verified(bh) &&
- !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data))
- return -EIO;
- set_buffer_verified(bh);
+ bh = ext4_read_dirblock(dir, block, DIRENT);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
de = (struct ext4_dir_entry_2 *) bh->b_data;
top = (struct ext4_dir_entry_2 *) ((char *) de +
@@ -937,7 +964,7 @@
dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
start_hash, start_minor_hash));
- dir = dir_file->f_path.dentry->d_inode;
+ dir = file_inode(dir_file);
if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
if (hinfo.hash_version <= DX_HASH_TEA)
@@ -1333,26 +1360,11 @@
return NULL;
do {
block = dx_get_block(frame->at);
- if (!(bh = ext4_bread(NULL, dir, block, 0, err))) {
- if (!(*err)) {
- *err = -EIO;
- ext4_error(dir->i_sb,
- "Directory hole detected on inode %lu\n",
- dir->i_ino);
- }
+ bh = ext4_read_dirblock(dir, block, DIRENT);
+ if (IS_ERR(bh)) {
+ *err = PTR_ERR(bh);
goto errout;
}
-
- if (!buffer_verified(bh) &&
- !ext4_dirent_csum_verify(dir,
- (struct ext4_dir_entry *)bh->b_data)) {
- EXT4_ERROR_INODE(dir, "checksumming directory "
- "block %lu", (unsigned long)block);
- brelse(bh);
- *err = -EIO;
- goto errout;
- }
- set_buffer_verified(bh);
retval = search_dirblock(bh, dir, d_name,
block << EXT4_BLOCK_SIZE_BITS(sb),
res_dir);
@@ -1536,11 +1548,12 @@
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
csum_size = sizeof(struct ext4_dir_entry_tail);
- bh2 = ext4_append (handle, dir, &newblock, &err);
- if (!(bh2)) {
+ bh2 = ext4_append(handle, dir, &newblock);
+ if (IS_ERR(bh2)) {
brelse(*bh);
*bh = NULL;
- goto errout;
+ *error = PTR_ERR(bh2);
+ return NULL;
}
BUFFER_TRACE(*bh, "get_write_access");
@@ -1621,7 +1634,6 @@
brelse(bh2);
*bh = NULL;
ext4_std_error(dir->i_sb, err);
-errout:
*error = err;
return NULL;
}
@@ -1699,7 +1711,6 @@
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned int blocksize = dir->i_sb->s_blocksize;
- unsigned short reclen;
int csum_size = 0;
int err;
@@ -1707,7 +1718,6 @@
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
csum_size = sizeof(struct ext4_dir_entry_tail);
- reclen = EXT4_DIR_REC_LEN(namelen);
if (!de) {
err = ext4_find_dest_de(dir, inode,
bh, bh->b_data, blocksize - csum_size,
@@ -1798,10 +1808,10 @@
len = ((char *) root) + (blocksize - csum_size) - (char *) de;
/* Allocate new block for the 0th block's dirents */
- bh2 = ext4_append(handle, dir, &block, &retval);
- if (!(bh2)) {
+ bh2 = ext4_append(handle, dir, &block);
+ if (IS_ERR(bh2)) {
brelse(bh);
- return retval;
+ return PTR_ERR(bh2);
}
ext4_set_inode_flag(dir, EXT4_INODE_INDEX);
data1 = bh2->b_data;
@@ -1918,20 +1928,10 @@
}
blocks = dir->i_size >> sb->s_blocksize_bits;
for (block = 0; block < blocks; block++) {
- if (!(bh = ext4_bread(handle, dir, block, 0, &retval))) {
- if (!retval) {
- retval = -EIO;
- ext4_error(inode->i_sb,
- "Directory hole detected on inode %lu\n",
- inode->i_ino);
- }
- return retval;
- }
- if (!buffer_verified(bh) &&
- !ext4_dirent_csum_verify(dir,
- (struct ext4_dir_entry *)bh->b_data))
- return -EIO;
- set_buffer_verified(bh);
+ bh = ext4_read_dirblock(dir, block, DIRENT);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
+
retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
if (retval != -ENOSPC) {
brelse(bh);
@@ -1943,9 +1943,9 @@
return make_indexed_dir(handle, dentry, inode, bh);
brelse(bh);
}
- bh = ext4_append(handle, dir, &block, &retval);
- if (!bh)
- return retval;
+ bh = ext4_append(handle, dir, &block);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
de = (struct ext4_dir_entry_2 *) bh->b_data;
de->inode = 0;
de->rec_len = ext4_rec_len_to_disk(blocksize - csum_size, blocksize);
@@ -1982,22 +1982,13 @@
return err;
entries = frame->entries;
at = frame->at;
-
- if (!(bh = ext4_bread(handle, dir, dx_get_block(frame->at), 0, &err))) {
- if (!err) {
- err = -EIO;
- ext4_error(dir->i_sb,
- "Directory hole detected on inode %lu\n",
- dir->i_ino);
- }
+ bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT);
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
+ bh = NULL;
goto cleanup;
}
- if (!buffer_verified(bh) &&
- !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data))
- goto journal_error;
- set_buffer_verified(bh);
-
BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
@@ -2025,9 +2016,11 @@
err = -ENOSPC;
goto cleanup;
}
- bh2 = ext4_append (handle, dir, &newblock, &err);
- if (!(bh2))
+ bh2 = ext4_append(handle, dir, &newblock);
+ if (IS_ERR(bh2)) {
+ err = PTR_ERR(bh2);
goto cleanup;
+ }
node2 = (struct dx_node *)(bh2->b_data);
entries2 = node2->entries;
memset(&node2->fake, 0, sizeof(struct fake_dirent));
@@ -2106,8 +2099,7 @@
journal_error:
ext4_std_error(dir->i_sb, err);
cleanup:
- if (bh)
- brelse(bh);
+ brelse(bh);
dx_release(frames);
return err;
}
@@ -2254,29 +2246,28 @@
{
handle_t *handle;
struct inode *inode;
- int err, retries = 0;
+ int err, credits, retries = 0;
dquot_initialize(dir);
+ credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
retry:
- handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- if (IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
- inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
+ inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0,
+ NULL, EXT4_HT_DIR, credits);
+ handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
inode->i_op = &ext4_file_inode_operations;
inode->i_fop = &ext4_file_operations;
ext4_set_aops(inode);
err = ext4_add_nondir(handle, dentry, inode);
+ if (!err && IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
}
- ext4_journal_stop(handle);
+ if (handle)
+ ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -2287,31 +2278,30 @@
{
handle_t *handle;
struct inode *inode;
- int err, retries = 0;
+ int err, credits, retries = 0;
if (!new_valid_dev(rdev))
return -EINVAL;
dquot_initialize(dir);
+ credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
retry:
- handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- if (IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
- inode = ext4_new_inode(handle, dir, mode, &dentry->d_name, 0, NULL);
+ inode = ext4_new_inode_start_handle(dir, mode, &dentry->d_name, 0,
+ NULL, EXT4_HT_DIR, credits);
+ handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
if (!IS_ERR(inode)) {
init_special_inode(inode, inode->i_mode, rdev);
inode->i_op = &ext4_special_inode_operations;
err = ext4_add_nondir(handle, dentry, inode);
+ if (!err && IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
}
- ext4_journal_stop(handle);
+ if (handle)
+ ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -2351,6 +2341,7 @@
struct buffer_head *dir_block = NULL;
struct ext4_dir_entry_2 *de;
struct ext4_dir_entry_tail *t;
+ ext4_lblk_t block = 0;
unsigned int blocksize = dir->i_sb->s_blocksize;
int csum_size = 0;
int err;
@@ -2367,16 +2358,10 @@
goto out;
}
- inode->i_size = EXT4_I(inode)->i_disksize = blocksize;
- if (!(dir_block = ext4_bread(handle, inode, 0, 1, &err))) {
- if (!err) {
- err = -EIO;
- ext4_error(inode->i_sb,
- "Directory hole detected on inode %lu\n",
- inode->i_ino);
- }
- goto out;
- }
+ inode->i_size = 0;
+ dir_block = ext4_append(handle, inode, &block);
+ if (IS_ERR(dir_block))
+ return PTR_ERR(dir_block);
BUFFER_TRACE(dir_block, "get_write_access");
err = ext4_journal_get_write_access(handle, dir_block);
if (err)
@@ -2403,25 +2388,21 @@
{
handle_t *handle;
struct inode *inode;
- int err, retries = 0;
+ int err, credits, retries = 0;
if (EXT4_DIR_LINK_MAX(dir))
return -EMLINK;
dquot_initialize(dir);
+ credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
+ EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
retry:
- handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
- EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- if (IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
- inode = ext4_new_inode(handle, dir, S_IFDIR | mode,
- &dentry->d_name, 0, NULL);
+ inode = ext4_new_inode_start_handle(dir, S_IFDIR | mode,
+ &dentry->d_name,
+ 0, NULL, EXT4_HT_DIR, credits);
+ handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
@@ -2449,8 +2430,12 @@
goto out_clear_inode;
unlock_new_inode(inode);
d_instantiate(dentry, inode);
+ if (IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
+
out_stop:
- ext4_journal_stop(handle);
+ if (handle)
+ ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -2476,25 +2461,14 @@
}
sb = inode->i_sb;
- if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
- !(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
- if (err)
- EXT4_ERROR_INODE(inode,
- "error %d reading directory lblock 0", err);
- else
- ext4_warning(inode->i_sb,
- "bad directory (dir #%lu) - no data block",
- inode->i_ino);
+ if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2)) {
+ EXT4_ERROR_INODE(inode, "invalid size");
return 1;
}
- if (!buffer_verified(bh) &&
- !ext4_dirent_csum_verify(inode,
- (struct ext4_dir_entry *)bh->b_data)) {
- EXT4_ERROR_INODE(inode, "checksum error reading directory "
- "lblock 0");
- return -EIO;
- }
- set_buffer_verified(bh);
+ bh = ext4_read_dirblock(inode, 0, EITHER);
+ if (IS_ERR(bh))
+ return 1;
+
de = (struct ext4_dir_entry_2 *) bh->b_data;
de1 = ext4_next_entry(de, sb->s_blocksize);
if (le32_to_cpu(de->inode) != inode->i_ino ||
@@ -2517,28 +2491,9 @@
err = 0;
brelse(bh);
lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb);
- bh = ext4_bread(NULL, inode, lblock, 0, &err);
- if (!bh) {
- if (err)
- EXT4_ERROR_INODE(inode,
- "error %d reading directory "
- "lblock %u", err, lblock);
- else
- ext4_warning(inode->i_sb,
- "bad directory (dir #%lu) - no data block",
- inode->i_ino);
-
- offset += sb->s_blocksize;
- continue;
- }
- if (!buffer_verified(bh) &&
- !ext4_dirent_csum_verify(inode,
- (struct ext4_dir_entry *)bh->b_data)) {
- EXT4_ERROR_INODE(inode, "checksum error "
- "reading directory lblock 0");
- return -EIO;
- }
- set_buffer_verified(bh);
+ bh = ext4_read_dirblock(inode, lblock, EITHER);
+ if (IS_ERR(bh))
+ return 1;
de = (struct ext4_dir_entry_2 *) bh->b_data;
}
if (ext4_check_dir_entry(inode, NULL, de, bh,
@@ -2717,25 +2672,18 @@
struct inode *inode;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
- handle_t *handle;
+ handle_t *handle = NULL;
/* Initialize quotas before so that eventual writes go in
* separate transaction */
dquot_initialize(dir);
dquot_initialize(dentry->d_inode);
- handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
if (!bh)
goto end_rmdir;
- if (IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
inode = dentry->d_inode;
retval = -EIO;
@@ -2746,6 +2694,17 @@
if (!empty_dir(inode))
goto end_rmdir;
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
+ EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle)) {
+ retval = PTR_ERR(handle);
+ handle = NULL;
+ goto end_rmdir;
+ }
+
+ if (IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
+
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
goto end_rmdir;
@@ -2767,8 +2726,9 @@
ext4_mark_inode_dirty(handle, dir);
end_rmdir:
- ext4_journal_stop(handle);
brelse(bh);
+ if (handle)
+ ext4_journal_stop(handle);
return retval;
}
@@ -2778,7 +2738,7 @@
struct inode *inode;
struct buffer_head *bh;
struct ext4_dir_entry_2 *de;
- handle_t *handle;
+ handle_t *handle = NULL;
trace_ext4_unlink_enter(dir, dentry);
/* Initialize quotas before so that eventual writes go
@@ -2786,13 +2746,6 @@
dquot_initialize(dir);
dquot_initialize(dentry->d_inode);
- handle = ext4_journal_start(dir, EXT4_DELETE_TRANS_BLOCKS(dir->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- if (IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
retval = -ENOENT;
bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
if (!bh)
@@ -2804,6 +2757,17 @@
if (le32_to_cpu(de->inode) != inode->i_ino)
goto end_unlink;
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
+ EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+ if (IS_ERR(handle)) {
+ retval = PTR_ERR(handle);
+ handle = NULL;
+ goto end_unlink;
+ }
+
+ if (IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
+
if (!inode->i_nlink) {
ext4_warning(inode->i_sb,
"Deleting nonexistent file (%lu), %d",
@@ -2824,8 +2788,9 @@
retval = 0;
end_unlink:
- ext4_journal_stop(handle);
brelse(bh);
+ if (handle)
+ ext4_journal_stop(handle);
trace_ext4_unlink_exit(dentry, retval);
return retval;
}
@@ -2865,15 +2830,10 @@
EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
}
retry:
- handle = ext4_journal_start(dir, credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- if (IS_DIRSYNC(dir))
- ext4_handle_sync(handle);
-
- inode = ext4_new_inode(handle, dir, S_IFLNK|S_IRWXUGO,
- &dentry->d_name, 0, NULL);
+ inode = ext4_new_inode_start_handle(dir, S_IFLNK|S_IRWXUGO,
+ &dentry->d_name, 0, NULL,
+ EXT4_HT_DIR, credits);
+ handle = ext4_journal_current_handle();
err = PTR_ERR(inode);
if (IS_ERR(inode))
goto out_stop;
@@ -2903,7 +2863,7 @@
* Now inode is being linked into dir (EXT4_DATA_TRANS_BLOCKS
* + EXT4_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified
*/
- handle = ext4_journal_start(dir,
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
if (IS_ERR(handle)) {
@@ -2926,8 +2886,12 @@
}
EXT4_I(inode)->i_disksize = inode->i_size;
err = ext4_add_nondir(handle, dentry, inode);
+ if (!err && IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
+
out_stop:
- ext4_journal_stop(handle);
+ if (handle)
+ ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
return err;
@@ -2950,8 +2914,9 @@
dquot_initialize(dir);
retry:
- handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS);
+ handle = ext4_journal_start(dir, EXT4_HT_DIR,
+ (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2991,13 +2956,9 @@
struct buffer_head *bh;
if (!ext4_has_inline_data(inode)) {
- if (!(bh = ext4_bread(handle, inode, 0, 0, retval))) {
- if (!*retval) {
- *retval = -EIO;
- ext4_error(inode->i_sb,
- "Directory hole detected on inode %lu\n",
- inode->i_ino);
- }
+ bh = ext4_read_dirblock(inode, 0, EITHER);
+ if (IS_ERR(bh)) {
+ *retval = PTR_ERR(bh);
return NULL;
}
*parent_de = ext4_next_entry(
@@ -3034,9 +2995,9 @@
* in separate transaction */
if (new_dentry->d_inode)
dquot_initialize(new_dentry->d_inode);
- handle = ext4_journal_start(old_dir, 2 *
- EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2);
+ handle = ext4_journal_start(old_dir, EXT4_HT_DIR,
+ (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -3076,11 +3037,6 @@
&inlined);
if (!dir_bh)
goto end_rename;
- if (!inlined && !buffer_verified(dir_bh) &&
- !ext4_dirent_csum_verify(old_inode,
- (struct ext4_dir_entry *)dir_bh->b_data))
- goto end_rename;
- set_buffer_verified(dir_bh);
if (le32_to_cpu(parent_de->inode) != old_dir->i_ino)
goto end_rename;
retval = -EMLINK;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 0016fbc..047a6de 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -23,6 +23,7 @@
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/slab.h>
+#include <linux/mm.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -49,11 +50,21 @@
kmem_cache_destroy(io_page_cachep);
}
-void ext4_ioend_wait(struct inode *inode)
+/*
+ * This function is called by ext4_evict_inode() to make sure there is
+ * no more pending I/O completion work left to do.
+ */
+void ext4_ioend_shutdown(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
+ /*
+ * We need to make sure the work structure is finished being
+ * used before we let the inode get destroyed.
+ */
+ if (work_pending(&EXT4_I(inode)->i_unwritten_work))
+ cancel_work_sync(&EXT4_I(inode)->i_unwritten_work);
}
static void put_io_page(struct ext4_io_page *io_page)
@@ -73,8 +84,6 @@
BUG_ON(!list_empty(&io->list));
BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN);
- if (io->page)
- put_page(io->page);
for (i = 0; i < io->num_io_pages; i++)
put_io_page(io->pages[i]);
io->num_io_pages = 0;
@@ -103,14 +112,13 @@
"(inode %lu, offset %llu, size %zd, error %d)",
inode->i_ino, offset, size, ret);
}
- if (io->iocb)
- aio_complete(io->iocb, io->result, 0);
-
- if (io->flag & EXT4_IO_END_DIRECT)
- inode_dio_done(inode);
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten))
wake_up_all(ext4_ioend_wq(inode));
+ if (io->flag & EXT4_IO_END_DIRECT)
+ inode_dio_done(inode);
+ if (io->iocb)
+ aio_complete(io->iocb, io->result, 0);
return ret;
}
@@ -119,7 +127,6 @@
#ifdef EXT4FS_DEBUG
struct list_head *cur, *before, *after;
ext4_io_end_t *io, *io0, *io1;
- unsigned long flags;
if (list_empty(&EXT4_I(inode)->i_completed_io_list)) {
ext4_debug("inode %lu completed_io list is empty\n",
@@ -152,26 +159,20 @@
wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- if (list_empty(&ei->i_completed_io_list)) {
- io_end->flag |= EXT4_IO_END_QUEUED;
- queue_work(wq, &io_end->work);
- }
+ if (list_empty(&ei->i_completed_io_list))
+ queue_work(wq, &ei->i_unwritten_work);
list_add_tail(&io_end->list, &ei->i_completed_io_list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
}
-static int ext4_do_flush_completed_IO(struct inode *inode,
- ext4_io_end_t *work_io)
+static int ext4_do_flush_completed_IO(struct inode *inode)
{
ext4_io_end_t *io;
- struct list_head unwritten, complete, to_free;
+ struct list_head unwritten;
unsigned long flags;
struct ext4_inode_info *ei = EXT4_I(inode);
int err, ret = 0;
- INIT_LIST_HEAD(&complete);
- INIT_LIST_HEAD(&to_free);
-
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
dump_completed_IO(inode);
list_replace_init(&ei->i_completed_io_list, &unwritten);
@@ -185,32 +186,7 @@
err = ext4_end_io(io);
if (unlikely(!ret && err))
ret = err;
-
- list_add_tail(&io->list, &complete);
- }
- spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- while (!list_empty(&complete)) {
- io = list_entry(complete.next, ext4_io_end_t, list);
io->flag &= ~EXT4_IO_END_UNWRITTEN;
- /* end_io context can not be destroyed now because it still
- * used by queued worker. Worker thread will destroy it later */
- if (io->flag & EXT4_IO_END_QUEUED)
- list_del_init(&io->list);
- else
- list_move(&io->list, &to_free);
- }
- /* If we are called from worker context, it is time to clear queued
- * flag, and destroy it's end_io if it was converted already */
- if (work_io) {
- work_io->flag &= ~EXT4_IO_END_QUEUED;
- if (!(work_io->flag & EXT4_IO_END_UNWRITTEN))
- list_add_tail(&work_io->list, &to_free);
- }
- spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-
- while (!list_empty(&to_free)) {
- io = list_entry(to_free.next, ext4_io_end_t, list);
- list_del_init(&io->list);
ext4_free_io_end(io);
}
return ret;
@@ -219,10 +195,11 @@
/*
* work on completed aio dio IO, to convert unwritten extents to extents
*/
-static void ext4_end_io_work(struct work_struct *work)
+void ext4_end_io_work(struct work_struct *work)
{
- ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
- ext4_do_flush_completed_IO(io->inode, io);
+ struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
+ i_unwritten_work);
+ ext4_do_flush_completed_IO(&ei->vfs_inode);
}
int ext4_flush_unwritten_io(struct inode *inode)
@@ -230,7 +207,7 @@
int ret;
WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) &&
!(inode->i_state & I_FREEING));
- ret = ext4_do_flush_completed_IO(inode, NULL);
+ ret = ext4_do_flush_completed_IO(inode);
ext4_unwritten_wait(inode);
return ret;
}
@@ -241,7 +218,6 @@
if (io) {
atomic_inc(&EXT4_I(inode)->i_ioend_count);
io->inode = inode;
- INIT_WORK(&io->work, ext4_end_io_work);
INIT_LIST_HEAD(&io->list);
}
return io;
@@ -382,14 +358,6 @@
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
}
- if (!buffer_mapped(bh) || buffer_delay(bh)) {
- if (!buffer_mapped(bh))
- clear_buffer_dirty(bh);
- if (io->io_bio)
- ext4_io_submit(io);
- return 0;
- }
-
if (io->io_bio && bh->b_blocknr != io->io_next_block) {
submit_and_retry:
ext4_io_submit(io);
@@ -436,7 +404,7 @@
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
- set_page_dirty(page);
+ redirty_page_for_writepage(wbc, page);
unlock_page(page);
return -ENOMEM;
}
@@ -468,7 +436,15 @@
set_buffer_uptodate(bh);
continue;
}
- clear_buffer_dirty(bh);
+ if (!buffer_dirty(bh) || buffer_delay(bh) ||
+ !buffer_mapped(bh) || buffer_unwritten(bh)) {
+ /* A hole? We can safely clear the dirty bit */
+ if (!buffer_mapped(bh))
+ clear_buffer_dirty(bh);
+ if (io->io_bio)
+ ext4_io_submit(io);
+ continue;
+ }
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
@@ -476,9 +452,10 @@
* we can do but mark the page as dirty, and
* better luck next time.
*/
- set_page_dirty(page);
+ redirty_page_for_writepage(wbc, page);
break;
}
+ clear_buffer_dirty(bh);
}
unlock_page(page);
/*
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index d99387b..c169477 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -333,8 +333,8 @@
int err;
bh = sb_getblk(sb, blk);
- if (!bh)
- return ERR_PTR(-EIO);
+ if (unlikely(!bh))
+ return ERR_PTR(-ENOMEM);
if ((err = ext4_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
@@ -410,8 +410,8 @@
return err;
bh = sb_getblk(sb, flex_gd->groups[group].block_bitmap);
- if (!bh)
- return -EIO;
+ if (unlikely(!bh))
+ return -ENOMEM;
err = ext4_journal_get_write_access(handle, bh);
if (err)
@@ -466,7 +466,7 @@
meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG);
/* This transaction may be extended/restarted along the way */
- handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, EXT4_MAX_TRANS_DATA);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -500,8 +500,8 @@
goto out;
gdb = sb_getblk(sb, block);
- if (!gdb) {
- err = -EIO;
+ if (unlikely(!gdb)) {
+ err = -ENOMEM;
goto out;
}
@@ -1031,7 +1031,7 @@
handle_t *handle;
int err = 0, err2;
- handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, EXT4_MAX_TRANS_DATA);
if (IS_ERR(handle)) {
group = 1;
err = PTR_ERR(handle);
@@ -1064,8 +1064,8 @@
ext4_bg_has_super(sb, group));
bh = sb_getblk(sb, backup_block);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
break;
}
ext4_debug("update metadata backup %llu(+%llu)\n",
@@ -1168,7 +1168,7 @@
static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block)
{
struct buffer_head *bh = sb_getblk(sb, block);
- if (!bh)
+ if (unlikely(!bh))
return NULL;
if (!bh_uptodate_or_lock(bh)) {
if (bh_submit_read(bh) < 0) {
@@ -1247,7 +1247,7 @@
ext4_inode_table_set(sb, gdp, group_data->inode_table);
ext4_free_group_clusters_set(sb, gdp,
- EXT4_B2C(sbi, group_data->free_blocks_count));
+ EXT4_NUM_B2C(sbi, group_data->free_blocks_count));
ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
if (ext4_has_group_desc_csum(sb))
ext4_itable_unused_set(sb, gdp,
@@ -1349,7 +1349,7 @@
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeclusters_counter,
- EXT4_B2C(sbi, free_blocks));
+ EXT4_NUM_B2C(sbi, free_blocks));
percpu_counter_add(&sbi->s_freeinodes_counter,
EXT4_INODES_PER_GROUP(sb) * flex_gd->count);
@@ -1360,8 +1360,8 @@
sbi->s_log_groups_per_flex) {
ext4_group_t flex_group;
flex_group = ext4_flex_group(sbi, group_data[0].group);
- atomic_add(EXT4_B2C(sbi, free_blocks),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
&sbi->s_flex_groups[flex_group].free_inodes);
}
@@ -1412,7 +1412,7 @@
* modify each of the reserved GDT dindirect blocks.
*/
credit = flex_gd->count * 4 + reserved_gdb;
- handle = ext4_journal_start_sb(sb, credit);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, credit);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto exit;
@@ -1506,10 +1506,12 @@
group_data[i].blocks_count = blocks_per_group;
overhead = ext4_group_overhead_blocks(sb, group + i);
group_data[i].free_blocks_count = blocks_per_group - overhead;
- if (ext4_has_group_desc_csum(sb))
+ if (ext4_has_group_desc_csum(sb)) {
flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT |
EXT4_BG_INODE_UNINIT;
- else
+ if (!test_opt(sb, INIT_INODE_TABLE))
+ flex_gd->bg_flags[i] |= EXT4_BG_INODE_ZEROED;
+ } else
flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED;
}
@@ -1594,7 +1596,7 @@
err = ext4_alloc_flex_bg_array(sb, input->group + 1);
if (err)
- return err;
+ goto out;
err = ext4_mb_alloc_groupinfo(sb, input->group + 1);
if (err)
@@ -1622,7 +1624,7 @@
/* We will update the superblock, one block bitmap, and
* one group descriptor via ext4_group_add_blocks().
*/
- handle = ext4_journal_start_sb(sb, 3);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, 3);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
ext4_warning(sb, "error %d on journal start", err);
@@ -1786,7 +1788,7 @@
credits += 3; /* block bitmap, bg descriptor, resize inode */
}
- handle = ext4_journal_start_sb(sb, credits);
+ handle = ext4_journal_start_sb(sb, EXT4_HT_RESIZE, credits);
if (IS_ERR(handle))
return PTR_ERR(handle);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3d4fb81..5d6d5357 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -69,8 +69,6 @@
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
-static const char *ext4_decode_error(struct super_block *sb, int errno,
- char nbuf[16]);
static int ext4_remount(struct super_block *sb, int *flags, char *data);
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
@@ -92,6 +90,8 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ext2");
+MODULE_ALIAS("ext2");
#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
#else
#define IS_EXT2_SB(sb) (0)
@@ -106,6 +106,8 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ext3");
+MODULE_ALIAS("ext3");
#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
#else
#define IS_EXT3_SB(sb) (0)
@@ -296,107 +298,6 @@
}
-/* Just increment the non-pointer handle value */
-static handle_t *ext4_get_nojournal(void)
-{
- handle_t *handle = current->journal_info;
- unsigned long ref_cnt = (unsigned long)handle;
-
- BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);
-
- ref_cnt++;
- handle = (handle_t *)ref_cnt;
-
- current->journal_info = handle;
- return handle;
-}
-
-
-/* Decrement the non-pointer handle value */
-static void ext4_put_nojournal(handle_t *handle)
-{
- unsigned long ref_cnt = (unsigned long)handle;
-
- BUG_ON(ref_cnt == 0);
-
- ref_cnt--;
- handle = (handle_t *)ref_cnt;
-
- current->journal_info = handle;
-}
-
-/*
- * Wrappers for jbd2_journal_start/end.
- */
-handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
-{
- journal_t *journal;
-
- trace_ext4_journal_start(sb, nblocks, _RET_IP_);
- if (sb->s_flags & MS_RDONLY)
- return ERR_PTR(-EROFS);
-
- WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
- journal = EXT4_SB(sb)->s_journal;
- if (!journal)
- return ext4_get_nojournal();
- /*
- * 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.
- */
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, "Detected aborted journal");
- return ERR_PTR(-EROFS);
- }
- return jbd2_journal_start(journal, nblocks);
-}
-
-int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
-{
- struct super_block *sb;
- int err;
- int rc;
-
- if (!ext4_handle_valid(handle)) {
- ext4_put_nojournal(handle);
- return 0;
- }
- sb = handle->h_transaction->t_journal->j_private;
- err = handle->h_err;
- rc = jbd2_journal_stop(handle);
-
- if (!err)
- err = rc;
- if (err)
- __ext4_std_error(sb, where, line, err);
- return 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);
-
- BUG_ON(!ext4_handle_valid(handle));
-
- if (bh)
- BUFFER_TRACE(bh, "abort");
-
- if (!handle->h_err)
- handle->h_err = err;
-
- if (is_handle_aborted(handle))
- return;
-
- printk(KERN_ERR "EXT4-fs: %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)
{
@@ -553,7 +454,7 @@
va_list args;
struct va_format vaf;
struct ext4_super_block *es;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
char pathname[80], *path;
es = EXT4_SB(inode->i_sb)->s_es;
@@ -582,8 +483,8 @@
ext4_handle_error(inode->i_sb);
}
-static const char *ext4_decode_error(struct super_block *sb, int errno,
- char nbuf[16])
+const char *ext4_decode_error(struct super_block *sb, int errno,
+ char nbuf[16])
{
char *errstr = NULL;
@@ -858,6 +759,7 @@
ext4_abort(sb, "Couldn't clean up the journal");
}
+ ext4_es_unregister_shrinker(sb);
del_timer(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
@@ -885,6 +787,7 @@
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_extent_cache_cnt);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
@@ -939,11 +842,12 @@
return NULL;
ei->vfs_inode.i_version = 1;
- memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
rwlock_init(&ei->i_es_lock);
+ INIT_LIST_HEAD(&ei->i_es_lru);
+ ei->i_es_lru_nr = 0;
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
@@ -960,6 +864,7 @@
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
atomic_set(&ei->i_unwritten, 0);
+ INIT_WORK(&ei->i_unwritten_work, ext4_end_io_work);
return &ei->vfs_inode;
}
@@ -1031,6 +936,7 @@
dquot_drop(inode);
ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
+ ext4_es_lru_del(inode);
if (EXT4_I(inode)->jinode) {
jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode);
@@ -1280,8 +1186,8 @@
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
{Opt_nodelalloc, "nodelalloc"},
- {Opt_mblk_io_submit, "mblk_io_submit"},
- {Opt_nomblk_io_submit, "nomblk_io_submit"},
+ {Opt_removed, "mblk_io_submit"},
+ {Opt_removed, "nomblk_io_submit"},
{Opt_block_validity, "block_validity"},
{Opt_noblock_validity, "noblock_validity"},
{Opt_inode_readahead_blks, "inode_readahead_blks=%u"},
@@ -1337,6 +1243,7 @@
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
char *qname;
+ int ret = -1;
if (sb_any_quota_loaded(sb) &&
!sbi->s_qf_names[qtype]) {
@@ -1345,29 +1252,37 @@
"quota options when quota turned on");
return -1;
}
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ ext4_msg(sb, KERN_ERR, "Cannot set journaled quota options "
+ "when QUOTA feature is enabled");
+ return -1;
+ }
qname = match_strdup(args);
if (!qname) {
ext4_msg(sb, KERN_ERR,
"Not enough memory for storing quotafile name");
return -1;
}
- if (sbi->s_qf_names[qtype] &&
- strcmp(sbi->s_qf_names[qtype], qname)) {
- ext4_msg(sb, KERN_ERR,
- "%s quota file already specified", QTYPE2NAME(qtype));
- kfree(qname);
- return -1;
+ if (sbi->s_qf_names[qtype]) {
+ if (strcmp(sbi->s_qf_names[qtype], qname) == 0)
+ ret = 1;
+ else
+ ext4_msg(sb, KERN_ERR,
+ "%s quota file already specified",
+ QTYPE2NAME(qtype));
+ goto errout;
}
- sbi->s_qf_names[qtype] = qname;
- if (strchr(sbi->s_qf_names[qtype], '/')) {
+ if (strchr(qname, '/')) {
ext4_msg(sb, KERN_ERR,
"quotafile must be on filesystem root");
- kfree(sbi->s_qf_names[qtype]);
- sbi->s_qf_names[qtype] = NULL;
- return -1;
+ goto errout;
}
+ sbi->s_qf_names[qtype] = qname;
set_opt(sb, QUOTA);
return 1;
+errout:
+ kfree(qname);
+ return ret;
}
static int clear_qf_name(struct super_block *sb, int qtype)
@@ -1381,10 +1296,7 @@
" when quota turned on");
return -1;
}
- /*
- * The space will be released later when all options are confirmed
- * to be correct
- */
+ kfree(sbi->s_qf_names[qtype]);
sbi->s_qf_names[qtype] = NULL;
return 1;
}
@@ -1404,6 +1316,9 @@
#define MOPT_QFMT MOPT_NOSUPPORT
#endif
#define MOPT_DATAJ 0x0080
+#define MOPT_NO_EXT2 0x0100
+#define MOPT_NO_EXT3 0x0200
+#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
static const struct mount_opts {
int token;
@@ -1414,25 +1329,31 @@
{Opt_bsd_df, EXT4_MOUNT_MINIX_DF, MOPT_CLEAR},
{Opt_grpid, EXT4_MOUNT_GRPID, MOPT_SET},
{Opt_nogrpid, EXT4_MOUNT_GRPID, MOPT_CLEAR},
- {Opt_mblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_SET},
- {Opt_nomblk_io_submit, EXT4_MOUNT_MBLK_IO_SUBMIT, MOPT_CLEAR},
{Opt_block_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_SET},
{Opt_noblock_validity, EXT4_MOUNT_BLOCK_VALIDITY, MOPT_CLEAR},
- {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_SET},
- {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK, MOPT_CLEAR},
+ {Opt_dioread_nolock, EXT4_MOUNT_DIOREAD_NOLOCK,
+ MOPT_EXT4_ONLY | MOPT_SET},
+ {Opt_dioread_lock, EXT4_MOUNT_DIOREAD_NOLOCK,
+ MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_discard, EXT4_MOUNT_DISCARD, MOPT_SET},
{Opt_nodiscard, EXT4_MOUNT_DISCARD, MOPT_CLEAR},
- {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_SET | MOPT_EXPLICIT},
- {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, MOPT_CLEAR | MOPT_EXPLICIT},
- {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_SET},
+ {Opt_delalloc, EXT4_MOUNT_DELALLOC,
+ MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
+ {Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
+ MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+ {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
+ MOPT_EXT4_ONLY | MOPT_SET},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
- EXT4_MOUNT_JOURNAL_CHECKSUM), MOPT_SET},
- {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_SET},
+ EXT4_MOUNT_JOURNAL_CHECKSUM),
+ MOPT_EXT4_ONLY | MOPT_SET},
+ {Opt_noload, EXT4_MOUNT_NOLOAD, MOPT_NO_EXT2 | MOPT_SET},
{Opt_err_panic, EXT4_MOUNT_ERRORS_PANIC, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_ro, EXT4_MOUNT_ERRORS_RO, MOPT_SET | MOPT_CLEAR_ERR},
{Opt_err_cont, EXT4_MOUNT_ERRORS_CONT, MOPT_SET | MOPT_CLEAR_ERR},
- {Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_SET},
- {Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT, MOPT_CLEAR},
+ {Opt_data_err_abort, EXT4_MOUNT_DATA_ERR_ABORT,
+ MOPT_NO_EXT2 | MOPT_SET},
+ {Opt_data_err_ignore, EXT4_MOUNT_DATA_ERR_ABORT,
+ MOPT_NO_EXT2 | MOPT_CLEAR},
{Opt_barrier, EXT4_MOUNT_BARRIER, MOPT_SET},
{Opt_nobarrier, EXT4_MOUNT_BARRIER, MOPT_CLEAR},
{Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET},
@@ -1444,9 +1365,14 @@
{Opt_inode_readahead_blks, 0, MOPT_GTE0},
{Opt_init_itable, 0, MOPT_GTE0},
{Opt_stripe, 0, MOPT_GTE0},
- {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_DATAJ},
- {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_DATAJ},
- {Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA, MOPT_DATAJ},
+ {Opt_resuid, 0, MOPT_GTE0},
+ {Opt_resgid, 0, MOPT_GTE0},
+ {Opt_journal_dev, 0, MOPT_GTE0},
+ {Opt_journal_ioprio, 0, MOPT_GTE0},
+ {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
+ {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
+ {Opt_data_writeback, EXT4_MOUNT_WRITEBACK_DATA,
+ MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_user_xattr, EXT4_MOUNT_XATTR_USER, MOPT_SET},
{Opt_nouser_xattr, EXT4_MOUNT_XATTR_USER, MOPT_CLEAR},
#ifdef CONFIG_EXT4_FS_POSIX_ACL
@@ -1496,8 +1422,6 @@
else if (token == Opt_offgrpjquota)
return clear_qf_name(sb, GRPQUOTA);
#endif
- if (args->from && match_int(args, &arg))
- return -1;
switch (token) {
case Opt_noacl:
case Opt_nouser_xattr:
@@ -1506,24 +1430,7 @@
case Opt_sb:
return 1; /* handled by get_sb_block() */
case Opt_removed:
- ext4_msg(sb, KERN_WARNING,
- "Ignoring removed %s option", opt);
- return 1;
- case Opt_resuid:
- uid = make_kuid(current_user_ns(), arg);
- if (!uid_valid(uid)) {
- ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
- return -1;
- }
- sbi->s_resuid = uid;
- return 1;
- case Opt_resgid:
- gid = make_kgid(current_user_ns(), arg);
- if (!gid_valid(gid)) {
- ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
- return -1;
- }
- sbi->s_resgid = gid;
+ ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
return 1;
case Opt_abort:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
@@ -1531,113 +1438,148 @@
case Opt_i_version:
sb->s_flags |= MS_I_VERSION;
return 1;
- case Opt_journal_dev:
+ }
+
+ for (m = ext4_mount_opts; m->token != Opt_err; m++)
+ if (token == m->token)
+ break;
+
+ if (m->token == Opt_err) {
+ ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
+ "or missing value", opt);
+ return -1;
+ }
+
+ if ((m->flags & MOPT_NO_EXT2) && IS_EXT2_SB(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "Mount option \"%s\" incompatible with ext2", opt);
+ return -1;
+ }
+ if ((m->flags & MOPT_NO_EXT3) && IS_EXT3_SB(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "Mount option \"%s\" incompatible with ext3", opt);
+ return -1;
+ }
+
+ if (args->from && match_int(args, &arg))
+ return -1;
+ if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
+ return -1;
+ if (m->flags & MOPT_EXPLICIT)
+ set_opt2(sb, EXPLICIT_DELALLOC);
+ if (m->flags & MOPT_CLEAR_ERR)
+ clear_opt(sb, ERRORS_MASK);
+ if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
+ ext4_msg(sb, KERN_ERR, "Cannot change quota "
+ "options when quota turned on");
+ return -1;
+ }
+
+ if (m->flags & MOPT_NOSUPPORT) {
+ ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
+ } else if (token == Opt_commit) {
+ if (arg == 0)
+ arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
+ sbi->s_commit_interval = HZ * arg;
+ } else if (token == Opt_max_batch_time) {
+ if (arg == 0)
+ arg = EXT4_DEF_MAX_BATCH_TIME;
+ sbi->s_max_batch_time = arg;
+ } else if (token == Opt_min_batch_time) {
+ sbi->s_min_batch_time = arg;
+ } else if (token == Opt_inode_readahead_blks) {
+ if (arg && (arg > (1 << 30) || !is_power_of_2(arg))) {
+ ext4_msg(sb, KERN_ERR,
+ "EXT4-fs: inode_readahead_blks must be "
+ "0 or a power of 2 smaller than 2^31");
+ return -1;
+ }
+ sbi->s_inode_readahead_blks = arg;
+ } else if (token == Opt_init_itable) {
+ set_opt(sb, INIT_INODE_TABLE);
+ if (!args->from)
+ arg = EXT4_DEF_LI_WAIT_MULT;
+ sbi->s_li_wait_mult = arg;
+ } else if (token == Opt_max_dir_size_kb) {
+ sbi->s_max_dir_size_kb = arg;
+ } else if (token == Opt_stripe) {
+ sbi->s_stripe = arg;
+ } else if (token == Opt_resuid) {
+ uid = make_kuid(current_user_ns(), arg);
+ if (!uid_valid(uid)) {
+ ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
+ return -1;
+ }
+ sbi->s_resuid = uid;
+ } else if (token == Opt_resgid) {
+ gid = make_kgid(current_user_ns(), arg);
+ if (!gid_valid(gid)) {
+ ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
+ return -1;
+ }
+ sbi->s_resgid = gid;
+ } else if (token == Opt_journal_dev) {
if (is_remount) {
ext4_msg(sb, KERN_ERR,
"Cannot specify journal on remount");
return -1;
}
*journal_devnum = arg;
- return 1;
- case Opt_journal_ioprio:
- if (arg < 0 || arg > 7)
- return -1;
- *journal_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
- return 1;
- }
-
- for (m = ext4_mount_opts; m->token != Opt_err; m++) {
- if (token != m->token)
- continue;
- if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
- return -1;
- if (m->flags & MOPT_EXPLICIT)
- set_opt2(sb, EXPLICIT_DELALLOC);
- if (m->flags & MOPT_CLEAR_ERR)
- clear_opt(sb, ERRORS_MASK);
- if (token == Opt_noquota && sb_any_quota_loaded(sb)) {
- ext4_msg(sb, KERN_ERR, "Cannot change quota "
- "options when quota turned on");
+ } else if (token == Opt_journal_ioprio) {
+ if (arg > 7) {
+ ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
+ " (must be 0-7)");
return -1;
}
-
- if (m->flags & MOPT_NOSUPPORT) {
- ext4_msg(sb, KERN_ERR, "%s option not supported", opt);
- } else if (token == Opt_commit) {
- if (arg == 0)
- arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
- sbi->s_commit_interval = HZ * arg;
- } else if (token == Opt_max_batch_time) {
- if (arg == 0)
- arg = EXT4_DEF_MAX_BATCH_TIME;
- sbi->s_max_batch_time = arg;
- } else if (token == Opt_min_batch_time) {
- sbi->s_min_batch_time = arg;
- } else if (token == Opt_inode_readahead_blks) {
- if (arg > (1 << 30))
- return -1;
- if (arg && !is_power_of_2(arg)) {
+ *journal_ioprio =
+ IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, arg);
+ } else if (m->flags & MOPT_DATAJ) {
+ if (is_remount) {
+ if (!sbi->s_journal)
+ ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
+ else if (test_opt(sb, DATA_FLAGS) != m->mount_opt) {
ext4_msg(sb, KERN_ERR,
- "EXT4-fs: inode_readahead_blks"
- " must be a power of 2");
- return -1;
- }
- sbi->s_inode_readahead_blks = arg;
- } else if (token == Opt_init_itable) {
- set_opt(sb, INIT_INODE_TABLE);
- if (!args->from)
- arg = EXT4_DEF_LI_WAIT_MULT;
- sbi->s_li_wait_mult = arg;
- } else if (token == Opt_max_dir_size_kb) {
- sbi->s_max_dir_size_kb = arg;
- } else if (token == Opt_stripe) {
- sbi->s_stripe = arg;
- } else if (m->flags & MOPT_DATAJ) {
- if (is_remount) {
- if (!sbi->s_journal)
- ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
- else if (test_opt(sb, DATA_FLAGS) !=
- m->mount_opt) {
- ext4_msg(sb, KERN_ERR,
"Cannot change data mode on remount");
- return -1;
- }
- } else {
- clear_opt(sb, DATA_FLAGS);
- sbi->s_mount_opt |= m->mount_opt;
- }
-#ifdef CONFIG_QUOTA
- } else if (m->flags & MOPT_QFMT) {
- if (sb_any_quota_loaded(sb) &&
- sbi->s_jquota_fmt != m->mount_opt) {
- ext4_msg(sb, KERN_ERR, "Cannot "
- "change journaled quota options "
- "when quota turned on");
return -1;
}
- sbi->s_jquota_fmt = m->mount_opt;
-#endif
} else {
- if (!args->from)
- arg = 1;
- if (m->flags & MOPT_CLEAR)
- arg = !arg;
- else if (unlikely(!(m->flags & MOPT_SET))) {
- ext4_msg(sb, KERN_WARNING,
- "buggy handling of option %s", opt);
- WARN_ON(1);
- return -1;
- }
- if (arg != 0)
- sbi->s_mount_opt |= m->mount_opt;
- else
- sbi->s_mount_opt &= ~m->mount_opt;
+ clear_opt(sb, DATA_FLAGS);
+ sbi->s_mount_opt |= m->mount_opt;
}
- return 1;
+#ifdef CONFIG_QUOTA
+ } else if (m->flags & MOPT_QFMT) {
+ if (sb_any_quota_loaded(sb) &&
+ sbi->s_jquota_fmt != m->mount_opt) {
+ ext4_msg(sb, KERN_ERR, "Cannot change journaled "
+ "quota options when quota turned on");
+ return -1;
+ }
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot set journaled quota options "
+ "when QUOTA feature is enabled");
+ return -1;
+ }
+ sbi->s_jquota_fmt = m->mount_opt;
+#endif
+ } else {
+ if (!args->from)
+ arg = 1;
+ if (m->flags & MOPT_CLEAR)
+ arg = !arg;
+ else if (unlikely(!(m->flags & MOPT_SET))) {
+ ext4_msg(sb, KERN_WARNING,
+ "buggy handling of option %s", opt);
+ WARN_ON(1);
+ return -1;
+ }
+ if (arg != 0)
+ sbi->s_mount_opt |= m->mount_opt;
+ else
+ sbi->s_mount_opt &= ~m->mount_opt;
}
- ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" "
- "or missing value", opt);
- return -1;
+ return 1;
}
static int parse_options(char *options, struct super_block *sb,
@@ -1667,6 +1609,12 @@
return 0;
}
#ifdef CONFIG_QUOTA
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+ (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
+ ext4_msg(sb, KERN_ERR, "Cannot set quota options when QUOTA "
+ "feature is enabled");
+ return 0;
+ }
if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sb, USRQUOTA);
@@ -1979,8 +1927,8 @@
flex_group = ext4_flex_group(sbi, i);
atomic_add(ext4_free_inodes_count(sb, gdp),
&sbi->s_flex_groups[flex_group].free_inodes);
- atomic_add(ext4_free_group_clusters(sb, gdp),
- &sbi->s_flex_groups[flex_group].free_clusters);
+ atomic64_add(ext4_free_group_clusters(sb, gdp),
+ &sbi->s_flex_groups[flex_group].free_clusters);
atomic_add(ext4_used_dirs_count(sb, gdp),
&sbi->s_flex_groups[flex_group].used_dirs);
}
@@ -2776,7 +2724,7 @@
break;
}
- if (group == ngroups)
+ if (group >= ngroups)
ret = 1;
if (!ret) {
@@ -3016,33 +2964,34 @@
return elr;
}
-static int ext4_register_li_request(struct super_block *sb,
- ext4_group_t first_not_zeroed)
+int ext4_register_li_request(struct super_block *sb,
+ ext4_group_t first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_li_request *elr;
+ struct ext4_li_request *elr = NULL;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
int ret = 0;
+ mutex_lock(&ext4_li_mtx);
if (sbi->s_li_request != NULL) {
/*
* Reset timeout so it can be computed again, because
* s_li_wait_mult might have changed.
*/
sbi->s_li_request->lr_timeout = 0;
- return 0;
+ goto out;
}
if (first_not_zeroed == ngroups ||
(sb->s_flags & MS_RDONLY) ||
!test_opt(sb, INIT_INODE_TABLE))
- return 0;
+ goto out;
elr = ext4_li_request_new(sb, first_not_zeroed);
- if (!elr)
- return -ENOMEM;
-
- mutex_lock(&ext4_li_mtx);
+ if (!elr) {
+ ret = -ENOMEM;
+ goto out;
+ }
if (NULL == ext4_li_info) {
ret = ext4_li_info_new();
@@ -3235,7 +3184,7 @@
}
/* Add the journal blocks as well */
if (sbi->s_journal)
- overhead += EXT4_B2C(sbi, sbi->s_journal->j_maxlen);
+ overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
sbi->s_overhead = overhead;
smp_wmb();
@@ -3379,7 +3328,6 @@
#ifdef CONFIG_EXT4_FS_POSIX_ACL
set_opt(sb, POSIX_ACL);
#endif
- set_opt(sb, MBLK_IO_SUBMIT);
if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
set_opt(sb, JOURNAL_DATA);
else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
@@ -3763,6 +3711,9 @@
if (!err) {
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0);
}
+ if (!err) {
+ err = percpu_counter_init(&sbi->s_extent_cache_cnt, 0);
+ }
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount3;
@@ -3772,6 +3723,9 @@
sbi->s_max_writeback_mb_bump = 128;
sbi->s_extent_max_zeroout_kb = 32;
+ /* Register extent status tree shrinker */
+ ext4_es_register_shrinker(sb);
+
/*
* set up enough so that it can read an inode
*/
@@ -3783,13 +3737,11 @@
sb->s_export_op = &ext4_export_ops;
sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
- sb->s_qcop = &ext4_qctl_operations;
sb->dq_op = &ext4_quota_operations;
-
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
- /* Use qctl operations for hidden quota files. */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
sb->s_qcop = &ext4_qctl_sysfile_operations;
- }
+ else
+ sb->s_qcop = &ext4_qctl_operations;
#endif
memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
@@ -3985,6 +3937,16 @@
if (err)
goto failed_mount7;
+#ifdef CONFIG_QUOTA
+ /* Enable quota usage during mount. */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+ !(sb->s_flags & MS_RDONLY)) {
+ err = ext4_enable_quotas(sb);
+ if (err)
+ goto failed_mount8;
+ }
+#endif /* CONFIG_QUOTA */
+
EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
ext4_orphan_cleanup(sb, es);
EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
@@ -4002,16 +3964,6 @@
} else
descr = "out journal";
-#ifdef CONFIG_QUOTA
- /* Enable quota usage during mount. */
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
- !(sb->s_flags & MS_RDONLY)) {
- err = ext4_enable_quotas(sb);
- if (err)
- goto failed_mount7;
- }
-#endif /* CONFIG_QUOTA */
-
if (test_opt(sb, DISCARD)) {
struct request_queue *q = bdev_get_queue(sb->s_bdev);
if (!blk_queue_discard(q))
@@ -4035,6 +3987,10 @@
ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
goto failed_mount;
+#ifdef CONFIG_QUOTA
+failed_mount8:
+ kobject_del(&sbi->s_kobj);
+#endif
failed_mount7:
ext4_unregister_li_request(sb);
failed_mount6:
@@ -4061,6 +4017,7 @@
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_extent_cache_cnt);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
@@ -4476,16 +4433,12 @@
int ext4_force_commit(struct super_block *sb)
{
journal_t *journal;
- int ret = 0;
if (sb->s_flags & MS_RDONLY)
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal)
- ret = ext4_journal_force_commit(journal);
-
- return ret;
+ return ext4_journal_force_commit(journal);
}
static int ext4_sync_fs(struct super_block *sb, int wait)
@@ -4588,7 +4541,7 @@
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
int err = 0;
#ifdef CONFIG_QUOTA
- int i;
+ int i, j;
#endif
char *orig_data = kstrdup(data, GFP_KERNEL);
@@ -4604,7 +4557,17 @@
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++)
- old_opts.s_qf_names[i] = sbi->s_qf_names[i];
+ if (sbi->s_qf_names[i]) {
+ old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
+ GFP_KERNEL);
+ if (!old_opts.s_qf_names[i]) {
+ for (j = 0; j < i; j++)
+ kfree(old_opts.s_qf_names[j]);
+ kfree(orig_data);
+ return -ENOMEM;
+ }
+ } else
+ old_opts.s_qf_names[i] = NULL;
#endif
if (sbi->s_journal && sbi->s_journal->j_task->io_context)
journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
@@ -4737,9 +4700,7 @@
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
- if (old_opts.s_qf_names[i] &&
- old_opts.s_qf_names[i] != sbi->s_qf_names[i])
- kfree(old_opts.s_qf_names[i]);
+ kfree(old_opts.s_qf_names[i]);
if (enable_quota) {
if (sb_any_quota_suspended(sb))
dquot_resume(sb, -1);
@@ -4768,9 +4729,7 @@
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
- if (sbi->s_qf_names[i] &&
- old_opts.s_qf_names[i] != sbi->s_qf_names[i])
- kfree(sbi->s_qf_names[i]);
+ kfree(sbi->s_qf_names[i]);
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
@@ -4835,7 +4794,7 @@
struct inode *inode;
inode = dquot_to_inode(dquot);
- handle = ext4_journal_start(inode,
+ handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
EXT4_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -4851,7 +4810,7 @@
int ret, err;
handle_t *handle;
- handle = ext4_journal_start(dquot_to_inode(dquot),
+ handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA,
EXT4_QUOTA_INIT_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -4867,7 +4826,7 @@
int ret, err;
handle_t *handle;
- handle = ext4_journal_start(dquot_to_inode(dquot),
+ handle = ext4_journal_start(dquot_to_inode(dquot), EXT4_HT_QUOTA,
EXT4_QUOTA_DEL_BLOCKS(dquot->dq_sb));
if (IS_ERR(handle)) {
/* Release dquot anyway to avoid endless cycle in dqput() */
@@ -4883,9 +4842,12 @@
static int ext4_mark_dquot_dirty(struct dquot *dquot)
{
+ struct super_block *sb = dquot->dq_sb;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
/* Are we journaling quotas? */
- if (EXT4_SB(dquot->dq_sb)->s_qf_names[USRQUOTA] ||
- EXT4_SB(dquot->dq_sb)->s_qf_names[GRPQUOTA]) {
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) ||
+ sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
dquot_mark_dquot_dirty(dquot);
return ext4_write_dquot(dquot);
} else {
@@ -4899,7 +4861,7 @@
handle_t *handle;
/* Data block + inode block */
- handle = ext4_journal_start(sb->s_root->d_inode, 2);
+ handle = ext4_journal_start(sb->s_root->d_inode, EXT4_HT_QUOTA, 2);
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit_info(sb, type);
@@ -5005,9 +4967,9 @@
DQUOT_USAGE_ENABLED);
if (err) {
ext4_warning(sb,
- "Failed to enable quota (type=%d) "
- "tracking. Please run e2fsck to fix.",
- type);
+ "Failed to enable quota tracking "
+ "(type=%d, err=%d). Please run "
+ "e2fsck to fix.", type, err);
return err;
}
}
@@ -5045,7 +5007,7 @@
/* Update modification times of quota files when userspace can
* start looking at them */
- handle = ext4_journal_start(inode, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1);
if (IS_ERR(handle))
goto out;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -5194,7 +5156,6 @@
return 0;
return 1;
}
-MODULE_ALIAS("ext2");
#else
static inline void register_as_ext2(void) { }
static inline void unregister_as_ext2(void) { }
@@ -5227,7 +5188,6 @@
return 0;
return 1;
}
-MODULE_ALIAS("ext3");
#else
static inline void register_as_ext3(void) { }
static inline void unregister_as_ext3(void) { }
@@ -5241,6 +5201,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ext4");
static int __init ext4_init_feat_adverts(void)
{
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 3a91ebc..3a120b2 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -549,7 +549,7 @@
error = ext4_handle_dirty_xattr_block(handle, inode, bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
- dquot_free_block(inode, 1);
+ dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
}
@@ -832,7 +832,8 @@
else {
/* The old block is released after updating
the inode. */
- error = dquot_alloc_block(inode, 1);
+ error = dquot_alloc_block(inode,
+ EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
error = ext4_journal_get_write_access(handle,
@@ -886,17 +887,18 @@
(unsigned long long)block);
new_bh = sb_getblk(sb, block);
- if (!new_bh) {
+ if (unlikely(!new_bh)) {
+ error = -ENOMEM;
getblk_failed:
ext4_free_blocks(handle, inode, NULL, block, 1,
EXT4_FREE_BLOCKS_METADATA);
- error = -EIO;
goto cleanup;
}
lock_buffer(new_bh);
error = ext4_journal_get_create_access(handle, new_bh);
if (error) {
unlock_buffer(new_bh);
+ error = -EIO;
goto getblk_failed;
}
memcpy(new_bh->b_data, s->base, new_bh->b_size);
@@ -928,7 +930,7 @@
return error;
cleanup_dquot:
- dquot_free_block(inode, 1);
+ dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1));
goto cleanup;
bad_block:
@@ -1164,17 +1166,10 @@
{
handle_t *handle;
int error, retries = 0;
- int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
+ int credits = ext4_jbd2_credits_xattr(inode);
retry:
- /*
- * In case of inline data, we may push out the data to a block,
- * So reserve the journal space first.
- */
- if (ext4_has_inline_data(inode))
- credits += ext4_writepage_trans_blocks(inode) + 1;
-
- handle = ext4_journal_start(inode, credits);
+ handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
} else {
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 69eda78..aa25deb 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -125,74 +125,6 @@
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is);
-extern int ext4_has_inline_data(struct inode *inode);
-extern int ext4_get_inline_size(struct inode *inode);
-extern int ext4_get_max_inline_size(struct inode *inode);
-extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern void ext4_write_inline_data(struct inode *inode,
- struct ext4_iloc *iloc,
- void *buffer, loff_t pos,
- unsigned int len);
-extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
-extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
- unsigned int len);
-extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
-
-extern int ext4_readpage_inline(struct inode *inode, struct page *page);
-extern int ext4_try_to_write_inline_data(struct address_space *mapping,
- struct inode *inode,
- loff_t pos, unsigned len,
- unsigned flags,
- struct page **pagep);
-extern int ext4_write_inline_data_end(struct inode *inode,
- loff_t pos, unsigned len,
- unsigned copied,
- struct page *page);
-extern struct buffer_head *
-ext4_journalled_write_inline_data(struct inode *inode,
- unsigned len,
- struct page *page);
-extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
- struct inode *inode,
- loff_t pos, unsigned len,
- unsigned flags,
- struct page **pagep,
- void **fsdata);
-extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
- unsigned len, unsigned copied,
- struct page *page);
-extern int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
- struct inode *inode);
-extern int ext4_try_create_inline_dir(handle_t *handle,
- struct inode *parent,
- struct inode *inode);
-extern int ext4_read_inline_dir(struct file *filp,
- void *dirent, filldir_t filldir,
- int *has_inline_data);
-extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
- const struct qstr *d_name,
- struct ext4_dir_entry_2 **res_dir,
- int *has_inline_data);
-extern int ext4_delete_inline_entry(handle_t *handle,
- struct inode *dir,
- struct ext4_dir_entry_2 *de_del,
- struct buffer_head *bh,
- int *has_inline_data);
-extern int empty_inline_dir(struct inode *dir, int *has_inline_data);
-extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
- struct ext4_dir_entry_2 **parent_de,
- int *retval);
-extern int ext4_inline_data_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo,
- int *has_inline);
-extern int ext4_try_to_evict_inline_data(handle_t *handle,
- struct inode *inode,
- int needed);
-extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
-
-extern int ext4_convert_inline_data(struct inode *inode);
-
#ifdef CONFIG_EXT4_FS_SECURITY
extern int ext4_init_security(handle_t *handle, struct inode *inode,
struct inode *dir, const struct qstr *qstr);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ff3c843..2b6fc13 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -72,22 +72,22 @@
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- int err;
+
+ /* Should not write any meta pages, if any IO error was occurred */
+ if (wbc->for_reclaim ||
+ is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG)) {
+ dec_page_count(sbi, F2FS_DIRTY_META);
+ wbc->pages_skipped++;
+ set_page_dirty(page);
+ return AOP_WRITEPAGE_ACTIVATE;
+ }
wait_on_page_writeback(page);
- err = write_meta_page(sbi, page, wbc);
- if (err) {
- wbc->pages_skipped++;
- set_page_dirty(page);
- }
-
+ write_meta_page(sbi, page);
dec_page_count(sbi, F2FS_DIRTY_META);
-
- /* In this case, we should not unlock this page */
- if (err != AOP_WRITEPAGE_ACTIVATE)
- unlock_page(page);
- return err;
+ unlock_page(page);
+ return 0;
}
static int f2fs_write_meta_pages(struct address_space *mapping,
@@ -138,7 +138,10 @@
BUG_ON(page->mapping != mapping);
BUG_ON(!PageDirty(page));
clear_page_dirty_for_io(page);
- f2fs_write_meta_page(page, &wbc);
+ if (f2fs_write_meta_page(page, &wbc)) {
+ unlock_page(page);
+ break;
+ }
if (nwritten++ >= nr_to_write)
break;
}
@@ -161,7 +164,6 @@
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
inc_page_count(sbi, F2FS_DIRTY_META);
- F2FS_SET_SB_DIRT(sbi);
return 1;
}
return 0;
@@ -216,19 +218,11 @@
new->ino = ino;
/* add new_oentry into list which is sorted by inode number */
- if (orphan) {
- struct orphan_inode_entry *prev;
-
- /* get previous entry */
- prev = list_entry(orphan->list.prev, typeof(*prev), list);
- if (&prev->list != head)
- /* insert new orphan inode entry */
- list_add(&new->list, &prev->list);
- else
- list_add(&new->list, head);
- } else {
+ if (orphan)
+ list_add(&new->list, this->prev);
+ else
list_add_tail(&new->list, head);
- }
+
sbi->n_orphans++;
out:
mutex_unlock(&sbi->orphan_inode_mutex);
@@ -545,7 +539,7 @@
/*
* Freeze all the FS-operations for checkpoint.
*/
-void block_operations(struct f2fs_sb_info *sbi)
+static void block_operations(struct f2fs_sb_info *sbi)
{
int t;
struct writeback_control wbc = {
@@ -717,27 +711,24 @@
sbi->alloc_valid_block_count = 0;
/* Here, we only have one bio having CP pack */
- if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG))
- sbi->sb->s_flags |= MS_RDONLY;
- else
- sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+ sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
- clear_prefree_segments(sbi);
- F2FS_RESET_SB_DIRT(sbi);
+ if (!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+ clear_prefree_segments(sbi);
+ F2FS_RESET_SB_DIRT(sbi);
+ }
}
/*
* We guarantee that this checkpoint procedure should not fail.
*/
-void write_checkpoint(struct f2fs_sb_info *sbi, bool blocked, bool is_umount)
+void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
- if (!blocked) {
- mutex_lock(&sbi->cp_mutex);
- block_operations(sbi);
- }
+ mutex_lock(&sbi->cp_mutex);
+ block_operations(sbi);
f2fs_submit_bio(sbi, DATA, true);
f2fs_submit_bio(sbi, NODE, true);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index c8c3730..025b9e2 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -183,10 +183,12 @@
mutex_lock(&f2fs_stat_mutex);
list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
+ char devname[BDEVNAME_SIZE];
update_general_status(si->sbi);
- seq_printf(s, "\n=====[ partition info. #%d ]=====\n", i++);
+ seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
+ bdevname(si->sbi->sb->s_bdev, devname), i++);
seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
si->sit_area_segs, si->nat_area_segs);
seq_printf(s, "[SSA: %d] [MAIN: %d",
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 989980e..a1f3844 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -265,7 +265,7 @@
mutex_unlock_op(sbi, DENTRY_OPS);
}
-void init_dent_inode(struct dentry *dentry, struct page *ipage)
+void init_dent_inode(const struct qstr *name, struct page *ipage)
{
struct f2fs_node *rn;
@@ -274,20 +274,19 @@
wait_on_page_writeback(ipage);
- /* copy dentry info. to this inode page */
+ /* copy name info. to this inode page */
rn = (struct f2fs_node *)page_address(ipage);
- rn->i.i_namelen = cpu_to_le32(dentry->d_name.len);
- memcpy(rn->i.i_name, dentry->d_name.name, dentry->d_name.len);
+ rn->i.i_namelen = cpu_to_le32(name->len);
+ memcpy(rn->i.i_name, name->name, name->len);
set_page_dirty(ipage);
}
-static int init_inode_metadata(struct inode *inode, struct dentry *dentry)
+static int init_inode_metadata(struct inode *inode,
+ struct inode *dir, const struct qstr *name)
{
- struct inode *dir = dentry->d_parent->d_inode;
-
if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
int err;
- err = new_inode_page(inode, dentry);
+ err = new_inode_page(inode, name);
if (err)
return err;
@@ -310,7 +309,7 @@
if (IS_ERR(ipage))
return PTR_ERR(ipage);
set_cold_node(inode, ipage);
- init_dent_inode(dentry, ipage);
+ init_dent_inode(name, ipage);
f2fs_put_page(ipage, 1);
}
if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
@@ -371,7 +370,7 @@
goto next;
}
-int f2fs_add_link(struct dentry *dentry, struct inode *inode)
+int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *inode)
{
unsigned int bit_pos;
unsigned int level;
@@ -380,17 +379,15 @@
f2fs_hash_t dentry_hash;
struct f2fs_dir_entry *de;
unsigned int nbucket, nblock;
- struct inode *dir = dentry->d_parent->d_inode;
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
- const char *name = dentry->d_name.name;
- size_t namelen = dentry->d_name.len;
+ size_t namelen = name->len;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
int slots = GET_DENTRY_SLOTS(namelen);
int err = 0;
int i;
- dentry_hash = f2fs_dentry_hash(name, dentry->d_name.len);
+ dentry_hash = f2fs_dentry_hash(name->name, name->len);
level = 0;
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
@@ -433,7 +430,7 @@
++level;
goto start;
add_dentry:
- err = init_inode_metadata(inode, dentry);
+ err = init_inode_metadata(inode, dir, name);
if (err)
goto fail;
@@ -442,7 +439,7 @@
de = &dentry_blk->dentry[bit_pos];
de->hash_code = dentry_hash;
de->name_len = cpu_to_le16(namelen);
- memcpy(dentry_blk->filename[bit_pos], name, namelen);
+ memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
de->ino = cpu_to_le32(inode->i_ino);
set_de_type(de, inode);
for (i = 0; i < slots; i++)
@@ -603,7 +600,7 @@
static int f2fs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
unsigned long pos = file->f_pos;
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
unsigned long npages = dir_blocks(inode);
unsigned char *types = NULL;
unsigned int bit_pos = 0, start_bit_pos = 0;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c8e2d75..cc2213a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -104,6 +104,20 @@
}
/*
+ * ioctl commands
+ */
+#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
+#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+
+#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
+/*
+ * ioctl commands in 32 bit emulation
+ */
+#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
+#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
+#endif
+
+/*
* For INODE and NODE manager
*/
#define XATTR_NODE_OFFSET (-1) /*
@@ -141,7 +155,7 @@
/* Use below internally in f2fs*/
unsigned long flags; /* use to pass per-file flags */
- unsigned long long data_version;/* lastes version of data for fsync */
+ unsigned long long data_version;/* latest version of data for fsync */
atomic_t dirty_dents; /* # of dirty dentry pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
@@ -573,6 +587,14 @@
return atomic_read(&sbi->nr_pages[count_type]);
}
+static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
+{
+ unsigned int pages_per_sec = sbi->segs_per_sec *
+ (1 << sbi->log_blocks_per_seg);
+ return ((get_pages(sbi, block_type) + pages_per_sec - 1)
+ >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+}
+
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
{
block_t ret;
@@ -842,12 +864,12 @@
int f2fs_setattr(struct dentry *, struct iattr *);
int truncate_hole(struct inode *, pgoff_t, pgoff_t);
long f2fs_ioctl(struct file *, unsigned int, unsigned long);
+long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
/*
* inode.c
*/
void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget_nowait(struct super_block *, unsigned long);
struct inode *f2fs_iget(struct super_block *, unsigned long);
void update_inode(struct inode *, struct page *);
int f2fs_write_inode(struct inode *, struct writeback_control *);
@@ -867,12 +889,18 @@
ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
struct page *, struct inode *);
-void init_dent_inode(struct dentry *, struct page *);
-int f2fs_add_link(struct dentry *, struct inode *);
+void init_dent_inode(const struct qstr *, struct page *);
+int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
int f2fs_make_empty(struct inode *, struct inode *);
bool f2fs_empty_dir(struct inode *);
+static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
+{
+ return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name,
+ inode);
+}
+
/*
* super.c
*/
@@ -896,7 +924,7 @@
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
int remove_inode_page(struct inode *);
-int new_inode_page(struct inode *, struct dentry *);
+int new_inode_page(struct inode *, const struct qstr *);
struct page *new_node_page(struct dnode_of_data *, unsigned int);
void ra_node_page(struct f2fs_sb_info *, nid_t);
struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
@@ -929,8 +957,7 @@
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
struct bio *f2fs_bio_alloc(struct block_device *, int);
void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync);
-int write_meta_page(struct f2fs_sb_info *, struct page *,
- struct writeback_control *);
+void write_meta_page(struct f2fs_sb_info *, struct page *);
void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
block_t, block_t *);
void write_data_page(struct inode *, struct page *, struct dnode_of_data*,
@@ -963,8 +990,7 @@
void set_dirty_dir_page(struct inode *, struct page *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void block_operations(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, bool, bool);
+void write_checkpoint(struct f2fs_sb_info *, bool);
void init_orphan_info(struct f2fs_sb_info *);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 3191b52..958a46d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -15,6 +15,7 @@
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/types.h>
+#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
@@ -28,7 +29,7 @@
struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
block_t old_blk_addr;
struct dnode_of_data dn;
@@ -157,11 +158,11 @@
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
- if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
+ else if (is_inode_flag_set(F2FS_I(inode), FI_NEED_CP))
need_cp = true;
- if (!space_for_roll_forward(sbi))
+ else if (!space_for_roll_forward(sbi))
need_cp = true;
- if (need_to_sync_dir(sbi, inode))
+ else if (need_to_sync_dir(sbi, inode))
need_cp = true;
if (need_cp) {
@@ -298,8 +299,6 @@
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
mark_inode_dirty(inode);
}
-
- f2fs_balance_fs(F2FS_SB(inode->i_sb));
}
static int f2fs_getattr(struct vfsmount *mnt,
@@ -356,6 +355,7 @@
attr->ia_size != i_size_read(inode)) {
truncate_setsize(inode, attr->ia_size);
f2fs_truncate(inode);
+ f2fs_balance_fs(F2FS_SB(inode->i_sb));
}
__setattr_copy(inode, attr);
@@ -387,12 +387,17 @@
static void fill_zero(struct inode *inode, pgoff_t index,
loff_t start, loff_t len)
{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *page;
if (!len)
return;
+ f2fs_balance_fs(sbi);
+
+ mutex_lock_op(sbi, DATA_NEW);
page = get_new_data_page(inode, index, false);
+ mutex_unlock_op(sbi, DATA_NEW);
if (!IS_ERR(page)) {
wait_on_page_writeback(page);
@@ -539,7 +544,7 @@
static long f2fs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
long ret;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
@@ -572,7 +577,7 @@
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int flags;
int ret;
@@ -630,6 +635,23 @@
}
}
+#ifdef CONFIG_COMPAT
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case F2FS_IOC32_GETFLAGS:
+ cmd = F2FS_IOC_GETFLAGS;
+ break;
+ case F2FS_IOC32_SETFLAGS:
+ cmd = F2FS_IOC_SETFLAGS;
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+ return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
+
const struct file_operations f2fs_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
@@ -641,6 +663,9 @@
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = f2fs_compat_ioctl,
+#endif
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
};
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index c386910..94b8a0c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -44,10 +44,10 @@
if (kthread_should_stop())
break;
- f2fs_balance_fs(sbi);
-
- if (!test_opt(sbi, BG_GC))
+ if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
+ wait_ms = GC_THREAD_MAX_SLEEP_TIME;
continue;
+ }
/*
* [GC triggering condition]
@@ -78,7 +78,8 @@
sbi->bg_gc++;
- if (f2fs_gc(sbi) == GC_NONE)
+ /* if return value is not zero, no victim was selected */
+ if (f2fs_gc(sbi))
wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
else if (wait_ms == GC_THREAD_NOGC_SLEEP_TIME)
wait_ms = GC_THREAD_MAX_SLEEP_TIME;
@@ -90,7 +91,10 @@
int start_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th;
+ dev_t dev = sbi->sb->s_bdev->bd_dev;
+ if (!test_opt(sbi, BG_GC))
+ return 0;
gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
if (!gc_th)
return -ENOMEM;
@@ -98,9 +102,10 @@
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
- GC_THREAD_NAME);
+ "f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(gc_th->f2fs_gc_task)) {
kfree(gc_th);
+ sbi->gc_thread = NULL;
return -ENOMEM;
}
return 0;
@@ -141,6 +146,9 @@
static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
struct victim_sel_policy *p)
{
+ /* SSR allocates in a segment unit */
+ if (p->alloc_mode == SSR)
+ return 1 << sbi->log_blocks_per_seg;
if (p->gc_mode == GC_GREEDY)
return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
else if (p->gc_mode == GC_CB)
@@ -356,7 +364,7 @@
sentry = get_seg_entry(sbi, segno);
ret = f2fs_test_bit(offset, sentry->cur_valid_map);
mutex_unlock(&sit_i->sentry_lock);
- return ret ? GC_OK : GC_NEXT;
+ return ret;
}
/*
@@ -364,7 +372,7 @@
* On validity, copy that node with cold status, otherwise (invalid node)
* ignore that.
*/
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
struct f2fs_summary *sum, unsigned int segno, int gc_type)
{
bool initial = true;
@@ -376,21 +384,12 @@
for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
nid_t nid = le32_to_cpu(entry->nid);
struct page *node_page;
- int err;
- /*
- * It makes sure that free segments are able to write
- * all the dirty node pages before CP after this CP.
- * So let's check the space of dirty node pages.
- */
- if (should_do_checkpoint(sbi)) {
- mutex_lock(&sbi->cp_mutex);
- block_operations(sbi);
- return GC_BLOCKED;
- }
+ /* stop BG_GC if there is not enough free sections. */
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+ return;
- err = check_valid_map(sbi, segno, off);
- if (err == GC_NEXT)
+ if (check_valid_map(sbi, segno, off) == 0)
continue;
if (initial) {
@@ -420,7 +419,6 @@
};
sync_node_pages(sbi, 0, &wbc);
}
- return GC_DONE;
}
/*
@@ -463,13 +461,13 @@
node_page = get_node_page(sbi, nid);
if (IS_ERR(node_page))
- return GC_NEXT;
+ return 0;
get_node_info(sbi, nid, dni);
if (sum->version != dni->version) {
f2fs_put_page(node_page, 1);
- return GC_NEXT;
+ return 0;
}
*nofs = ofs_of_node(node_page);
@@ -477,8 +475,8 @@
f2fs_put_page(node_page, 1);
if (source_blkaddr != blkaddr)
- return GC_NEXT;
- return GC_OK;
+ return 0;
+ return 1;
}
static void move_data_page(struct inode *inode, struct page *page, int gc_type)
@@ -519,13 +517,13 @@
* If the parent node is not valid or the data block address is different,
* the victim data block is ignored.
*/
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
struct list_head *ilist, unsigned int segno, int gc_type)
{
struct super_block *sb = sbi->sb;
struct f2fs_summary *entry;
block_t start_addr;
- int err, off;
+ int off;
int phase = 0;
start_addr = START_BLOCK(sbi, segno);
@@ -539,20 +537,11 @@
unsigned int ofs_in_node, nofs;
block_t start_bidx;
- /*
- * It makes sure that free segments are able to write
- * all the dirty node pages before CP after this CP.
- * So let's check the space of dirty node pages.
- */
- if (should_do_checkpoint(sbi)) {
- mutex_lock(&sbi->cp_mutex);
- block_operations(sbi);
- err = GC_BLOCKED;
- goto stop;
- }
+ /* stop BG_GC if there is not enough free sections. */
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+ return;
- err = check_valid_map(sbi, segno, off);
- if (err == GC_NEXT)
+ if (check_valid_map(sbi, segno, off) == 0)
continue;
if (phase == 0) {
@@ -561,8 +550,7 @@
}
/* Get an inode by ino with checking validity */
- err = check_dnode(sbi, entry, &dni, start_addr + off, &nofs);
- if (err == GC_NEXT)
+ if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0)
continue;
if (phase == 1) {
@@ -574,7 +562,7 @@
ofs_in_node = le16_to_cpu(entry->ofs_in_node);
if (phase == 2) {
- inode = f2fs_iget_nowait(sb, dni.ino);
+ inode = f2fs_iget(sb, dni.ino);
if (IS_ERR(inode))
continue;
@@ -602,11 +590,9 @@
}
if (++phase < 4)
goto next_step;
- err = GC_DONE;
-stop:
+
if (gc_type == FG_GC)
f2fs_submit_bio(sbi, DATA, true);
- return err;
}
static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -620,17 +606,16 @@
return ret;
}
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
struct list_head *ilist, int gc_type)
{
struct page *sum_page;
struct f2fs_summary_block *sum;
- int ret = GC_DONE;
/* read segment summary of victim */
sum_page = get_sum_page(sbi, segno);
if (IS_ERR(sum_page))
- return GC_ERROR;
+ return;
/*
* CP needs to lock sum_page. In this time, we don't need
@@ -642,17 +627,16 @@
switch (GET_SUM_TYPE((&sum->footer))) {
case SUM_TYPE_NODE:
- ret = gc_node_segment(sbi, sum->entries, segno, gc_type);
+ gc_node_segment(sbi, sum->entries, segno, gc_type);
break;
case SUM_TYPE_DATA:
- ret = gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
+ gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
break;
}
stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
stat_inc_call_count(sbi->stat_info);
f2fs_put_page(sum_page, 0);
- return ret;
}
int f2fs_gc(struct f2fs_sb_info *sbi)
@@ -660,40 +644,38 @@
struct list_head ilist;
unsigned int segno, i;
int gc_type = BG_GC;
- int gc_status = GC_NONE;
+ int nfree = 0;
+ int ret = -1;
INIT_LIST_HEAD(&ilist);
gc_more:
if (!(sbi->sb->s_flags & MS_ACTIVE))
goto stop;
- if (has_not_enough_free_secs(sbi))
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree))
gc_type = FG_GC;
if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
goto stop;
+ ret = 0;
- for (i = 0; i < sbi->segs_per_sec; i++) {
- /*
- * do_garbage_collect will give us three gc_status:
- * GC_ERROR, GC_DONE, and GC_BLOCKED.
- * If GC is finished uncleanly, we have to return
- * the victim to dirty segment list.
- */
- gc_status = do_garbage_collect(sbi, segno + i, &ilist, gc_type);
- if (gc_status != GC_DONE)
- break;
- }
- if (has_not_enough_free_secs(sbi)) {
- write_checkpoint(sbi, (gc_status == GC_BLOCKED), false);
- if (has_not_enough_free_secs(sbi))
- goto gc_more;
- }
+ for (i = 0; i < sbi->segs_per_sec; i++)
+ do_garbage_collect(sbi, segno + i, &ilist, gc_type);
+
+ if (gc_type == FG_GC &&
+ get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
+ nfree++;
+
+ if (has_not_enough_free_secs(sbi, nfree))
+ goto gc_more;
+
+ if (gc_type == FG_GC)
+ write_checkpoint(sbi, false);
stop:
mutex_unlock(&sbi->gc_mutex);
put_gc_inode(&ilist);
- return gc_status;
+ return ret;
}
void build_gc_manager(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index b026d93..30b2db0 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -8,7 +8,6 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
-#define GC_THREAD_NAME "f2fs_gc_task"
#define GC_THREAD_MIN_WB_PAGES 1 /*
* a threshold to determine
* whether IO subsystem is idle
@@ -23,15 +22,6 @@
/* Search max. number of dirty segments to select a victim segment */
#define MAX_VICTIM_SEARCH 20
-enum {
- GC_NONE = 0,
- GC_ERROR,
- GC_OK,
- GC_NEXT,
- GC_BLOCKED,
- GC_DONE,
-};
-
struct f2fs_gc_kthread {
struct task_struct *f2fs_gc_task;
wait_queue_head_t gc_wait_queue_head;
@@ -104,14 +94,3 @@
struct request_list *rl = &q->root_rl;
return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
}
-
-static inline bool should_do_checkpoint(struct f2fs_sb_info *sbi)
-{
- unsigned int pages_per_sec = sbi->segs_per_sec *
- (1 << sbi->log_blocks_per_seg);
- int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
- int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
- return free_sections(sbi) <= (node_secs + 2 * dent_secs + 2);
-}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 7942417..ddae412 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -16,11 +16,6 @@
#include "f2fs.h"
#include "node.h"
-struct f2fs_iget_args {
- u64 ino;
- int on_free;
-};
-
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
@@ -40,34 +35,6 @@
inode->i_flags |= S_DIRSYNC;
}
-static int f2fs_iget_test(struct inode *inode, void *data)
-{
- struct f2fs_iget_args *args = data;
-
- if (inode->i_ino != args->ino)
- return 0;
- if (inode->i_state & (I_FREEING | I_WILL_FREE)) {
- args->on_free = 1;
- return 0;
- }
- return 1;
-}
-
-struct inode *f2fs_iget_nowait(struct super_block *sb, unsigned long ino)
-{
- struct f2fs_iget_args args = {
- .ino = ino,
- .on_free = 0
- };
- struct inode *inode = ilookup5(sb, ino, f2fs_iget_test, &args);
-
- if (inode)
- return inode;
- if (!args.on_free)
- return f2fs_iget(sb, ino);
- return ERR_PTR(-ENOENT);
-}
-
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -100,6 +67,10 @@
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
+ if (ri->i_addr[0])
+ inode->i_rdev = old_decode_dev(le32_to_cpu(ri->i_addr[0]));
+ else
+ inode->i_rdev = new_decode_dev(le32_to_cpu(ri->i_addr[1]));
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
@@ -203,6 +174,20 @@
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
+
+ if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+ if (old_valid_dev(inode->i_rdev)) {
+ ri->i_addr[0] =
+ cpu_to_le32(old_encode_dev(inode->i_rdev));
+ ri->i_addr[1] = 0;
+ } else {
+ ri->i_addr[0] = 0;
+ ri->i_addr[1] =
+ cpu_to_le32(new_encode_dev(inode->i_rdev));
+ ri->i_addr[2] = 0;
+ }
+ }
+
set_cold_node(inode, node_page);
set_page_dirty(node_page);
}
@@ -260,6 +245,7 @@
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
+ sb_start_intwrite(inode->i_sb);
set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
i_size_write(inode, 0);
@@ -267,6 +253,7 @@
f2fs_truncate(inode);
remove_inode_page(inode);
+ sb_end_intwrite(inode->i_sb);
no_delete:
clear_inode(inode);
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9bda63c..e275218 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -104,7 +104,7 @@
f2fs_put_page(page, 1);
continue;
}
- page_cache_release(page);
+ f2fs_put_page(page, 0);
}
}
@@ -660,7 +660,7 @@
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
int err = 0, cont = 1;
int level, offset[4], noffset[4];
- unsigned int nofs;
+ unsigned int nofs = 0;
struct f2fs_node *rn;
struct dnode_of_data dn;
struct page *page;
@@ -780,7 +780,7 @@
return 0;
}
-int new_inode_page(struct inode *inode, struct dentry *dentry)
+int new_inode_page(struct inode *inode, const struct qstr *name)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct page *page;
@@ -790,7 +790,7 @@
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
mutex_lock_op(sbi, NODE_NEW);
page = new_node_page(&dn, 0);
- init_dent_inode(dentry, page);
+ init_dent_inode(name, page);
mutex_unlock_op(sbi, NODE_NEW);
if (IS_ERR(page))
return PTR_ERR(page);
@@ -874,15 +874,11 @@
return;
if (read_node_page(apage, READA))
- goto unlock_out;
+ unlock_page(apage);
- page_cache_release(apage);
- return;
-
-unlock_out:
- unlock_page(apage);
release_out:
- page_cache_release(apage);
+ f2fs_put_page(apage, 0);
+ return;
}
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
@@ -1139,7 +1135,7 @@
/* First check balancing cached NAT entries */
if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
- write_checkpoint(sbi, false, false);
+ write_checkpoint(sbi, false);
return 0;
}
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index f42e406..b235215 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -42,7 +42,7 @@
{
struct f2fs_node *raw_node = (struct f2fs_node *)kmap(ipage);
struct f2fs_inode *raw_inode = &(raw_node->i);
- struct dentry dent, parent;
+ struct qstr name;
struct f2fs_dir_entry *de;
struct page *page;
struct inode *dir;
@@ -57,17 +57,15 @@
goto out;
}
- parent.d_inode = dir;
- dent.d_parent = &parent;
- dent.d_name.len = le32_to_cpu(raw_inode->i_namelen);
- dent.d_name.name = raw_inode->i_name;
+ name.len = le32_to_cpu(raw_inode->i_namelen);
+ name.name = raw_inode->i_name;
- de = f2fs_find_entry(dir, &dent.d_name, &page);
+ de = f2fs_find_entry(dir, &name, &page);
if (de) {
kunmap(page);
f2fs_put_page(page, 0);
} else {
- err = f2fs_add_link(&dent, inode);
+ err = __f2fs_add_link(dir, &name, inode);
}
iput(dir);
out:
@@ -226,7 +224,7 @@
f2fs_put_page(node_page, 1);
/* Deallocate previous index in the node page */
- inode = f2fs_iget_nowait(sbi->sb, ino);
+ inode = f2fs_iget(sbi->sb, ino);
if (IS_ERR(inode))
return;
@@ -373,5 +371,5 @@
out:
destroy_fsync_dnodes(sbi, &inode_list);
kmem_cache_destroy(fsync_entry_slab);
- write_checkpoint(sbi, false, false);
+ write_checkpoint(sbi, false);
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4b00990..777f17e 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -29,7 +29,7 @@
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
*/
- if (has_not_enough_free_secs(sbi)) {
+ if (has_not_enough_free_secs(sbi, 0)) {
mutex_lock(&sbi->gc_mutex);
f2fs_gc(sbi);
}
@@ -308,7 +308,7 @@
* If there is not enough reserved sections,
* we should not reuse prefree segments.
*/
- if (has_not_enough_free_secs(sbi))
+ if (has_not_enough_free_secs(sbi, 0))
return NULL_SEGNO;
/*
@@ -536,6 +536,23 @@
}
}
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
+ const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+
+ if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0))
+ return v_ops->get_victim(sbi,
+ &(curseg)->next_segno, BG_GC, type, SSR);
+
+ /* For data segments, let's do SSR more intensively */
+ for (; type >= CURSEG_HOT_DATA; type--)
+ if (v_ops->get_victim(sbi, &(curseg)->next_segno,
+ BG_GC, type, SSR))
+ return 1;
+ return 0;
+}
+
/*
* flush out current segment and replace it with new segment
* This function should be returned with success, otherwise BUG
@@ -600,6 +617,7 @@
if (page->mapping)
set_bit(AS_EIO, &page->mapping->flags);
set_ckpt_flags(p->sbi->ckpt, CP_ERROR_FLAG);
+ p->sbi->sb->s_flags |= MS_RDONLY;
}
end_page_writeback(page);
dec_page_count(p->sbi, F2FS_WRITEBACK);
@@ -815,15 +833,10 @@
mutex_unlock(&curseg->curseg_mutex);
}
-int write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
- struct writeback_control *wbc)
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
{
- if (wbc->for_reclaim)
- return AOP_WRITEPAGE_ACTIVATE;
-
set_page_writeback(page);
submit_write_page(sbi, page, page->index, META);
- return 0;
}
void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 66a288a..552dadb 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -450,29 +450,16 @@
return (free_sections(sbi) < overprovision_sections(sbi));
}
-static inline int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
{
- struct curseg_info *curseg = CURSEG_I(sbi, type);
- return DIRTY_I(sbi)->v_ops->get_victim(sbi,
- &(curseg)->next_segno, BG_GC, type, SSR);
-}
-
-static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi)
-{
- unsigned int pages_per_sec = (1 << sbi->log_blocks_per_seg) *
- sbi->segs_per_sec;
- int node_secs = ((get_pages(sbi, F2FS_DIRTY_NODES) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
- int dent_secs = ((get_pages(sbi, F2FS_DIRTY_DENTS) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+ int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+ int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
if (sbi->por_doing)
return false;
- if (free_sections(sbi) <= (node_secs + 2 * dent_secs +
- reserved_sections(sbi)))
- return true;
- return false;
+ return ((free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
+ reserved_sections(sbi)));
}
static inline int utilization(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 37fad04..fea6e58 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -112,7 +112,7 @@
f2fs_destroy_stats(sbi);
stop_gc_thread(sbi);
- write_checkpoint(sbi, false, true);
+ write_checkpoint(sbi, true);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -136,13 +136,29 @@
return 0;
if (sync)
- write_checkpoint(sbi, false, false);
+ write_checkpoint(sbi, false);
else
f2fs_balance_fs(sbi);
return 0;
}
+static int f2fs_freeze(struct super_block *sb)
+{
+ int err;
+
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
+
+ err = f2fs_sync_fs(sb, 1);
+ return err;
+}
+
+static int f2fs_unfreeze(struct super_block *sb)
+{
+ return 0;
+}
+
static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
@@ -198,7 +214,7 @@
seq_puts(seq, ",noacl");
#endif
if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
- seq_puts(seq, ",disable_ext_indentify");
+ seq_puts(seq, ",disable_ext_identify");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
@@ -213,6 +229,8 @@
.evict_inode = f2fs_evict_inode,
.put_super = f2fs_put_super,
.sync_fs = f2fs_sync_fs,
+ .freeze_fs = f2fs_freeze,
+ .unfreeze_fs = f2fs_unfreeze,
.statfs = f2fs_statfs,
};
@@ -366,14 +384,23 @@
return 1;
}
+ /* Currently, support only 4KB page cache size */
+ if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid page_cache_size (%lu), supports only 4KB\n",
+ PAGE_CACHE_SIZE);
+ return 1;
+ }
+
/* Currently, support only 4KB block size */
blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
- if (blocksize != PAGE_CACHE_SIZE) {
+ if (blocksize != F2FS_BLKSIZE) {
f2fs_msg(sb, KERN_INFO,
"Invalid blocksize (%u), supports only 4KB\n",
blocksize);
return 1;
}
+
if (le32_to_cpu(raw_super->log_sectorsize) !=
F2FS_LOG_SECTOR_SIZE) {
f2fs_msg(sb, KERN_INFO, "Invalid log sectorsize");
@@ -387,10 +414,11 @@
return 0;
}
-static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
- struct f2fs_checkpoint *ckpt)
+static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
+ struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
total = le32_to_cpu(raw_super->segment_count);
fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -401,6 +429,11 @@
if (fsmeta >= total)
return 1;
+
+ if (is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
+ return 1;
+ }
return 0;
}
@@ -429,6 +462,32 @@
atomic_set(&sbi->nr_pages[i], 0);
}
+static int validate_superblock(struct super_block *sb,
+ struct f2fs_super_block **raw_super,
+ struct buffer_head **raw_super_buf, sector_t block)
+{
+ const char *super = (block == 0 ? "first" : "second");
+
+ /* read f2fs raw super block */
+ *raw_super_buf = sb_bread(sb, block);
+ if (!*raw_super_buf) {
+ f2fs_msg(sb, KERN_ERR, "unable to read %s superblock",
+ super);
+ return 1;
+ }
+
+ *raw_super = (struct f2fs_super_block *)
+ ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);
+
+ /* sanity checking of raw super */
+ if (!sanity_check_raw_super(sb, *raw_super))
+ return 0;
+
+ f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem "
+ "in %s superblock", super);
+ return 1;
+}
+
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
@@ -449,16 +508,11 @@
goto free_sbi;
}
- /* read f2fs raw super block */
- raw_super_buf = sb_bread(sb, 0);
- if (!raw_super_buf) {
- err = -EIO;
- f2fs_msg(sb, KERN_ERR, "unable to read superblock");
- goto free_sbi;
+ if (validate_superblock(sb, &raw_super, &raw_super_buf, 0)) {
+ brelse(raw_super_buf);
+ if (validate_superblock(sb, &raw_super, &raw_super_buf, 1))
+ goto free_sb_buf;
}
- raw_super = (struct f2fs_super_block *)
- ((char *)raw_super_buf->b_data + F2FS_SUPER_OFFSET);
-
/* init some FS parameters */
sbi->active_logs = NR_CURSEG_TYPE;
@@ -474,12 +528,6 @@
if (parse_options(sb, sbi, (char *)data))
goto free_sb_buf;
- /* sanity checking of raw super */
- if (sanity_check_raw_super(sb, raw_super)) {
- f2fs_msg(sb, KERN_ERR, "Can't find a valid F2FS filesystem");
- goto free_sb_buf;
- }
-
sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
sb->s_max_links = F2FS_LINK_MAX;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
@@ -525,7 +573,7 @@
/* sanity checking of checkpoint */
err = -EINVAL;
- if (sanity_check_ckpt(raw_super, sbi->ckpt)) {
+ if (sanity_check_ckpt(sbi)) {
f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
goto free_cp;
}
@@ -639,6 +687,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("f2fs");
static int __init init_inodecache(void)
{
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 58bf744..165012e 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -698,7 +698,7 @@
static int fat_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
return __fat_readdir(inode, filp, dirent, filldir, 0, 0);
}
@@ -779,7 +779,7 @@
static long fat_dir_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct __fat_dirent __user *d1 = (struct __fat_dirent __user *)arg;
int short_only, both;
@@ -819,7 +819,7 @@
static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd,
unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct compat_dirent __user *d1 = compat_ptr(arg);
int short_only, both;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 12701a5..e9cc3f0 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -95,6 +95,8 @@
spinlock_t dir_hash_lock;
struct hlist_head dir_hashtable[FAT_HASH_SIZE];
+
+ unsigned int dirty; /* fs state before mount */
};
#define FAT_CACHE_VALID 0 /* special case for valid cache */
diff --git a/fs/fat/file.c b/fs/fat/file.c
index a62e0ec..3978f8c 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -32,7 +32,7 @@
static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
int is_dir = S_ISDIR(inode->i_mode);
u32 attr, oldattr;
@@ -116,7 +116,7 @@
long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
u32 __user *user_attr = (u32 __user *)arg;
switch (cmd) {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index f8f4916..acf6e47 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -341,12 +341,11 @@
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);
- struct hlist_node *_p;
struct msdos_inode_info *i;
struct inode *inode = NULL;
spin_lock(&sbi->inode_hash_lock);
- hlist_for_each_entry(i, _p, head, i_fat_hash) {
+ hlist_for_each_entry(i, head, i_fat_hash) {
BUG_ON(i->vfs_inode.i_sb != sb);
if (i->i_pos != i_pos)
continue;
@@ -488,10 +487,59 @@
fat_detach(inode);
}
+static void fat_set_state(struct super_block *sb,
+ unsigned int set, unsigned int force)
+{
+ struct buffer_head *bh;
+ struct fat_boot_sector *b;
+ struct msdos_sb_info *sbi = sb->s_fs_info;
+
+ /* do not change any thing if mounted read only */
+ if ((sb->s_flags & MS_RDONLY) && !force)
+ return;
+
+ /* do not change state if fs was dirty */
+ if (sbi->dirty) {
+ /* warn only on set (mount). */
+ if (set)
+ fat_msg(sb, KERN_WARNING, "Volume was not properly "
+ "unmounted. Some data may be corrupt. "
+ "Please run fsck.");
+ return;
+ }
+
+ bh = sb_bread(sb, 0);
+ if (bh == NULL) {
+ fat_msg(sb, KERN_ERR, "unable to read boot sector "
+ "to mark fs as dirty");
+ return;
+ }
+
+ b = (struct fat_boot_sector *) bh->b_data;
+
+ if (sbi->fat_bits == 32) {
+ if (set)
+ b->fat32.state |= FAT_STATE_DIRTY;
+ else
+ b->fat32.state &= ~FAT_STATE_DIRTY;
+ } else /* fat 16 and 12 */ {
+ if (set)
+ b->fat16.state |= FAT_STATE_DIRTY;
+ else
+ b->fat16.state &= ~FAT_STATE_DIRTY;
+ }
+
+ mark_buffer_dirty(bh);
+ sync_dirty_buffer(bh);
+ brelse(bh);
+}
+
static void fat_put_super(struct super_block *sb)
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ fat_set_state(sb, 0, 0);
+
iput(sbi->fsinfo_inode);
iput(sbi->fat_inode);
@@ -566,8 +614,18 @@
static int fat_remount(struct super_block *sb, int *flags, char *data)
{
+ int new_rdonly;
struct msdos_sb_info *sbi = MSDOS_SB(sb);
*flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
+
+ /* make sure we update state on remount. */
+ new_rdonly = *flags & MS_RDONLY;
+ if (new_rdonly != (sb->s_flags & MS_RDONLY)) {
+ if (new_rdonly)
+ fat_set_state(sb, 0, 0);
+ else
+ fat_set_state(sb, 1, 1);
+ }
return 0;
}
@@ -1298,17 +1356,17 @@
sbi->prev_free = FAT_START_ENT;
sb->s_maxbytes = 0xffffffff;
- if (!sbi->fat_length && b->fat32_length) {
+ if (!sbi->fat_length && b->fat32.length) {
struct fat_boot_fsinfo *fsinfo;
struct buffer_head *fsinfo_bh;
/* Must be FAT32 */
sbi->fat_bits = 32;
- sbi->fat_length = le32_to_cpu(b->fat32_length);
- sbi->root_cluster = le32_to_cpu(b->root_cluster);
+ sbi->fat_length = le32_to_cpu(b->fat32.length);
+ sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster);
/* MC - if info_sector is 0, don't multiply by 0 */
- sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
+ sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector);
if (sbi->fsinfo_sector == 0)
sbi->fsinfo_sector = 1;
@@ -1362,6 +1420,12 @@
if (sbi->fat_bits != 32)
sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12;
+ /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */
+ if (sbi->fat_bits == 32)
+ sbi->dirty = b->fat32.state & FAT_STATE_DIRTY;
+ else /* fat 16 or 12 */
+ sbi->dirty = b->fat16.state & FAT_STATE_DIRTY;
+
/* check that FAT table does not overflow */
fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT);
@@ -1456,6 +1520,7 @@
"the device does not support discard");
}
+ fat_set_state(sb, 1, 0);
return 0;
out_invalid:
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index e2cfda9..081b759 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -668,6 +668,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("msdos");
static int __init init_msdos_fs(void)
{
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index ac959d6..2da9520 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -1073,6 +1073,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("vfat");
static int __init init_vfat_fs(void)
{
diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c
index ef4b5fa..499c104 100644
--- a/fs/fat/nfs.c
+++ b/fs/fat/nfs.c
@@ -21,13 +21,12 @@
{
struct msdos_sb_info *sbi = MSDOS_SB(sb);
struct hlist_head *head;
- struct hlist_node *_p;
struct msdos_inode_info *i;
struct inode *inode = NULL;
head = sbi->dir_hashtable + fat_dir_hash(i_logstart);
spin_lock(&sbi->dir_hash_lock);
- hlist_for_each_entry(i, _p, head, i_dir_hash) {
+ hlist_for_each_entry(i, head, i_dir_hash) {
BUG_ON(i->vfs_inode.i_sb != sb);
if (i->i_logstart != i_logstart)
continue;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 71a600a..6599222 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -30,7 +30,7 @@
static int setfl(int fd, struct file * filp, unsigned long arg)
{
- struct inode * inode = filp->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(filp);
int error = 0;
/*
diff --git a/fs/file.c b/fs/file.c
index 2b3570b..3906d95 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -516,7 +516,7 @@
.close_on_exec = init_files.close_on_exec_init,
.open_fds = init_files.open_fds_init,
},
- .file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock),
+ .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock),
};
/*
diff --git a/fs/file_table.c b/fs/file_table.c
index de9e965..cd4d87a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -94,8 +94,8 @@
#endif
/* Find an unused file structure and return a pointer to it.
- * Returns NULL, if there are no more free file structures or
- * we run out of memory.
+ * Returns an error pointer if some error happend e.g. we over file
+ * structures limit, run out of memory or operation is not permitted.
*
* Be very careful using this. You are responsible for
* getting write access to any mount that you might assign
@@ -107,7 +107,8 @@
{
const struct cred *cred = current_cred();
static long old_max;
- struct file * f;
+ struct file *f;
+ int error;
/*
* Privileged users can go above max_files
@@ -122,13 +123,16 @@
}
f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
- if (f == NULL)
- goto fail;
+ if (unlikely(!f))
+ return ERR_PTR(-ENOMEM);
percpu_counter_inc(&nr_files);
f->f_cred = get_cred(cred);
- if (security_file_alloc(f))
- goto fail_sec;
+ error = security_file_alloc(f);
+ if (unlikely(error)) {
+ file_free(f);
+ return ERR_PTR(error);
+ }
INIT_LIST_HEAD(&f->f_u.fu_list);
atomic_long_set(&f->f_count, 1);
@@ -144,12 +148,7 @@
pr_info("VFS: file-max limit %lu reached\n", get_max_files());
old_max = get_nr_files();
}
- goto fail;
-
-fail_sec:
- file_free(f);
-fail:
- return NULL;
+ return ERR_PTR(-ENFILE);
}
/**
@@ -173,10 +172,11 @@
struct file *file;
file = get_empty_filp();
- if (!file)
- return NULL;
+ if (IS_ERR(file))
+ return file;
file->f_path = *path;
+ file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_mode = mode;
file->f_op = fop;
@@ -259,6 +259,7 @@
drop_file_write_access(file);
file->f_path.dentry = NULL;
file->f_path.mnt = NULL;
+ file->f_inode = NULL;
file_free(file);
dput(dentry);
mntput(mnt);
@@ -447,7 +448,7 @@
lg_global_lock(&files_lglock);
do_file_list_for_each_entry(sb, f) {
- if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
+ if (!S_ISREG(file_inode(f)->i_mode))
continue;
if (!file_count(f))
continue;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index da165f6..92567d9 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -273,7 +273,7 @@
int len = dot ? dot - name : strlen(name);
fs = __get_fs_type(name, len);
- if (!fs && (request_module("%.*s", len, name) == 0))
+ if (!fs && (request_module("fs-%.*s", len, name) == 0))
fs = __get_fs_type(name, len);
if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index bd447e8..664b07a 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -237,7 +237,7 @@
static int
vxfs_readdir(struct file *fp, void *retp, filldir_t filler)
{
- struct inode *ip = fp->f_path.dentry->d_inode;
+ struct inode *ip = file_inode(fp);
struct super_block *sbp = ip->i_sb;
u_long bsize = sbp->s_blocksize;
u_long page, npages, block, pblocks, nblocks, offset;
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index fed2c8a..e37eb27 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -52,7 +52,6 @@
MODULE_DESCRIPTION("Veritas Filesystem (VxFS) driver");
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS("vxfs"); /* makes mount -t vxfs autoload the module */
static void vxfs_put_super(struct super_block *);
@@ -258,6 +257,8 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("vxfs"); /* makes mount -t vxfs autoload the module */
+MODULE_ALIAS("vxfs");
static int __init
vxfs_init(void)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 310972b..21f46fb 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -318,8 +318,14 @@
static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
- if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, wbc);
+ int ret;
+
+ if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) {
+ trace_writeback_write_inode_start(inode, wbc);
+ ret = inode->i_sb->s_op->write_inode(inode, wbc);
+ trace_writeback_write_inode(inode, wbc);
+ return ret;
+ }
return 0;
}
@@ -450,6 +456,8 @@
WARN_ON(!(inode->i_state & I_SYNC));
+ trace_writeback_single_inode_start(inode, wbc, nr_to_write);
+
ret = do_writepages(mapping, wbc);
/*
@@ -1150,8 +1158,12 @@
* dirty the inode itself
*/
if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ trace_writeback_dirty_inode_start(inode, flags);
+
if (sb->s_op->dirty_inode)
sb->s_op->dirty_inode(inode, flags);
+
+ trace_writeback_dirty_inode(inode, flags);
}
/*
@@ -1332,47 +1344,43 @@
EXPORT_SYMBOL(writeback_inodes_sb);
/**
- * writeback_inodes_sb_if_idle - start writeback if none underway
- * @sb: the superblock
- * @reason: reason why some writeback work was initiated
- *
- * Invoke writeback_inodes_sb if no writeback is currently underway.
- * Returns 1 if writeback was started, 0 if not.
- */
-int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason)
-{
- if (!writeback_in_progress(sb->s_bdi)) {
- down_read(&sb->s_umount);
- writeback_inodes_sb(sb, reason);
- up_read(&sb->s_umount);
- return 1;
- } else
- return 0;
-}
-EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
-
-/**
- * writeback_inodes_sb_nr_if_idle - start writeback if none underway
+ * try_to_writeback_inodes_sb_nr - try to start writeback if none underway
* @sb: the superblock
* @nr: the number of pages to write
- * @reason: reason why some writeback work was initiated
+ * @reason: the reason of writeback
*
- * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Invoke writeback_inodes_sb_nr if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
*/
-int writeback_inodes_sb_nr_if_idle(struct super_block *sb,
- unsigned long nr,
- enum wb_reason reason)
+int try_to_writeback_inodes_sb_nr(struct super_block *sb,
+ unsigned long nr,
+ enum wb_reason reason)
{
- if (!writeback_in_progress(sb->s_bdi)) {
- down_read(&sb->s_umount);
- writeback_inodes_sb_nr(sb, nr, reason);
- up_read(&sb->s_umount);
+ if (writeback_in_progress(sb->s_bdi))
return 1;
- } else
+
+ if (!down_read_trylock(&sb->s_umount))
return 0;
+
+ writeback_inodes_sb_nr(sb, nr, reason);
+ up_read(&sb->s_umount);
+ return 1;
}
-EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle);
+EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);
+
+/**
+ * try_to_writeback_inodes_sb - try to start writeback if none underway
+ * @sb: the superblock
+ * @reason: reason why some writeback work was initiated
+ *
+ * Implement by try_to_writeback_inodes_sb_nr()
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
+{
+ return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
+}
+EXPORT_SYMBOL(try_to_writeback_inodes_sb);
/**
* sync_inodes_sb - sync sb inode pages
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index fe6ca58..d8ac61d 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -10,7 +10,7 @@
* Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
* It can block.
*/
-void set_fs_root(struct fs_struct *fs, struct path *path)
+void set_fs_root(struct fs_struct *fs, const struct path *path)
{
struct path old_root;
@@ -29,7 +29,7 @@
* Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
* It can block.
*/
-void set_fs_pwd(struct fs_struct *fs, struct path *path)
+void set_fs_pwd(struct fs_struct *fs, const struct path *path)
{
struct path old_pwd;
@@ -53,7 +53,7 @@
return 1;
}
-void chroot_fs_refs(struct path *old_root, struct path *new_root)
+void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
{
struct task_struct *g, *p;
struct fs_struct *fs;
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 8dcb114..e2cba1f 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -237,13 +237,12 @@
struct fscache_cookie *cookie)
{
struct fscache_object *object;
- struct hlist_node *_n;
int ret;
_enter("%p,%p{%s}", cache, cookie, cookie->def->name);
spin_lock(&cookie->lock);
- hlist_for_each_entry(object, _n, &cookie->backing_objects,
+ hlist_for_each_entry(object, &cookie->backing_objects,
cookie_link) {
if (object->cache == cache)
goto object_already_extant;
@@ -311,7 +310,6 @@
{
struct fscache_object *p;
struct fscache_cache *cache = object->cache;
- struct hlist_node *_n;
int ret;
_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
@@ -321,7 +319,7 @@
/* there may be multiple initial creations of this object, but we only
* want one */
ret = -EEXIST;
- hlist_for_each_entry(p, _n, &cookie->backing_objects, cookie_link) {
+ hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) {
if (p->cache == object->cache) {
if (p->state >= FSCACHE_OBJECT_DYING)
ret = -ENOBUFS;
@@ -331,7 +329,7 @@
/* pin the parent object */
spin_lock_nested(&cookie->parent->lock, 1);
- hlist_for_each_entry(p, _n, &cookie->parent->backing_objects,
+ hlist_for_each_entry(p, &cookie->parent->backing_objects,
cookie_link) {
if (p->cache == object->cache) {
if (p->state >= FSCACHE_OBJECT_DYING) {
@@ -435,7 +433,6 @@
void __fscache_update_cookie(struct fscache_cookie *cookie)
{
struct fscache_object *object;
- struct hlist_node *_p;
fscache_stat(&fscache_n_updates);
@@ -452,7 +449,7 @@
spin_lock(&cookie->lock);
/* update the index entry on disk in each cache backing this cookie */
- hlist_for_each_entry(object, _p,
+ hlist_for_each_entry(object,
&cookie->backing_objects, cookie_link) {
fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
}
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 75a20c0..a0b0855 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -23,7 +23,7 @@
{
struct fuse_conn *fc;
mutex_lock(&fuse_mutex);
- fc = file->f_path.dentry->d_inode->i_private;
+ fc = file_inode(file)->i_private;
if (fc)
fc = fuse_conn_get(fc);
mutex_unlock(&fuse_mutex);
@@ -341,6 +341,7 @@
.mount = fuse_ctl_mount,
.kill_sb = fuse_ctl_kill_sb,
};
+MODULE_ALIAS_FS("fusectl");
int __init fuse_ctl_init(void)
{
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index e397b67..6f96a8d 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -91,19 +91,22 @@
loff_t *ppos)
{
loff_t pos = 0;
+ struct iovec iov = { .iov_base = buf, .iov_len = count };
- return fuse_direct_io(file, buf, count, &pos, 0);
+ return fuse_direct_io(file, &iov, 1, count, &pos, 0);
}
static ssize_t cuse_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
loff_t pos = 0;
+ struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
+
/*
* No locking or generic_write_checks(), the server is
* responsible for locking and sanity checks.
*/
- return fuse_direct_io(file, buf, count, &pos, 1);
+ return fuse_direct_io(file, &iov, 1, count, &pos, 1);
}
static int cuse_open(struct inode *inode, struct file *file)
@@ -419,7 +422,7 @@
BUILD_BUG_ON(CUSE_INIT_INFO_MAX > PAGE_SIZE);
- req = fuse_get_req(fc);
+ req = fuse_get_req(fc, 1);
if (IS_ERR(req)) {
rc = PTR_ERR(req);
goto err;
@@ -449,6 +452,7 @@
req->out.argvar = 1;
req->out.argpages = 1;
req->pages[0] = page;
+ req->page_descs[0].length = req->out.args[1].size;
req->num_pages = 1;
req->end = cuse_process_init_reply;
fuse_request_send_background(fc, req);
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e83351a..11dfa0c 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -34,34 +34,67 @@
return file->private_data;
}
-static void fuse_request_init(struct fuse_req *req)
+static void fuse_request_init(struct fuse_req *req, struct page **pages,
+ struct fuse_page_desc *page_descs,
+ unsigned npages)
{
memset(req, 0, sizeof(*req));
+ memset(pages, 0, sizeof(*pages) * npages);
+ memset(page_descs, 0, sizeof(*page_descs) * npages);
INIT_LIST_HEAD(&req->list);
INIT_LIST_HEAD(&req->intr_entry);
init_waitqueue_head(&req->waitq);
atomic_set(&req->count, 1);
+ req->pages = pages;
+ req->page_descs = page_descs;
+ req->max_pages = npages;
}
-struct fuse_req *fuse_request_alloc(void)
+static struct fuse_req *__fuse_request_alloc(unsigned npages, gfp_t flags)
{
- struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, GFP_KERNEL);
- if (req)
- fuse_request_init(req);
+ struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, flags);
+ if (req) {
+ struct page **pages;
+ struct fuse_page_desc *page_descs;
+
+ if (npages <= FUSE_REQ_INLINE_PAGES) {
+ pages = req->inline_pages;
+ page_descs = req->inline_page_descs;
+ } else {
+ pages = kmalloc(sizeof(struct page *) * npages, flags);
+ page_descs = kmalloc(sizeof(struct fuse_page_desc) *
+ npages, flags);
+ }
+
+ if (!pages || !page_descs) {
+ kfree(pages);
+ kfree(page_descs);
+ kmem_cache_free(fuse_req_cachep, req);
+ return NULL;
+ }
+
+ fuse_request_init(req, pages, page_descs, npages);
+ }
return req;
}
+
+struct fuse_req *fuse_request_alloc(unsigned npages)
+{
+ return __fuse_request_alloc(npages, GFP_KERNEL);
+}
EXPORT_SYMBOL_GPL(fuse_request_alloc);
-struct fuse_req *fuse_request_alloc_nofs(void)
+struct fuse_req *fuse_request_alloc_nofs(unsigned npages)
{
- struct fuse_req *req = kmem_cache_alloc(fuse_req_cachep, GFP_NOFS);
- if (req)
- fuse_request_init(req);
- return req;
+ return __fuse_request_alloc(npages, GFP_NOFS);
}
void fuse_request_free(struct fuse_req *req)
{
+ if (req->pages != req->inline_pages) {
+ kfree(req->pages);
+ kfree(req->page_descs);
+ }
kmem_cache_free(fuse_req_cachep, req);
}
@@ -97,7 +130,7 @@
req->in.h.pid = current->pid;
}
-struct fuse_req *fuse_get_req(struct fuse_conn *fc)
+struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages)
{
struct fuse_req *req;
sigset_t oldset;
@@ -116,7 +149,7 @@
if (!fc->connected)
goto out;
- req = fuse_request_alloc();
+ req = fuse_request_alloc(npages);
err = -ENOMEM;
if (!req)
goto out;
@@ -165,7 +198,7 @@
struct fuse_file *ff = file->private_data;
spin_lock(&fc->lock);
- fuse_request_init(req);
+ fuse_request_init(req, req->pages, req->page_descs, req->max_pages);
BUG_ON(ff->reserved_req);
ff->reserved_req = req;
wake_up_all(&fc->reserved_req_waitq);
@@ -186,13 +219,14 @@
* filesystem should not have it's own file open. If deadlock is
* intentional, it can still be broken by "aborting" the filesystem.
*/
-struct fuse_req *fuse_get_req_nofail(struct fuse_conn *fc, struct file *file)
+struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
+ struct file *file)
{
struct fuse_req *req;
atomic_inc(&fc->num_waiting);
wait_event(fc->blocked_waitq, !fc->blocked);
- req = fuse_request_alloc();
+ req = fuse_request_alloc(0);
if (!req)
req = get_reserved_req(fc, file);
@@ -406,9 +440,8 @@
}
}
-void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
+static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
{
- req->isreply = 1;
spin_lock(&fc->lock);
if (!fc->connected)
req->out.h.error = -ENOTCONN;
@@ -425,6 +458,12 @@
}
spin_unlock(&fc->lock);
}
+
+void fuse_request_send(struct fuse_conn *fc, struct fuse_req *req)
+{
+ req->isreply = 1;
+ __fuse_request_send(fc, req);
+}
EXPORT_SYMBOL_GPL(fuse_request_send);
static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
@@ -491,6 +530,27 @@
fuse_request_send_nowait_locked(fc, req);
}
+void fuse_force_forget(struct file *file, u64 nodeid)
+{
+ struct inode *inode = file_inode(file);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_req *req;
+ struct fuse_forget_in inarg;
+
+ memset(&inarg, 0, sizeof(inarg));
+ inarg.nlookup = 1;
+ req = fuse_get_req_nofail_nopages(fc, file);
+ req->in.h.opcode = FUSE_FORGET;
+ req->in.h.nodeid = nodeid;
+ req->in.numargs = 1;
+ req->in.args[0].size = sizeof(inarg);
+ req->in.args[0].value = &inarg;
+ req->isreply = 0;
+ __fuse_request_send(fc, req);
+ /* ignore errors */
+ fuse_put_request(fc, req);
+}
+
/*
* Lock the request. Up to the next unlock_request() there mustn't be
* anything that could cause a page-fault. If the request was already
@@ -850,11 +910,11 @@
{
unsigned i;
struct fuse_req *req = cs->req;
- unsigned offset = req->page_offset;
- unsigned count = min(nbytes, (unsigned) PAGE_SIZE - offset);
for (i = 0; i < req->num_pages && (nbytes || zeroing); i++) {
int err;
+ unsigned offset = req->page_descs[i].offset;
+ unsigned count = min(nbytes, req->page_descs[i].length);
err = fuse_copy_page(cs, &req->pages[i], offset, count,
zeroing);
@@ -862,8 +922,6 @@
return err;
nbytes -= count;
- count = min(nbytes, (unsigned) PAGE_SIZE);
- offset = 0;
}
return 0;
}
@@ -1536,29 +1594,34 @@
unsigned int num;
unsigned int offset;
size_t total_len = 0;
-
- req = fuse_get_req(fc);
- if (IS_ERR(req))
- return PTR_ERR(req);
+ int num_pages;
offset = outarg->offset & ~PAGE_CACHE_MASK;
-
- req->in.h.opcode = FUSE_NOTIFY_REPLY;
- req->in.h.nodeid = outarg->nodeid;
- req->in.numargs = 2;
- req->in.argpages = 1;
- req->page_offset = offset;
- req->end = fuse_retrieve_end;
-
- index = outarg->offset >> PAGE_CACHE_SHIFT;
file_size = i_size_read(inode);
+
num = outarg->size;
if (outarg->offset > file_size)
num = 0;
else if (outarg->offset + num > file_size)
num = file_size - outarg->offset;
- while (num && req->num_pages < FUSE_MAX_PAGES_PER_REQ) {
+ num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ num_pages = min(num_pages, FUSE_MAX_PAGES_PER_REQ);
+
+ req = fuse_get_req(fc, num_pages);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ req->in.h.opcode = FUSE_NOTIFY_REPLY;
+ req->in.h.nodeid = outarg->nodeid;
+ req->in.numargs = 2;
+ req->in.argpages = 1;
+ req->page_descs[0].offset = offset;
+ req->end = fuse_retrieve_end;
+
+ index = outarg->offset >> PAGE_CACHE_SHIFT;
+
+ while (num && req->num_pages < num_pages) {
struct page *page;
unsigned int this_num;
@@ -1568,6 +1631,7 @@
this_num = min_t(unsigned, num, PAGE_CACHE_SIZE - offset);
req->pages[req->num_pages] = page;
+ req->page_descs[req->num_pages].length = this_num;
req->num_pages++;
offset = 0;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b7c09f9..ff15522 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -14,6 +14,29 @@
#include <linux/namei.h>
#include <linux/slab.h>
+static bool fuse_use_readdirplus(struct inode *dir, struct file *filp)
+{
+ struct fuse_conn *fc = get_fuse_conn(dir);
+ struct fuse_inode *fi = get_fuse_inode(dir);
+
+ if (!fc->do_readdirplus)
+ return false;
+ if (!fc->readdirplus_auto)
+ return true;
+ if (test_and_clear_bit(FUSE_I_ADVISE_RDPLUS, &fi->state))
+ return true;
+ if (filp->f_pos == 0)
+ return true;
+ return false;
+}
+
+static void fuse_advise_use_readdirplus(struct inode *dir)
+{
+ struct fuse_inode *fi = get_fuse_inode(dir);
+
+ set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
+}
+
#if BITS_PER_LONG >= 64
static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
{
@@ -178,7 +201,7 @@
return -ECHILD;
fc = get_fuse_conn(inode);
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return 0;
@@ -219,6 +242,7 @@
attr_version);
fuse_change_entry_timeout(entry, &outarg);
}
+ fuse_advise_use_readdirplus(inode);
return 1;
}
@@ -271,7 +295,7 @@
if (name->len > FUSE_NAME_MAX)
goto out;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
err = PTR_ERR(req);
if (IS_ERR(req))
goto out;
@@ -355,6 +379,7 @@
else
fuse_invalidate_entry_cache(entry);
+ fuse_advise_use_readdirplus(dir);
return newent;
out_iput:
@@ -391,7 +416,7 @@
if (!forget)
goto out_err;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
err = PTR_ERR(req);
if (IS_ERR(req))
goto out_put_forget_req;
@@ -592,7 +617,7 @@
{
struct fuse_mknod_in inarg;
struct fuse_conn *fc = get_fuse_conn(dir);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -623,7 +648,7 @@
{
struct fuse_mkdir_in inarg;
struct fuse_conn *fc = get_fuse_conn(dir);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -647,7 +672,7 @@
{
struct fuse_conn *fc = get_fuse_conn(dir);
unsigned len = strlen(link) + 1;
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -664,7 +689,7 @@
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -682,7 +707,14 @@
spin_lock(&fc->lock);
fi->attr_version = ++fc->attr_version;
- drop_nlink(inode);
+ /*
+ * If i_nlink == 0 then unlink doesn't make sense, yet this can
+ * happen if userspace filesystem is careless. It would be
+ * difficult to enforce correct nlink usage so just ignore this
+ * condition here
+ */
+ if (inode->i_nlink > 0)
+ drop_nlink(inode);
spin_unlock(&fc->lock);
fuse_invalidate_attr(inode);
fuse_invalidate_attr(dir);
@@ -696,7 +728,7 @@
{
int err;
struct fuse_conn *fc = get_fuse_conn(dir);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -723,7 +755,7 @@
int err;
struct fuse_rename_in inarg;
struct fuse_conn *fc = get_fuse_conn(olddir);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -776,7 +808,7 @@
struct fuse_link_in inarg;
struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -848,7 +880,7 @@
struct fuse_req *req;
u64 attr_version;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -985,7 +1017,7 @@
/*
* Calling into a user-controlled filesystem gives the filesystem
- * daemon ptrace-like capabilities over the requester process. This
+ * daemon ptrace-like capabilities over the current process. This
* means, that the filesystem daemon is able to record the exact
* filesystem operations performed, and can also control the behavior
* of the requester process in otherwise impossible ways. For example
@@ -996,27 +1028,23 @@
* for which the owner of the mount has ptrace privilege. This
* excludes processes started by other users, suid or sgid processes.
*/
-int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task)
+int fuse_allow_current_process(struct fuse_conn *fc)
{
const struct cred *cred;
- int ret;
if (fc->flags & FUSE_ALLOW_OTHER)
return 1;
- rcu_read_lock();
- ret = 0;
- cred = __task_cred(task);
+ cred = current_cred();
if (uid_eq(cred->euid, fc->user_id) &&
uid_eq(cred->suid, fc->user_id) &&
uid_eq(cred->uid, fc->user_id) &&
gid_eq(cred->egid, fc->group_id) &&
gid_eq(cred->sgid, fc->group_id) &&
gid_eq(cred->gid, fc->group_id))
- ret = 1;
- rcu_read_unlock();
+ return 1;
- return ret;
+ return 0;
}
static int fuse_access(struct inode *inode, int mask)
@@ -1029,7 +1057,7 @@
if (fc->no_access)
return 0;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1077,7 +1105,7 @@
bool refreshed = false;
int err = 0;
- if (!fuse_allow_task(fc, current))
+ if (!fuse_allow_current_process(fc))
return -EACCES;
/*
@@ -1155,19 +1183,157 @@
return 0;
}
-static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir)
+static int fuse_direntplus_link(struct file *file,
+ struct fuse_direntplus *direntplus,
+ u64 attr_version)
{
int err;
+ struct fuse_entry_out *o = &direntplus->entry_out;
+ struct fuse_dirent *dirent = &direntplus->dirent;
+ struct dentry *parent = file->f_path.dentry;
+ struct qstr name = QSTR_INIT(dirent->name, dirent->namelen);
+ struct dentry *dentry;
+ struct dentry *alias;
+ struct inode *dir = parent->d_inode;
+ struct fuse_conn *fc;
+ struct inode *inode;
+
+ if (!o->nodeid) {
+ /*
+ * Unlike in the case of fuse_lookup, zero nodeid does not mean
+ * ENOENT. Instead, it only means the userspace filesystem did
+ * not want to return attributes/handle for this entry.
+ *
+ * So do nothing.
+ */
+ return 0;
+ }
+
+ if (name.name[0] == '.') {
+ /*
+ * We could potentially refresh the attributes of the directory
+ * and its parent?
+ */
+ if (name.len == 1)
+ return 0;
+ if (name.name[1] == '.' && name.len == 2)
+ return 0;
+ }
+ fc = get_fuse_conn(dir);
+
+ name.hash = full_name_hash(name.name, name.len);
+ dentry = d_lookup(parent, &name);
+ if (dentry && dentry->d_inode) {
+ inode = dentry->d_inode;
+ if (get_node_id(inode) == o->nodeid) {
+ struct fuse_inode *fi;
+ fi = get_fuse_inode(inode);
+ spin_lock(&fc->lock);
+ fi->nlookup++;
+ spin_unlock(&fc->lock);
+
+ /*
+ * The other branch to 'found' comes via fuse_iget()
+ * which bumps nlookup inside
+ */
+ goto found;
+ }
+ err = d_invalidate(dentry);
+ if (err)
+ goto out;
+ dput(dentry);
+ dentry = NULL;
+ }
+
+ dentry = d_alloc(parent, &name);
+ err = -ENOMEM;
+ if (!dentry)
+ goto out;
+
+ inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
+ &o->attr, entry_attr_timeout(o), attr_version);
+ if (!inode)
+ goto out;
+
+ alias = d_materialise_unique(dentry, inode);
+ err = PTR_ERR(alias);
+ if (IS_ERR(alias))
+ goto out;
+ if (alias) {
+ dput(dentry);
+ dentry = alias;
+ }
+
+found:
+ fuse_change_attributes(inode, &o->attr, entry_attr_timeout(o),
+ attr_version);
+
+ fuse_change_entry_timeout(dentry, o);
+
+ err = 0;
+out:
+ if (dentry)
+ dput(dentry);
+ return err;
+}
+
+static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file,
+ void *dstbuf, filldir_t filldir, u64 attr_version)
+{
+ struct fuse_direntplus *direntplus;
+ struct fuse_dirent *dirent;
+ size_t reclen;
+ int over = 0;
+ int ret;
+
+ while (nbytes >= FUSE_NAME_OFFSET_DIRENTPLUS) {
+ direntplus = (struct fuse_direntplus *) buf;
+ dirent = &direntplus->dirent;
+ reclen = FUSE_DIRENTPLUS_SIZE(direntplus);
+
+ if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX)
+ return -EIO;
+ if (reclen > nbytes)
+ break;
+
+ if (!over) {
+ /* We fill entries into dstbuf only as much as
+ it can hold. But we still continue iterating
+ over remaining entries to link them. If not,
+ we need to send a FORGET for each of those
+ which we did not link.
+ */
+ over = filldir(dstbuf, dirent->name, dirent->namelen,
+ file->f_pos, dirent->ino,
+ dirent->type);
+ file->f_pos = dirent->off;
+ }
+
+ buf += reclen;
+ nbytes -= reclen;
+
+ ret = fuse_direntplus_link(file, direntplus, attr_version);
+ if (ret)
+ fuse_force_forget(file, direntplus->entry_out.nodeid);
+ }
+
+ return 0;
+}
+
+static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir)
+{
+ int plus, err;
size_t nbytes;
struct page *page;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
+ u64 attr_version = 0;
if (is_bad_inode(inode))
return -EIO;
- req = fuse_get_req(fc);
+ req = fuse_get_req(fc, 1);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1176,17 +1342,34 @@
fuse_put_request(fc, req);
return -ENOMEM;
}
+
+ plus = fuse_use_readdirplus(inode, file);
req->out.argpages = 1;
req->num_pages = 1;
req->pages[0] = page;
- fuse_read_fill(req, file, file->f_pos, PAGE_SIZE, FUSE_READDIR);
+ req->page_descs[0].length = PAGE_SIZE;
+ if (plus) {
+ attr_version = fuse_get_attr_version(fc);
+ fuse_read_fill(req, file, file->f_pos, PAGE_SIZE,
+ FUSE_READDIRPLUS);
+ } else {
+ fuse_read_fill(req, file, file->f_pos, PAGE_SIZE,
+ FUSE_READDIR);
+ }
fuse_request_send(fc, req);
nbytes = req->out.args[0].size;
err = req->out.h.error;
fuse_put_request(fc, req);
- if (!err)
- err = parse_dirfile(page_address(page), nbytes, file, dstbuf,
- filldir);
+ if (!err) {
+ if (plus) {
+ err = parse_dirplusfile(page_address(page), nbytes,
+ file, dstbuf, filldir,
+ attr_version);
+ } else {
+ err = parse_dirfile(page_address(page), nbytes, file,
+ dstbuf, filldir);
+ }
+ }
__free_page(page);
fuse_invalidate_attr(inode); /* atime changed */
@@ -1197,7 +1380,7 @@
{
struct inode *inode = dentry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
- struct fuse_req *req = fuse_get_req(fc);
+ struct fuse_req *req = fuse_get_req_nopages(fc);
char *link;
if (IS_ERR(req))
@@ -1391,7 +1574,7 @@
loff_t oldsize;
int err;
- if (!fuse_allow_task(fc, current))
+ if (!fuse_allow_current_process(fc))
return -EACCES;
if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
@@ -1410,7 +1593,7 @@
if (attr->ia_valid & ATTR_SIZE)
is_truncate = true;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1500,7 +1683,7 @@
struct inode *inode = entry->d_inode;
struct fuse_conn *fc = get_fuse_conn(inode);
- if (!fuse_allow_task(fc, current))
+ if (!fuse_allow_current_process(fc))
return -EACCES;
return fuse_update_attributes(inode, stat, NULL, NULL);
@@ -1518,7 +1701,7 @@
if (fc->no_setxattr)
return -EOPNOTSUPP;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1557,7 +1740,7 @@
if (fc->no_getxattr)
return -EOPNOTSUPP;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1603,13 +1786,13 @@
struct fuse_getxattr_out outarg;
ssize_t ret;
- if (!fuse_allow_task(fc, current))
+ if (!fuse_allow_current_process(fc))
return -EACCES;
if (fc->no_listxattr)
return -EOPNOTSUPP;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1654,7 +1837,7 @@
if (fc->no_removexattr)
return -EOPNOTSUPP;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f3ab824..34b80ba 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -25,7 +25,7 @@
struct fuse_req *req;
int err;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -57,7 +57,7 @@
return NULL;
ff->fc = fc;
- ff->reserved_req = fuse_request_alloc();
+ ff->reserved_req = fuse_request_alloc(0);
if (unlikely(!ff->reserved_req)) {
kfree(ff);
return NULL;
@@ -355,7 +355,7 @@
static int fuse_flush(struct file *file, fl_owner_t id)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_file *ff = file->private_data;
struct fuse_req *req;
@@ -368,7 +368,7 @@
if (fc->no_flush)
return 0;
- req = fuse_get_req_nofail(fc, file);
+ req = fuse_get_req_nofail_nopages(fc, file);
memset(&inarg, 0, sizeof(inarg));
inarg.fh = ff->fh;
inarg.lock_owner = fuse_lock_owner_id(fc, id);
@@ -436,7 +436,7 @@
fuse_sync_writes(inode);
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out;
@@ -544,7 +544,7 @@
*/
fuse_wait_on_page_writeback(inode, page->index);
- req = fuse_get_req(fc);
+ req = fuse_get_req(fc, 1);
err = PTR_ERR(req);
if (IS_ERR(req))
goto out;
@@ -555,6 +555,7 @@
req->out.argpages = 1;
req->num_pages = 1;
req->pages[0] = page;
+ req->page_descs[0].length = count;
num_read = fuse_send_read(req, file, pos, count, NULL);
err = req->out.h.error;
fuse_put_request(fc, req);
@@ -641,6 +642,7 @@
struct fuse_req *req;
struct file *file;
struct inode *inode;
+ unsigned nr_pages;
};
static int fuse_readpages_fill(void *_data, struct page *page)
@@ -656,16 +658,26 @@
(req->num_pages == FUSE_MAX_PAGES_PER_REQ ||
(req->num_pages + 1) * PAGE_CACHE_SIZE > fc->max_read ||
req->pages[req->num_pages - 1]->index + 1 != page->index)) {
+ int nr_alloc = min_t(unsigned, data->nr_pages,
+ FUSE_MAX_PAGES_PER_REQ);
fuse_send_readpages(req, data->file);
- data->req = req = fuse_get_req(fc);
+ data->req = req = fuse_get_req(fc, nr_alloc);
if (IS_ERR(req)) {
unlock_page(page);
return PTR_ERR(req);
}
}
+
+ if (WARN_ON(req->num_pages >= req->max_pages)) {
+ fuse_put_request(fc, req);
+ return -EIO;
+ }
+
page_cache_get(page);
req->pages[req->num_pages] = page;
+ req->page_descs[req->num_pages].length = PAGE_SIZE;
req->num_pages++;
+ data->nr_pages--;
return 0;
}
@@ -676,6 +688,7 @@
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_fill_data data;
int err;
+ int nr_alloc = min_t(unsigned, nr_pages, FUSE_MAX_PAGES_PER_REQ);
err = -EIO;
if (is_bad_inode(inode))
@@ -683,7 +696,8 @@
data.file = file;
data.inode = inode;
- data.req = fuse_get_req(fc);
+ data.req = fuse_get_req(fc, nr_alloc);
+ data.nr_pages = nr_pages;
err = PTR_ERR(data.req);
if (IS_ERR(data.req))
goto out;
@@ -786,7 +800,7 @@
res = fuse_send_write(req, file, pos, count, NULL);
- offset = req->page_offset;
+ offset = req->page_descs[0].offset;
count = res;
for (i = 0; i < req->num_pages; i++) {
struct page *page = req->pages[i];
@@ -817,7 +831,7 @@
int err;
req->in.argpages = 1;
- req->page_offset = offset;
+ req->page_descs[0].offset = offset;
do {
size_t tmp;
@@ -857,6 +871,7 @@
err = 0;
req->pages[req->num_pages] = page;
+ req->page_descs[req->num_pages].length = tmp;
req->num_pages++;
iov_iter_advance(ii, tmp);
@@ -869,11 +884,19 @@
if (!fc->big_writes)
break;
} while (iov_iter_count(ii) && count < fc->max_write &&
- req->num_pages < FUSE_MAX_PAGES_PER_REQ && offset == 0);
+ req->num_pages < req->max_pages && offset == 0);
return count > 0 ? count : err;
}
+static inline unsigned fuse_wr_pages(loff_t pos, size_t len)
+{
+ return min_t(unsigned,
+ ((pos + len - 1) >> PAGE_CACHE_SHIFT) -
+ (pos >> PAGE_CACHE_SHIFT) + 1,
+ FUSE_MAX_PAGES_PER_REQ);
+}
+
static ssize_t fuse_perform_write(struct file *file,
struct address_space *mapping,
struct iov_iter *ii, loff_t pos)
@@ -889,8 +912,9 @@
do {
struct fuse_req *req;
ssize_t count;
+ unsigned nr_pages = fuse_wr_pages(pos, iov_iter_count(ii));
- req = fuse_get_req(fc);
+ req = fuse_get_req(fc, nr_pages);
if (IS_ERR(req)) {
err = PTR_ERR(req);
break;
@@ -1023,47 +1047,110 @@
}
}
-static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf,
+static inline void fuse_page_descs_length_init(struct fuse_req *req,
+ unsigned index, unsigned nr_pages)
+{
+ int i;
+
+ for (i = index; i < index + nr_pages; i++)
+ req->page_descs[i].length = PAGE_SIZE -
+ req->page_descs[i].offset;
+}
+
+static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii)
+{
+ return (unsigned long)ii->iov->iov_base + ii->iov_offset;
+}
+
+static inline size_t fuse_get_frag_size(const struct iov_iter *ii,
+ size_t max_size)
+{
+ return min(iov_iter_single_seg_count(ii), max_size);
+}
+
+static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
size_t *nbytesp, int write)
{
- size_t nbytes = *nbytesp;
- unsigned long user_addr = (unsigned long) buf;
- unsigned offset = user_addr & ~PAGE_MASK;
- int npages;
+ size_t nbytes = 0; /* # bytes already packed in req */
/* Special case for kernel I/O: can copy directly into the buffer */
if (segment_eq(get_fs(), KERNEL_DS)) {
+ unsigned long user_addr = fuse_get_user_addr(ii);
+ size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
+
if (write)
req->in.args[1].value = (void *) user_addr;
else
req->out.args[0].value = (void *) user_addr;
+ iov_iter_advance(ii, frag_size);
+ *nbytesp = frag_size;
return 0;
}
- nbytes = min_t(size_t, nbytes, FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT);
- npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
- npages = clamp(npages, 1, FUSE_MAX_PAGES_PER_REQ);
- npages = get_user_pages_fast(user_addr, npages, !write, req->pages);
- if (npages < 0)
- return npages;
+ while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
+ unsigned npages;
+ unsigned long user_addr = fuse_get_user_addr(ii);
+ unsigned offset = user_addr & ~PAGE_MASK;
+ size_t frag_size = fuse_get_frag_size(ii, *nbytesp - nbytes);
+ int ret;
- req->num_pages = npages;
- req->page_offset = offset;
+ unsigned n = req->max_pages - req->num_pages;
+ frag_size = min_t(size_t, frag_size, n << PAGE_SHIFT);
+
+ npages = (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ npages = clamp(npages, 1U, n);
+
+ ret = get_user_pages_fast(user_addr, npages, !write,
+ &req->pages[req->num_pages]);
+ if (ret < 0)
+ return ret;
+
+ npages = ret;
+ frag_size = min_t(size_t, frag_size,
+ (npages << PAGE_SHIFT) - offset);
+ iov_iter_advance(ii, frag_size);
+
+ req->page_descs[req->num_pages].offset = offset;
+ fuse_page_descs_length_init(req, req->num_pages, npages);
+
+ req->num_pages += npages;
+ req->page_descs[req->num_pages - 1].length -=
+ (npages << PAGE_SHIFT) - offset - frag_size;
+
+ nbytes += frag_size;
+ }
if (write)
req->in.argpages = 1;
else
req->out.argpages = 1;
- nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset;
- *nbytesp = min(*nbytesp, nbytes);
+ *nbytesp = nbytes;
return 0;
}
-ssize_t fuse_direct_io(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos, int write)
+static inline int fuse_iter_npages(const struct iov_iter *ii_p)
+{
+ struct iov_iter ii = *ii_p;
+ int npages = 0;
+
+ while (iov_iter_count(&ii) && npages < FUSE_MAX_PAGES_PER_REQ) {
+ unsigned long user_addr = fuse_get_user_addr(&ii);
+ unsigned offset = user_addr & ~PAGE_MASK;
+ size_t frag_size = iov_iter_single_seg_count(&ii);
+
+ npages += (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ iov_iter_advance(&ii, frag_size);
+ }
+
+ return min(npages, FUSE_MAX_PAGES_PER_REQ);
+}
+
+ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
+ unsigned long nr_segs, size_t count, loff_t *ppos,
+ int write)
{
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = ff->fc;
@@ -1071,8 +1158,11 @@
loff_t pos = *ppos;
ssize_t res = 0;
struct fuse_req *req;
+ struct iov_iter ii;
- req = fuse_get_req(fc);
+ iov_iter_init(&ii, iov, nr_segs, count, 0);
+
+ req = fuse_get_req(fc, fuse_iter_npages(&ii));
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1080,7 +1170,7 @@
size_t nres;
fl_owner_t owner = current->files;
size_t nbytes = min(count, nmax);
- int err = fuse_get_user_pages(req, buf, &nbytes, write);
+ int err = fuse_get_user_pages(req, &ii, &nbytes, write);
if (err) {
res = err;
break;
@@ -1103,12 +1193,11 @@
count -= nres;
res += nres;
pos += nres;
- buf += nres;
if (nres != nbytes)
break;
if (count) {
fuse_put_request(fc, req);
- req = fuse_get_req(fc);
+ req = fuse_get_req(fc, fuse_iter_npages(&ii));
if (IS_ERR(req))
break;
}
@@ -1122,31 +1211,40 @@
}
EXPORT_SYMBOL_GPL(fuse_direct_io);
-static ssize_t fuse_direct_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
+static ssize_t __fuse_direct_read(struct file *file, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
{
ssize_t res;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
if (is_bad_inode(inode))
return -EIO;
- res = fuse_direct_io(file, buf, count, ppos, 0);
+ res = fuse_direct_io(file, iov, nr_segs, iov_length(iov, nr_segs),
+ ppos, 0);
fuse_invalidate_attr(inode);
return res;
}
-static ssize_t __fuse_direct_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
+static ssize_t fuse_direct_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct iovec iov = { .iov_base = buf, .iov_len = count };
+ return __fuse_direct_read(file, &iov, 1, ppos);
+}
+
+static ssize_t __fuse_direct_write(struct file *file, const struct iovec *iov,
+ unsigned long nr_segs, loff_t *ppos)
+{
+ struct inode *inode = file_inode(file);
+ size_t count = iov_length(iov, nr_segs);
ssize_t res;
res = generic_write_checks(file, ppos, &count, 0);
if (!res) {
- res = fuse_direct_io(file, buf, count, ppos, 1);
+ res = fuse_direct_io(file, iov, nr_segs, count, ppos, 1);
if (res > 0)
fuse_write_update_size(inode, *ppos);
}
@@ -1159,7 +1257,8 @@
static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
+ struct inode *inode = file_inode(file);
ssize_t res;
if (is_bad_inode(inode))
@@ -1167,7 +1266,7 @@
/* Don't allow parallel writes to the same file */
mutex_lock(&inode->i_mutex);
- res = __fuse_direct_write(file, buf, count, ppos);
+ res = __fuse_direct_write(file, &iov, 1, ppos);
mutex_unlock(&inode->i_mutex);
return res;
@@ -1272,7 +1371,7 @@
set_page_writeback(page);
- req = fuse_request_alloc_nofs();
+ req = fuse_request_alloc_nofs(1);
if (!req)
goto err;
@@ -1293,7 +1392,8 @@
req->in.argpages = 1;
req->num_pages = 1;
req->pages[0] = tmp_page;
- req->page_offset = 0;
+ req->page_descs[0].offset = 0;
+ req->page_descs[0].length = PAGE_SIZE;
req->end = fuse_writepage_end;
req->inode = inode;
@@ -1385,7 +1485,7 @@
static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
{
if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) {
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_file *ff = file->private_data;
@@ -1443,7 +1543,7 @@
const struct file_lock *fl, int opcode, pid_t pid,
int flock)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_file *ff = file->private_data;
struct fuse_lk_in *arg = &req->misc.lk_in;
@@ -1465,13 +1565,13 @@
static int fuse_getlk(struct file *file, struct file_lock *fl)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
struct fuse_lk_out outarg;
int err;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1490,7 +1590,7 @@
static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_req *req;
int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
@@ -1506,7 +1606,7 @@
if (fl->fl_flags & FL_CLOSE)
return 0;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -1522,7 +1622,7 @@
static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
int err;
@@ -1545,7 +1645,7 @@
static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
int err;
@@ -1575,7 +1675,7 @@
if (!inode->i_sb->s_bdev || fc->no_bmap)
return 0;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return 0;
@@ -1602,7 +1702,7 @@
static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
{
loff_t retval;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
/* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */
if (whence == SEEK_CUR || whence == SEEK_SET)
@@ -1873,7 +1973,7 @@
num_pages++;
}
- req = fuse_get_req(fc);
+ req = fuse_get_req(fc, num_pages);
if (IS_ERR(req)) {
err = PTR_ERR(req);
req = NULL;
@@ -1881,6 +1981,7 @@
}
memcpy(req->pages, pages, sizeof(req->pages[0]) * num_pages);
req->num_pages = num_pages;
+ fuse_page_descs_length_init(req, 0, req->num_pages);
/* okay, let's send it to the client */
req->in.h.opcode = FUSE_IOCTL;
@@ -1978,10 +2079,10 @@
long fuse_ioctl_common(struct file *file, unsigned int cmd,
unsigned long arg, unsigned int flags)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct fuse_conn *fc = get_fuse_conn(inode);
- if (!fuse_allow_task(fc, current))
+ if (!fuse_allow_current_process(fc))
return -EACCES;
if (is_bad_inode(inode))
@@ -2066,6 +2167,7 @@
return DEFAULT_POLLMASK;
poll_wait(file, &ff->poll_wait, wait);
+ inarg.events = (__u32)poll_requested_events(wait);
/*
* Ask for notification iff there's someone waiting for it.
@@ -2076,7 +2178,7 @@
fuse_register_polled_file(fc, ff);
}
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return POLLERR;
@@ -2126,41 +2228,6 @@
return 0;
}
-static ssize_t fuse_loop_dio(struct file *filp, const struct iovec *iov,
- unsigned long nr_segs, loff_t *ppos, int rw)
-{
- const struct iovec *vector = iov;
- ssize_t ret = 0;
-
- while (nr_segs > 0) {
- void __user *base;
- size_t len;
- ssize_t nr;
-
- base = vector->iov_base;
- len = vector->iov_len;
- vector++;
- nr_segs--;
-
- if (rw == WRITE)
- nr = __fuse_direct_write(filp, base, len, ppos);
- else
- nr = fuse_direct_read(filp, base, len, ppos);
-
- if (nr < 0) {
- if (!ret)
- ret = nr;
- break;
- }
- ret += nr;
- if (nr != len)
- break;
- }
-
- return ret;
-}
-
-
static ssize_t
fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
loff_t offset, unsigned long nr_segs)
@@ -2172,7 +2239,10 @@
file = iocb->ki_filp;
pos = offset;
- ret = fuse_loop_dio(file, iov, nr_segs, &pos, rw);
+ if (rw == WRITE)
+ ret = __fuse_direct_write(file, iov, nr_segs, &pos);
+ else
+ ret = __fuse_direct_read(file, iov, nr_segs, &pos);
return ret;
}
@@ -2194,7 +2264,7 @@
if (fc->no_fallocate)
return -EOPNOTSUPP;
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index e105a53..6aeba86 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -44,6 +44,9 @@
doing the mount will be allowed to access the filesystem */
#define FUSE_ALLOW_OTHER (1 << 1)
+/** Number of page pointers embedded in fuse_req */
+#define FUSE_REQ_INLINE_PAGES 1
+
/** List of active connections */
extern struct list_head fuse_conn_list;
@@ -103,6 +106,15 @@
/** List of writepage requestst (pending or sent) */
struct list_head writepages;
+
+ /** Miscellaneous bits describing inode state */
+ unsigned long state;
+};
+
+/** FUSE inode state bits */
+enum {
+ /** Advise readdirplus */
+ FUSE_I_ADVISE_RDPLUS,
};
struct fuse_conn;
@@ -200,6 +212,12 @@
struct fuse_arg args[3];
};
+/** FUSE page descriptor */
+struct fuse_page_desc {
+ unsigned int length;
+ unsigned int offset;
+};
+
/** The request state */
enum fuse_req_state {
FUSE_REQ_INIT = 0,
@@ -291,14 +309,23 @@
} misc;
/** page vector */
- struct page *pages[FUSE_MAX_PAGES_PER_REQ];
+ struct page **pages;
+
+ /** page-descriptor vector */
+ struct fuse_page_desc *page_descs;
+
+ /** size of the 'pages' array */
+ unsigned max_pages;
+
+ /** inline page vector */
+ struct page *inline_pages[FUSE_REQ_INLINE_PAGES];
+
+ /** inline page-descriptor vector */
+ struct fuse_page_desc inline_page_descs[FUSE_REQ_INLINE_PAGES];
/** number of pages in vector */
unsigned num_pages;
- /** offset of data on first page */
- unsigned page_offset;
-
/** File used in the request (or NULL) */
struct fuse_file *ff;
@@ -487,6 +514,12 @@
/** Use enhanced/automatic page cache invalidation. */
unsigned auto_inval_data:1;
+ /** Does the filesystem support readdirplus? */
+ unsigned do_readdirplus:1;
+
+ /** Does the filesystem want adaptive readdirplus? */
+ unsigned readdirplus_auto:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -578,6 +611,9 @@
struct fuse_forget_link *fuse_alloc_forget(void);
+/* Used by READDIRPLUS */
+void fuse_force_forget(struct file *file, u64 nodeid);
+
/**
* Initialize READ or READDIR request
*/
@@ -658,9 +694,9 @@
/**
* Allocate a request
*/
-struct fuse_req *fuse_request_alloc(void);
+struct fuse_req *fuse_request_alloc(unsigned npages);
-struct fuse_req *fuse_request_alloc_nofs(void);
+struct fuse_req *fuse_request_alloc_nofs(unsigned npages);
/**
* Free a request
@@ -668,14 +704,25 @@
void fuse_request_free(struct fuse_req *req);
/**
- * Get a request, may fail with -ENOMEM
+ * Get a request, may fail with -ENOMEM,
+ * caller should specify # elements in req->pages[] explicitly
*/
-struct fuse_req *fuse_get_req(struct fuse_conn *fc);
+struct fuse_req *fuse_get_req(struct fuse_conn *fc, unsigned npages);
+
+/**
+ * Get a request, may fail with -ENOMEM,
+ * useful for callers who doesn't use req->pages[]
+ */
+static inline struct fuse_req *fuse_get_req_nopages(struct fuse_conn *fc)
+{
+ return fuse_get_req(fc, 0);
+}
/**
* Gets a requests for a file operation, always succeeds
*/
-struct fuse_req *fuse_get_req_nofail(struct fuse_conn *fc, struct file *file);
+struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
+ struct file *file);
/**
* Decrement reference count of a request. If count goes to zero free
@@ -739,9 +786,9 @@
int fuse_valid_type(int m);
/**
- * Is task allowed to perform filesystem operation?
+ * Is current process allowed to perform filesystem operation?
*/
-int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task);
+int fuse_allow_current_process(struct fuse_conn *fc);
u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id);
@@ -776,8 +823,9 @@
int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
bool isdir);
-ssize_t fuse_direct_io(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos, int write);
+ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
+ unsigned long nr_segs, size_t count, loff_t *ppos,
+ int write);
long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
unsigned int flags);
long fuse_ioctl_common(struct file *file, unsigned int cmd,
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 73ca6b7..137185c 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -92,6 +92,7 @@
fi->attr_version = 0;
fi->writectr = 0;
fi->orig_ino = 0;
+ fi->state = 0;
INIT_LIST_HEAD(&fi->write_files);
INIT_LIST_HEAD(&fi->queued_writes);
INIT_LIST_HEAD(&fi->writepages);
@@ -408,12 +409,12 @@
struct fuse_statfs_out outarg;
int err;
- if (!fuse_allow_task(fc, current)) {
+ if (!fuse_allow_current_process(fc)) {
buf->f_type = FUSE_SUPER_MAGIC;
return 0;
}
- req = fuse_get_req(fc);
+ req = fuse_get_req_nopages(fc);
if (IS_ERR(req))
return PTR_ERR(req);
@@ -678,7 +679,7 @@
if (*max_len < len) {
*max_len = len;
- return 255;
+ return FILEID_INVALID;
}
nodeid = get_fuse_inode(inode)->nodeid;
@@ -863,6 +864,10 @@
fc->dont_mask = 1;
if (arg->flags & FUSE_AUTO_INVAL_DATA)
fc->auto_inval_data = 1;
+ if (arg->flags & FUSE_DO_READDIRPLUS)
+ fc->do_readdirplus = 1;
+ if (arg->flags & FUSE_READDIRPLUS_AUTO)
+ fc->readdirplus_auto = 1;
} else {
ra_pages = fc->max_read / PAGE_CACHE_SIZE;
fc->no_lock = 1;
@@ -889,7 +894,8 @@
arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
- FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA;
+ FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
+ FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO;
req->in.h.opcode = FUSE_INIT;
req->in.numargs = 1;
req->in.args[0].size = sizeof(*arg);
@@ -1034,12 +1040,12 @@
/* only now - we want root dentry with NULL ->d_op */
sb->s_d_op = &fuse_dentry_operations;
- init_req = fuse_request_alloc();
+ init_req = fuse_request_alloc(0);
if (!init_req)
goto err_put_root;
if (is_bdev) {
- fc->destroy_req = fuse_request_alloc();
+ fc->destroy_req = fuse_request_alloc(0);
if (!fc->destroy_req)
goto err_free_init_req;
}
@@ -1111,6 +1117,7 @@
.mount = fuse_mount,
.kill_sb = fuse_kill_sb_anon,
};
+MODULE_ALIAS_FS("fuse");
#ifdef CONFIG_BLOCK
static struct dentry *fuse_mount_blk(struct file_system_type *fs_type,
@@ -1140,6 +1147,7 @@
.kill_sb = fuse_kill_sb_blk,
.fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
};
+MODULE_ALIAS_FS("fuseblk");
static inline int register_fuseblk(void)
{
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index f850020..f69ac0a 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -237,7 +237,7 @@
return -EINVAL;
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
return value ? -EACCES : 0;
- if ((current_fsuid() != inode->i_uid) && !capable(CAP_FOWNER))
+ if (!uid_eq(current_fsuid(), inode->i_uid) && !capable(CAP_FOWNER))
return -EPERM;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 30de4f2..24f414f 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -51,7 +51,7 @@
continue;
if (gfs2_is_jdata(ip))
set_buffer_uptodate(bh);
- gfs2_trans_add_bh(ip->i_gl, bh, 0);
+ gfs2_trans_add_data(ip->i_gl, bh);
}
}
@@ -230,16 +230,14 @@
}
/**
- * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk
+ * gfs2_writepages - Write a bunch of dirty pages back to disk
* @mapping: The mapping to write
* @wbc: Write-back control
*
- * For the data=writeback case we can already ignore buffer heads
- * and write whole extents at once. This is a big reduction in the
- * number of I/O requests we send and the bmap calls we make in this case.
+ * Used for both ordered and writeback modes.
*/
-static int gfs2_writeback_writepages(struct address_space *mapping,
- struct writeback_control *wbc)
+static int gfs2_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
{
return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
}
@@ -852,7 +850,7 @@
goto failed;
}
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
if (gfs2_is_stuffed(ip))
return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
@@ -1102,7 +1100,7 @@
static const struct address_space_operations gfs2_writeback_aops = {
.writepage = gfs2_writeback_writepage,
- .writepages = gfs2_writeback_writepages,
+ .writepages = gfs2_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.write_begin = gfs2_write_begin,
@@ -1118,6 +1116,7 @@
static const struct address_space_operations gfs2_ordered_aops = {
.writepage = gfs2_ordered_writepage,
+ .writepages = gfs2_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
.write_begin = gfs2_write_begin,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index a68e91b..5e83657 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -22,6 +22,7 @@
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
+#include "log.h"
#include "super.h"
#include "trans.h"
#include "dir.h"
@@ -93,7 +94,7 @@
if (!gfs2_is_jdata(ip))
mark_buffer_dirty(bh);
if (!gfs2_is_writeback(ip))
- gfs2_trans_add_bh(ip->i_gl, bh, 0);
+ gfs2_trans_add_data(ip->i_gl, bh);
if (release) {
unlock_page(page);
@@ -153,7 +154,7 @@
/* Set up the pointer to the new block */
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
di = (struct gfs2_dinode *)dibh->b_data;
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
@@ -405,7 +406,7 @@
BUG_ON(i < 1);
BUG_ON(mp->mp_bh[i] != NULL);
mp->mp_bh[i] = gfs2_meta_new(gl, bn);
- gfs2_trans_add_bh(gl, mp->mp_bh[i], 1);
+ gfs2_trans_add_meta(gl, mp->mp_bh[i]);
gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
ptr += offset;
@@ -468,7 +469,7 @@
BUG_ON(sheight < 1);
BUG_ON(dibh == NULL);
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
if (height == sheight) {
struct buffer_head *bh;
@@ -544,7 +545,7 @@
/* Branching from existing tree */
case ALLOC_GROW_DEPTH:
if (i > 1 && i < height)
- gfs2_trans_add_bh(ip->i_gl, mp->mp_bh[i-1], 1);
+ gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
for (; i < height && n > 0; i++, n--)
gfs2_indirect_init(mp, ip->i_gl, i,
mp->mp_list[i-1], bn++);
@@ -556,7 +557,7 @@
case ALLOC_DATA:
BUG_ON(n > dblks);
BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
- gfs2_trans_add_bh(ip->i_gl, mp->mp_bh[end_of_metadata], 1);
+ gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
dblks = n;
ptr = metapointer(end_of_metadata, mp);
dblock = bn;
@@ -796,8 +797,8 @@
down_write(&ip->i_rw_mutex);
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
+ gfs2_trans_add_meta(ip->i_gl, bh);
bstart = 0;
blen = 0;
@@ -981,7 +982,7 @@
}
if (!gfs2_is_writeback(ip))
- gfs2_trans_add_bh(ip->i_gl, bh, 0);
+ gfs2_trans_add_data(ip->i_gl, bh);
zero_user(page, offset, length);
mark_buffer_dirty(bh);
@@ -1046,7 +1047,7 @@
if (error)
goto out;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
if (gfs2_is_stuffed(ip)) {
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
@@ -1098,7 +1099,7 @@
if (error)
return error;
- error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (error)
return error;
@@ -1137,11 +1138,12 @@
ip->i_height = 0;
ip->i_goal = ip->i_no_addr;
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
+ gfs2_ordered_del_inode(ip);
}
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
@@ -1246,7 +1248,7 @@
i_size_write(inode, size);
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
@@ -1286,6 +1288,10 @@
inode_dio_wait(inode);
+ ret = gfs2_rs_alloc(GFS2_I(inode));
+ if (ret)
+ return ret;
+
oldsize = inode->i_size;
if (newsize >= oldsize)
return do_grow(inode, newsize);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 9a35670..c3e82bd 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -93,7 +93,7 @@
struct buffer_head *bh;
bh = gfs2_meta_new(ip->i_gl, block);
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_metatype_set(bh, GFS2_METATYPE_JD, GFS2_FORMAT_JD);
gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
*bhp = bh;
@@ -127,7 +127,7 @@
if (error)
return error;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size);
if (ip->i_inode.i_size < offset + size)
i_size_write(&ip->i_inode, offset + size);
@@ -209,7 +209,7 @@
if (error)
goto fail;
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
memcpy(bh->b_data + o, buf, amount);
brelse(bh);
@@ -231,7 +231,7 @@
i_size_write(&ip->i_inode, offset + copied);
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
@@ -647,7 +647,7 @@
return;
}
- gfs2_trans_add_bh(dip->i_gl, bh, 1);
+ gfs2_trans_add_meta(dip->i_gl, bh);
/* If there is no prev entry, this is the first entry in the block.
The de_rec_len is already as big as it needs to be. Just zero
@@ -690,7 +690,7 @@
offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
totlen = be16_to_cpu(dent->de_rec_len);
BUG_ON(offset + name->len > totlen);
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
ndent = (struct gfs2_dirent *)((char *)dent + offset);
dent->de_rec_len = cpu_to_be16(offset);
gfs2_qstr2dirent(name, totlen - offset, ndent);
@@ -831,7 +831,7 @@
return NULL;
gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1);
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF);
leaf = (struct gfs2_leaf *)bh->b_data;
leaf->lf_depth = cpu_to_be16(depth);
@@ -916,7 +916,7 @@
/* We're done with the new leaf block, now setup the new
hash table. */
- gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(dip->i_gl, dibh);
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
lp = (__be64 *)(dibh->b_data + sizeof(struct gfs2_dinode));
@@ -976,7 +976,7 @@
return 1; /* can't split */
}
- gfs2_trans_add_bh(dip->i_gl, obh, 1);
+ gfs2_trans_add_meta(dip->i_gl, obh);
nleaf = new_leaf(inode, &nbh, be16_to_cpu(oleaf->lf_depth) + 1);
if (!nleaf) {
@@ -1069,7 +1069,7 @@
error = gfs2_meta_inode_buffer(dip, &dibh);
if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) {
- gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(dip->i_gl, dibh);
gfs2_add_inode_blocks(&dip->i_inode, 1);
gfs2_dinode_out(dip, dibh->b_data);
brelse(dibh);
@@ -1622,7 +1622,7 @@
return error;
} while(1);
- gfs2_trans_add_bh(ip->i_gl, obh, 1);
+ gfs2_trans_add_meta(ip->i_gl, obh);
leaf = new_leaf(inode, &bh, be16_to_cpu(oleaf->lf_depth));
if (!leaf) {
@@ -1636,7 +1636,7 @@
error = gfs2_meta_inode_buffer(ip, &bh);
if (error)
return error;
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_add_inode_blocks(&ip->i_inode, 1);
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
@@ -1795,7 +1795,7 @@
if (IS_ERR(dent))
return PTR_ERR(dent);
- gfs2_trans_add_bh(dip->i_gl, bh, 1);
+ gfs2_trans_add_meta(dip->i_gl, bh);
gfs2_inum_out(nip, dent);
dent->de_type = cpu_to_be16(new_type);
@@ -1804,7 +1804,7 @@
error = gfs2_meta_inode_buffer(dip, &bh);
if (error)
return error;
- gfs2_trans_add_bh(dip->i_gl, bh, 1);
+ gfs2_trans_add_meta(dip->i_gl, bh);
}
dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
@@ -1849,7 +1849,7 @@
if (!ht)
return -ENOMEM;
- error = gfs2_quota_hold(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_hold(dip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (error)
goto out;
@@ -1917,7 +1917,7 @@
if (error)
goto out_end_trans;
- gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(dip->i_gl, dibh);
/* On the last dealloc, make this a regular file in case we crash.
(We don't want to free these blocks a second time.) */
if (last_dealloc)
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 4767774..9973df4 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -37,10 +37,10 @@
if (parent && (*len < GFS2_LARGE_FH_SIZE)) {
*len = GFS2_LARGE_FH_SIZE;
- return 255;
+ return FILEID_INVALID;
} else if (*len < GFS2_SMALL_FH_SIZE) {
*len = GFS2_SMALL_FH_SIZE;
- return 255;
+ return FILEID_INVALID;
}
fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 991ab2d..019f45e 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -157,7 +157,7 @@
static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
@@ -217,7 +217,7 @@
*/
static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
@@ -276,7 +276,7 @@
error = gfs2_meta_inode_buffer(ip, &bh);
if (error)
goto out_trans_end;
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
ip->i_diskflags = new_flags;
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
@@ -293,7 +293,7 @@
static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
u32 fsflags, gfsflags;
if (get_user(fsflags, ptr))
@@ -336,7 +336,7 @@
static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size)
{
- struct inode *inode = filep->f_dentry->d_inode;
+ struct inode *inode = file_inode(filep);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *ip = GFS2_I(inode);
size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift;
@@ -386,7 +386,7 @@
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned long last_index;
@@ -483,7 +483,7 @@
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
- wait_on_page_writeback(page);
+ wait_for_stable_page(page);
}
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
@@ -673,8 +673,7 @@
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
- struct dentry *dentry = file->f_dentry;
- struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+ struct gfs2_inode *ip = GFS2_I(file_inode(file));
int ret;
ret = gfs2_rs_alloc(ip);
@@ -709,7 +708,7 @@
if (unlikely(error))
return error;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
if (gfs2_is_stuffed(ip)) {
error = gfs2_unstuff_dinode(ip, NULL);
@@ -772,7 +771,7 @@
static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *ip = GFS2_I(inode);
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
@@ -938,7 +937,7 @@
{
struct gfs2_file *fp = file->private_data;
struct gfs2_holder *fl_gh = &fp->f_fl_gh;
- struct gfs2_inode *ip = GFS2_I(file->f_path.dentry->d_inode);
+ struct gfs2_inode *ip = GFS2_I(file_inode(file));
struct gfs2_glock *gl;
unsigned int state;
int flags;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 992c5c0..cf35155 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -30,6 +30,7 @@
#include <linux/rculist_bl.h>
#include <linux/bit_spinlock.h>
#include <linux/percpu.h>
+#include <linux/list_sort.h>
#include "gfs2.h"
#include "incore.h"
@@ -1376,56 +1377,105 @@
gfs2_glock_put(gl);
}
+static int glock_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+ struct gfs2_glock *gla, *glb;
-static int gfs2_shrink_glock_memory(struct shrinker *shrink,
- struct shrink_control *sc)
+ gla = list_entry(a, struct gfs2_glock, gl_lru);
+ glb = list_entry(b, struct gfs2_glock, gl_lru);
+
+ if (gla->gl_name.ln_number > glb->gl_name.ln_number)
+ return 1;
+ if (gla->gl_name.ln_number < glb->gl_name.ln_number)
+ return -1;
+
+ return 0;
+}
+
+/**
+ * gfs2_dispose_glock_lru - Demote a list of glocks
+ * @list: The list to dispose of
+ *
+ * Disposing of glocks may involve disk accesses, so that here we sort
+ * the glocks by number (i.e. disk location of the inodes) so that if
+ * there are any such accesses, they'll be sent in order (mostly).
+ *
+ * Must be called under the lru_lock, but may drop and retake this
+ * lock. While the lru_lock is dropped, entries may vanish from the
+ * list, but no new entries will appear on the list (since it is
+ * private)
+ */
+
+static void gfs2_dispose_glock_lru(struct list_head *list)
+__releases(&lru_lock)
+__acquires(&lru_lock)
{
struct gfs2_glock *gl;
- int may_demote;
- int nr_skipped = 0;
- int nr = sc->nr_to_scan;
- gfp_t gfp_mask = sc->gfp_mask;
+
+ list_sort(NULL, list, glock_cmp);
+
+ while(!list_empty(list)) {
+ gl = list_entry(list->next, struct gfs2_glock, gl_lru);
+ list_del_init(&gl->gl_lru);
+ clear_bit(GLF_LRU, &gl->gl_flags);
+ gfs2_glock_hold(gl);
+ spin_unlock(&lru_lock);
+ spin_lock(&gl->gl_spin);
+ if (demote_ok(gl))
+ handle_callback(gl, LM_ST_UNLOCKED, 0);
+ WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags));
+ smp_mb__after_clear_bit();
+ if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+ gfs2_glock_put_nolock(gl);
+ spin_unlock(&gl->gl_spin);
+ spin_lock(&lru_lock);
+ }
+}
+
+/**
+ * gfs2_scan_glock_lru - Scan the LRU looking for locks to demote
+ * @nr: The number of entries to scan
+ *
+ * This function selects the entries on the LRU which are able to
+ * be demoted, and then kicks off the process by calling
+ * gfs2_dispose_glock_lru() above.
+ */
+
+static void gfs2_scan_glock_lru(int nr)
+{
+ struct gfs2_glock *gl;
LIST_HEAD(skipped);
-
- if (nr == 0)
- goto out;
-
- if (!(gfp_mask & __GFP_FS))
- return -1;
+ LIST_HEAD(dispose);
spin_lock(&lru_lock);
while(nr && !list_empty(&lru_list)) {
gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
- list_del_init(&gl->gl_lru);
- clear_bit(GLF_LRU, &gl->gl_flags);
- atomic_dec(&lru_count);
/* Test for being demotable */
if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
- gfs2_glock_hold(gl);
- spin_unlock(&lru_lock);
- spin_lock(&gl->gl_spin);
- may_demote = demote_ok(gl);
- if (may_demote) {
- handle_callback(gl, LM_ST_UNLOCKED, 0);
- nr--;
- }
- clear_bit(GLF_LOCK, &gl->gl_flags);
- smp_mb__after_clear_bit();
- if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
- gfs2_glock_put_nolock(gl);
- spin_unlock(&gl->gl_spin);
- spin_lock(&lru_lock);
+ list_move(&gl->gl_lru, &dispose);
+ atomic_dec(&lru_count);
+ nr--;
continue;
}
- nr_skipped++;
- list_add(&gl->gl_lru, &skipped);
- set_bit(GLF_LRU, &gl->gl_flags);
+
+ list_move(&gl->gl_lru, &skipped);
}
list_splice(&skipped, &lru_list);
- atomic_add(nr_skipped, &lru_count);
+ if (!list_empty(&dispose))
+ gfs2_dispose_glock_lru(&dispose);
spin_unlock(&lru_lock);
-out:
+}
+
+static int gfs2_shrink_glock_memory(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ if (sc->nr_to_scan) {
+ if (!(sc->gfp_mask & __GFP_FS))
+ return -1;
+ gfs2_scan_glock_lru(sc->nr_to_scan);
+ }
+
return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 78d4184..444b650 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -322,8 +322,8 @@
break;
};
- ip->i_inode.i_uid = be32_to_cpu(str->di_uid);
- ip->i_inode.i_gid = be32_to_cpu(str->di_gid);
+ i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid));
+ i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid));
gfs2_set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink));
i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index c373a24..156e42e 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -52,7 +52,6 @@
*/
struct gfs2_log_operations {
- void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
void (*lo_before_commit) (struct gfs2_sbd *sdp);
void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai);
void (*lo_before_scan) (struct gfs2_jdesc *jd,
@@ -341,6 +340,7 @@
GIF_QD_LOCKED = 1,
GIF_ALLOC_FAILED = 2,
GIF_SW_PAGED = 3,
+ GIF_ORDERED = 4,
};
struct gfs2_inode {
@@ -357,6 +357,7 @@
struct gfs2_rgrpd *i_rgd;
u64 i_goal; /* goal block for allocations */
struct rw_semaphore i_rw_mutex;
+ struct list_head i_ordered;
struct list_head i_trunc_list;
__be64 *i_hash_cache;
u32 i_entries;
@@ -391,7 +392,6 @@
};
enum {
- QDF_USER = 0,
QDF_CHANGE = 1,
QDF_LOCKED = 2,
QDF_REFRESH = 3,
@@ -403,7 +403,7 @@
atomic_t qd_count;
- u32 qd_id;
+ struct kqid qd_id;
unsigned long qd_flags; /* QDF_... */
s64 qd_change;
@@ -641,6 +641,7 @@
wait_queue_head_t sd_glock_wait;
atomic_t sd_glock_disposal;
struct completion sd_locking_init;
+ struct completion sd_wdack;
struct delayed_work sd_control_work;
/* Inode Stuff */
@@ -723,6 +724,7 @@
struct list_head sd_log_le_revoke;
struct list_head sd_log_le_databuf;
struct list_head sd_log_le_ordered;
+ spinlock_t sd_ordered_lock;
atomic_t sd_log_thresh1;
atomic_t sd_log_thresh2;
@@ -758,10 +760,7 @@
unsigned int sd_replayed_blocks;
/* For quiescing the filesystem */
-
struct gfs2_holder sd_freeze_gh;
- struct mutex sd_freeze_lock;
- unsigned int sd_freeze_count;
char sd_fsname[GFS2_FSNAME_LEN];
char sd_table_name[GFS2_FSNAME_LEN];
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 2b6f569..cc00bd1 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -368,10 +368,11 @@
struct inode *inode)
{
if (GFS2_SB(&dip->i_inode)->sd_args.ar_suiddir &&
- (dip->i_inode.i_mode & S_ISUID) && dip->i_inode.i_uid) {
+ (dip->i_inode.i_mode & S_ISUID) &&
+ !uid_eq(dip->i_inode.i_uid, GLOBAL_ROOT_UID)) {
if (S_ISDIR(inode->i_mode))
inode->i_mode |= S_ISUID;
- else if (dip->i_inode.i_uid != current_fsuid())
+ else if (!uid_eq(dip->i_inode.i_uid, current_fsuid()))
inode->i_mode &= ~07111;
inode->i_uid = dip->i_inode.i_uid;
} else
@@ -447,7 +448,7 @@
struct timespec tv = CURRENT_TIME;
dibh = gfs2_meta_new(ip->i_gl, ip->i_no_addr);
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
di = (struct gfs2_dinode *)dibh->b_data;
@@ -455,8 +456,8 @@
di->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
di->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
di->di_mode = cpu_to_be32(ip->i_inode.i_mode);
- di->di_uid = cpu_to_be32(ip->i_inode.i_uid);
- di->di_gid = cpu_to_be32(ip->i_inode.i_gid);
+ di->di_uid = cpu_to_be32(i_uid_read(&ip->i_inode));
+ di->di_gid = cpu_to_be32(i_gid_read(&ip->i_inode));
di->di_nlink = 0;
di->di_size = cpu_to_be64(ip->i_inode.i_size);
di->di_blocks = cpu_to_be64(1);
@@ -548,7 +549,7 @@
if (error)
return error;
- error = gfs2_quota_lock(dip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_lock(dip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (error)
goto fail;
@@ -584,7 +585,7 @@
if (error)
goto fail_end_trans;
set_nlink(&ip->i_inode, S_ISDIR(ip->i_inode.i_mode) ? 2 : 1);
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
return 0;
@@ -931,7 +932,7 @@
if (error)
goto out_brelse;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
inc_nlink(&ip->i_inode);
ip->i_inode.i_ctime = CURRENT_TIME;
ihold(inode);
@@ -978,8 +979,8 @@
return -EPERM;
if ((dip->i_inode.i_mode & S_ISVTX) &&
- dip->i_inode.i_uid != current_fsuid() &&
- ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
+ !uid_eq(dip->i_inode.i_uid, current_fsuid()) &&
+ !uid_eq(ip->i_inode.i_uid, current_fsuid()) && !capable(CAP_FOWNER))
return -EPERM;
if (IS_APPEND(&dip->i_inode))
@@ -1412,7 +1413,7 @@
if (error)
goto out_end_trans;
ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
@@ -1580,7 +1581,8 @@
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
- u32 ouid, ogid, nuid, ngid;
+ kuid_t ouid, nuid;
+ kgid_t ogid, ngid;
int error;
ouid = inode->i_uid;
@@ -1588,16 +1590,17 @@
nuid = attr->ia_uid;
ngid = attr->ia_gid;
- if (!(attr->ia_valid & ATTR_UID) || ouid == nuid)
- ouid = nuid = NO_QUOTA_CHANGE;
- if (!(attr->ia_valid & ATTR_GID) || ogid == ngid)
- ogid = ngid = NO_QUOTA_CHANGE;
+ if (!(attr->ia_valid & ATTR_UID) || uid_eq(ouid, nuid))
+ ouid = nuid = NO_UID_QUOTA_CHANGE;
+ if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid))
+ ogid = ngid = NO_GID_QUOTA_CHANGE;
error = gfs2_quota_lock(ip, nuid, ngid);
if (error)
return error;
- if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
+ if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) ||
+ !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) {
error = gfs2_quota_check(ip, nuid, ngid);
if (error)
goto out_gunlock_q;
@@ -1611,7 +1614,8 @@
if (error)
goto out_end_trans;
- if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
+ if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) ||
+ !gid_eq(ogid, NO_GID_QUOTA_CHANGE)) {
u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
gfs2_quota_change(ip, -blocks, ouid, ogid);
gfs2_quota_change(ip, blocks, nuid, ngid);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index f4beeb9..9a2ca8b 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -482,70 +482,66 @@
}
}
-static int bd_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
{
- struct gfs2_bufdata *bda, *bdb;
+ struct gfs2_inode *ipa, *ipb;
- bda = list_entry(a, struct gfs2_bufdata, bd_list);
- bdb = list_entry(b, struct gfs2_bufdata, bd_list);
+ ipa = list_entry(a, struct gfs2_inode, i_ordered);
+ ipb = list_entry(b, struct gfs2_inode, i_ordered);
- if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
+ if (ipa->i_no_addr < ipb->i_no_addr)
return -1;
- if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
+ if (ipa->i_no_addr > ipb->i_no_addr)
return 1;
return 0;
}
static void gfs2_ordered_write(struct gfs2_sbd *sdp)
{
- struct gfs2_bufdata *bd;
- struct buffer_head *bh;
+ struct gfs2_inode *ip;
LIST_HEAD(written);
- gfs2_log_lock(sdp);
- list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp);
+ spin_lock(&sdp->sd_ordered_lock);
+ list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp);
while (!list_empty(&sdp->sd_log_le_ordered)) {
- bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_list);
- list_move(&bd->bd_list, &written);
- bh = bd->bd_bh;
- if (!buffer_dirty(bh))
+ ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+ list_move(&ip->i_ordered, &written);
+ if (ip->i_inode.i_mapping->nrpages == 0)
continue;
- get_bh(bh);
- gfs2_log_unlock(sdp);
- lock_buffer(bh);
- if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
- bh->b_end_io = end_buffer_write_sync;
- submit_bh(WRITE_SYNC, bh);
- } else {
- unlock_buffer(bh);
- brelse(bh);
- }
- gfs2_log_lock(sdp);
+ spin_unlock(&sdp->sd_ordered_lock);
+ filemap_fdatawrite(ip->i_inode.i_mapping);
+ spin_lock(&sdp->sd_ordered_lock);
}
list_splice(&written, &sdp->sd_log_le_ordered);
- gfs2_log_unlock(sdp);
+ spin_unlock(&sdp->sd_ordered_lock);
}
static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
{
- struct gfs2_bufdata *bd;
- struct buffer_head *bh;
+ struct gfs2_inode *ip;
- gfs2_log_lock(sdp);
+ spin_lock(&sdp->sd_ordered_lock);
while (!list_empty(&sdp->sd_log_le_ordered)) {
- bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_list);
- bh = bd->bd_bh;
- if (buffer_locked(bh)) {
- get_bh(bh);
- gfs2_log_unlock(sdp);
- wait_on_buffer(bh);
- brelse(bh);
- gfs2_log_lock(sdp);
+ ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+ list_del(&ip->i_ordered);
+ WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
+ if (ip->i_inode.i_mapping->nrpages == 0)
continue;
- }
- list_del_init(&bd->bd_list);
+ spin_unlock(&sdp->sd_ordered_lock);
+ filemap_fdatawait(ip->i_inode.i_mapping);
+ spin_lock(&sdp->sd_ordered_lock);
}
- gfs2_log_unlock(sdp);
+ spin_unlock(&sdp->sd_ordered_lock);
+}
+
+void gfs2_ordered_del_inode(struct gfs2_inode *ip)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+ spin_lock(&sdp->sd_ordered_lock);
+ if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
+ list_del(&ip->i_ordered);
+ spin_unlock(&sdp->sd_ordered_lock);
}
/**
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 3fd5215..3566f35 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -48,6 +48,18 @@
sdp->sd_log_head = sdp->sd_log_tail = value;
}
+static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+ if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
+ spin_lock(&sdp->sd_ordered_lock);
+ if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
+ list_add(&ip->i_ordered, &sdp->sd_log_le_ordered);
+ spin_unlock(&sdp->sd_ordered_lock);
+ }
+}
+extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
unsigned int ssize);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 9ceccb1..a505597 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -37,7 +37,7 @@
*
* The log lock must be held when calling this function
*/
-static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
@@ -388,32 +388,6 @@
return page;
}
-static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
- struct gfs2_meta_header *mh;
- struct gfs2_trans *tr;
-
- tr = current->journal_info;
- tr->tr_touched = 1;
- if (!list_empty(&bd->bd_list))
- return;
- set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
- set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
- mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
- if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
- printk(KERN_ERR
- "Attempting to add uninitialised block to journal (inplace block=%lld)\n",
- (unsigned long long)bd->bd_bh->b_blocknr);
- BUG();
- }
- gfs2_pin(sdp, bd->bd_bh);
- mh->__pad0 = cpu_to_be64(0);
- mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
- sdp->sd_log_num_buf++;
- list_add(&bd->bd_list, &sdp->sd_log_le_buf);
- tr->tr_num_buf_new++;
-}
-
static void gfs2_check_magic(struct buffer_head *bh)
{
void *kaddr;
@@ -600,20 +574,6 @@
jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
}
-static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
- struct gfs2_glock *gl = bd->bd_gl;
- struct gfs2_trans *tr;
-
- tr = current->journal_info;
- tr->tr_touched = 1;
- tr->tr_num_revoke++;
- sdp->sd_log_num_revoke++;
- atomic_inc(&gl->gl_revokes);
- set_bit(GLF_LFLUSH, &gl->gl_flags);
- list_add(&bd->bd_list, &sdp->sd_log_le_revoke);
-}
-
static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
{
struct gfs2_meta_header *mh;
@@ -749,44 +709,6 @@
}
/**
- * databuf_lo_add - Add a databuf to the transaction.
- *
- * This is used in two distinct cases:
- * i) In ordered write mode
- * We put the data buffer on a list so that we can ensure that its
- * synced to disk at the right time
- * ii) In journaled data mode
- * We need to journal the data block in the same way as metadata in
- * the functions above. The difference is that here we have a tag
- * which is two __be64's being the block number (as per meta data)
- * and a flag which says whether the data block needs escaping or
- * not. This means we need a new log entry for each 251 or so data
- * blocks, which isn't an enormous overhead but twice as much as
- * for normal metadata blocks.
- */
-static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
- struct gfs2_trans *tr = current->journal_info;
- struct address_space *mapping = bd->bd_bh->b_page->mapping;
- struct gfs2_inode *ip = GFS2_I(mapping->host);
-
- if (tr)
- tr->tr_touched = 1;
- if (!list_empty(&bd->bd_list))
- return;
- set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
- set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
- if (gfs2_is_jdata(ip)) {
- gfs2_pin(sdp, bd->bd_bh);
- tr->tr_num_databuf_new++;
- sdp->sd_log_num_databuf++;
- list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf);
- } else {
- list_add_tail(&bd->bd_list, &sdp->sd_log_le_ordered);
- }
-}
-
-/**
* databuf_lo_before_commit - Scan the data buffers, writing as we go
*
*/
@@ -885,7 +807,6 @@
const struct gfs2_log_operations gfs2_buf_lops = {
- .lo_add = buf_lo_add,
.lo_before_commit = buf_lo_before_commit,
.lo_after_commit = buf_lo_after_commit,
.lo_before_scan = buf_lo_before_scan,
@@ -895,7 +816,6 @@
};
const struct gfs2_log_operations gfs2_revoke_lops = {
- .lo_add = revoke_lo_add,
.lo_before_commit = revoke_lo_before_commit,
.lo_after_commit = revoke_lo_after_commit,
.lo_before_scan = revoke_lo_before_scan,
@@ -909,7 +829,6 @@
};
const struct gfs2_log_operations gfs2_databuf_lops = {
- .lo_add = databuf_lo_add,
.lo_before_commit = databuf_lo_before_commit,
.lo_after_commit = databuf_lo_after_commit,
.lo_scan_elements = databuf_lo_scan_elements,
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 954a330..ba77b7d 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -29,6 +29,7 @@
extern const struct gfs2_log_operations *gfs2_log_ops[];
extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page);
extern void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw);
+extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
static inline unsigned int buf_limit(struct gfs2_sbd *sdp)
{
@@ -46,19 +47,6 @@
return limit;
}
-static inline void lops_init_le(struct gfs2_bufdata *bd,
- const struct gfs2_log_operations *lops)
-{
- INIT_LIST_HEAD(&bd->bd_list);
- bd->bd_ops = lops;
-}
-
-static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
- if (bd->bd_ops->lo_add)
- bd->bd_ops->lo_add(sdp, bd);
-}
-
static inline void lops_before_commit(struct gfs2_sbd *sdp)
{
int x;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 22255d9..b059bbb 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -271,41 +271,6 @@
return 0;
}
-/**
- * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer
- * @gl: the glock the buffer belongs to
- * @bh: The buffer to be attached to
- * @meta: Flag to indicate whether its metadata or not
- */
-
-void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
- int meta)
-{
- struct gfs2_bufdata *bd;
-
- if (meta)
- lock_page(bh->b_page);
-
- if (bh->b_private) {
- if (meta)
- unlock_page(bh->b_page);
- return;
- }
-
- bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
- bd->bd_bh = bh;
- bd->bd_gl = gl;
-
- if (meta)
- lops_init_le(bd, &gfs2_buf_lops);
- else
- lops_init_le(bd, &gfs2_databuf_lops);
- bh->b_private = bd;
-
- if (meta)
- unlock_page(bh->b_page);
-}
-
void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta)
{
struct address_space *mapping = bh->b_page->mapping;
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index c30973b..0d4c843 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -56,9 +56,6 @@
int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create);
-void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh,
- int meta);
-
void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr,
int meta);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 0e3554e..60ede2a 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -20,6 +20,7 @@
#include <linux/gfs2_ondisk.h>
#include <linux/quotaops.h>
#include <linux/lockdep.h>
+#include <linux/module.h>
#include "gfs2.h"
#include "incore.h"
@@ -81,6 +82,7 @@
init_waitqueue_head(&sdp->sd_glock_wait);
atomic_set(&sdp->sd_glock_disposal, 0);
init_completion(&sdp->sd_locking_init);
+ init_completion(&sdp->sd_wdack);
spin_lock_init(&sdp->sd_statfs_spin);
spin_lock_init(&sdp->sd_rindex_spin);
@@ -102,6 +104,7 @@
INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
+ spin_lock_init(&sdp->sd_ordered_lock);
init_waitqueue_head(&sdp->sd_log_waitq);
init_waitqueue_head(&sdp->sd_logd_waitq);
@@ -115,8 +118,6 @@
INIT_LIST_HEAD(&sdp->sd_revoke_list);
- mutex_init(&sdp->sd_freeze_lock);
-
return sdp;
}
@@ -1425,6 +1426,7 @@
.kill_sb = gfs2_kill_sb,
.owner = THIS_MODULE,
};
+MODULE_ALIAS_FS("gfs2");
struct file_system_type gfs2meta_fs_type = {
.name = "gfs2meta",
@@ -1432,4 +1434,4 @@
.mount = gfs2_mount_meta,
.owner = THIS_MODULE,
};
-
+MODULE_ALIAS_FS("gfs2meta");
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index ae55e24..c7c840e 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -65,13 +65,10 @@
#include "inode.h"
#include "util.h"
-#define QUOTA_USER 1
-#define QUOTA_GROUP 0
-
struct gfs2_quota_change_host {
u64 qc_change;
u32 qc_flags; /* GFS2_QCF_... */
- u32 qc_id;
+ struct kqid qc_id;
};
static LIST_HEAD(qd_lru_list);
@@ -120,17 +117,24 @@
return (atomic_read(&qd_lru_count) * sysctl_vfs_cache_pressure) / 100;
}
+static u64 qd2index(struct gfs2_quota_data *qd)
+{
+ struct kqid qid = qd->qd_id;
+ return (2 * (u64)from_kqid(&init_user_ns, qid)) +
+ (qid.type == USRQUOTA) ? 0 : 1;
+}
+
static u64 qd2offset(struct gfs2_quota_data *qd)
{
u64 offset;
- offset = 2 * (u64)qd->qd_id + !test_bit(QDF_USER, &qd->qd_flags);
+ offset = qd2index(qd);
offset *= sizeof(struct gfs2_quota);
return offset;
}
-static int qd_alloc(struct gfs2_sbd *sdp, int user, u32 id,
+static int qd_alloc(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd;
@@ -141,13 +145,11 @@
return -ENOMEM;
atomic_set(&qd->qd_count, 1);
- qd->qd_id = id;
- if (user)
- set_bit(QDF_USER, &qd->qd_flags);
+ qd->qd_id = qid;
qd->qd_slot = -1;
INIT_LIST_HEAD(&qd->qd_reclaim);
- error = gfs2_glock_get(sdp, 2 * (u64)id + !user,
+ error = gfs2_glock_get(sdp, qd2index(qd),
&gfs2_quota_glops, CREATE, &qd->qd_gl);
if (error)
goto fail;
@@ -161,7 +163,7 @@
return error;
}
-static int qd_get(struct gfs2_sbd *sdp, int user, u32 id,
+static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
struct gfs2_quota_data *qd = NULL, *new_qd = NULL;
@@ -173,8 +175,7 @@
found = 0;
spin_lock(&qd_lru_lock);
list_for_each_entry(qd, &sdp->sd_quota_list, qd_list) {
- if (qd->qd_id == id &&
- !test_bit(QDF_USER, &qd->qd_flags) == !user) {
+ if (qid_eq(qd->qd_id, qid)) {
if (!atomic_read(&qd->qd_count) &&
!list_empty(&qd->qd_reclaim)) {
/* Remove it from reclaim list */
@@ -208,7 +209,7 @@
return 0;
}
- error = qd_alloc(sdp, user, id, &new_qd);
+ error = qd_alloc(sdp, qid, &new_qd);
if (error)
return error;
}
@@ -458,12 +459,12 @@
qd_put(qd);
}
-static int qdsb_get(struct gfs2_sbd *sdp, int user, u32 id,
+static int qdsb_get(struct gfs2_sbd *sdp, struct kqid qid,
struct gfs2_quota_data **qdp)
{
int error;
- error = qd_get(sdp, user, id, qdp);
+ error = qd_get(sdp, qid, qdp);
if (error)
return error;
@@ -491,7 +492,7 @@
qd_put(qd);
}
-int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid)
+int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data **qd;
@@ -512,28 +513,30 @@
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
- error = qdsb_get(sdp, QUOTA_USER, ip->i_inode.i_uid, qd);
+ error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
- error = qdsb_get(sdp, QUOTA_GROUP, ip->i_inode.i_gid, qd);
+ error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
- if (uid != NO_QUOTA_CHANGE && uid != ip->i_inode.i_uid) {
- error = qdsb_get(sdp, QUOTA_USER, uid, qd);
+ if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) &&
+ !uid_eq(uid, ip->i_inode.i_uid)) {
+ error = qdsb_get(sdp, make_kqid_uid(uid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
qd++;
}
- if (gid != NO_QUOTA_CHANGE && gid != ip->i_inode.i_gid) {
- error = qdsb_get(sdp, QUOTA_GROUP, gid, qd);
+ if (!gid_eq(gid, NO_GID_QUOTA_CHANGE) &&
+ !gid_eq(gid, ip->i_inode.i_gid)) {
+ error = qdsb_get(sdp, make_kqid_gid(gid), qd);
if (error)
goto out;
ip->i_res->rs_qa_qd_num++;
@@ -567,18 +570,10 @@
const struct gfs2_quota_data *qd_a = *(const struct gfs2_quota_data **)a;
const struct gfs2_quota_data *qd_b = *(const struct gfs2_quota_data **)b;
- if (!test_bit(QDF_USER, &qd_a->qd_flags) !=
- !test_bit(QDF_USER, &qd_b->qd_flags)) {
- if (test_bit(QDF_USER, &qd_a->qd_flags))
- return -1;
- else
- return 1;
- }
- if (qd_a->qd_id < qd_b->qd_id)
+ if (qid_lt(qd_a->qd_id, qd_b->qd_id))
return -1;
- if (qd_a->qd_id > qd_b->qd_id)
+ if (qid_lt(qd_b->qd_id, qd_a->qd_id))
return 1;
-
return 0;
}
@@ -590,14 +585,14 @@
s64 x;
mutex_lock(&sdp->sd_quota_mutex);
- gfs2_trans_add_bh(ip->i_gl, qd->qd_bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, qd->qd_bh);
if (!test_bit(QDF_CHANGE, &qd->qd_flags)) {
qc->qc_change = 0;
qc->qc_flags = 0;
- if (test_bit(QDF_USER, &qd->qd_flags))
+ if (qd->qd_id.type == USRQUOTA)
qc->qc_flags = cpu_to_be32(GFS2_QCF_USER);
- qc->qc_id = cpu_to_be32(qd->qd_id);
+ qc->qc_id = cpu_to_be32(from_kqid(&init_user_ns, qd->qd_id));
}
x = be64_to_cpu(qc->qc_change) + change;
@@ -726,7 +721,7 @@
goto unlock_out;
}
- gfs2_trans_add_bh(ip->i_gl, bh, 0);
+ gfs2_trans_add_meta(ip->i_gl, bh);
kaddr = kmap_atomic(page);
if (offset + sizeof(struct gfs2_quota) > PAGE_CACHE_SIZE)
@@ -925,7 +920,7 @@
return error;
}
-int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
+int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data *qd;
@@ -1040,13 +1035,13 @@
printk(KERN_INFO "GFS2: fsid=%s: quota %s for %s %u\n",
sdp->sd_fsname, type,
- (test_bit(QDF_USER, &qd->qd_flags)) ? "user" : "group",
- qd->qd_id);
+ (qd->qd_id.type == USRQUOTA) ? "user" : "group",
+ from_kqid(&init_user_ns, qd->qd_id));
return 0;
}
-int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid)
+int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_quota_data *qd;
@@ -1063,8 +1058,8 @@
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
qd = ip->i_res->rs_qa_qd[x];
- if (!((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
- (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))))
+ if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
+ qid_eq(qd->qd_id, make_kqid_gid(gid))))
continue;
value = (s64)be64_to_cpu(qd->qd_qb.qb_value);
@@ -1074,10 +1069,7 @@
if (be64_to_cpu(qd->qd_qb.qb_limit) && (s64)be64_to_cpu(qd->qd_qb.qb_limit) < value) {
print_message(qd, "exceeded");
- quota_send_warning(make_kqid(&init_user_ns,
- test_bit(QDF_USER, &qd->qd_flags) ?
- USRQUOTA : GRPQUOTA,
- qd->qd_id),
+ quota_send_warning(qd->qd_id,
sdp->sd_vfs->s_dev, QUOTA_NL_BHARDWARN);
error = -EDQUOT;
@@ -1087,10 +1079,7 @@
time_after_eq(jiffies, qd->qd_last_warn +
gfs2_tune_get(sdp,
gt_quota_warn_period) * HZ)) {
- quota_send_warning(make_kqid(&init_user_ns,
- test_bit(QDF_USER, &qd->qd_flags) ?
- USRQUOTA : GRPQUOTA,
- qd->qd_id),
+ quota_send_warning(qd->qd_id,
sdp->sd_vfs->s_dev, QUOTA_NL_BSOFTWARN);
error = print_message(qd, "warning");
qd->qd_last_warn = jiffies;
@@ -1101,7 +1090,7 @@
}
void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
- u32 uid, u32 gid)
+ kuid_t uid, kgid_t gid)
{
struct gfs2_quota_data *qd;
unsigned int x;
@@ -1114,8 +1103,8 @@
for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
qd = ip->i_res->rs_qa_qd[x];
- if ((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) ||
- (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))) {
+ if (qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
+ qid_eq(qd->qd_id, make_kqid_gid(gid))) {
do_qc(qd, change);
}
}
@@ -1170,13 +1159,13 @@
return gfs2_quota_sync(sb, type);
}
-int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id)
+int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid)
{
struct gfs2_quota_data *qd;
struct gfs2_holder q_gh;
int error;
- error = qd_get(sdp, user, id, &qd);
+ error = qd_get(sdp, qid, &qd);
if (error)
return error;
@@ -1194,7 +1183,9 @@
qc->qc_change = be64_to_cpu(str->qc_change);
qc->qc_flags = be32_to_cpu(str->qc_flags);
- qc->qc_id = be32_to_cpu(str->qc_id);
+ qc->qc_id = make_kqid(&init_user_ns,
+ (qc->qc_flags & GFS2_QCF_USER)?USRQUOTA:GRPQUOTA,
+ be32_to_cpu(str->qc_id));
}
int gfs2_quota_init(struct gfs2_sbd *sdp)
@@ -1257,8 +1248,7 @@
if (!qc.qc_change)
continue;
- error = qd_alloc(sdp, (qc.qc_flags & GFS2_QCF_USER),
- qc.qc_id, &qd);
+ error = qd_alloc(sdp, qc.qc_id, &qd);
if (error) {
brelse(bh);
goto fail;
@@ -1485,21 +1475,17 @@
struct gfs2_quota_data *qd;
struct gfs2_holder q_gh;
int error;
- int type;
memset(fdq, 0, sizeof(struct fs_disk_quota));
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return -ESRCH; /* Crazy XFS error code */
- if (qid.type == USRQUOTA)
- type = QUOTA_USER;
- else if (qid.type == GRPQUOTA)
- type = QUOTA_GROUP;
- else
+ if ((qid.type != USRQUOTA) &&
+ (qid.type != GRPQUOTA))
return -EINVAL;
- error = qd_get(sdp, type, from_kqid(&init_user_ns, qid), &qd);
+ error = qd_get(sdp, qid, &qd);
if (error)
return error;
error = do_glock(qd, FORCE, &q_gh);
@@ -1508,8 +1494,8 @@
qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
fdq->d_version = FS_DQUOT_VERSION;
- fdq->d_flags = (type == QUOTA_USER) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
- fdq->d_id = from_kqid(&init_user_ns, qid);
+ fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
+ fdq->d_id = from_kqid_munged(current_user_ns(), qid);
fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift;
fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift;
fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift;
@@ -1535,32 +1521,18 @@
int alloc_required;
loff_t offset;
int error;
- int type;
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return -ESRCH; /* Crazy XFS error code */
- switch(qid.type) {
- case USRQUOTA:
- type = QUOTA_USER;
- if (fdq->d_flags != FS_USER_QUOTA)
- return -EINVAL;
- break;
- case GRPQUOTA:
- type = QUOTA_GROUP;
- if (fdq->d_flags != FS_GROUP_QUOTA)
- return -EINVAL;
- break;
- default:
+ if ((qid.type != USRQUOTA) &&
+ (qid.type != GRPQUOTA))
return -EINVAL;
- }
if (fdq->d_fieldmask & ~GFS2_FIELDMASK)
return -EINVAL;
- if (fdq->d_id != from_kqid(&init_user_ns, qid))
- return -EINVAL;
- error = qd_get(sdp, type, from_kqid(&init_user_ns, qid), &qd);
+ error = qd_get(sdp, qid, &qd);
if (error)
return error;
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index f25d98b..4f5e6e4 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -14,20 +14,21 @@
struct gfs2_sbd;
struct shrink_control;
-#define NO_QUOTA_CHANGE ((u32)-1)
+#define NO_UID_QUOTA_CHANGE INVALID_UID
+#define NO_GID_QUOTA_CHANGE INVALID_GID
-extern int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid);
+extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
extern void gfs2_quota_unhold(struct gfs2_inode *ip);
-extern int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid);
+extern int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
extern void gfs2_quota_unlock(struct gfs2_inode *ip);
-extern int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid);
+extern int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
extern void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
- u32 uid, u32 gid);
+ kuid_t uid, kgid_t gid);
extern int gfs2_quota_sync(struct super_block *sb, int type);
-extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id);
+extern int gfs2_quota_refresh(struct gfs2_sbd *sdp, struct kqid qid);
extern int gfs2_quota_init(struct gfs2_sbd *sdp);
extern void gfs2_quota_cleanup(struct gfs2_sbd *sdp);
@@ -41,7 +42,7 @@
int ret;
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
- ret = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (ret)
return ret;
if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index b7eff07..d1f51fd 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1257,7 +1257,7 @@
int gfs2_fitrim(struct file *filp, void __user *argp)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct request_queue *q = bdev_get_queue(sdp->sd_vfs->s_bdev);
struct buffer_head *bh;
@@ -1323,7 +1323,7 @@
if (ret == 0) {
bh = rgd->rd_bits[0].bi_bh;
rgd->rd_flags |= GFS2_RGF_TRIMMED;
- gfs2_trans_add_bh(rgd->rd_gl, bh, 1);
+ gfs2_trans_add_meta(rgd->rd_gl, bh);
gfs2_rgrp_out(rgd, bh->b_data);
gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, bh->b_data);
gfs2_trans_end(sdp);
@@ -1968,14 +1968,14 @@
*n = 1;
block = gfs2_rbm_to_block(rbm);
- gfs2_trans_add_bh(rbm->rgd->rd_gl, rbm->bi->bi_bh, 1);
+ gfs2_trans_add_meta(rbm->rgd->rd_gl, rbm->bi->bi_bh);
gfs2_setbit(rbm, true, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED);
block++;
while (*n < elen) {
ret = gfs2_rbm_from_block(&pos, block);
if (ret || gfs2_testbit(&pos) != GFS2_BLKST_FREE)
break;
- gfs2_trans_add_bh(pos.rgd->rd_gl, pos.bi->bi_bh, 1);
+ gfs2_trans_add_meta(pos.rgd->rd_gl, pos.bi->bi_bh);
gfs2_setbit(&pos, true, GFS2_BLKST_USED);
(*n)++;
block++;
@@ -2014,7 +2014,7 @@
rbm.bi->bi_bh->b_data + rbm.bi->bi_offset,
rbm.bi->bi_len);
}
- gfs2_trans_add_bh(rbm.rgd->rd_gl, rbm.bi->bi_bh, 1);
+ gfs2_trans_add_meta(rbm.rgd->rd_gl, rbm.bi->bi_bh);
gfs2_setbit(&rbm, false, new_state);
}
@@ -2157,7 +2157,7 @@
if (error == 0) {
struct gfs2_dinode *di =
(struct gfs2_dinode *)dibh->b_data;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
di->di_goal_meta = di->di_goal_data =
cpu_to_be64(ip->i_goal);
brelse(dibh);
@@ -2176,7 +2176,7 @@
*generation = rbm.rgd->rd_igeneration++;
}
- gfs2_trans_add_bh(rbm.rgd->rd_gl, rbm.rgd->rd_bits[0].bi_bh, 1);
+ gfs2_trans_add_meta(rbm.rgd->rd_gl, rbm.rgd->rd_bits[0].bi_bh);
gfs2_rgrp_out(rbm.rgd, rbm.rgd->rd_bits[0].bi_bh->b_data);
gfs2_rgrp_ondisk2lvb(rbm.rgd->rd_rgl, rbm.rgd->rd_bits[0].bi_bh->b_data);
@@ -2223,7 +2223,7 @@
trace_gfs2_block_alloc(ip, rgd, bstart, blen, GFS2_BLKST_FREE);
rgd->rd_free += blen;
rgd->rd_flags &= ~GFS2_RGF_TRIMMED;
- gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+ gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
@@ -2260,7 +2260,7 @@
if (!rgd)
return;
trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
- gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+ gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
update_rgrp_lvb_unlinked(rgd, 1);
@@ -2281,7 +2281,7 @@
rgd->rd_dinodes--;
rgd->rd_free++;
- gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
+ gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
update_rgrp_lvb_unlinked(rgd, -1);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index d648867..cab77b8 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -500,7 +500,7 @@
if (error)
return;
- gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+ gfs2_trans_add_meta(l_ip->i_gl, l_bh);
spin_lock(&sdp->sd_statfs_spin);
l_sc->sc_total += total;
@@ -528,7 +528,7 @@
struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
- gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+ gfs2_trans_add_meta(l_ip->i_gl, l_bh);
spin_lock(&sdp->sd_statfs_spin);
m_sc->sc_total += l_sc->sc_total;
@@ -539,7 +539,7 @@
0, sizeof(struct gfs2_statfs_change));
spin_unlock(&sdp->sd_statfs_spin);
- gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
+ gfs2_trans_add_meta(m_ip->i_gl, m_bh);
gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
}
@@ -663,54 +663,6 @@
return error;
}
-/**
- * gfs2_freeze_fs - freezes the file system
- * @sdp: the file system
- *
- * This function flushes data and meta data for all machines by
- * acquiring the transaction log exclusively. All journals are
- * ensured to be in a clean state as well.
- *
- * Returns: errno
- */
-
-int gfs2_freeze_fs(struct gfs2_sbd *sdp)
-{
- int error = 0;
-
- mutex_lock(&sdp->sd_freeze_lock);
-
- if (!sdp->sd_freeze_count++) {
- error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
- if (error)
- sdp->sd_freeze_count--;
- }
-
- mutex_unlock(&sdp->sd_freeze_lock);
-
- return error;
-}
-
-/**
- * gfs2_unfreeze_fs - unfreezes the file system
- * @sdp: the file system
- *
- * This function allows the file system to proceed by unlocking
- * the exclusively held transaction lock. Other GFS2 nodes are
- * now free to acquire the lock shared and go on with their lives.
- *
- */
-
-void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
-{
- mutex_lock(&sdp->sd_freeze_lock);
-
- if (sdp->sd_freeze_count && !--sdp->sd_freeze_count)
- gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
-
- mutex_unlock(&sdp->sd_freeze_lock);
-}
-
void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
{
struct gfs2_dinode *str = buf;
@@ -721,8 +673,8 @@
str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
- str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
- str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
+ str->di_uid = cpu_to_be32(i_uid_read(&ip->i_inode));
+ str->di_gid = cpu_to_be32(i_gid_read(&ip->i_inode));
str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
@@ -824,7 +776,7 @@
ret = gfs2_meta_inode_buffer(ip, &bh);
if (ret == 0) {
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
}
@@ -888,13 +840,6 @@
int error;
struct gfs2_jdesc *jd;
- /* Unfreeze the filesystem, if we need to */
-
- mutex_lock(&sdp->sd_freeze_lock);
- if (sdp->sd_freeze_count)
- gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
- mutex_unlock(&sdp->sd_freeze_lock);
-
/* No more recovery requests */
set_bit(SDF_NORECOVERY, &sdp->sd_flags);
smp_mb();
@@ -985,7 +930,7 @@
return -EINVAL;
for (;;) {
- error = gfs2_freeze_fs(sdp);
+ error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
if (!error)
break;
@@ -1013,7 +958,9 @@
static int gfs2_unfreeze(struct super_block *sb)
{
- gfs2_unfreeze_fs(sb->s_fs_info);
+ struct gfs2_sbd *sdp = sb->s_fs_info;
+
+ gfs2_glock_dq_uninit(&sdp->sd_freeze_gh);
return 0;
}
@@ -1429,7 +1376,7 @@
if (error)
return error;
- error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (error)
return error;
@@ -1577,6 +1524,7 @@
/* Case 3 starts here */
truncate_inode_pages(&inode->i_data, 0);
gfs2_rs_delete(ip);
+ gfs2_ordered_del_inode(ip);
clear_inode(inode);
gfs2_dir_hash_inval(ip);
ip->i_gl->gl_object = NULL;
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index a046468..90e3322 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -46,9 +46,6 @@
struct buffer_head *l_bh);
extern int gfs2_statfs_sync(struct super_block *sb, int type);
-extern int gfs2_freeze_fs(struct gfs2_sbd *sdp);
-extern void gfs2_unfreeze_fs(struct gfs2_sbd *sdp);
-
extern struct file_system_type gfs2_fs_type;
extern struct file_system_type gfs2meta_fs_type;
extern const struct export_operations gfs2_export_ops;
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 8056b7b..aa5c480 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -91,39 +91,37 @@
static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
{
- unsigned int count;
+ struct super_block *sb = sdp->sd_vfs;
+ int frozen = (sb->s_writers.frozen == SB_UNFROZEN) ? 0 : 1;
- mutex_lock(&sdp->sd_freeze_lock);
- count = sdp->sd_freeze_count;
- mutex_unlock(&sdp->sd_freeze_lock);
-
- return snprintf(buf, PAGE_SIZE, "%u\n", count);
+ return snprintf(buf, PAGE_SIZE, "%u\n", frozen);
}
static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
- ssize_t ret = len;
- int error = 0;
+ int error;
int n = simple_strtol(buf, NULL, 0);
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
switch (n) {
case 0:
- gfs2_unfreeze_fs(sdp);
+ error = thaw_super(sdp->sd_vfs);
break;
case 1:
- error = gfs2_freeze_fs(sdp);
+ error = freeze_super(sdp->sd_vfs);
break;
default:
- ret = -EINVAL;
+ return -EINVAL;
}
- if (error)
+ if (error) {
fs_warn(sdp, "freeze %d error %d", n, error);
+ return error;
+ }
- return ret;
+ return len;
}
static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
@@ -135,7 +133,7 @@
static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
if (simple_strtol(buf, NULL, 0) != 1)
return -EINVAL;
@@ -150,7 +148,7 @@
size_t len)
{
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
if (simple_strtol(buf, NULL, 0) != 1)
return -EINVAL;
@@ -163,7 +161,7 @@
size_t len)
{
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
if (simple_strtol(buf, NULL, 0) != 1)
return -EINVAL;
@@ -175,30 +173,40 @@
static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf,
size_t len)
{
+ struct kqid qid;
int error;
u32 id;
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
id = simple_strtoul(buf, NULL, 0);
- error = gfs2_quota_refresh(sdp, 1, id);
+ qid = make_kqid(current_user_ns(), USRQUOTA, id);
+ if (!qid_valid(qid))
+ return -EINVAL;
+
+ error = gfs2_quota_refresh(sdp, qid);
return error ? error : len;
}
static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf,
size_t len)
{
+ struct kqid qid;
int error;
u32 id;
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
id = simple_strtoul(buf, NULL, 0);
- error = gfs2_quota_refresh(sdp, 0, id);
+ qid = make_kqid(current_user_ns(), GRPQUOTA, id);
+ if (!qid_valid(qid))
+ return -EINVAL;
+
+ error = gfs2_quota_refresh(sdp, qid);
return error ? error : len;
}
@@ -213,7 +221,7 @@
int rv;
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum,
mode);
@@ -332,6 +340,28 @@
return ret;
}
+static ssize_t wdack_show(struct gfs2_sbd *sdp, char *buf)
+{
+ int val = completion_done(&sdp->sd_wdack) ? 1 : 0;
+
+ return sprintf(buf, "%d\n", val);
+}
+
+static ssize_t wdack_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+ ssize_t ret = len;
+ int val;
+
+ val = simple_strtol(buf, NULL, 0);
+
+ if ((val == 1) &&
+ !strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
+ complete(&sdp->sd_wdack);
+ else
+ ret = -EINVAL;
+ return ret;
+}
+
static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf)
{
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
@@ -463,7 +493,7 @@
GDLM_ATTR(proto_name, 0444, proto_name_show, NULL);
GDLM_ATTR(block, 0644, block_show, block_store);
-GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store);
+GDLM_ATTR(withdraw, 0644, wdack_show, wdack_store);
GDLM_ATTR(jid, 0644, jid_show, jid_store);
GDLM_ATTR(first, 0644, lkfirst_show, lkfirst_store);
GDLM_ATTR(first_done, 0444, first_done_show, NULL);
@@ -502,7 +532,7 @@
unsigned int x, y;
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
if (sscanf(buf, "%u %u", &x, &y) != 2 || !y)
return -EINVAL;
@@ -521,7 +551,7 @@
unsigned int x;
if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
+ return -EPERM;
x = simple_strtoul(buf, NULL, 0);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 4136270..88162fa 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -18,6 +18,7 @@
#include "gfs2.h"
#include "incore.h"
#include "glock.h"
+#include "inode.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
@@ -142,44 +143,143 @@
sb_end_intwrite(sdp->sd_vfs);
}
-/**
- * gfs2_trans_add_bh - Add a to-be-modified buffer to the current transaction
- * @gl: the glock the buffer belongs to
- * @bh: The buffer to add
- * @meta: True in the case of adding metadata
- *
- */
-
-void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta)
+static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
+ struct buffer_head *bh,
+ const struct gfs2_log_operations *lops)
{
+ struct gfs2_bufdata *bd;
+
+ bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
+ bd->bd_bh = bh;
+ bd->bd_gl = gl;
+ bd->bd_ops = lops;
+ INIT_LIST_HEAD(&bd->bd_list);
+ bh->b_private = bd;
+ return bd;
+}
+
+/**
+ * gfs2_trans_add_data - Add a databuf to the transaction.
+ * @gl: The inode glock associated with the buffer
+ * @bh: The buffer to add
+ *
+ * This is used in two distinct cases:
+ * i) In ordered write mode
+ * We put the data buffer on a list so that we can ensure that its
+ * synced to disk at the right time
+ * ii) In journaled data mode
+ * We need to journal the data block in the same way as metadata in
+ * the functions above. The difference is that here we have a tag
+ * which is two __be64's being the block number (as per meta data)
+ * and a flag which says whether the data block needs escaping or
+ * not. This means we need a new log entry for each 251 or so data
+ * blocks, which isn't an enormous overhead but twice as much as
+ * for normal metadata blocks.
+ */
+void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
+{
+ struct gfs2_trans *tr = current->journal_info;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct address_space *mapping = bh->b_page->mapping;
+ struct gfs2_inode *ip = GFS2_I(mapping->host);
+ struct gfs2_bufdata *bd;
+
+ if (!gfs2_is_jdata(ip)) {
+ gfs2_ordered_add_inode(ip);
+ return;
+ }
+
+ lock_buffer(bh);
+ gfs2_log_lock(sdp);
+ bd = bh->b_private;
+ if (bd == NULL) {
+ gfs2_log_unlock(sdp);
+ unlock_buffer(bh);
+ if (bh->b_private == NULL)
+ bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops);
+ lock_buffer(bh);
+ gfs2_log_lock(sdp);
+ }
+ gfs2_assert(sdp, bd->bd_gl == gl);
+ tr->tr_touched = 1;
+ if (list_empty(&bd->bd_list)) {
+ set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+ set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+ gfs2_pin(sdp, bd->bd_bh);
+ tr->tr_num_databuf_new++;
+ sdp->sd_log_num_databuf++;
+ list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf);
+ }
+ gfs2_log_unlock(sdp);
+ unlock_buffer(bh);
+}
+
+static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
+{
+ struct gfs2_meta_header *mh;
+ struct gfs2_trans *tr;
+
+ tr = current->journal_info;
+ tr->tr_touched = 1;
+ if (!list_empty(&bd->bd_list))
+ return;
+ set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+ set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+ mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
+ if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
+ printk(KERN_ERR
+ "Attempting to add uninitialised block to journal (inplace block=%lld)\n",
+ (unsigned long long)bd->bd_bh->b_blocknr);
+ BUG();
+ }
+ gfs2_pin(sdp, bd->bd_bh);
+ mh->__pad0 = cpu_to_be64(0);
+ mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+ sdp->sd_log_num_buf++;
+ list_add(&bd->bd_list, &sdp->sd_log_le_buf);
+ tr->tr_num_buf_new++;
+}
+
+void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
+{
+
struct gfs2_sbd *sdp = gl->gl_sbd;
struct gfs2_bufdata *bd;
lock_buffer(bh);
gfs2_log_lock(sdp);
bd = bh->b_private;
- if (bd)
- gfs2_assert(sdp, bd->bd_gl == gl);
- else {
+ if (bd == NULL) {
gfs2_log_unlock(sdp);
unlock_buffer(bh);
- gfs2_attach_bufdata(gl, bh, meta);
- bd = bh->b_private;
+ lock_page(bh->b_page);
+ if (bh->b_private == NULL)
+ bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops);
+ unlock_page(bh->b_page);
lock_buffer(bh);
gfs2_log_lock(sdp);
}
- lops_add(sdp, bd);
+ gfs2_assert(sdp, bd->bd_gl == gl);
+ meta_lo_add(sdp, bd);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
}
void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
{
+ struct gfs2_glock *gl = bd->bd_gl;
+ struct gfs2_trans *tr = current->journal_info;
+
BUG_ON(!list_empty(&bd->bd_list));
BUG_ON(!list_empty(&bd->bd_ail_st_list));
BUG_ON(!list_empty(&bd->bd_ail_gl_list));
- lops_init_le(bd, &gfs2_revoke_lops);
- lops_add(sdp, bd);
+ bd->bd_ops = &gfs2_revoke_lops;
+ tr->tr_touched = 1;
+ tr->tr_num_revoke++;
+ sdp->sd_log_num_revoke++;
+ atomic_inc(&gl->gl_revokes);
+ set_bit(GLF_LFLUSH, &gl->gl_flags);
+ list_add(&bd->bd_list, &sdp->sd_log_le_revoke);
}
void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index bf2ae9a..1e6e7da 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -39,7 +39,8 @@
unsigned int revokes);
extern void gfs2_trans_end(struct gfs2_sbd *sdp);
-extern void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
+extern void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh);
+extern void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh);
extern void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
extern void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index f00d7c5..6402fb6 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -54,6 +54,9 @@
kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE);
+ if (!strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
+ wait_for_completion(&sdp->sd_wdack);
+
if (lm->lm_unmount) {
fs_err(sdp, "telling LM to unmount\n");
lm->lm_unmount(sdp);
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 76c144b..ecd37f3 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -270,7 +270,7 @@
if (error)
goto out_gunlock;
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
dataptrs = GFS2_EA2DATAPTRS(ea);
for (x = 0; x < ea->ea_num_ptrs; x++, dataptrs++) {
@@ -309,7 +309,7 @@
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
@@ -331,7 +331,7 @@
if (error)
return error;
- error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (error)
goto out_alloc;
@@ -509,7 +509,7 @@
}
if (din) {
- gfs2_trans_add_bh(ip->i_gl, bh[x], 1);
+ gfs2_trans_add_meta(ip->i_gl, bh[x]);
memcpy(pos, din, cp_size);
din += sdp->sd_jbsize;
}
@@ -629,7 +629,7 @@
return error;
gfs2_trans_add_unrevoke(sdp, block, 1);
*bhp = gfs2_meta_new(ip->i_gl, block);
- gfs2_trans_add_bh(ip->i_gl, *bhp, 1);
+ gfs2_trans_add_meta(ip->i_gl, *bhp);
gfs2_metatype_set(*bhp, GFS2_METATYPE_EA, GFS2_FORMAT_EA);
gfs2_buffer_clear_tail(*bhp, sizeof(struct gfs2_meta_header));
@@ -691,7 +691,7 @@
return error;
gfs2_trans_add_unrevoke(sdp, block, 1);
bh = gfs2_meta_new(ip->i_gl, block);
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
gfs2_metatype_set(bh, GFS2_METATYPE_ED, GFS2_FORMAT_ED);
gfs2_add_inode_blocks(&ip->i_inode, 1);
@@ -751,7 +751,7 @@
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
@@ -834,7 +834,7 @@
struct gfs2_ea_header *prev = el->el_prev;
u32 len;
- gfs2_trans_add_bh(ip->i_gl, el->el_bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, el->el_bh);
if (!prev || !GFS2_EA_IS_STUFFED(ea)) {
ea->ea_type = GFS2_EATYPE_UNUSED;
@@ -872,7 +872,7 @@
if (error)
return error;
- gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, bh);
if (es->ea_split)
ea = ea_split_ea(ea);
@@ -886,7 +886,7 @@
if (error)
goto out;
ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
out:
@@ -901,7 +901,7 @@
struct gfs2_ea_header *ea = es->es_ea;
int error;
- gfs2_trans_add_bh(ip->i_gl, es->es_bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, es->es_bh);
if (es->ea_split)
ea = ea_split_ea(ea);
@@ -997,7 +997,7 @@
goto out;
}
- gfs2_trans_add_bh(ip->i_gl, indbh, 1);
+ gfs2_trans_add_meta(ip->i_gl, indbh);
} else {
u64 blk;
unsigned int n = 1;
@@ -1006,7 +1006,7 @@
return error;
gfs2_trans_add_unrevoke(sdp, blk, 1);
indbh = gfs2_meta_new(ip->i_gl, blk);
- gfs2_trans_add_bh(ip->i_gl, indbh, 1);
+ gfs2_trans_add_meta(ip->i_gl, indbh);
gfs2_metatype_set(indbh, GFS2_METATYPE_IN, GFS2_FORMAT_IN);
gfs2_buffer_clear_tail(indbh, mh_size);
@@ -1092,7 +1092,7 @@
if (error)
return error;
- gfs2_trans_add_bh(ip->i_gl, el->el_bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, el->el_bh);
if (prev) {
u32 len;
@@ -1109,7 +1109,7 @@
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
@@ -1265,7 +1265,7 @@
if (GFS2_EA_IS_STUFFED(el.el_ea)) {
error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0);
if (error == 0) {
- gfs2_trans_add_bh(ip->i_gl, el.el_bh, 1);
+ gfs2_trans_add_meta(ip->i_gl, el.el_bh);
memcpy(GFS2_EA2DATA(el.el_ea), data,
GFS2_EA_DATA_LEN(el.el_ea));
}
@@ -1352,7 +1352,7 @@
if (error)
goto out_gunlock;
- gfs2_trans_add_bh(ip->i_gl, indbh, 1);
+ gfs2_trans_add_meta(ip->i_gl, indbh);
eablk = (__be64 *)(indbh->b_data + sizeof(struct gfs2_meta_header));
bstart = 0;
@@ -1384,7 +1384,7 @@
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
@@ -1434,7 +1434,7 @@
error = gfs2_meta_inode_buffer(ip, &dibh);
if (!error) {
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_trans_add_meta(ip->i_gl, dibh);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
}
@@ -1461,7 +1461,7 @@
if (error)
return error;
- error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (error)
return error;
diff --git a/fs/hfs/Kconfig b/fs/hfs/Kconfig
index b77c5bc..998e3a6 100644
--- a/fs/hfs/Kconfig
+++ b/fs/hfs/Kconfig
@@ -1,6 +1,6 @@
config HFS_FS
- tristate "Apple Macintosh file system support (EXPERIMENTAL)"
- depends on BLOCK && EXPERIMENTAL
+ tristate "Apple Macintosh file system support"
+ depends on BLOCK
select NLS
help
If you say Y here, you will be able to mount Macintosh-formatted
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 422dde2..5f7f1ab 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -51,7 +51,7 @@
*/
static int hfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
int len, err;
char strbuf[HFS_MAX_NAMELEN];
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index d47f116..3031dfd 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -128,7 +128,7 @@
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
- struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
+ struct inode *inode = file_inode(file)->i_mapping->host;
ssize_t ret;
ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index e93ddaa..bbaaa8a 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -466,6 +466,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("hfs");
static void hfs_init_once(void *p)
{
diff --git a/fs/hfsplus/Makefile b/fs/hfsplus/Makefile
index 3cc0df7..09d278b 100644
--- a/fs/hfsplus/Makefile
+++ b/fs/hfsplus/Makefile
@@ -5,5 +5,5 @@
obj-$(CONFIG_HFSPLUS_FS) += hfsplus.o
hfsplus-objs := super.o options.o inode.o ioctl.o extents.o catalog.o dir.o btree.o \
- bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o
-
+ bnode.o brec.o bfind.o tables.o unicode.o wrapper.o bitmap.o part_tbl.o \
+ attributes.o xattr.o xattr_user.o xattr_security.o xattr_trusted.o
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
new file mode 100644
index 0000000..8d691f1
--- /dev/null
+++ b/fs/hfsplus/attributes.c
@@ -0,0 +1,399 @@
+/*
+ * linux/fs/hfsplus/attributes.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handling of records in attributes tree
+ */
+
+#include "hfsplus_fs.h"
+#include "hfsplus_raw.h"
+
+static struct kmem_cache *hfsplus_attr_tree_cachep;
+
+int hfsplus_create_attr_tree_cache(void)
+{
+ if (hfsplus_attr_tree_cachep)
+ return -EEXIST;
+
+ hfsplus_attr_tree_cachep =
+ kmem_cache_create("hfsplus_attr_cache",
+ sizeof(hfsplus_attr_entry), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!hfsplus_attr_tree_cachep)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void hfsplus_destroy_attr_tree_cache(void)
+{
+ kmem_cache_destroy(hfsplus_attr_tree_cachep);
+}
+
+int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *k1,
+ const hfsplus_btree_key *k2)
+{
+ __be32 k1_cnid, k2_cnid;
+
+ k1_cnid = k1->attr.cnid;
+ k2_cnid = k2->attr.cnid;
+ if (k1_cnid != k2_cnid)
+ return be32_to_cpu(k1_cnid) < be32_to_cpu(k2_cnid) ? -1 : 1;
+
+ return hfsplus_strcmp(
+ (const struct hfsplus_unistr *)&k1->attr.key_name,
+ (const struct hfsplus_unistr *)&k2->attr.key_name);
+}
+
+int hfsplus_attr_build_key(struct super_block *sb, hfsplus_btree_key *key,
+ u32 cnid, const char *name)
+{
+ int len;
+
+ memset(key, 0, sizeof(struct hfsplus_attr_key));
+ key->attr.cnid = cpu_to_be32(cnid);
+ if (name) {
+ len = strlen(name);
+ if (len > HFSPLUS_ATTR_MAX_STRLEN) {
+ printk(KERN_ERR "hfs: invalid xattr name's length\n");
+ return -EINVAL;
+ }
+ hfsplus_asc2uni(sb,
+ (struct hfsplus_unistr *)&key->attr.key_name,
+ HFSPLUS_ATTR_MAX_STRLEN, name, len);
+ len = be16_to_cpu(key->attr.key_name.length);
+ } else {
+ key->attr.key_name.length = 0;
+ len = 0;
+ }
+
+ /* The length of the key, as stored in key_len field, does not include
+ * the size of the key_len field itself.
+ * So, offsetof(hfsplus_attr_key, key_name) is a trick because
+ * it takes into consideration key_len field (__be16) of
+ * hfsplus_attr_key structure instead of length field (__be16) of
+ * hfsplus_attr_unistr structure.
+ */
+ key->key_len =
+ cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) +
+ 2 * len);
+
+ return 0;
+}
+
+void hfsplus_attr_build_key_uni(hfsplus_btree_key *key,
+ u32 cnid,
+ struct hfsplus_attr_unistr *name)
+{
+ int ustrlen;
+
+ memset(key, 0, sizeof(struct hfsplus_attr_key));
+ ustrlen = be16_to_cpu(name->length);
+ key->attr.cnid = cpu_to_be32(cnid);
+ key->attr.key_name.length = cpu_to_be16(ustrlen);
+ ustrlen *= 2;
+ memcpy(key->attr.key_name.unicode, name->unicode, ustrlen);
+
+ /* The length of the key, as stored in key_len field, does not include
+ * the size of the key_len field itself.
+ * So, offsetof(hfsplus_attr_key, key_name) is a trick because
+ * it takes into consideration key_len field (__be16) of
+ * hfsplus_attr_key structure instead of length field (__be16) of
+ * hfsplus_attr_unistr structure.
+ */
+ key->key_len =
+ cpu_to_be16(offsetof(struct hfsplus_attr_key, key_name) +
+ ustrlen);
+}
+
+hfsplus_attr_entry *hfsplus_alloc_attr_entry(void)
+{
+ return kmem_cache_alloc(hfsplus_attr_tree_cachep, GFP_KERNEL);
+}
+
+void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry)
+{
+ if (entry)
+ kmem_cache_free(hfsplus_attr_tree_cachep, entry);
+}
+
+#define HFSPLUS_INVALID_ATTR_RECORD -1
+
+static int hfsplus_attr_build_record(hfsplus_attr_entry *entry, int record_type,
+ u32 cnid, const void *value, size_t size)
+{
+ if (record_type == HFSPLUS_ATTR_FORK_DATA) {
+ /*
+ * Mac OS X supports only inline data attributes.
+ * Do nothing
+ */
+ memset(entry, 0, sizeof(*entry));
+ return sizeof(struct hfsplus_attr_fork_data);
+ } else if (record_type == HFSPLUS_ATTR_EXTENTS) {
+ /*
+ * Mac OS X supports only inline data attributes.
+ * Do nothing.
+ */
+ memset(entry, 0, sizeof(*entry));
+ return sizeof(struct hfsplus_attr_extents);
+ } else if (record_type == HFSPLUS_ATTR_INLINE_DATA) {
+ u16 len;
+
+ memset(entry, 0, sizeof(struct hfsplus_attr_inline_data));
+ entry->inline_data.record_type = cpu_to_be32(record_type);
+ if (size <= HFSPLUS_MAX_INLINE_DATA_SIZE)
+ len = size;
+ else
+ return HFSPLUS_INVALID_ATTR_RECORD;
+ entry->inline_data.length = cpu_to_be16(len);
+ memcpy(entry->inline_data.raw_bytes, value, len);
+ /*
+ * Align len on two-byte boundary.
+ * It needs to add pad byte if we have odd len.
+ */
+ len = round_up(len, 2);
+ return offsetof(struct hfsplus_attr_inline_data, raw_bytes) +
+ len;
+ } else /* invalid input */
+ memset(entry, 0, sizeof(*entry));
+
+ return HFSPLUS_INVALID_ATTR_RECORD;
+}
+
+int hfsplus_find_attr(struct super_block *sb, u32 cnid,
+ const char *name, struct hfs_find_data *fd)
+{
+ int err = 0;
+
+ dprint(DBG_ATTR_MOD, "find_attr: %s,%d\n", name ? name : NULL, cnid);
+
+ if (!HFSPLUS_SB(sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ if (name) {
+ err = hfsplus_attr_build_key(sb, fd->search_key, cnid, name);
+ if (err)
+ goto failed_find_attr;
+ err = hfs_brec_find(fd, hfs_find_rec_by_key);
+ if (err)
+ goto failed_find_attr;
+ } else {
+ err = hfsplus_attr_build_key(sb, fd->search_key, cnid, NULL);
+ if (err)
+ goto failed_find_attr;
+ err = hfs_brec_find(fd, hfs_find_1st_rec_by_cnid);
+ if (err)
+ goto failed_find_attr;
+ }
+
+failed_find_attr:
+ return err;
+}
+
+int hfsplus_attr_exists(struct inode *inode, const char *name)
+{
+ int err = 0;
+ struct super_block *sb = inode->i_sb;
+ struct hfs_find_data fd;
+
+ if (!HFSPLUS_SB(sb)->attr_tree)
+ return 0;
+
+ err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd);
+ if (err)
+ return 0;
+
+ err = hfsplus_find_attr(sb, inode->i_ino, name, &fd);
+ if (err)
+ goto attr_not_found;
+
+ hfs_find_exit(&fd);
+ return 1;
+
+attr_not_found:
+ hfs_find_exit(&fd);
+ return 0;
+}
+
+int hfsplus_create_attr(struct inode *inode,
+ const char *name,
+ const void *value, size_t size)
+{
+ struct super_block *sb = inode->i_sb;
+ struct hfs_find_data fd;
+ hfsplus_attr_entry *entry_ptr;
+ int entry_size;
+ int err;
+
+ dprint(DBG_ATTR_MOD, "create_attr: %s,%ld\n",
+ name ? name : NULL, inode->i_ino);
+
+ if (!HFSPLUS_SB(sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ entry_ptr = hfsplus_alloc_attr_entry();
+ if (!entry_ptr)
+ return -ENOMEM;
+
+ err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd);
+ if (err)
+ goto failed_init_create_attr;
+
+ if (name) {
+ err = hfsplus_attr_build_key(sb, fd.search_key,
+ inode->i_ino, name);
+ if (err)
+ goto failed_create_attr;
+ } else {
+ err = -EINVAL;
+ goto failed_create_attr;
+ }
+
+ /* Mac OS X supports only inline data attributes. */
+ entry_size = hfsplus_attr_build_record(entry_ptr,
+ HFSPLUS_ATTR_INLINE_DATA,
+ inode->i_ino,
+ value, size);
+ if (entry_size == HFSPLUS_INVALID_ATTR_RECORD) {
+ err = -EINVAL;
+ goto failed_create_attr;
+ }
+
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
+ if (err != -ENOENT) {
+ if (!err)
+ err = -EEXIST;
+ goto failed_create_attr;
+ }
+
+ err = hfs_brec_insert(&fd, entry_ptr, entry_size);
+ if (err)
+ goto failed_create_attr;
+
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY);
+
+failed_create_attr:
+ hfs_find_exit(&fd);
+
+failed_init_create_attr:
+ hfsplus_destroy_attr_entry(entry_ptr);
+ return err;
+}
+
+static int __hfsplus_delete_attr(struct inode *inode, u32 cnid,
+ struct hfs_find_data *fd)
+{
+ int err = 0;
+ __be32 found_cnid, record_type;
+
+ hfs_bnode_read(fd->bnode, &found_cnid,
+ fd->keyoffset +
+ offsetof(struct hfsplus_attr_key, cnid),
+ sizeof(__be32));
+ if (cnid != be32_to_cpu(found_cnid))
+ return -ENOENT;
+
+ hfs_bnode_read(fd->bnode, &record_type,
+ fd->entryoffset, sizeof(record_type));
+
+ switch (be32_to_cpu(record_type)) {
+ case HFSPLUS_ATTR_INLINE_DATA:
+ /* All is OK. Do nothing. */
+ break;
+ case HFSPLUS_ATTR_FORK_DATA:
+ case HFSPLUS_ATTR_EXTENTS:
+ printk(KERN_ERR "hfs: only inline data xattr are supported\n");
+ return -EOPNOTSUPP;
+ default:
+ printk(KERN_ERR "hfs: invalid extended attribute record\n");
+ return -ENOENT;
+ }
+
+ err = hfs_brec_remove(fd);
+ if (err)
+ return err;
+
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ATTR_DIRTY);
+ return err;
+}
+
+int hfsplus_delete_attr(struct inode *inode, const char *name)
+{
+ int err = 0;
+ struct super_block *sb = inode->i_sb;
+ struct hfs_find_data fd;
+
+ dprint(DBG_ATTR_MOD, "delete_attr: %s,%ld\n",
+ name ? name : NULL, inode->i_ino);
+
+ if (!HFSPLUS_SB(sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ err = hfs_find_init(HFSPLUS_SB(sb)->attr_tree, &fd);
+ if (err)
+ return err;
+
+ if (name) {
+ err = hfsplus_attr_build_key(sb, fd.search_key,
+ inode->i_ino, name);
+ if (err)
+ goto out;
+ } else {
+ printk(KERN_ERR "hfs: invalid extended attribute name\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
+ if (err)
+ goto out;
+
+ err = __hfsplus_delete_attr(inode, inode->i_ino, &fd);
+ if (err)
+ goto out;
+
+out:
+ hfs_find_exit(&fd);
+ return err;
+}
+
+int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid)
+{
+ int err = 0;
+ struct hfs_find_data fd;
+
+ dprint(DBG_ATTR_MOD, "delete_all_attrs: %d\n", cnid);
+
+ if (!HFSPLUS_SB(dir->i_sb)->attr_tree) {
+ printk(KERN_ERR "hfs: attributes file doesn't exist\n");
+ return -EINVAL;
+ }
+
+ err = hfs_find_init(HFSPLUS_SB(dir->i_sb)->attr_tree, &fd);
+ if (err)
+ return err;
+
+ for (;;) {
+ err = hfsplus_find_attr(dir->i_sb, cnid, NULL, &fd);
+ if (err) {
+ if (err != -ENOENT)
+ printk(KERN_ERR "hfs: xattr search failed.\n");
+ goto end_delete_all;
+ }
+
+ err = __hfsplus_delete_attr(dir, cnid, &fd);
+ if (err)
+ goto end_delete_all;
+ }
+
+end_delete_all:
+ hfs_find_exit(&fd);
+ return err;
+}
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index 5d799c1..d73c98d 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -24,7 +24,19 @@
fd->key = ptr + tree->max_key_len + 2;
dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n",
tree->cnid, __builtin_return_address(0));
- mutex_lock(&tree->tree_lock);
+ switch (tree->cnid) {
+ case HFSPLUS_CAT_CNID:
+ mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
+ break;
+ case HFSPLUS_EXT_CNID:
+ mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
+ break;
+ case HFSPLUS_ATTR_CNID:
+ mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
+ break;
+ default:
+ BUG();
+ }
return 0;
}
@@ -38,15 +50,73 @@
fd->tree = NULL;
}
-/* Find the record in bnode that best matches key (not greater than...)*/
-int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
+int hfs_find_1st_rec_by_cnid(struct hfs_bnode *bnode,
+ struct hfs_find_data *fd,
+ int *begin,
+ int *end,
+ int *cur_rec)
+{
+ __be32 cur_cnid, search_cnid;
+
+ if (bnode->tree->cnid == HFSPLUS_EXT_CNID) {
+ cur_cnid = fd->key->ext.cnid;
+ search_cnid = fd->search_key->ext.cnid;
+ } else if (bnode->tree->cnid == HFSPLUS_CAT_CNID) {
+ cur_cnid = fd->key->cat.parent;
+ search_cnid = fd->search_key->cat.parent;
+ } else if (bnode->tree->cnid == HFSPLUS_ATTR_CNID) {
+ cur_cnid = fd->key->attr.cnid;
+ search_cnid = fd->search_key->attr.cnid;
+ } else
+ BUG();
+
+ if (cur_cnid == search_cnid) {
+ (*end) = (*cur_rec);
+ if ((*begin) == (*end))
+ return 1;
+ } else {
+ if (be32_to_cpu(cur_cnid) < be32_to_cpu(search_cnid))
+ (*begin) = (*cur_rec) + 1;
+ else
+ (*end) = (*cur_rec) - 1;
+ }
+
+ return 0;
+}
+
+int hfs_find_rec_by_key(struct hfs_bnode *bnode,
+ struct hfs_find_data *fd,
+ int *begin,
+ int *end,
+ int *cur_rec)
{
int cmpval;
+
+ cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
+ if (!cmpval) {
+ (*end) = (*cur_rec);
+ return 1;
+ }
+ if (cmpval < 0)
+ (*begin) = (*cur_rec) + 1;
+ else
+ *(end) = (*cur_rec) - 1;
+
+ return 0;
+}
+
+/* Find the record in bnode that best matches key (not greater than...)*/
+int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd,
+ search_strategy_t rec_found)
+{
u16 off, len, keylen;
int rec;
int b, e;
int res;
+ if (!rec_found)
+ BUG();
+
b = 0;
e = bnode->num_recs - 1;
res = -ENOENT;
@@ -59,17 +129,12 @@
goto fail;
}
hfs_bnode_read(bnode, fd->key, off, keylen);
- cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
- if (!cmpval) {
- e = rec;
+ if (rec_found(bnode, fd, &b, &e, &rec)) {
res = 0;
goto done;
}
- if (cmpval < 0)
- b = rec + 1;
- else
- e = rec - 1;
} while (b <= e);
+
if (rec != e && e >= 0) {
len = hfs_brec_lenoff(bnode, e, &off);
keylen = hfs_brec_keylen(bnode, e);
@@ -79,19 +144,21 @@
}
hfs_bnode_read(bnode, fd->key, off, keylen);
}
+
done:
fd->record = e;
fd->keyoffset = off;
fd->keylength = keylen;
fd->entryoffset = off + keylen;
fd->entrylength = len - keylen;
+
fail:
return res;
}
/* Traverse a B*Tree from the root to a leaf finding best fit to key */
/* Return allocated copy of node found, set recnum to best record */
-int hfs_brec_find(struct hfs_find_data *fd)
+int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare)
{
struct hfs_btree *tree;
struct hfs_bnode *bnode;
@@ -122,7 +189,7 @@
goto invalid;
bnode->parent = parent;
- res = __hfs_brec_find(bnode, fd);
+ res = __hfs_brec_find(bnode, fd, do_key_compare);
if (!height)
break;
if (fd->record < 0)
@@ -149,7 +216,7 @@
{
int res;
- res = hfs_brec_find(fd);
+ res = hfs_brec_find(fd, hfs_find_rec_by_key);
if (res)
return res;
if (fd->entrylength > rec_len)
diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
index 1c42cc5..f31ac6f 100644
--- a/fs/hfsplus/bnode.c
+++ b/fs/hfsplus/bnode.c
@@ -62,7 +62,8 @@
tree = node->tree;
if (node->type == HFS_NODE_LEAF ||
- tree->attributes & HFS_TREE_VARIDXKEYS)
+ tree->attributes & HFS_TREE_VARIDXKEYS ||
+ node->tree->cnid == HFSPLUS_ATTR_CNID)
key_len = hfs_bnode_read_u16(node, off) + 2;
else
key_len = tree->max_key_len + 2;
@@ -314,7 +315,8 @@
if (i && node->type == HFS_NODE_INDEX) {
int tmp;
- if (node->tree->attributes & HFS_TREE_VARIDXKEYS)
+ if (node->tree->attributes & HFS_TREE_VARIDXKEYS ||
+ node->tree->cnid == HFSPLUS_ATTR_CNID)
tmp = hfs_bnode_read_u16(node, key_off) + 2;
else
tmp = node->tree->max_key_len + 2;
@@ -646,6 +648,8 @@
if (test_bit(HFS_BNODE_DELETED, &node->flags)) {
hfs_bnode_unhash(node);
spin_unlock(&tree->hash_lock);
+ hfs_bnode_clear(node, 0,
+ PAGE_CACHE_SIZE * tree->pages_per_bnode);
hfs_bmap_free(node);
hfs_bnode_free(node);
return;
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 2a734cf..298d4e4 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -36,7 +36,8 @@
return 0;
if ((node->type == HFS_NODE_INDEX) &&
- !(node->tree->attributes & HFS_TREE_VARIDXKEYS)) {
+ !(node->tree->attributes & HFS_TREE_VARIDXKEYS) &&
+ (node->tree->cnid != HFSPLUS_ATTR_CNID)) {
retval = node->tree->max_key_len + 2;
} else {
recoff = hfs_bnode_read_u16(node,
@@ -151,12 +152,13 @@
/* get index key */
hfs_bnode_read_key(new_node, fd->search_key, 14);
- __hfs_brec_find(fd->bnode, fd);
+ __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key);
hfs_bnode_put(new_node);
new_node = NULL;
- if (tree->attributes & HFS_TREE_VARIDXKEYS)
+ if ((tree->attributes & HFS_TREE_VARIDXKEYS) ||
+ (tree->cnid == HFSPLUS_ATTR_CNID))
key_len = be16_to_cpu(fd->search_key->key_len) + 2;
else {
fd->search_key->key_len =
@@ -201,7 +203,7 @@
hfs_bnode_put(node);
node = fd->bnode = parent;
- __hfs_brec_find(node, fd);
+ __hfs_brec_find(node, fd, hfs_find_rec_by_key);
goto again;
}
hfs_bnode_write_u16(node,
@@ -367,12 +369,13 @@
parent = hfs_bnode_find(tree, node->parent);
if (IS_ERR(parent))
return PTR_ERR(parent);
- __hfs_brec_find(parent, fd);
+ __hfs_brec_find(parent, fd, hfs_find_rec_by_key);
hfs_bnode_dump(parent);
rec = fd->record;
/* size difference between old and new key */
- if (tree->attributes & HFS_TREE_VARIDXKEYS)
+ if ((tree->attributes & HFS_TREE_VARIDXKEYS) ||
+ (tree->cnid == HFSPLUS_ATTR_CNID))
newkeylen = hfs_bnode_read_u16(node, 14) + 2;
else
fd->keylength = newkeylen = tree->max_key_len + 2;
@@ -427,7 +430,7 @@
hfs_bnode_read_key(new_node, fd->search_key, 14);
cnid = cpu_to_be32(new_node->this);
- __hfs_brec_find(fd->bnode, fd);
+ __hfs_brec_find(fd->bnode, fd, hfs_find_rec_by_key);
hfs_brec_insert(fd, &cnid, sizeof(cnid));
hfs_bnode_put(fd->bnode);
hfs_bnode_put(new_node);
@@ -495,13 +498,15 @@
/* insert old root idx into new root */
node->parent = tree->root;
if (node->type == HFS_NODE_LEAF ||
- tree->attributes & HFS_TREE_VARIDXKEYS)
+ tree->attributes & HFS_TREE_VARIDXKEYS ||
+ tree->cnid == HFSPLUS_ATTR_CNID)
key_size = hfs_bnode_read_u16(node, 14) + 2;
else
key_size = tree->max_key_len + 2;
hfs_bnode_copy(new_node, 14, node, 14, key_size);
- if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) {
+ if (!(tree->attributes & HFS_TREE_VARIDXKEYS) &&
+ (tree->cnid != HFSPLUS_ATTR_CNID)) {
key_size = tree->max_key_len + 2;
hfs_bnode_write_u16(new_node, 14, tree->max_key_len);
}
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index 685d07d..efb689c 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -98,6 +98,14 @@
set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
}
break;
+ case HFSPLUS_ATTR_CNID:
+ if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) {
+ printk(KERN_ERR "hfs: invalid attributes max_key_len %d\n",
+ tree->max_key_len);
+ goto fail_page;
+ }
+ tree->keycmp = hfsplus_attr_bin_cmp_key;
+ break;
default:
printk(KERN_ERR "hfs: unknown B*Tree requested\n");
goto fail_page;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 798d9c4..840d71e 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -45,7 +45,8 @@
key->cat.parent = cpu_to_be32(parent);
if (str) {
- hfsplus_asc2uni(sb, &key->cat.name, str->name, str->len);
+ hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
+ str->name, str->len);
len = be16_to_cpu(key->cat.name.length);
} else {
key->cat.name.length = 0;
@@ -167,7 +168,8 @@
entry->type = cpu_to_be16(type);
entry->thread.reserved = 0;
entry->thread.parentID = cpu_to_be32(parentid);
- hfsplus_asc2uni(sb, &entry->thread.nodeName, str->name, str->len);
+ hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
+ str->name, str->len);
return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2;
}
@@ -198,7 +200,7 @@
hfsplus_cat_build_key_uni(fd->search_key,
be32_to_cpu(tmp.thread.parentID),
&tmp.thread.nodeName);
- return hfs_brec_find(fd);
+ return hfs_brec_find(fd, hfs_find_rec_by_key);
}
int hfsplus_create_cat(u32 cnid, struct inode *dir,
@@ -221,7 +223,7 @@
S_ISDIR(inode->i_mode) ?
HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
dir->i_ino, str);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
if (!err)
err = -EEXIST;
@@ -233,7 +235,7 @@
hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
entry_size = hfsplus_cat_build_record(&entry, cnid, inode);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
/* panic? */
if (!err)
@@ -253,7 +255,7 @@
err1:
hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
- if (!hfs_brec_find(&fd))
+ if (!hfs_brec_find(&fd, hfs_find_rec_by_key))
hfs_brec_remove(&fd);
err2:
hfs_find_exit(&fd);
@@ -279,7 +281,7 @@
int len;
hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -296,7 +298,7 @@
} else
hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -326,7 +328,7 @@
goto out;
hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -337,6 +339,12 @@
dir->i_size--;
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
+
+ if (type == HFSPLUS_FILE || type == HFSPLUS_FOLDER) {
+ if (HFSPLUS_SB(sb)->attr_tree)
+ hfsplus_delete_all_attrs(dir, cnid);
+ }
+
out:
hfs_find_exit(&fd);
@@ -363,7 +371,7 @@
/* find the old dir entry and read the data */
hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
- err = hfs_brec_find(&src_fd);
+ err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
if (err)
goto out;
if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) {
@@ -376,7 +384,7 @@
/* create new dir entry with the data from the old entry */
hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
- err = hfs_brec_find(&dst_fd);
+ err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
if (!err)
err = -EEXIST;
@@ -391,7 +399,7 @@
/* finally remove the old entry */
hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
- err = hfs_brec_find(&src_fd);
+ err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
if (err)
goto out;
err = hfs_brec_remove(&src_fd);
@@ -402,7 +410,7 @@
/* remove old thread entry */
hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
- err = hfs_brec_find(&src_fd);
+ err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
if (err)
goto out;
type = hfs_bnode_read_u16(src_fd.bnode, src_fd.entryoffset);
@@ -414,7 +422,7 @@
hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
dst_dir->i_ino, dst_name);
- err = hfs_brec_find(&dst_fd);
+ err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
if (err != -ENOENT) {
if (!err)
err = -EEXIST;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 6b9f921..031c24e 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -15,6 +15,7 @@
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
+#include "xattr.h"
static inline void hfsplus_instantiate(struct dentry *dentry,
struct inode *inode, u32 cnid)
@@ -122,7 +123,7 @@
static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
int len, err;
char strbuf[HFSPLUS_MAX_STRLEN + 1];
@@ -138,7 +139,7 @@
if (err)
return err;
hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
- err = hfs_brec_find(&fd);
+ err = hfs_brec_find(&fd, hfs_find_rec_by_key);
if (err)
goto out;
@@ -421,6 +422,15 @@
if (res)
goto out_err;
+ res = hfsplus_init_inode_security(inode, dir, &dentry->d_name);
+ if (res == -EOPNOTSUPP)
+ res = 0; /* Operation is not supported. */
+ else if (res) {
+ /* Try to delete anyway without error analysis. */
+ hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
+ goto out_err;
+ }
+
hfsplus_instantiate(dentry, inode, inode->i_ino);
mark_inode_dirty(inode);
goto out;
@@ -450,15 +460,26 @@
init_special_inode(inode, mode, rdev);
res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
- if (res) {
- clear_nlink(inode);
- hfsplus_delete_inode(inode);
- iput(inode);
- goto out;
+ if (res)
+ goto failed_mknod;
+
+ res = hfsplus_init_inode_security(inode, dir, &dentry->d_name);
+ if (res == -EOPNOTSUPP)
+ res = 0; /* Operation is not supported. */
+ else if (res) {
+ /* Try to delete anyway without error analysis. */
+ hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
+ goto failed_mknod;
}
hfsplus_instantiate(dentry, inode, inode->i_ino);
mark_inode_dirty(inode);
+ goto out;
+
+failed_mknod:
+ clear_nlink(inode);
+ hfsplus_delete_inode(inode);
+ iput(inode);
out:
mutex_unlock(&sbi->vh_mutex);
return res;
@@ -499,15 +520,19 @@
}
const struct inode_operations hfsplus_dir_inode_operations = {
- .lookup = hfsplus_lookup,
- .create = hfsplus_create,
- .link = hfsplus_link,
- .unlink = hfsplus_unlink,
- .mkdir = hfsplus_mkdir,
- .rmdir = hfsplus_rmdir,
- .symlink = hfsplus_symlink,
- .mknod = hfsplus_mknod,
- .rename = hfsplus_rename,
+ .lookup = hfsplus_lookup,
+ .create = hfsplus_create,
+ .link = hfsplus_link,
+ .unlink = hfsplus_unlink,
+ .mkdir = hfsplus_mkdir,
+ .rmdir = hfsplus_rmdir,
+ .symlink = hfsplus_symlink,
+ .mknod = hfsplus_mknod,
+ .rename = hfsplus_rename,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = hfsplus_listxattr,
+ .removexattr = hfsplus_removexattr,
};
const struct file_operations hfsplus_dir_operations = {
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index eba76ea..a94f0f7 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -95,7 +95,7 @@
HFSPLUS_IS_RSRC(inode) ?
HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
- res = hfs_brec_find(fd);
+ res = hfs_brec_find(fd, hfs_find_rec_by_key);
if (hip->extent_state & HFSPLUS_EXT_NEW) {
if (res != -ENOENT)
return;
@@ -154,7 +154,7 @@
hfsplus_ext_build_key(fd->search_key, cnid, block, type);
fd->key->ext.cnid = 0;
- res = hfs_brec_find(fd);
+ res = hfs_brec_find(fd, hfs_find_rec_by_key);
if (res && res != -ENOENT)
return res;
if (fd->key->ext.cnid != fd->search_key->ext.cnid ||
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index a6da86b..05b11f3 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -23,6 +23,7 @@
#define DBG_SUPER 0x00000010
#define DBG_EXTENT 0x00000020
#define DBG_BITMAP 0x00000040
+#define DBG_ATTR_MOD 0x00000080
#if 0
#define DBG_MASK (DBG_EXTENT|DBG_INODE|DBG_BNODE_MOD)
@@ -46,6 +47,13 @@
#define NODE_HASH_SIZE 256
+/* B-tree mutex nested subclasses */
+enum hfsplus_btree_mutex_classes {
+ CATALOG_BTREE_MUTEX,
+ EXTENTS_BTREE_MUTEX,
+ ATTR_BTREE_MUTEX,
+};
+
/* An HFS+ BTree held in memory */
struct hfs_btree {
struct super_block *sb;
@@ -223,6 +231,7 @@
#define HFSPLUS_I_CAT_DIRTY 1 /* has changes in the catalog tree */
#define HFSPLUS_I_EXT_DIRTY 2 /* has changes in the extent tree */
#define HFSPLUS_I_ALLOC_DIRTY 3 /* has changes in the allocation file */
+#define HFSPLUS_I_ATTR_DIRTY 4 /* has changes in the attributes tree */
#define HFSPLUS_IS_RSRC(inode) \
test_bit(HFSPLUS_I_RSRC, &HFSPLUS_I(inode)->flags)
@@ -302,7 +311,7 @@
#define hfs_brec_remove hfsplus_brec_remove
#define hfs_find_init hfsplus_find_init
#define hfs_find_exit hfsplus_find_exit
-#define __hfs_brec_find __hplusfs_brec_find
+#define __hfs_brec_find __hfsplus_brec_find
#define hfs_brec_find hfsplus_brec_find
#define hfs_brec_read hfsplus_brec_read
#define hfs_brec_goto hfsplus_brec_goto
@@ -324,10 +333,33 @@
*/
#define HFSPLUS_IOC_BLESS _IO('h', 0x80)
+typedef int (*search_strategy_t)(struct hfs_bnode *,
+ struct hfs_find_data *,
+ int *, int *, int *);
+
/*
* Functions in any *.c used in other files
*/
+/* attributes.c */
+int hfsplus_create_attr_tree_cache(void);
+void hfsplus_destroy_attr_tree_cache(void);
+hfsplus_attr_entry *hfsplus_alloc_attr_entry(void);
+void hfsplus_destroy_attr_entry(hfsplus_attr_entry *entry_p);
+int hfsplus_attr_bin_cmp_key(const hfsplus_btree_key *,
+ const hfsplus_btree_key *);
+int hfsplus_attr_build_key(struct super_block *, hfsplus_btree_key *,
+ u32, const char *);
+void hfsplus_attr_build_key_uni(hfsplus_btree_key *key,
+ u32 cnid,
+ struct hfsplus_attr_unistr *name);
+int hfsplus_find_attr(struct super_block *, u32,
+ const char *, struct hfs_find_data *);
+int hfsplus_attr_exists(struct inode *inode, const char *name);
+int hfsplus_create_attr(struct inode *, const char *, const void *, size_t);
+int hfsplus_delete_attr(struct inode *, const char *);
+int hfsplus_delete_all_attrs(struct inode *dir, u32 cnid);
+
/* bitmap.c */
int hfsplus_block_allocate(struct super_block *, u32, u32, u32 *);
int hfsplus_block_free(struct super_block *, u32, u32);
@@ -369,8 +401,15 @@
/* bfind.c */
int hfs_find_init(struct hfs_btree *, struct hfs_find_data *);
void hfs_find_exit(struct hfs_find_data *);
-int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *);
-int hfs_brec_find(struct hfs_find_data *);
+int hfs_find_1st_rec_by_cnid(struct hfs_bnode *,
+ struct hfs_find_data *,
+ int *, int *, int *);
+int hfs_find_rec_by_key(struct hfs_bnode *,
+ struct hfs_find_data *,
+ int *, int *, int *);
+int __hfs_brec_find(struct hfs_bnode *, struct hfs_find_data *,
+ search_strategy_t);
+int hfs_brec_find(struct hfs_find_data *, search_strategy_t);
int hfs_brec_read(struct hfs_find_data *, void *, int);
int hfs_brec_goto(struct hfs_find_data *, int);
@@ -417,11 +456,6 @@
/* ioctl.c */
long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
-int hfsplus_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags);
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size);
-ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
/* options.c */
int hfsplus_parse_options(char *, struct hfsplus_sb_info *);
@@ -446,7 +480,7 @@
int hfsplus_uni2asc(struct super_block *,
const struct hfsplus_unistr *, char *, int *);
int hfsplus_asc2uni(struct super_block *,
- struct hfsplus_unistr *, const char *, int);
+ struct hfsplus_unistr *, int, const char *, int);
int hfsplus_hash_dentry(const struct dentry *dentry,
const struct inode *inode, struct qstr *str);
int hfsplus_compare_dentry(const struct dentry *parent,
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 921967e..452ede0 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -52,13 +52,23 @@
typedef __be32 hfsplus_cnid;
typedef __be16 hfsplus_unichr;
+#define HFSPLUS_MAX_STRLEN 255
+#define HFSPLUS_ATTR_MAX_STRLEN 127
+
/* A "string" as used in filenames, etc. */
struct hfsplus_unistr {
__be16 length;
- hfsplus_unichr unicode[255];
+ hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN];
} __packed;
-#define HFSPLUS_MAX_STRLEN 255
+/*
+ * A "string" is used in attributes file
+ * for name of extended attribute
+ */
+struct hfsplus_attr_unistr {
+ __be16 length;
+ hfsplus_unichr unicode[HFSPLUS_ATTR_MAX_STRLEN];
+} __packed;
/* POSIX permissions */
struct hfsplus_perm {
@@ -291,6 +301,8 @@
/* File attribute bits */
#define HFSPLUS_FILE_LOCKED 0x0001
#define HFSPLUS_FILE_THREAD_EXISTS 0x0002
+#define HFSPLUS_XATTR_EXISTS 0x0004
+#define HFSPLUS_ACL_EXISTS 0x0008
/* HFS+ catalog thread (part of a cat_entry) */
struct hfsplus_cat_thread {
@@ -327,11 +339,63 @@
#define HFSPLUS_EXT_KEYLEN sizeof(struct hfsplus_ext_key)
+#define HFSPLUS_XATTR_FINDER_INFO_NAME "com.apple.FinderInfo"
+#define HFSPLUS_XATTR_ACL_NAME "com.apple.system.Security"
+
+#define HFSPLUS_ATTR_INLINE_DATA 0x10
+#define HFSPLUS_ATTR_FORK_DATA 0x20
+#define HFSPLUS_ATTR_EXTENTS 0x30
+
+/* HFS+ attributes tree key */
+struct hfsplus_attr_key {
+ __be16 key_len;
+ __be16 pad;
+ hfsplus_cnid cnid;
+ __be32 start_block;
+ struct hfsplus_attr_unistr key_name;
+} __packed;
+
+#define HFSPLUS_ATTR_KEYLEN sizeof(struct hfsplus_attr_key)
+
+/* HFS+ fork data attribute */
+struct hfsplus_attr_fork_data {
+ __be32 record_type;
+ __be32 reserved;
+ struct hfsplus_fork_raw the_fork;
+} __packed;
+
+/* HFS+ extension attribute */
+struct hfsplus_attr_extents {
+ __be32 record_type;
+ __be32 reserved;
+ struct hfsplus_extent extents;
+} __packed;
+
+#define HFSPLUS_MAX_INLINE_DATA_SIZE 3802
+
+/* HFS+ attribute inline data */
+struct hfsplus_attr_inline_data {
+ __be32 record_type;
+ __be32 reserved1;
+ u8 reserved2[6];
+ __be16 length;
+ u8 raw_bytes[HFSPLUS_MAX_INLINE_DATA_SIZE];
+} __packed;
+
+/* A data record in the attributes tree */
+typedef union {
+ __be32 record_type;
+ struct hfsplus_attr_fork_data fork_data;
+ struct hfsplus_attr_extents extents;
+ struct hfsplus_attr_inline_data inline_data;
+} __packed hfsplus_attr_entry;
+
/* HFS+ generic BTree key */
typedef union {
__be16 key_len;
struct hfsplus_cat_key cat;
struct hfsplus_ext_key ext;
+ struct hfsplus_attr_key attr;
} __packed hfsplus_btree_key;
#endif
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 799b336..160ccc9 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -17,6 +17,7 @@
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
+#include "xattr.h"
static int hfsplus_readpage(struct file *file, struct page *page)
{
@@ -124,7 +125,7 @@
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
- struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
+ struct inode *inode = file_inode(file)->i_mapping->host;
ssize_t ret;
ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
@@ -348,6 +349,18 @@
error = error2;
}
+ if (test_and_clear_bit(HFSPLUS_I_ATTR_DIRTY, &hip->flags)) {
+ if (sbi->attr_tree) {
+ error2 =
+ filemap_write_and_wait(
+ sbi->attr_tree->inode->i_mapping);
+ if (!error)
+ error = error2;
+ } else {
+ printk(KERN_ERR "hfs: sync non-existent attributes tree\n");
+ }
+ }
+
if (test_and_clear_bit(HFSPLUS_I_ALLOC_DIRTY, &hip->flags)) {
error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
if (!error)
@@ -365,9 +378,10 @@
static const struct inode_operations hfsplus_file_inode_operations = {
.lookup = hfsplus_file_lookup,
.setattr = hfsplus_setattr,
- .setxattr = hfsplus_setxattr,
- .getxattr = hfsplus_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
+ .removexattr = hfsplus_removexattr,
};
static const struct file_operations hfsplus_file_operations = {
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index 09addc8..d3ff5cc 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -16,7 +16,6 @@
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/sched.h>
-#include <linux/xattr.h>
#include <asm/uaccess.h>
#include "hfsplus_fs.h"
@@ -59,7 +58,7 @@
static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
unsigned int flags = 0;
@@ -75,7 +74,7 @@
static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
unsigned int flags;
int err = 0;
@@ -151,110 +150,3 @@
return -ENOTTY;
}
}
-
-int hfsplus_setxattr(struct dentry *dentry, const char *name,
- const void *value, size_t size, int flags)
-{
- struct inode *inode = dentry->d_inode;
- struct hfs_find_data fd;
- hfsplus_cat_entry entry;
- struct hfsplus_cat_file *file;
- int res;
-
- if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
- res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
- if (res)
- return res;
- res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
- if (res)
- goto out;
- hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
- sizeof(struct hfsplus_cat_file));
- file = &entry.file;
-
- if (!strcmp(name, "hfs.type")) {
- if (size == 4)
- memcpy(&file->user_info.fdType, value, 4);
- else
- res = -ERANGE;
- } else if (!strcmp(name, "hfs.creator")) {
- if (size == 4)
- memcpy(&file->user_info.fdCreator, value, 4);
- else
- res = -ERANGE;
- } else
- res = -EOPNOTSUPP;
- if (!res) {
- hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
- sizeof(struct hfsplus_cat_file));
- hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
- }
-out:
- hfs_find_exit(&fd);
- return res;
-}
-
-ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
- void *value, size_t size)
-{
- struct inode *inode = dentry->d_inode;
- struct hfs_find_data fd;
- hfsplus_cat_entry entry;
- struct hfsplus_cat_file *file;
- ssize_t res = 0;
-
- if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
- if (size) {
- res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
- if (res)
- return res;
- res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
- if (res)
- goto out;
- hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
- sizeof(struct hfsplus_cat_file));
- }
- file = &entry.file;
-
- if (!strcmp(name, "hfs.type")) {
- if (size >= 4) {
- memcpy(value, &file->user_info.fdType, 4);
- res = 4;
- } else
- res = size ? -ERANGE : 4;
- } else if (!strcmp(name, "hfs.creator")) {
- if (size >= 4) {
- memcpy(value, &file->user_info.fdCreator, 4);
- res = 4;
- } else
- res = size ? -ERANGE : 4;
- } else
- res = -EOPNOTSUPP;
-out:
- if (size)
- hfs_find_exit(&fd);
- return res;
-}
-
-#define HFSPLUS_ATTRLIST_SIZE (sizeof("hfs.creator")+sizeof("hfs.type"))
-
-ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
- struct inode *inode = dentry->d_inode;
-
- if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
- if (!buffer || !size)
- return HFSPLUS_ATTRLIST_SIZE;
- if (size < HFSPLUS_ATTRLIST_SIZE)
- return -ERANGE;
- strcpy(buffer, "hfs.type");
- strcpy(buffer + sizeof("hfs.type"), "hfs.creator");
-
- return HFSPLUS_ATTRLIST_SIZE;
-}
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 796198d..7b87284 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -20,6 +20,7 @@
static void hfsplus_destroy_inode(struct inode *inode);
#include "hfsplus_fs.h"
+#include "xattr.h"
static int hfsplus_system_read_inode(struct inode *inode)
{
@@ -118,6 +119,7 @@
case HFSPLUS_ATTR_CNID:
fork = &vhdr->attr_file;
tree = sbi->attr_tree;
+ break;
default:
return -EIO;
}
@@ -191,6 +193,12 @@
error2 = filemap_write_and_wait(sbi->ext_tree->inode->i_mapping);
if (!error)
error = error2;
+ if (sbi->attr_tree) {
+ error2 =
+ filemap_write_and_wait(sbi->attr_tree->inode->i_mapping);
+ if (!error)
+ error = error2;
+ }
error2 = filemap_write_and_wait(sbi->alloc_file->i_mapping);
if (!error)
error = error2;
@@ -281,6 +289,7 @@
hfsplus_sync_fs(sb, 1);
}
+ hfs_btree_close(sbi->attr_tree);
hfs_btree_close(sbi->cat_tree);
hfs_btree_close(sbi->ext_tree);
iput(sbi->alloc_file);
@@ -477,12 +486,20 @@
printk(KERN_ERR "hfs: failed to load catalog file\n");
goto out_close_ext_tree;
}
+ if (vhdr->attr_file.total_blocks != 0) {
+ sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID);
+ if (!sbi->attr_tree) {
+ printk(KERN_ERR "hfs: failed to load attributes file\n");
+ goto out_close_cat_tree;
+ }
+ }
+ sb->s_xattr = hfsplus_xattr_handlers;
inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID);
if (IS_ERR(inode)) {
printk(KERN_ERR "hfs: failed to load allocation file\n");
err = PTR_ERR(inode);
- goto out_close_cat_tree;
+ goto out_close_attr_tree;
}
sbi->alloc_file = inode;
@@ -542,10 +559,27 @@
}
err = hfsplus_create_cat(sbi->hidden_dir->i_ino, root,
&str, sbi->hidden_dir);
- mutex_unlock(&sbi->vh_mutex);
- if (err)
+ if (err) {
+ mutex_unlock(&sbi->vh_mutex);
goto out_put_hidden_dir;
+ }
+ err = hfsplus_init_inode_security(sbi->hidden_dir,
+ root, &str);
+ if (err == -EOPNOTSUPP)
+ err = 0; /* Operation is not supported. */
+ else if (err) {
+ /*
+ * Try to delete anyway without
+ * error analysis.
+ */
+ hfsplus_delete_cat(sbi->hidden_dir->i_ino,
+ root, &str);
+ mutex_unlock(&sbi->vh_mutex);
+ goto out_put_hidden_dir;
+ }
+
+ mutex_unlock(&sbi->vh_mutex);
hfsplus_mark_inode_dirty(sbi->hidden_dir,
HFSPLUS_I_CAT_DIRTY);
}
@@ -562,6 +596,8 @@
sb->s_root = NULL;
out_put_alloc_file:
iput(sbi->alloc_file);
+out_close_attr_tree:
+ hfs_btree_close(sbi->attr_tree);
out_close_cat_tree:
hfs_btree_close(sbi->cat_tree);
out_close_ext_tree:
@@ -618,6 +654,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("hfsplus");
static void hfsplus_init_once(void *p)
{
@@ -635,9 +672,20 @@
hfsplus_init_once);
if (!hfsplus_inode_cachep)
return -ENOMEM;
+ err = hfsplus_create_attr_tree_cache();
+ if (err)
+ goto destroy_inode_cache;
err = register_filesystem(&hfsplus_fs_type);
if (err)
- kmem_cache_destroy(hfsplus_inode_cachep);
+ goto destroy_attr_tree_cache;
+ return 0;
+
+destroy_attr_tree_cache:
+ hfsplus_destroy_attr_tree_cache();
+
+destroy_inode_cache:
+ kmem_cache_destroy(hfsplus_inode_cachep);
+
return err;
}
@@ -650,6 +698,7 @@
* destroy cache.
*/
rcu_barrier();
+ hfsplus_destroy_attr_tree_cache();
kmem_cache_destroy(hfsplus_inode_cachep);
}
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index a32998f2..2c2e47d 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -295,7 +295,8 @@
return hfsplus_decompose_table + (off / 4);
}
-int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
+int hfsplus_asc2uni(struct super_block *sb,
+ struct hfsplus_unistr *ustr, int max_unistr_len,
const char *astr, int len)
{
int size, dsize, decompose;
@@ -303,7 +304,7 @@
wchar_t c;
decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
- while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
+ while (outlen < max_unistr_len && len > 0) {
size = asc2unichar(sb, astr, len, &c);
if (decompose)
@@ -311,7 +312,7 @@
else
dstr = NULL;
if (dstr) {
- if (outlen + dsize > HFSPLUS_MAX_STRLEN)
+ if (outlen + dsize > max_unistr_len)
break;
do {
ustr->unicode[outlen++] = cpu_to_be16(*dstr++);
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
new file mode 100644
index 0000000..e8a4b08
--- /dev/null
+++ b/fs/hfsplus/xattr.c
@@ -0,0 +1,709 @@
+/*
+ * linux/fs/hfsplus/xattr.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Logic of processing extended attributes
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+const struct xattr_handler *hfsplus_xattr_handlers[] = {
+ &hfsplus_xattr_osx_handler,
+ &hfsplus_xattr_user_handler,
+ &hfsplus_xattr_trusted_handler,
+ &hfsplus_xattr_security_handler,
+ NULL
+};
+
+static int strcmp_xattr_finder_info(const char *name)
+{
+ if (name) {
+ return strncmp(name, HFSPLUS_XATTR_FINDER_INFO_NAME,
+ sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME));
+ }
+ return -1;
+}
+
+static int strcmp_xattr_acl(const char *name)
+{
+ if (name) {
+ return strncmp(name, HFSPLUS_XATTR_ACL_NAME,
+ sizeof(HFSPLUS_XATTR_ACL_NAME));
+ }
+ return -1;
+}
+
+static inline int is_known_namespace(const char *name)
+{
+ if (strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) &&
+ strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
+ strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) &&
+ strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
+ return false;
+
+ return true;
+}
+
+static int can_set_xattr(struct inode *inode, const char *name,
+ const void *value, size_t value_len)
+{
+ if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
+ return -EOPNOTSUPP; /* TODO: implement ACL support */
+
+ if (!strncmp(name, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN)) {
+ /*
+ * This makes sure that we aren't trying to set an
+ * attribute in a different namespace by prefixing it
+ * with "osx."
+ */
+ if (is_known_namespace(name + XATTR_MAC_OSX_PREFIX_LEN))
+ return -EOPNOTSUPP;
+
+ return 0;
+ }
+
+ /*
+ * Don't allow setting an attribute in an unknown namespace.
+ */
+ if (strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) &&
+ strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) &&
+ strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+int __hfsplus_setxattr(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ int err = 0;
+ struct hfs_find_data cat_fd;
+ hfsplus_cat_entry entry;
+ u16 cat_entry_flags, cat_entry_type;
+ u16 folder_finderinfo_len = sizeof(struct DInfo) +
+ sizeof(struct DXInfo);
+ u16 file_finderinfo_len = sizeof(struct FInfo) +
+ sizeof(struct FXInfo);
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ err = can_set_xattr(inode, name, value, size);
+ if (err)
+ return err;
+
+ if (strncmp(name, XATTR_MAC_OSX_PREFIX,
+ XATTR_MAC_OSX_PREFIX_LEN) == 0)
+ name += XATTR_MAC_OSX_PREFIX_LEN;
+
+ if (value == NULL) {
+ value = "";
+ size = 0;
+ }
+
+ err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return err;
+ }
+
+ err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: catalog searching failed\n");
+ goto end_setxattr;
+ }
+
+ if (!strcmp_xattr_finder_info(name)) {
+ if (flags & XATTR_CREATE) {
+ printk(KERN_ERR "hfs: xattr exists yet\n");
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ hfs_bnode_read(cat_fd.bnode, &entry, cat_fd.entryoffset,
+ sizeof(hfsplus_cat_entry));
+ if (be16_to_cpu(entry.type) == HFSPLUS_FOLDER) {
+ if (size == folder_finderinfo_len) {
+ memcpy(&entry.folder.user_info, value,
+ folder_finderinfo_len);
+ hfs_bnode_write(cat_fd.bnode, &entry,
+ cat_fd.entryoffset,
+ sizeof(struct hfsplus_cat_folder));
+ hfsplus_mark_inode_dirty(inode,
+ HFSPLUS_I_CAT_DIRTY);
+ } else {
+ err = -ERANGE;
+ goto end_setxattr;
+ }
+ } else if (be16_to_cpu(entry.type) == HFSPLUS_FILE) {
+ if (size == file_finderinfo_len) {
+ memcpy(&entry.file.user_info, value,
+ file_finderinfo_len);
+ hfs_bnode_write(cat_fd.bnode, &entry,
+ cat_fd.entryoffset,
+ sizeof(struct hfsplus_cat_file));
+ hfsplus_mark_inode_dirty(inode,
+ HFSPLUS_I_CAT_DIRTY);
+ } else {
+ err = -ERANGE;
+ goto end_setxattr;
+ }
+ } else {
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ goto end_setxattr;
+ }
+
+ if (!HFSPLUS_SB(inode->i_sb)->attr_tree) {
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+
+ if (hfsplus_attr_exists(inode, name)) {
+ if (flags & XATTR_CREATE) {
+ printk(KERN_ERR "hfs: xattr exists yet\n");
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ err = hfsplus_delete_attr(inode, name);
+ if (err)
+ goto end_setxattr;
+ err = hfsplus_create_attr(inode, name, value, size);
+ if (err)
+ goto end_setxattr;
+ } else {
+ if (flags & XATTR_REPLACE) {
+ printk(KERN_ERR "hfs: cannot replace xattr\n");
+ err = -EOPNOTSUPP;
+ goto end_setxattr;
+ }
+ err = hfsplus_create_attr(inode, name, value, size);
+ if (err)
+ goto end_setxattr;
+ }
+
+ cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset);
+ if (cat_entry_type == HFSPLUS_FOLDER) {
+ cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode,
+ cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags));
+ cat_entry_flags |= HFSPLUS_XATTR_EXISTS;
+ if (!strcmp_xattr_acl(name))
+ cat_entry_flags |= HFSPLUS_ACL_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags),
+ cat_entry_flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else if (cat_entry_type == HFSPLUS_FILE) {
+ cat_entry_flags = hfs_bnode_read_u16(cat_fd.bnode,
+ cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags));
+ cat_entry_flags |= HFSPLUS_XATTR_EXISTS;
+ if (!strcmp_xattr_acl(name))
+ cat_entry_flags |= HFSPLUS_ACL_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags),
+ cat_entry_flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else {
+ printk(KERN_ERR "hfs: invalid catalog entry type\n");
+ err = -EIO;
+ goto end_setxattr;
+ }
+
+end_setxattr:
+ hfs_find_exit(&cat_fd);
+ return err;
+}
+
+static inline int is_osx_xattr(const char *xattr_name)
+{
+ return !is_known_namespace(xattr_name);
+}
+
+static int name_len(const char *xattr_name, int xattr_name_len)
+{
+ int len = xattr_name_len + 1;
+
+ if (is_osx_xattr(xattr_name))
+ len += XATTR_MAC_OSX_PREFIX_LEN;
+
+ return len;
+}
+
+static int copy_name(char *buffer, const char *xattr_name, int name_len)
+{
+ int len = name_len;
+ int offset = 0;
+
+ if (is_osx_xattr(xattr_name)) {
+ strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN);
+ offset += XATTR_MAC_OSX_PREFIX_LEN;
+ len += XATTR_MAC_OSX_PREFIX_LEN;
+ }
+
+ strncpy(buffer + offset, xattr_name, name_len);
+ memset(buffer + offset + name_len, 0, 1);
+ len += 1;
+
+ return len;
+}
+
+static ssize_t hfsplus_getxattr_finder_info(struct dentry *dentry,
+ void *value, size_t size)
+{
+ ssize_t res = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ u16 entry_type;
+ u16 folder_rec_len = sizeof(struct DInfo) + sizeof(struct DXInfo);
+ u16 file_rec_len = sizeof(struct FInfo) + sizeof(struct FXInfo);
+ u16 record_len = max(folder_rec_len, file_rec_len);
+ u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)];
+ u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)];
+
+ if (size >= record_len) {
+ res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+ if (res) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return res;
+ }
+ res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+ if (res)
+ goto end_getxattr_finder_info;
+ entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset);
+
+ if (entry_type == HFSPLUS_FOLDER) {
+ hfs_bnode_read(fd.bnode, folder_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, user_info),
+ folder_rec_len);
+ memcpy(value, folder_finder_info, folder_rec_len);
+ res = folder_rec_len;
+ } else if (entry_type == HFSPLUS_FILE) {
+ hfs_bnode_read(fd.bnode, file_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, user_info),
+ file_rec_len);
+ memcpy(value, file_finder_info, file_rec_len);
+ res = file_rec_len;
+ } else {
+ res = -EOPNOTSUPP;
+ goto end_getxattr_finder_info;
+ }
+ } else
+ res = size ? -ERANGE : record_len;
+
+end_getxattr_finder_info:
+ if (size >= record_len)
+ hfs_find_exit(&fd);
+ return res;
+}
+
+ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size)
+{
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ hfsplus_attr_entry *entry;
+ __be32 xattr_record_type;
+ u32 record_type;
+ u16 record_length = 0;
+ ssize_t res = 0;
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ if (strncmp(name, XATTR_MAC_OSX_PREFIX,
+ XATTR_MAC_OSX_PREFIX_LEN) == 0) {
+ /* skip "osx." prefix */
+ name += XATTR_MAC_OSX_PREFIX_LEN;
+ /*
+ * Don't allow retrieving properly prefixed attributes
+ * by prepending them with "osx."
+ */
+ if (is_known_namespace(name))
+ return -EOPNOTSUPP;
+ }
+
+ if (!strcmp_xattr_finder_info(name))
+ return hfsplus_getxattr_finder_info(dentry, value, size);
+
+ if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
+ return -EOPNOTSUPP;
+
+ entry = hfsplus_alloc_attr_entry();
+ if (!entry) {
+ printk(KERN_ERR "hfs: can't allocate xattr entry\n");
+ return -ENOMEM;
+ }
+
+ res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd);
+ if (res) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ goto failed_getxattr_init;
+ }
+
+ res = hfsplus_find_attr(inode->i_sb, inode->i_ino, name, &fd);
+ if (res) {
+ if (res == -ENOENT)
+ res = -ENODATA;
+ else
+ printk(KERN_ERR "hfs: xattr searching failed\n");
+ goto out;
+ }
+
+ hfs_bnode_read(fd.bnode, &xattr_record_type,
+ fd.entryoffset, sizeof(xattr_record_type));
+ record_type = be32_to_cpu(xattr_record_type);
+ if (record_type == HFSPLUS_ATTR_INLINE_DATA) {
+ record_length = hfs_bnode_read_u16(fd.bnode,
+ fd.entryoffset +
+ offsetof(struct hfsplus_attr_inline_data,
+ length));
+ if (record_length > HFSPLUS_MAX_INLINE_DATA_SIZE) {
+ printk(KERN_ERR "hfs: invalid xattr record size\n");
+ res = -EIO;
+ goto out;
+ }
+ } else if (record_type == HFSPLUS_ATTR_FORK_DATA ||
+ record_type == HFSPLUS_ATTR_EXTENTS) {
+ printk(KERN_ERR "hfs: only inline data xattr are supported\n");
+ res = -EOPNOTSUPP;
+ goto out;
+ } else {
+ printk(KERN_ERR "hfs: invalid xattr record\n");
+ res = -EIO;
+ goto out;
+ }
+
+ if (size) {
+ hfs_bnode_read(fd.bnode, entry, fd.entryoffset,
+ offsetof(struct hfsplus_attr_inline_data,
+ raw_bytes) + record_length);
+ }
+
+ if (size >= record_length) {
+ memcpy(value, entry->inline_data.raw_bytes, record_length);
+ res = record_length;
+ } else
+ res = size ? -ERANGE : record_length;
+
+out:
+ hfs_find_exit(&fd);
+
+failed_getxattr_init:
+ hfsplus_destroy_attr_entry(entry);
+ return res;
+}
+
+static inline int can_list(const char *xattr_name)
+{
+ if (!xattr_name)
+ return 0;
+
+ return strncmp(xattr_name, XATTR_TRUSTED_PREFIX,
+ XATTR_TRUSTED_PREFIX_LEN) ||
+ capable(CAP_SYS_ADMIN);
+}
+
+static ssize_t hfsplus_listxattr_finder_info(struct dentry *dentry,
+ char *buffer, size_t size)
+{
+ ssize_t res = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ u16 entry_type;
+ u8 folder_finder_info[sizeof(struct DInfo) + sizeof(struct DXInfo)];
+ u8 file_finder_info[sizeof(struct FInfo) + sizeof(struct FXInfo)];
+ unsigned long len, found_bit;
+ int xattr_name_len, symbols_count;
+
+ res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+ if (res) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return res;
+ }
+
+ res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+ if (res)
+ goto end_listxattr_finder_info;
+
+ entry_type = hfs_bnode_read_u16(fd.bnode, fd.entryoffset);
+ if (entry_type == HFSPLUS_FOLDER) {
+ len = sizeof(struct DInfo) + sizeof(struct DXInfo);
+ hfs_bnode_read(fd.bnode, folder_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, user_info),
+ len);
+ found_bit = find_first_bit((void *)folder_finder_info, len*8);
+ } else if (entry_type == HFSPLUS_FILE) {
+ len = sizeof(struct FInfo) + sizeof(struct FXInfo);
+ hfs_bnode_read(fd.bnode, file_finder_info,
+ fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, user_info),
+ len);
+ found_bit = find_first_bit((void *)file_finder_info, len*8);
+ } else {
+ res = -EOPNOTSUPP;
+ goto end_listxattr_finder_info;
+ }
+
+ if (found_bit >= (len*8))
+ res = 0;
+ else {
+ symbols_count = sizeof(HFSPLUS_XATTR_FINDER_INFO_NAME) - 1;
+ xattr_name_len =
+ name_len(HFSPLUS_XATTR_FINDER_INFO_NAME, symbols_count);
+ if (!buffer || !size) {
+ if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME))
+ res = xattr_name_len;
+ } else if (can_list(HFSPLUS_XATTR_FINDER_INFO_NAME)) {
+ if (size < xattr_name_len)
+ res = -ERANGE;
+ else {
+ res = copy_name(buffer,
+ HFSPLUS_XATTR_FINDER_INFO_NAME,
+ symbols_count);
+ }
+ }
+ }
+
+end_listxattr_finder_info:
+ hfs_find_exit(&fd);
+
+ return res;
+}
+
+ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+ ssize_t err;
+ ssize_t res = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data fd;
+ u16 key_len = 0;
+ struct hfsplus_attr_key attr_key;
+ char strbuf[HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ int xattr_name_len;
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ res = hfsplus_listxattr_finder_info(dentry, buffer, size);
+ if (res < 0)
+ return res;
+ else if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
+ return (res == 0) ? -EOPNOTSUPP : res;
+
+ err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->attr_tree, &fd);
+ if (err) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return err;
+ }
+
+ err = hfsplus_find_attr(inode->i_sb, inode->i_ino, NULL, &fd);
+ if (err) {
+ if (err == -ENOENT) {
+ if (res == 0)
+ res = -ENODATA;
+ goto end_listxattr;
+ } else {
+ res = err;
+ goto end_listxattr;
+ }
+ }
+
+ for (;;) {
+ key_len = hfs_bnode_read_u16(fd.bnode, fd.keyoffset);
+ if (key_len == 0 || key_len > fd.tree->max_key_len) {
+ printk(KERN_ERR "hfs: invalid xattr key length: %d\n",
+ key_len);
+ res = -EIO;
+ goto end_listxattr;
+ }
+
+ hfs_bnode_read(fd.bnode, &attr_key,
+ fd.keyoffset, key_len + sizeof(key_len));
+
+ if (be32_to_cpu(attr_key.cnid) != inode->i_ino)
+ goto end_listxattr;
+
+ xattr_name_len = HFSPLUS_ATTR_MAX_STRLEN;
+ if (hfsplus_uni2asc(inode->i_sb,
+ (const struct hfsplus_unistr *)&fd.key->attr.key_name,
+ strbuf, &xattr_name_len)) {
+ printk(KERN_ERR "hfs: unicode conversion failed\n");
+ res = -EIO;
+ goto end_listxattr;
+ }
+
+ if (!buffer || !size) {
+ if (can_list(strbuf))
+ res += name_len(strbuf, xattr_name_len);
+ } else if (can_list(strbuf)) {
+ if (size < (res + name_len(strbuf, xattr_name_len))) {
+ res = -ERANGE;
+ goto end_listxattr;
+ } else
+ res += copy_name(buffer + res,
+ strbuf, xattr_name_len);
+ }
+
+ if (hfs_brec_goto(&fd, 1))
+ goto end_listxattr;
+ }
+
+end_listxattr:
+ hfs_find_exit(&fd);
+ return res;
+}
+
+int hfsplus_removexattr(struct dentry *dentry, const char *name)
+{
+ int err = 0;
+ struct inode *inode = dentry->d_inode;
+ struct hfs_find_data cat_fd;
+ u16 flags;
+ u16 cat_entry_type;
+ int is_xattr_acl_deleted = 0;
+ int is_all_xattrs_deleted = 0;
+
+ if ((!S_ISREG(inode->i_mode) &&
+ !S_ISDIR(inode->i_mode)) ||
+ HFSPLUS_IS_RSRC(inode))
+ return -EOPNOTSUPP;
+
+ if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
+ return -EOPNOTSUPP;
+
+ err = can_set_xattr(inode, name, NULL, 0);
+ if (err)
+ return err;
+
+ if (strncmp(name, XATTR_MAC_OSX_PREFIX,
+ XATTR_MAC_OSX_PREFIX_LEN) == 0)
+ name += XATTR_MAC_OSX_PREFIX_LEN;
+
+ if (!strcmp_xattr_finder_info(name))
+ return -EOPNOTSUPP;
+
+ err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: can't init xattr find struct\n");
+ return err;
+ }
+
+ err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &cat_fd);
+ if (err) {
+ printk(KERN_ERR "hfs: catalog searching failed\n");
+ goto end_removexattr;
+ }
+
+ err = hfsplus_delete_attr(inode, name);
+ if (err)
+ goto end_removexattr;
+
+ is_xattr_acl_deleted = !strcmp_xattr_acl(name);
+ is_all_xattrs_deleted = !hfsplus_attr_exists(inode, NULL);
+
+ if (!is_xattr_acl_deleted && !is_all_xattrs_deleted)
+ goto end_removexattr;
+
+ cat_entry_type = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset);
+
+ if (cat_entry_type == HFSPLUS_FOLDER) {
+ flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags));
+ if (is_xattr_acl_deleted)
+ flags &= ~HFSPLUS_ACL_EXISTS;
+ if (is_all_xattrs_deleted)
+ flags &= ~HFSPLUS_XATTR_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_folder, flags),
+ flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else if (cat_entry_type == HFSPLUS_FILE) {
+ flags = hfs_bnode_read_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags));
+ if (is_xattr_acl_deleted)
+ flags &= ~HFSPLUS_ACL_EXISTS;
+ if (is_all_xattrs_deleted)
+ flags &= ~HFSPLUS_XATTR_EXISTS;
+ hfs_bnode_write_u16(cat_fd.bnode, cat_fd.entryoffset +
+ offsetof(struct hfsplus_cat_file, flags),
+ flags);
+ hfsplus_mark_inode_dirty(inode, HFSPLUS_I_CAT_DIRTY);
+ } else {
+ printk(KERN_ERR "hfs: invalid catalog entry type\n");
+ err = -EIO;
+ goto end_removexattr;
+ }
+
+end_removexattr:
+ hfs_find_exit(&cat_fd);
+ return err;
+}
+
+static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
+ strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN +
+ XATTR_MAC_OSX_PREFIX_LEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
+ strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_osx_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_osx_handler = {
+ .prefix = XATTR_MAC_OSX_PREFIX,
+ .list = hfsplus_osx_listxattr,
+ .get = hfsplus_osx_getxattr,
+ .set = hfsplus_osx_setxattr,
+};
diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h
new file mode 100644
index 0000000..847b695
--- /dev/null
+++ b/fs/hfsplus/xattr.h
@@ -0,0 +1,60 @@
+/*
+ * linux/fs/hfsplus/xattr.h
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Logic of processing extended attributes
+ */
+
+#ifndef _LINUX_HFSPLUS_XATTR_H
+#define _LINUX_HFSPLUS_XATTR_H
+
+#include <linux/xattr.h>
+
+extern const struct xattr_handler hfsplus_xattr_osx_handler;
+extern const struct xattr_handler hfsplus_xattr_user_handler;
+extern const struct xattr_handler hfsplus_xattr_trusted_handler;
+/*extern const struct xattr_handler hfsplus_xattr_acl_access_handler;*/
+/*extern const struct xattr_handler hfsplus_xattr_acl_default_handler;*/
+extern const struct xattr_handler hfsplus_xattr_security_handler;
+
+extern const struct xattr_handler *hfsplus_xattr_handlers[];
+
+int __hfsplus_setxattr(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags);
+
+static inline int hfsplus_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ return __hfsplus_setxattr(dentry->d_inode, name, value, size, flags);
+}
+
+ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
+ void *value, size_t size);
+
+ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
+
+int hfsplus_removexattr(struct dentry *dentry, const char *name);
+
+int hfsplus_init_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr);
+
+static inline int hfsplus_init_acl(struct inode *inode, struct inode *dir)
+{
+ /*TODO: implement*/
+ return 0;
+}
+
+static inline int hfsplus_init_inode_security(struct inode *inode,
+ struct inode *dir,
+ const struct qstr *qstr)
+{
+ int err;
+
+ err = hfsplus_init_acl(inode, dir);
+ if (!err)
+ err = hfsplus_init_security(inode, dir, qstr);
+ return err;
+}
+
+#endif
diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
new file mode 100644
index 0000000..83b842f
--- /dev/null
+++ b/fs/hfsplus/xattr_security.c
@@ -0,0 +1,104 @@
+/*
+ * linux/fs/hfsplus/xattr_trusted.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for storing security labels as extended attributes.
+ */
+
+#include <linux/security.h>
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+static int hfsplus_security_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_SECURITY_PREFIX);
+ strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_security_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_SECURITY_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_SECURITY_PREFIX);
+ strcpy(xattr_name + XATTR_SECURITY_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_security_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+static int hfsplus_initxattrs(struct inode *inode,
+ const struct xattr *xattr_array,
+ void *fs_info)
+{
+ const struct xattr *xattr;
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t xattr_name_len;
+ int err = 0;
+
+ for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+ xattr_name_len = strlen(xattr->name);
+
+ if (xattr_name_len == 0)
+ continue;
+
+ if (xattr_name_len + XATTR_SECURITY_PREFIX_LEN >
+ HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_SECURITY_PREFIX);
+ strcpy(xattr_name +
+ XATTR_SECURITY_PREFIX_LEN, xattr->name);
+ memset(xattr_name +
+ XATTR_SECURITY_PREFIX_LEN + xattr_name_len, 0, 1);
+
+ err = __hfsplus_setxattr(inode, xattr_name,
+ xattr->value, xattr->value_len, 0);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+int hfsplus_init_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr)
+{
+ return security_inode_init_security(inode, dir, qstr,
+ &hfsplus_initxattrs, NULL);
+}
+
+const struct xattr_handler hfsplus_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .list = hfsplus_security_listxattr,
+ .get = hfsplus_security_getxattr,
+ .set = hfsplus_security_setxattr,
+};
diff --git a/fs/hfsplus/xattr_trusted.c b/fs/hfsplus/xattr_trusted.c
new file mode 100644
index 0000000..426cee2
--- /dev/null
+++ b/fs/hfsplus/xattr_trusted.c
@@ -0,0 +1,63 @@
+/*
+ * linux/fs/hfsplus/xattr_trusted.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for trusted extended attributes.
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+static int hfsplus_trusted_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_TRUSTED_PREFIX);
+ strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_trusted_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_TRUSTED_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_TRUSTED_PREFIX);
+ strcpy(xattr_name + XATTR_TRUSTED_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_trusted_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_trusted_handler = {
+ .prefix = XATTR_TRUSTED_PREFIX,
+ .list = hfsplus_trusted_listxattr,
+ .get = hfsplus_trusted_getxattr,
+ .set = hfsplus_trusted_setxattr,
+};
diff --git a/fs/hfsplus/xattr_user.c b/fs/hfsplus/xattr_user.c
new file mode 100644
index 0000000..e340165
--- /dev/null
+++ b/fs/hfsplus/xattr_user.c
@@ -0,0 +1,63 @@
+/*
+ * linux/fs/hfsplus/xattr_user.c
+ *
+ * Vyacheslav Dubeyko <slava@dubeyko.com>
+ *
+ * Handler for user extended attributes.
+ */
+
+#include "hfsplus_fs.h"
+#include "xattr.h"
+
+static int hfsplus_user_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_USER_PREFIX);
+ strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name);
+
+ return hfsplus_getxattr(dentry, xattr_name, buffer, size);
+}
+
+static int hfsplus_user_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
+{
+ char xattr_name[HFSPLUS_ATTR_MAX_STRLEN + 1] = {0};
+ size_t len = strlen(name);
+
+ if (!strcmp(name, ""))
+ return -EINVAL;
+
+ if (len + XATTR_USER_PREFIX_LEN > HFSPLUS_ATTR_MAX_STRLEN)
+ return -EOPNOTSUPP;
+
+ strcpy(xattr_name, XATTR_USER_PREFIX);
+ strcpy(xattr_name + XATTR_USER_PREFIX_LEN, name);
+
+ return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
+}
+
+static size_t hfsplus_user_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
+{
+ /*
+ * This method is not used.
+ * It is used hfsplus_listxattr() instead of generic_listxattr().
+ */
+ return -EOPNOTSUPP;
+}
+
+const struct xattr_handler hfsplus_xattr_user_handler = {
+ .prefix = XATTR_USER_PREFIX,
+ .list = hfsplus_user_listxattr,
+ .get = hfsplus_user_getxattr,
+ .set = hfsplus_user_setxattr,
+};
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 457addc..0f6e52d 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -30,7 +30,7 @@
return list_entry(inode, struct hostfs_inode_info, vfs_inode);
}
-#define FILE_HOSTFS_I(file) HOSTFS_I((file)->f_path.dentry->d_inode)
+#define FILE_HOSTFS_I(file) HOSTFS_I(file_inode(file))
static int hostfs_d_delete(const struct dentry *dentry)
{
@@ -845,15 +845,8 @@
return err;
if ((attr->ia_valid & ATTR_SIZE) &&
- attr->ia_size != i_size_read(inode)) {
- int error;
-
- error = inode_newsize_ok(inode, attr->ia_size);
- if (error)
- return error;
-
+ attr->ia_size != i_size_read(inode))
truncate_setsize(inode, attr->ia_size);
- }
setattr_copy(inode, attr);
mark_inode_dirty(inode);
@@ -861,14 +854,6 @@
}
static const struct inode_operations hostfs_iops = {
- .create = hostfs_create,
- .link = hostfs_link,
- .unlink = hostfs_unlink,
- .symlink = hostfs_symlink,
- .mkdir = hostfs_mkdir,
- .rmdir = hostfs_rmdir,
- .mknod = hostfs_mknod,
- .rename = hostfs_rename,
.permission = hostfs_permission,
.setattr = hostfs_setattr,
};
@@ -1001,6 +986,7 @@
.kill_sb = hostfs_kill_sb,
.fs_flags = 0,
};
+MODULE_ALIAS_FS("hostfs");
static int __init init_hostfs(void)
{
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 78e12b2..546f6d3 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -25,7 +25,7 @@
loff_t new_off = off + (whence == 1 ? filp->f_pos : 0);
loff_t pos;
struct quad_buffer_head qbh;
- struct inode *i = filp->f_path.dentry->d_inode;
+ struct inode *i = file_inode(filp);
struct hpfs_inode_info *hpfs_inode = hpfs_i(i);
struct super_block *s = i->i_sb;
@@ -57,7 +57,7 @@
static int hpfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct hpfs_inode_info *hpfs_inode = hpfs_i(inode);
struct quad_buffer_head qbh;
struct hpfs_dirent *de;
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index fbfe2df..9f9dbec 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -152,7 +152,7 @@
retval = do_sync_write(file, buf, count, ppos);
if (retval > 0) {
hpfs_lock(file->f_path.dentry->d_sb);
- hpfs_i(file->f_path.dentry->d_inode)->i_dirty = 1;
+ hpfs_i(file_inode(file))->i_dirty = 1;
hpfs_unlock(file->f_path.dentry->d_sb);
}
return retval;
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 5dc06c8..9edeeb0 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -147,7 +147,7 @@
/*if (le32_to_cpu(fnode->acl_size_l) || le16_to_cpu(fnode->acl_size_s)) {
Some unknown structures like ACL may be in fnode,
we'd better not overwrite them
- hpfs_error(i->i_sb, "fnode %08x has some unknown HPFS386 stuctures", i->i_ino);
+ hpfs_error(i->i_sb, "fnode %08x has some unknown HPFS386 structures", i->i_ino);
} else*/ if (hpfs_sb(i->i_sb)->sb_eas >= 2) {
__le32 ea;
if (!uid_eq(i->i_uid, hpfs_sb(i->i_sb)->sb_uid) || hpfs_inode->i_ea_uid) {
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index a307622..a0617e7 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -688,6 +688,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("hpfs");
static int __init init_hpfs_fs(void)
{
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index 43b315f..126d3c2 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -180,7 +180,7 @@
ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
ssize_t n;
- read = file->f_path.dentry->d_inode->i_fop->read;
+ read = file_inode(file)->i_fop->read;
if (!is_user)
set_fs(KERNEL_DS);
@@ -288,7 +288,7 @@
struct file *proc_file = data->proc_file;
ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
- write = proc_file->f_path.dentry->d_inode->i_fop->write;
+ write = file_inode(proc_file)->i_fop->write;
return (*write)(proc_file, buf, len, ppos);
}
@@ -513,7 +513,7 @@
loff_t (*llseek)(struct file *, loff_t, int);
loff_t ret;
- llseek = proc_file->f_path.dentry->d_inode->i_fop->llseek;
+ llseek = file_inode(proc_file)->i_fop->llseek;
if (llseek != NULL) {
ret = (*llseek)(proc_file, off, where);
if (ret < 0)
@@ -561,7 +561,7 @@
});
int err;
- readdir = proc_file->f_path.dentry->d_inode->i_fop->readdir;
+ readdir = file_inode(proc_file)->i_fop->readdir;
proc_file->f_pos = file->f_pos;
err = (*readdir)(proc_file, &dirent, hppfs_filldir);
@@ -748,6 +748,7 @@
.kill_sb = kill_anon_super,
.fs_flags = 0,
};
+MODULE_ALIAS_FS("hppfs");
static int __init init_hppfs(void)
{
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 78bde32..84e3d85 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -97,7 +97,7 @@
static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
loff_t len, vma_len;
int ret;
struct hstate *h = hstate_file(file);
@@ -896,6 +896,7 @@
.mount = hugetlbfs_mount,
.kill_sb = kill_litter_super,
};
+MODULE_ALIAS_FS("hugetlbfs");
static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
@@ -918,16 +919,25 @@
return h - hstates;
}
+static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
+ dentry->d_name.name);
+}
+
+static struct dentry_operations anon_ops = {
+ .d_dname = hugetlb_dname
+};
+
struct file *hugetlb_file_setup(const char *name, unsigned long addr,
size_t size, vm_flags_t acctflag,
struct user_struct **user,
int creat_flags, int page_size_log)
{
- int error = -ENOMEM;
- struct file *file;
+ struct file *file = ERR_PTR(-ENOMEM);
struct inode *inode;
struct path path;
- struct dentry *root;
+ struct super_block *sb;
struct qstr quick_string;
struct hstate *hstate;
unsigned long num_pages;
@@ -955,17 +965,18 @@
}
}
- root = hugetlbfs_vfsmount[hstate_idx]->mnt_root;
+ sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
- path.dentry = d_alloc(root, &quick_string);
+ path.dentry = d_alloc_pseudo(sb, &quick_string);
if (!path.dentry)
goto out_shm_unlock;
+ d_set_d_op(path.dentry, &anon_ops);
path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
- error = -ENOSPC;
- inode = hugetlbfs_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0);
+ file = ERR_PTR(-ENOSPC);
+ inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
if (!inode)
goto out_dentry;
@@ -973,7 +984,7 @@
size += addr & ~huge_page_mask(hstate);
num_pages = ALIGN(size, huge_page_size(hstate)) >>
huge_page_shift(hstate);
- error = -ENOMEM;
+ file = ERR_PTR(-ENOMEM);
if (hugetlb_reserve_pages(inode, 0, num_pages, NULL, acctflag))
goto out_inode;
@@ -981,10 +992,9 @@
inode->i_size = size;
clear_nlink(inode);
- error = -ENFILE;
file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
&hugetlbfs_file_operations);
- if (!file)
+ if (IS_ERR(file))
goto out_dentry; /* inode is already attached */
return file;
@@ -998,7 +1008,7 @@
user_shm_unlock(size, *user);
*user = NULL;
}
- return ERR_PTR(error);
+ return file;
}
static int __init init_hugetlbfs_fs(void)
diff --git a/fs/inode.c b/fs/inode.c
index 14084b7..f5f7c06 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -798,11 +798,10 @@
int (*test)(struct inode *, void *),
void *data)
{
- struct hlist_node *node;
struct inode *inode = NULL;
repeat:
- hlist_for_each_entry(inode, node, head, i_hash) {
+ hlist_for_each_entry(inode, head, i_hash) {
spin_lock(&inode->i_lock);
if (inode->i_sb != sb) {
spin_unlock(&inode->i_lock);
@@ -830,11 +829,10 @@
static struct inode *find_inode_fast(struct super_block *sb,
struct hlist_head *head, unsigned long ino)
{
- struct hlist_node *node;
struct inode *inode = NULL;
repeat:
- hlist_for_each_entry(inode, node, head, i_hash) {
+ hlist_for_each_entry(inode, head, i_hash) {
spin_lock(&inode->i_lock);
if (inode->i_ino != ino) {
spin_unlock(&inode->i_lock);
@@ -1132,11 +1130,10 @@
static int test_inode_iunique(struct super_block *sb, unsigned long ino)
{
struct hlist_head *b = inode_hashtable + hash(sb, ino);
- struct hlist_node *node;
struct inode *inode;
spin_lock(&inode_hash_lock);
- hlist_for_each_entry(inode, node, b, i_hash) {
+ hlist_for_each_entry(inode, b, i_hash) {
if (inode->i_ino == ino && inode->i_sb == sb) {
spin_unlock(&inode_hash_lock);
return 0;
@@ -1291,10 +1288,9 @@
struct hlist_head *head = inode_hashtable + hash(sb, ino);
while (1) {
- struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
- hlist_for_each_entry(old, node, head, i_hash) {
+ hlist_for_each_entry(old, head, i_hash) {
if (old->i_ino != ino)
continue;
if (old->i_sb != sb)
@@ -1306,7 +1302,7 @@
}
break;
}
- if (likely(!node)) {
+ if (likely(!old)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
@@ -1334,11 +1330,10 @@
struct hlist_head *head = inode_hashtable + hash(sb, hashval);
while (1) {
- struct hlist_node *node;
struct inode *old = NULL;
spin_lock(&inode_hash_lock);
- hlist_for_each_entry(old, node, head, i_hash) {
+ hlist_for_each_entry(old, head, i_hash) {
if (old->i_sb != sb)
continue;
if (!test(old, data))
@@ -1350,7 +1345,7 @@
}
break;
}
- if (likely(!node)) {
+ if (likely(!old)) {
spin_lock(&inode->i_lock);
inode->i_state |= I_NEW;
hlist_add_head(&inode->i_hash, head);
@@ -1655,7 +1650,7 @@
int file_update_time(struct file *file)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct timespec now;
int sync_it = 0;
int ret;
diff --git a/fs/internal.h b/fs/internal.h
index 2f6af7f..4be7823 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -69,7 +69,7 @@
/*
* fs_struct.c
*/
-extern void chroot_fs_refs(struct path *, struct path *);
+extern void chroot_fs_refs(const struct path *, const struct path *);
/*
* file_table.c
@@ -125,3 +125,8 @@
* dcache.c
*/
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
+
+/*
+ * read_write.c
+ */
+extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 3bdad6d..fd507fb 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -175,7 +175,7 @@
struct fiemap fiemap;
struct fiemap __user *ufiemap = (struct fiemap __user *) arg;
struct fiemap_extent_info fieinfo = { 0, };
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
u64 len;
int error;
@@ -424,7 +424,7 @@
*/
int ioctl_preallocate(struct file *filp, void __user *argp)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct space_resv sr;
if (copy_from_user(&sr, argp, sizeof(sr)))
@@ -449,7 +449,7 @@
static int file_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int __user *p = (int __user *)arg;
switch (cmd) {
@@ -512,7 +512,7 @@
static int ioctl_fsfreeze(struct file *filp)
{
- struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
+ struct super_block *sb = file_inode(filp)->i_sb;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -527,7 +527,7 @@
static int ioctl_fsthaw(struct file *filp)
{
- struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
+ struct super_block *sb = file_inode(filp)->i_sb;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -548,7 +548,7 @@
{
int error = 0;
int __user *argp = (int __user *)arg;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
switch (cmd) {
case FIOCLEX:
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 0b3fa79..592e511 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -296,7 +296,7 @@
*/
static int zisofs_readpage(struct file *file, struct page *page)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
int err;
int i, pcount, full_page;
diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c
index f20437c..a7d5c3c 100644
--- a/fs/isofs/dir.c
+++ b/fs/isofs/dir.c
@@ -253,7 +253,7 @@
int result;
char *tmpname;
struct iso_directory_record *tmpde;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
tmpname = (char *)__get_free_page(GFP_KERNEL);
if (tmpname == NULL)
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index 2b4f235..12088d8 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -125,10 +125,10 @@
*/
if (parent && (len < 5)) {
*max_len = 5;
- return 255;
+ return FILEID_INVALID;
} else if (len < 3) {
*max_len = 3;
- return 255;
+ return FILEID_INVALID;
}
len = 3;
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 67ce525..d9b8aeb 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1556,6 +1556,8 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("iso9660");
+MODULE_ALIAS("iso9660");
static int __init init_iso9660_fs(void)
{
@@ -1593,5 +1595,3 @@
module_init(init_iso9660_fs)
module_exit(exit_iso9660_fs)
MODULE_LICENSE("GPL");
-/* Actual filesystem name is iso9660, as requested in filesystems.c */
-MODULE_ALIAS("iso9660");
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 3091d42..750c701 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -435,7 +435,12 @@
trace_jbd2_commit_locking(journal, commit_transaction);
stats.run.rs_wait = commit_transaction->t_max_wait;
+ stats.run.rs_request_delay = 0;
stats.run.rs_locked = jiffies;
+ if (commit_transaction->t_requested)
+ stats.run.rs_request_delay =
+ jbd2_time_diff(commit_transaction->t_requested,
+ stats.run.rs_locked);
stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
stats.run.rs_locked);
@@ -1116,7 +1121,10 @@
*/
spin_lock(&journal->j_history_lock);
journal->j_stats.ts_tid++;
+ if (commit_transaction->t_requested)
+ journal->j_stats.ts_requested++;
journal->j_stats.run.rs_wait += stats.run.rs_wait;
+ journal->j_stats.run.rs_request_delay += stats.run.rs_request_delay;
journal->j_stats.run.rs_running += stats.run.rs_running;
journal->j_stats.run.rs_locked += stats.run.rs_locked;
journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index dbf41f9..ed10991 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -35,7 +35,6 @@
#include <linux/kthread.h>
#include <linux/poison.h>
#include <linux/proc_fs.h>
-#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/math64.h>
#include <linux/hash.h>
@@ -51,6 +50,14 @@
#include <asm/uaccess.h>
#include <asm/page.h>
+#ifdef CONFIG_JBD2_DEBUG
+ushort jbd2_journal_enable_debug __read_mostly;
+EXPORT_SYMBOL(jbd2_journal_enable_debug);
+
+module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644);
+MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2");
+#endif
+
EXPORT_SYMBOL(jbd2_journal_extend);
EXPORT_SYMBOL(jbd2_journal_stop);
EXPORT_SYMBOL(jbd2_journal_lock_updates);
@@ -513,6 +520,10 @@
*/
int __jbd2_log_start_commit(journal_t *journal, tid_t target)
{
+ /* Return if the txn has already requested to be committed */
+ if (journal->j_commit_request == target)
+ return 0;
+
/*
* The only transaction we can possibly wait upon is the
* currently running transaction (if it exists). Otherwise,
@@ -529,6 +540,7 @@
jbd_debug(1, "JBD2: requesting commit %d/%d\n",
journal->j_commit_request,
journal->j_commit_sequence);
+ journal->j_running_transaction->t_requested = jiffies;
wake_up(&journal->j_wait_commit);
return 1;
} else if (!tid_geq(journal->j_commit_request, target))
@@ -894,13 +906,18 @@
if (v != SEQ_START_TOKEN)
return 0;
- seq_printf(seq, "%lu transaction, each up to %u blocks\n",
- s->stats->ts_tid,
- s->journal->j_max_transaction_buffers);
+ seq_printf(seq, "%lu transactions (%lu requested), "
+ "each up to %u blocks\n",
+ s->stats->ts_tid, s->stats->ts_requested,
+ s->journal->j_max_transaction_buffers);
if (s->stats->ts_tid == 0)
return 0;
seq_printf(seq, "average: \n %ums waiting for transaction\n",
jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid));
+ seq_printf(seq, " %ums request delay\n",
+ (s->stats->ts_requested == 0) ? 0 :
+ jiffies_to_msecs(s->stats->run.rs_request_delay /
+ s->stats->ts_requested));
seq_printf(seq, " %ums running transaction\n",
jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid));
seq_printf(seq, " %ums transaction was being locked\n",
@@ -2485,45 +2502,6 @@
spin_unlock(&journal->j_list_lock);
}
-/*
- * debugfs tunables
- */
-#ifdef CONFIG_JBD2_DEBUG
-u8 jbd2_journal_enable_debug __read_mostly;
-EXPORT_SYMBOL(jbd2_journal_enable_debug);
-
-#define JBD2_DEBUG_NAME "jbd2-debug"
-
-static struct dentry *jbd2_debugfs_dir;
-static struct dentry *jbd2_debug;
-
-static void __init jbd2_create_debugfs_entry(void)
-{
- jbd2_debugfs_dir = debugfs_create_dir("jbd2", NULL);
- if (jbd2_debugfs_dir)
- jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME,
- S_IRUGO | S_IWUSR,
- jbd2_debugfs_dir,
- &jbd2_journal_enable_debug);
-}
-
-static void __exit jbd2_remove_debugfs_entry(void)
-{
- debugfs_remove(jbd2_debug);
- debugfs_remove(jbd2_debugfs_dir);
-}
-
-#else
-
-static void __init jbd2_create_debugfs_entry(void)
-{
-}
-
-static void __exit jbd2_remove_debugfs_entry(void)
-{
-}
-
-#endif
#ifdef CONFIG_PROC_FS
@@ -2609,7 +2587,6 @@
ret = journal_init_caches();
if (ret == 0) {
- jbd2_create_debugfs_entry();
jbd2_create_jbd_stats_proc_entry();
} else {
jbd2_journal_destroy_caches();
@@ -2624,7 +2601,6 @@
if (n)
printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
#endif
- jbd2_remove_debugfs_entry();
jbd2_remove_jbd_stats_proc_entry();
jbd2_journal_destroy_caches();
}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index df9f297..325bc01 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -30,6 +30,8 @@
#include <linux/bug.h>
#include <linux/module.h>
+#include <trace/events/jbd2.h>
+
static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
static void __jbd2_journal_unfile_buffer(struct journal_head *jh);
@@ -100,6 +102,7 @@
journal->j_running_transaction = transaction;
transaction->t_max_wait = 0;
transaction->t_start = jiffies;
+ transaction->t_requested = 0;
return transaction;
}
@@ -306,6 +309,8 @@
*/
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
+ handle->h_requested_credits = nblocks;
+ handle->h_start_jiffies = jiffies;
atomic_inc(&transaction->t_updates);
atomic_inc(&transaction->t_handle_count);
jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
@@ -352,7 +357,8 @@
* Return a pointer to a newly allocated handle, or an ERR_PTR() value
* on failure.
*/
-handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask)
+handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask,
+ unsigned int type, unsigned int line_no)
{
handle_t *handle = journal_current_handle();
int err;
@@ -376,8 +382,13 @@
if (err < 0) {
jbd2_free_handle(handle);
current->journal_info = NULL;
- handle = ERR_PTR(err);
+ return ERR_PTR(err);
}
+ handle->h_type = type;
+ handle->h_line_no = line_no;
+ trace_jbd2_handle_start(journal->j_fs_dev->bd_dev,
+ handle->h_transaction->t_tid, type,
+ line_no, nblocks);
return handle;
}
EXPORT_SYMBOL(jbd2__journal_start);
@@ -385,7 +396,7 @@
handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
{
- return jbd2__journal_start(journal, nblocks, GFP_NOFS);
+ return jbd2__journal_start(journal, nblocks, GFP_NOFS, 0, 0);
}
EXPORT_SYMBOL(jbd2_journal_start);
@@ -447,7 +458,14 @@
goto unlock;
}
+ trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev,
+ handle->h_transaction->t_tid,
+ handle->h_type, handle->h_line_no,
+ handle->h_buffer_credits,
+ nblocks);
+
handle->h_buffer_credits += nblocks;
+ handle->h_requested_credits += nblocks;
atomic_add(nblocks, &transaction->t_outstanding_credits);
result = 0;
@@ -1047,9 +1065,12 @@
void jbd2_journal_set_triggers(struct buffer_head *bh,
struct jbd2_buffer_trigger_type *type)
{
- struct journal_head *jh = bh2jh(bh);
+ struct journal_head *jh = jbd2_journal_grab_journal_head(bh);
+ if (WARN_ON(!jh))
+ return;
jh->b_triggers = type;
+ jbd2_journal_put_journal_head(jh);
}
void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data,
@@ -1101,17 +1122,18 @@
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
- struct journal_head *jh = bh2jh(bh);
+ struct journal_head *jh;
int ret = 0;
- jbd_debug(5, "journal_head %p\n", jh);
- JBUFFER_TRACE(jh, "entry");
if (is_handle_aborted(handle))
goto out;
- if (!buffer_jbd(bh)) {
+ jh = jbd2_journal_grab_journal_head(bh);
+ if (!jh) {
ret = -EUCLEAN;
goto out;
}
+ jbd_debug(5, "journal_head %p\n", jh);
+ JBUFFER_TRACE(jh, "entry");
jbd_lock_bh_state(bh);
@@ -1202,6 +1224,7 @@
spin_unlock(&journal->j_list_lock);
out_unlock_bh:
jbd_unlock_bh_state(bh);
+ jbd2_journal_put_journal_head(jh);
out:
JBUFFER_TRACE(jh, "exit");
WARN_ON(ret); /* All errors are bugs, so dump the stack */
@@ -1376,6 +1399,13 @@
}
jbd_debug(4, "Handle %p going down\n", handle);
+ trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev,
+ handle->h_transaction->t_tid,
+ handle->h_type, handle->h_line_no,
+ jiffies - handle->h_start_jiffies,
+ handle->h_sync, handle->h_requested_credits,
+ (handle->h_requested_credits -
+ handle->h_buffer_credits));
/*
* Implement synchronous transaction batching. If the handle
diff --git a/fs/jffs2/Kconfig b/fs/jffs2/Kconfig
index 6ae169c..d8bb6c4 100644
--- a/fs/jffs2/Kconfig
+++ b/fs/jffs2/Kconfig
@@ -50,8 +50,8 @@
write-buffer, and check for errors.
config JFFS2_SUMMARY
- bool "JFFS2 summary support (EXPERIMENTAL)"
- depends on JFFS2_FS && EXPERIMENTAL
+ bool "JFFS2 summary support"
+ depends on JFFS2_FS
default n
help
This feature makes it possible to use summary information
@@ -63,8 +63,8 @@
If unsure, say 'N'.
config JFFS2_FS_XATTR
- bool "JFFS2 XATTR support (EXPERIMENTAL)"
- depends on JFFS2_FS && EXPERIMENTAL
+ bool "JFFS2 XATTR support"
+ depends on JFFS2_FS
default n
help
Extended attributes are name:value pairs associated with inodes by
@@ -173,7 +173,7 @@
successful one.
config JFFS2_CMODE_SIZE
- bool "size (EXPERIMENTAL)"
+ bool "size"
help
Tries all compressors and chooses the one which has the smallest
result.
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index ad7774d..acd46a4 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -117,12 +117,12 @@
static int jffs2_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
struct jffs2_inode_info *f;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct jffs2_full_dirent *fd;
unsigned long offset, curofs;
jffs2_dbg(1, "jffs2_readdir() for dir_i #%lu\n",
- filp->f_path.dentry->d_inode->i_ino);
+ file_inode(filp)->i_ino);
f = JFFS2_INODE_INFO(inode);
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index d3d8799..0defb1c 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -356,6 +356,7 @@
.mount = jffs2_mount,
.kill_sb = jffs2_kill_sb,
};
+MODULE_ALIAS_FS("jffs2");
static int __init init_jffs2_fs(void)
{
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index bc555ff4..93a1232 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -58,7 +58,7 @@
long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct jfs_inode_info *jfs_inode = JFS_IP(inode);
unsigned int flags;
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 9197a1b..0ddbece 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -3004,7 +3004,7 @@
*/
int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *ip = filp->f_path.dentry->d_inode;
+ struct inode *ip = file_inode(filp);
struct nls_table *codepage = JFS_SBI(ip->i_sb)->nls_tab;
int rc = 0;
loff_t dtpos; /* legacy OS/2 style position */
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 1a543be..2003e83 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -154,7 +154,7 @@
/*
* If we really return the number of allocated & free inodes, some
* applications will fail because they won't see enough free inodes.
- * We'll try to calculate some guess as to how may inodes we can
+ * We'll try to calculate some guess as to how many inodes we can
* really allocate
*
* buf->f_files = atomic_read(&imap->im_numinos);
@@ -833,6 +833,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("jfs");
static void init_once(void *foo)
{
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index ca0a080..0796c45 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -11,7 +11,7 @@
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/nfs_fs.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
#include <linux/kthread.h>
@@ -178,7 +178,7 @@
continue;
if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
continue;
- if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0)
+ if (nfs_compare_fh(NFS_FH(file_inode(fl_blocked->fl_file)) ,fh) != 0)
continue;
/* Alright, we found a lock. Set the return status
* and wake up the caller
@@ -220,10 +220,19 @@
{
struct nlm_host *host = (struct nlm_host *) ptr;
struct nlm_wait *block;
+ struct nlm_rqst *req;
struct file_lock *fl, *next;
u32 nsmstate;
struct net *net = host->net;
+ req = kmalloc(sizeof(*req), GFP_KERNEL);
+ if (!req) {
+ printk(KERN_ERR "lockd: reclaimer unable to alloc memory."
+ " Locks for %s won't be reclaimed!\n",
+ host->h_name);
+ return 0;
+ }
+
allow_signal(SIGKILL);
down_write(&host->h_rwsem);
@@ -253,7 +262,7 @@
*/
if (signalled())
continue;
- if (nlmclnt_reclaim(host, fl) != 0)
+ if (nlmclnt_reclaim(host, fl, req) != 0)
continue;
list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted);
if (host->h_nsmstate != nsmstate) {
@@ -279,5 +288,6 @@
/* Release host handle after use */
nlmclnt_release_host(host);
lockd_down(net);
+ kfree(req);
return 0;
}
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 54f9e6c..7e529c3 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -127,7 +127,7 @@
struct nlm_lock *lock = &argp->lock;
nlmclnt_next_cookie(&argp->cookie);
- memcpy(&lock->fh, NFS_FH(fl->fl_file->f_path.dentry->d_inode), sizeof(struct nfs_fh));
+ memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
lock->caller = utsname()->nodename;
lock->oh.data = req->a_owner;
lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
@@ -550,6 +550,9 @@
status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT);
if (status < 0)
break;
+ /* Resend the blocking lock request after a server reboot */
+ if (resp->status == nlm_lck_denied_grace_period)
+ continue;
if (resp->status != nlm_lck_blocked)
break;
}
@@ -615,17 +618,15 @@
* RECLAIM: Try to reclaim a lock
*/
int
-nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl)
+nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl,
+ struct nlm_rqst *req)
{
- struct nlm_rqst reqst, *req;
int status;
- req = &reqst;
memset(req, 0, sizeof(*req));
locks_init_lock(&req->a_args.lock.fl);
locks_init_lock(&req->a_res.lock.fl);
req->a_host = host;
- req->a_flags = 0;
/* Set up the argument struct */
nlmclnt_setlockargs(req, fl);
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 0e17090..969d589 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -13,6 +13,7 @@
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
#include <linux/mutex.h>
@@ -32,15 +33,15 @@
static struct hlist_head nlm_server_hosts[NLM_HOST_NRHASH];
static struct hlist_head nlm_client_hosts[NLM_HOST_NRHASH];
-#define for_each_host(host, pos, chain, table) \
+#define for_each_host(host, chain, table) \
for ((chain) = (table); \
(chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \
- hlist_for_each_entry((host), (pos), (chain), h_hash)
+ hlist_for_each_entry((host), (chain), h_hash)
-#define for_each_host_safe(host, pos, next, chain, table) \
+#define for_each_host_safe(host, next, chain, table) \
for ((chain) = (table); \
(chain) < (table) + NLM_HOST_NRHASH; ++(chain)) \
- hlist_for_each_entry_safe((host), (pos), (next), \
+ hlist_for_each_entry_safe((host), (next), \
(chain), h_hash)
static unsigned long nrhosts;
@@ -225,7 +226,6 @@
.net = net,
};
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host;
struct nsm_handle *nsm = NULL;
struct lockd_net *ln = net_generic(net, lockd_net_id);
@@ -237,7 +237,7 @@
mutex_lock(&nlm_host_mutex);
chain = &nlm_client_hosts[nlm_hash_address(sap)];
- hlist_for_each_entry(host, pos, chain, h_hash) {
+ hlist_for_each_entry(host, chain, h_hash) {
if (host->net != net)
continue;
if (!rpc_cmp_addr(nlm_addr(host), sap))
@@ -322,7 +322,6 @@
const size_t hostname_len)
{
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host = NULL;
struct nsm_handle *nsm = NULL;
struct sockaddr *src_sap = svc_daddr(rqstp);
@@ -350,7 +349,7 @@
nlm_gc_hosts(net);
chain = &nlm_server_hosts[nlm_hash_address(ni.sap)];
- hlist_for_each_entry(host, pos, chain, h_hash) {
+ hlist_for_each_entry(host, chain, h_hash) {
if (host->net != net)
continue;
if (!rpc_cmp_addr(nlm_addr(host), ni.sap))
@@ -515,10 +514,9 @@
{
struct nlm_host *host;
struct hlist_head *chain;
- struct hlist_node *pos;
mutex_lock(&nlm_host_mutex);
- for_each_host(host, pos, chain, cache) {
+ for_each_host(host, chain, cache) {
if (host->h_nsmhandle == nsm
&& host->h_nsmstate != info->state) {
host->h_nsmstate = info->state;
@@ -570,7 +568,6 @@
static void nlm_complain_hosts(struct net *net)
{
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host;
if (net) {
@@ -587,7 +584,7 @@
dprintk("lockd: %lu hosts left:\n", nrhosts);
}
- for_each_host(host, pos, chain, nlm_server_hosts) {
+ for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
dprintk(" %s (cnt %d use %d exp %ld net %p)\n",
@@ -600,14 +597,13 @@
nlm_shutdown_hosts_net(struct net *net)
{
struct hlist_head *chain;
- struct hlist_node *pos;
struct nlm_host *host;
mutex_lock(&nlm_host_mutex);
/* First, make all hosts eligible for gc */
dprintk("lockd: nuking all hosts in net %p...\n", net);
- for_each_host(host, pos, chain, nlm_server_hosts) {
+ for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
host->h_expires = jiffies - 1;
@@ -644,11 +640,11 @@
nlm_gc_hosts(struct net *net)
{
struct hlist_head *chain;
- struct hlist_node *pos, *next;
+ struct hlist_node *next;
struct nlm_host *host;
dprintk("lockd: host garbage collection for net %p\n", net);
- for_each_host(host, pos, chain, nlm_server_hosts) {
+ for_each_host(host, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
host->h_inuse = 0;
@@ -657,7 +653,7 @@
/* Mark all hosts that hold locks, blocks or shares */
nlmsvc_mark_resources(net);
- for_each_host_safe(host, pos, next, chain, nlm_server_hosts) {
+ for_each_host_safe(host, next, chain, nlm_server_hosts) {
if (net && host->net != net)
continue;
if (atomic_read(&host->h_count) || host->h_inuse
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 3c2cfc6..1812f02 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -12,6 +12,7 @@
#include <linux/slab.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/xprtsock.h>
#include <linux/sunrpc/svc.h>
#include <linux/lockd/lockd.h>
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 8d80c99..e703318 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -406,8 +406,8 @@
__be32 ret;
dprintk("lockd: nlmsvc_lock(%s/%ld, ty=%d, pi=%d, %Ld-%Ld, bl=%d)\n",
- file->f_file->f_path.dentry->d_inode->i_sb->s_id,
- file->f_file->f_path.dentry->d_inode->i_ino,
+ file_inode(file->f_file)->i_sb->s_id,
+ file_inode(file->f_file)->i_ino,
lock->fl.fl_type, lock->fl.fl_pid,
(long long)lock->fl.fl_start,
(long long)lock->fl.fl_end,
@@ -513,8 +513,8 @@
__be32 ret;
dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
- file->f_file->f_path.dentry->d_inode->i_sb->s_id,
- file->f_file->f_path.dentry->d_inode->i_ino,
+ file_inode(file->f_file)->i_sb->s_id,
+ file_inode(file->f_file)->i_ino,
lock->fl.fl_type,
(long long)lock->fl.fl_start,
(long long)lock->fl.fl_end);
@@ -606,8 +606,8 @@
int error;
dprintk("lockd: nlmsvc_unlock(%s/%ld, pi=%d, %Ld-%Ld)\n",
- file->f_file->f_path.dentry->d_inode->i_sb->s_id,
- file->f_file->f_path.dentry->d_inode->i_ino,
+ file_inode(file->f_file)->i_sb->s_id,
+ file_inode(file->f_file)->i_ino,
lock->fl.fl_pid,
(long long)lock->fl.fl_start,
(long long)lock->fl.fl_end);
@@ -635,8 +635,8 @@
int status = 0;
dprintk("lockd: nlmsvc_cancel(%s/%ld, pi=%d, %Ld-%Ld)\n",
- file->f_file->f_path.dentry->d_inode->i_sb->s_id,
- file->f_file->f_path.dentry->d_inode->i_ino,
+ file_inode(file->f_file)->i_sb->s_id,
+ file_inode(file->f_file)->i_ino,
lock->fl.fl_pid,
(long long)lock->fl.fl_start,
(long long)lock->fl.fl_end);
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 0deb5f6..97e8741 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -13,7 +13,7 @@
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/nfsd/nfsfh.h>
#include <linux/nfsd/export.h>
#include <linux/lockd/lockd.h>
@@ -45,7 +45,7 @@
static inline void nlm_debug_print_file(char *msg, struct nlm_file *file)
{
- struct inode *inode = file->f_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file->f_file);
dprintk("lockd: %s %s/%ld\n",
msg, inode->i_sb->s_id, inode->i_ino);
@@ -84,7 +84,6 @@
nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result,
struct nfs_fh *f)
{
- struct hlist_node *pos;
struct nlm_file *file;
unsigned int hash;
__be32 nfserr;
@@ -96,7 +95,7 @@
/* Lock file table */
mutex_lock(&nlm_file_mutex);
- hlist_for_each_entry(file, pos, &nlm_files[hash], f_list)
+ hlist_for_each_entry(file, &nlm_files[hash], f_list)
if (!nfs_compare_fh(&file->f_handle, f))
goto found;
@@ -248,13 +247,13 @@
nlm_traverse_files(void *data, nlm_host_match_fn_t match,
int (*is_failover_file)(void *data, struct nlm_file *file))
{
- struct hlist_node *pos, *next;
+ struct hlist_node *next;
struct nlm_file *file;
int i, ret = 0;
mutex_lock(&nlm_file_mutex);
for (i = 0; i < FILE_NRHASH; i++) {
- hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) {
+ hlist_for_each_entry_safe(file, next, &nlm_files[i], f_list) {
if (is_failover_file && !is_failover_file(data, file))
continue;
file->f_count++;
diff --git a/fs/locks.c b/fs/locks.c
index a94e331..cb424a4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -334,7 +334,7 @@
start = filp->f_pos;
break;
case SEEK_END:
- start = i_size_read(filp->f_path.dentry->d_inode);
+ start = i_size_read(file_inode(filp));
break;
default:
return -EINVAL;
@@ -384,7 +384,7 @@
start = filp->f_pos;
break;
case SEEK_END:
- start = i_size_read(filp->f_path.dentry->d_inode);
+ start = i_size_read(file_inode(filp));
break;
default:
return -EINVAL;
@@ -627,7 +627,7 @@
struct file_lock *cfl;
lock_flocks();
- for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) {
+ for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) {
if (!IS_POSIX(cfl))
continue;
if (posix_locks_conflict(fl, cfl))
@@ -708,7 +708,7 @@
{
struct file_lock *new_fl = NULL;
struct file_lock **before;
- struct inode * inode = filp->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(filp);
int error = 0;
int found = 0;
@@ -1002,7 +1002,7 @@
int posix_lock_file(struct file *filp, struct file_lock *fl,
struct file_lock *conflock)
{
- return __posix_lock_file(filp->f_path.dentry->d_inode, fl, conflock);
+ return __posix_lock_file(file_inode(filp), fl, conflock);
}
EXPORT_SYMBOL(posix_lock_file);
@@ -1326,8 +1326,8 @@
int type = F_UNLCK;
lock_flocks();
- time_out_leases(filp->f_path.dentry->d_inode);
- for (fl = filp->f_path.dentry->d_inode->i_flock; fl && IS_LEASE(fl);
+ time_out_leases(file_inode(filp));
+ for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
fl = fl->fl_next) {
if (fl->fl_file == filp) {
type = target_leasetype(fl);
@@ -1843,7 +1843,7 @@
if (copy_from_user(&flock, l, sizeof(flock)))
goto out;
- inode = filp->f_path.dentry->d_inode;
+ inode = file_inode(filp);
/* Don't allow mandatory locks on files that may be memory mapped
* and shared.
@@ -1961,7 +1961,7 @@
if (copy_from_user(&flock, l, sizeof(flock)))
goto out;
- inode = filp->f_path.dentry->d_inode;
+ inode = file_inode(filp);
/* Don't allow mandatory locks on files that may be memory mapped
* and shared.
@@ -2030,7 +2030,7 @@
* posix_lock_file(). Another process could be setting a lock on this
* file at the same time, but we wouldn't remove that lock anyway.
*/
- if (!filp->f_path.dentry->d_inode->i_flock)
+ if (!file_inode(filp)->i_flock)
return;
lock.fl_type = F_UNLCK;
@@ -2056,7 +2056,7 @@
*/
void locks_remove_flock(struct file *filp)
{
- struct inode * inode = filp->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(filp);
struct file_lock *fl;
struct file_lock **before;
@@ -2152,7 +2152,7 @@
fl_pid = fl->fl_pid;
if (fl->fl_file != NULL)
- inode = fl->fl_file->f_path.dentry->d_inode;
+ inode = file_inode(fl->fl_file);
seq_printf(f, "%lld:%s ", id, pfx);
if (IS_POSIX(fl)) {
diff --git a/fs/logfs/Kconfig b/fs/logfs/Kconfig
index daf9a9b..09ed066 100644
--- a/fs/logfs/Kconfig
+++ b/fs/logfs/Kconfig
@@ -1,6 +1,6 @@
config LOGFS
- tristate "LogFS file system (EXPERIMENTAL)"
- depends on (MTD || BLOCK) && EXPERIMENTAL
+ tristate "LogFS file system"
+ depends on (MTD || BLOCK)
select ZLIB_INFLATE
select ZLIB_DEFLATE
select CRC32
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 26e4a94..b827510 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -284,7 +284,7 @@
#define IMPLICIT_NODES 2
static int __logfs_readdir(struct file *file, void *buf, filldir_t filldir)
{
- struct inode *dir = file->f_dentry->d_inode;
+ struct inode *dir = file_inode(file);
loff_t pos = file->f_pos - IMPLICIT_NODES;
struct page *page;
struct logfs_disk_dentry *dd;
@@ -320,7 +320,7 @@
static int logfs_readdir(struct file *file, void *buf, filldir_t filldir)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
ino_t pino = parent_ino(file->f_dentry);
int err;
diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index 3886cde..c2219a6 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -183,7 +183,7 @@
long logfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct logfs_inode *li = logfs_inode(inode);
unsigned int oldflags, flags;
int err;
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 345c24b..5436029 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -608,6 +608,7 @@
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("logfs");
static int __init logfs_init(void)
{
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index 685b2d9..a9ed6f3 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -85,7 +85,7 @@
static int minix_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
unsigned long pos = filp->f_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
unsigned offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 99541cc..df12249 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -660,6 +660,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("minix");
static int __init init_minix_fs(void)
{
diff --git a/fs/namei.c b/fs/namei.c
index 43a97ee..57ae9c8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -451,7 +451,7 @@
*
* Given a path increment the reference count to the dentry and the vfsmount.
*/
-void path_get(struct path *path)
+void path_get(const struct path *path)
{
mntget(path->mnt);
dget(path->dentry);
@@ -464,7 +464,7 @@
*
* Given a path decrement the reference count to the dentry and the vfsmount.
*/
-void path_put(struct path *path)
+void path_put(const struct path *path)
{
dput(path->dentry);
mntput(path->mnt);
@@ -600,14 +600,10 @@
if (likely(!(nd->flags & LOOKUP_JUMPED)))
return 0;
- if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
+ if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
return 0;
- if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
- return 0;
-
- /* Note: we do not d_invalidate() */
- status = d_revalidate(dentry, nd->flags);
+ status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
if (status > 0)
return 0;
@@ -693,8 +689,6 @@
nd->path = *path;
nd->inode = nd->path.dentry->d_inode;
nd->flags |= LOOKUP_JUMPED;
-
- BUG_ON(nd->inode->i_op->follow_link);
}
static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
@@ -1342,7 +1336,7 @@
* small and for now I'd prefer to have fast path as straight as possible.
* It _is_ time-critical.
*/
-static int lookup_fast(struct nameidata *nd, struct qstr *name,
+static int lookup_fast(struct nameidata *nd,
struct path *path, struct inode **inode)
{
struct vfsmount *mnt = nd->path.mnt;
@@ -1358,7 +1352,7 @@
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
- dentry = __d_lookup_rcu(parent, name, &seq, nd->inode);
+ dentry = __d_lookup_rcu(parent, &nd->last, &seq, nd->inode);
if (!dentry)
goto unlazy;
@@ -1400,7 +1394,7 @@
if (unlazy_walk(nd, dentry))
return -ECHILD;
} else {
- dentry = __d_lookup(parent, name);
+ dentry = __d_lookup(parent, &nd->last);
}
if (unlikely(!dentry))
@@ -1436,8 +1430,7 @@
}
/* Fast lookup failed, do it the slow way */
-static int lookup_slow(struct nameidata *nd, struct qstr *name,
- struct path *path)
+static int lookup_slow(struct nameidata *nd, struct path *path)
{
struct dentry *dentry, *parent;
int err;
@@ -1446,7 +1439,7 @@
BUG_ON(nd->inode != parent->d_inode);
mutex_lock(&parent->d_inode->i_mutex);
- dentry = __lookup_hash(name, parent, nd->flags);
+ dentry = __lookup_hash(&nd->last, parent, nd->flags);
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
@@ -1519,7 +1512,7 @@
}
static inline int walk_component(struct nameidata *nd, struct path *path,
- struct qstr *name, int type, int follow)
+ int follow)
{
struct inode *inode;
int err;
@@ -1528,14 +1521,14 @@
* to be able to know about the current root directory and
* parent relationships.
*/
- if (unlikely(type != LAST_NORM))
- return handle_dots(nd, type);
- err = lookup_fast(nd, name, path, &inode);
+ if (unlikely(nd->last_type != LAST_NORM))
+ return handle_dots(nd, nd->last_type);
+ err = lookup_fast(nd, path, &inode);
if (unlikely(err)) {
if (err < 0)
goto out_err;
- err = lookup_slow(nd, name, path);
+ err = lookup_slow(nd, path);
if (err < 0)
goto out_err;
@@ -1594,8 +1587,7 @@
res = follow_link(&link, nd, &cookie);
if (res)
break;
- res = walk_component(nd, path, &nd->last,
- nd->last_type, LOOKUP_FOLLOW);
+ res = walk_component(nd, path, LOOKUP_FOLLOW);
put_link(nd, &link, cookie);
} while (res > 0);
@@ -1802,8 +1794,11 @@
}
}
+ nd->last = this;
+ nd->last_type = type;
+
if (!name[len])
- goto last_component;
+ return 0;
/*
* If it wasn't NUL, we know it was '/'. Skip that
* slash, and continue until no more slashes.
@@ -1812,10 +1807,11 @@
len++;
} while (unlikely(name[len] == '/'));
if (!name[len])
- goto last_component;
+ return 0;
+
name += len;
- err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
+ err = walk_component(nd, &next, LOOKUP_FOLLOW);
if (err < 0)
return err;
@@ -1824,16 +1820,10 @@
if (err)
return err;
}
- if (can_lookup(nd->inode))
- continue;
- err = -ENOTDIR;
- break;
- /* here ends the main loop */
-
-last_component:
- nd->last = this;
- nd->last_type = type;
- return 0;
+ if (!can_lookup(nd->inode)) {
+ err = -ENOTDIR;
+ break;
+ }
}
terminate_walk(nd);
return err;
@@ -1932,8 +1922,7 @@
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
nd->flags &= ~LOOKUP_PARENT;
- return walk_component(nd, path, &nd->last, nd->last_type,
- nd->flags & LOOKUP_FOLLOW);
+ return walk_component(nd, path, nd->flags & LOOKUP_FOLLOW);
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
@@ -2732,7 +2721,7 @@
if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
symlink_ok = true;
/* we _can_ be in RCU mode here */
- error = lookup_fast(nd, &nd->last, path, &inode);
+ error = lookup_fast(nd, path, &inode);
if (likely(!error))
goto finish_lookup;
@@ -2778,7 +2767,7 @@
goto out;
if ((*opened & FILE_CREATED) ||
- !S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ !S_ISREG(file_inode(file)->i_mode))
will_truncate = false;
audit_inode(name, file->f_path.dentry, 0);
@@ -2941,8 +2930,8 @@
int error;
file = get_empty_filp();
- if (!file)
- return ERR_PTR(-ENFILE);
+ if (IS_ERR(file))
+ return file;
file->f_flags = op->open_flag;
diff --git a/fs/namespace.c b/fs/namespace.c
index 55605c5..d581e45 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -384,7 +384,7 @@
*/
int __mnt_want_write_file(struct file *file)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
return __mnt_want_write(file->f_path.mnt);
@@ -798,6 +798,10 @@
}
mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+ /* Don't allow unprivileged users to change mount flags */
+ if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
+ mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
atomic_inc(&sb->s_active);
mnt->mnt.mnt_sb = sb;
mnt->mnt.mnt_root = dget(root);
@@ -1237,6 +1241,14 @@
return retval;
}
+/*
+ * Is the caller allowed to modify his namespace?
+ */
+static inline bool may_mount(void)
+{
+ return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
+}
+
/*
* Now umount can handle mount points as well as block devices.
* This is important for filesystems which use unnamed block devices.
@@ -1255,6 +1267,9 @@
if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
return -EINVAL;
+ if (!may_mount())
+ return -EPERM;
+
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
@@ -1268,10 +1283,6 @@
if (!check_mnt(mnt))
goto dput_and_out;
- retval = -EPERM;
- if (!ns_capable(mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
- goto dput_and_out;
-
retval = do_umount(mnt, flags);
dput_and_out:
/* we mustn't call path_put() as that would clear mnt_expiry_mark */
@@ -1293,24 +1304,6 @@
#endif
-static int mount_is_safe(struct path *path)
-{
- if (ns_capable(real_mount(path->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN))
- return 0;
- return -EPERM;
-#ifdef notyet
- if (S_ISLNK(path->dentry->d_inode->i_mode))
- return -EPERM;
- if (path->dentry->d_inode->i_mode & S_ISVTX) {
- if (current_uid() != path->dentry->d_inode->i_uid)
- return -EPERM;
- }
- if (inode_permission(path->dentry->d_inode, MAY_WRITE))
- return -EPERM;
- return 0;
-#endif
-}
-
static bool mnt_ns_loop(struct path *path)
{
/* Could bind mounting the mount namespace inode cause a
@@ -1633,9 +1626,6 @@
int type;
int err = 0;
- if (!ns_capable(mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
- return -EPERM;
-
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
@@ -1669,9 +1659,7 @@
LIST_HEAD(umount_list);
struct path old_path;
struct mount *mnt = NULL, *old;
- int err = mount_is_safe(path);
- if (err)
- return err;
+ int err;
if (!old_name || !*old_name)
return -EINVAL;
err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
@@ -1729,6 +1717,9 @@
if (readonly_request == __mnt_is_readonly(mnt))
return 0;
+ if (mnt->mnt_flags & MNT_LOCK_READONLY)
+ return -EPERM;
+
if (readonly_request)
error = mnt_make_readonly(real_mount(mnt));
else
@@ -1748,9 +1739,6 @@
struct super_block *sb = path->mnt->mnt_sb;
struct mount *mnt = real_mount(path->mnt);
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
if (!check_mnt(mnt))
return -EINVAL;
@@ -1764,6 +1752,8 @@
down_write(&sb->s_umount);
if (flags & MS_BIND)
err = change_mount_flags(path->mnt, flags);
+ else if (!capable(CAP_SYS_ADMIN))
+ err = -EPERM;
else
err = do_remount_sb(sb, flags, data, 0);
if (!err) {
@@ -1796,9 +1786,7 @@
struct path old_path, parent_path;
struct mount *p;
struct mount *old;
- int err = 0;
- if (!ns_capable(real_mount(path->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN))
- return -EPERM;
+ int err;
if (!old_name || !*old_name)
return -EINVAL;
err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
@@ -1933,18 +1921,13 @@
int mnt_flags, const char *name, void *data)
{
struct file_system_type *type;
- struct user_namespace *user_ns;
+ struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
struct vfsmount *mnt;
int err;
if (!fstype)
return -EINVAL;
- /* we need capabilities... */
- user_ns = real_mount(path->mnt)->mnt_ns->user_ns;
- if (!ns_capable(user_ns, CAP_SYS_ADMIN))
- return -EPERM;
-
type = get_fs_type(fstype);
if (!type)
return -ENODEV;
@@ -2258,6 +2241,9 @@
if (retval)
goto dput_out;
+ if (!may_mount())
+ return -EPERM;
+
/* Default to relatime unless overriden */
if (!(flags & MS_NOATIME))
mnt_flags |= MNT_RELATIME;
@@ -2360,7 +2346,7 @@
/* First pass: copy the tree topology */
copy_flags = CL_COPY_ALL | CL_EXPIRE;
if (user_ns != mnt_ns->user_ns)
- copy_flags |= CL_SHARED_TO_SLAVE;
+ copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED;
new = copy_tree(old, old->mnt.mnt_root, copy_flags);
if (IS_ERR(new)) {
up_write(&namespace_sem);
@@ -2567,7 +2553,7 @@
struct mount *new_mnt, *root_mnt;
int error;
- if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
+ if (!may_mount())
return -EPERM;
error = user_path_dir(new_root, &new);
@@ -2753,6 +2739,51 @@
return check_mnt(real_mount(mnt));
}
+bool current_chrooted(void)
+{
+ /* Does the current process have a non-standard root */
+ struct path ns_root;
+ struct path fs_root;
+ bool chrooted;
+
+ /* Find the namespace root */
+ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt;
+ ns_root.dentry = ns_root.mnt->mnt_root;
+ path_get(&ns_root);
+ while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root))
+ ;
+
+ get_fs_root(current->fs, &fs_root);
+
+ chrooted = !path_equal(&fs_root, &ns_root);
+
+ path_put(&fs_root);
+ path_put(&ns_root);
+
+ return chrooted;
+}
+
+void update_mnt_policy(struct user_namespace *userns)
+{
+ struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+ struct mount *mnt;
+
+ down_read(&namespace_sem);
+ list_for_each_entry(mnt, &ns->list, mnt_list) {
+ switch (mnt->mnt.mnt_sb->s_magic) {
+ case SYSFS_MAGIC:
+ userns->may_mount_sysfs = true;
+ break;
+ case PROC_SUPER_MAGIC:
+ userns->may_mount_proc = true;
+ break;
+ }
+ if (userns->may_mount_sysfs && userns->may_mount_proc)
+ break;
+ }
+ up_read(&namespace_sem);
+}
+
static void *mntns_get(struct task_struct *task)
{
struct mnt_namespace *ns = NULL;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 4117e7b..8163260 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -593,14 +593,10 @@
return 1; /* I'm not sure */
qname.name = __name;
- qname.hash = full_name_hash(qname.name, qname.len);
- if (dentry->d_op && dentry->d_op->d_hash)
- if (dentry->d_op->d_hash(dentry, dentry->d_inode, &qname) != 0)
- goto end_advance;
-
- newdent = d_lookup(dentry, &qname);
-
+ newdent = d_hash_and_lookup(dentry, &qname);
+ if (unlikely(IS_ERR(newdent)))
+ goto end_advance;
if (!newdent) {
newdent = d_alloc(dentry, &qname);
if (!newdent)
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 1acdad7..26910c8 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -331,12 +331,15 @@
struct ncp_server *server = NCP_SBP(root->d_sb);
unsigned int tmp;
- if (server->m.uid != 0)
- seq_printf(seq, ",uid=%u", server->m.uid);
- if (server->m.gid != 0)
- seq_printf(seq, ",gid=%u", server->m.gid);
- if (server->m.mounted_uid != 0)
- seq_printf(seq, ",owner=%u", server->m.mounted_uid);
+ if (!uid_eq(server->m.uid, GLOBAL_ROOT_UID))
+ seq_printf(seq, ",uid=%u",
+ from_kuid_munged(&init_user_ns, server->m.uid));
+ if (!gid_eq(server->m.gid, GLOBAL_ROOT_GID))
+ seq_printf(seq, ",gid=%u",
+ from_kgid_munged(&init_user_ns, server->m.gid));
+ if (!uid_eq(server->m.mounted_uid, GLOBAL_ROOT_UID))
+ seq_printf(seq, ",owner=%u",
+ from_kuid_munged(&init_user_ns, server->m.mounted_uid));
tmp = server->m.file_mode & S_IALLUGO;
if (tmp != NCP_DEFAULT_FILE_MODE)
seq_printf(seq, ",mode=0%o", tmp);
@@ -381,13 +384,13 @@
data->flags = 0;
data->int_flags = 0;
- data->mounted_uid = 0;
+ data->mounted_uid = GLOBAL_ROOT_UID;
data->wdog_pid = NULL;
data->ncp_fd = ~0;
data->time_out = NCP_DEFAULT_TIME_OUT;
data->retry_count = NCP_DEFAULT_RETRY_COUNT;
- data->uid = 0;
- data->gid = 0;
+ data->uid = GLOBAL_ROOT_UID;
+ data->gid = GLOBAL_ROOT_GID;
data->file_mode = NCP_DEFAULT_FILE_MODE;
data->dir_mode = NCP_DEFAULT_DIR_MODE;
data->info_fd = -1;
@@ -399,13 +402,19 @@
goto err;
switch (optval) {
case 'u':
- data->uid = optint;
+ data->uid = make_kuid(current_user_ns(), optint);
+ if (!uid_valid(data->uid))
+ goto err;
break;
case 'g':
- data->gid = optint;
+ data->gid = make_kgid(current_user_ns(), optint);
+ if (!gid_valid(data->gid))
+ goto err;
break;
case 'o':
- data->mounted_uid = optint;
+ data->mounted_uid = make_kuid(current_user_ns(), optint);
+ if (!uid_valid(data->mounted_uid))
+ goto err;
break;
case 'm':
data->file_mode = optint;
@@ -480,13 +489,13 @@
data.flags = md->flags;
data.int_flags = NCP_IMOUNT_LOGGEDIN_POSSIBLE;
- data.mounted_uid = md->mounted_uid;
+ data.mounted_uid = make_kuid(current_user_ns(), md->mounted_uid);
data.wdog_pid = find_get_pid(md->wdog_pid);
data.ncp_fd = md->ncp_fd;
data.time_out = md->time_out;
data.retry_count = md->retry_count;
- data.uid = md->uid;
- data.gid = md->gid;
+ data.uid = make_kuid(current_user_ns(), md->uid);
+ data.gid = make_kgid(current_user_ns(), md->gid);
data.file_mode = md->file_mode;
data.dir_mode = md->dir_mode;
data.info_fd = -1;
@@ -499,13 +508,13 @@
struct ncp_mount_data_v4* md = (struct ncp_mount_data_v4*)raw_data;
data.flags = md->flags;
- data.mounted_uid = md->mounted_uid;
+ data.mounted_uid = make_kuid(current_user_ns(), md->mounted_uid);
data.wdog_pid = find_get_pid(md->wdog_pid);
data.ncp_fd = md->ncp_fd;
data.time_out = md->time_out;
data.retry_count = md->retry_count;
- data.uid = md->uid;
- data.gid = md->gid;
+ data.uid = make_kuid(current_user_ns(), md->uid);
+ data.gid = make_kgid(current_user_ns(), md->gid);
data.file_mode = md->file_mode;
data.dir_mode = md->dir_mode;
data.info_fd = -1;
@@ -520,12 +529,16 @@
goto out;
break;
}
+ error = -EINVAL;
+ if (!uid_valid(data.mounted_uid) || !uid_valid(data.uid) ||
+ !gid_valid(data.gid))
+ goto out;
error = -EBADF;
ncp_filp = fget(data.ncp_fd);
if (!ncp_filp)
goto out;
error = -ENOTSOCK;
- sock_inode = ncp_filp->f_path.dentry->d_inode;
+ sock_inode = file_inode(ncp_filp);
if (!S_ISSOCK(sock_inode->i_mode))
goto out_fput;
sock = SOCKET_I(sock_inode);
@@ -564,7 +577,7 @@
if (!server->info_filp)
goto out_bdi;
error = -ENOTSOCK;
- sock_inode = server->info_filp->f_path.dentry->d_inode;
+ sock_inode = file_inode(server->info_filp);
if (!S_ISSOCK(sock_inode->i_mode))
goto out_fput2;
info_sock = SOCKET_I(sock_inode);
@@ -886,12 +899,10 @@
goto out;
result = -EPERM;
- if (((attr->ia_valid & ATTR_UID) &&
- (attr->ia_uid != server->m.uid)))
+ if ((attr->ia_valid & ATTR_UID) && !uid_eq(attr->ia_uid, server->m.uid))
goto out;
- if (((attr->ia_valid & ATTR_GID) &&
- (attr->ia_gid != server->m.gid)))
+ if ((attr->ia_valid & ATTR_GID) && !gid_eq(attr->ia_gid, server->m.gid))
goto out;
if (((attr->ia_valid & ATTR_MODE) &&
@@ -1040,6 +1051,7 @@
.kill_sb = kill_anon_super,
.fs_flags = FS_BINARY_MOUNTDATA,
};
+MODULE_ALIAS_FS("ncpfs");
static int __init init_ncp_fs(void)
{
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 6958adf..60426cc 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -45,7 +45,7 @@
return -EINVAL;
}
/* TODO: info.addr = server->m.serv_addr; */
- SET_UID(info.mounted_uid, server->m.mounted_uid);
+ SET_UID(info.mounted_uid, from_kuid_munged(current_user_ns(), server->m.mounted_uid));
info.connection = server->connection;
info.buffer_size = server->buffer_size;
info.volume_number = NCP_FINFO(inode)->volNumber;
@@ -69,7 +69,7 @@
DPRINTK("info.version invalid: %d\n", info2.version);
return -EINVAL;
}
- info2.mounted_uid = server->m.mounted_uid;
+ info2.mounted_uid = from_kuid_munged(current_user_ns(), server->m.mounted_uid);
info2.connection = server->connection;
info2.buffer_size = server->buffer_size;
info2.volume_number = NCP_FINFO(inode)->volNumber;
@@ -135,7 +135,7 @@
DPRINTK("info.version invalid: %d\n", info2.version);
return -EINVAL;
}
- info2.mounted_uid = server->m.mounted_uid;
+ info2.mounted_uid = from_kuid_munged(current_user_ns(), server->m.mounted_uid);
info2.connection = server->connection;
info2.buffer_size = server->buffer_size;
info2.volume_number = NCP_FINFO(inode)->volNumber;
@@ -348,22 +348,25 @@
{
u16 uid;
- SET_UID(uid, server->m.mounted_uid);
+ SET_UID(uid, from_kuid_munged(current_user_ns(), server->m.mounted_uid));
if (put_user(uid, (u16 __user *)argp))
return -EFAULT;
return 0;
}
case NCP_IOC_GETMOUNTUID32:
- if (put_user(server->m.mounted_uid,
- (u32 __user *)argp))
+ {
+ uid_t uid = from_kuid_munged(current_user_ns(), server->m.mounted_uid);
+ if (put_user(uid, (u32 __user *)argp))
return -EFAULT;
return 0;
+ }
case NCP_IOC_GETMOUNTUID64:
- if (put_user(server->m.mounted_uid,
- (u64 __user *)argp))
+ {
+ uid_t uid = from_kuid_munged(current_user_ns(), server->m.mounted_uid);
+ if (put_user(uid, (u64 __user *)argp))
return -EFAULT;
return 0;
-
+ }
case NCP_IOC_GETROOT:
{
struct ncp_setroot_ioctl sr;
@@ -808,9 +811,9 @@
long ncp_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ncp_server *server = NCP_SERVER(inode);
- uid_t uid = current_uid();
+ kuid_t uid = current_uid();
int need_drop_write = 0;
long ret;
@@ -819,12 +822,12 @@
case NCP_IOC_CONN_LOGGED_IN:
case NCP_IOC_SETROOT:
if (!capable(CAP_SYS_ADMIN)) {
- ret = -EACCES;
+ ret = -EPERM;
goto out;
}
break;
}
- if (server->m.mounted_uid != uid) {
+ if (!uid_eq(server->m.mounted_uid, uid)) {
switch (cmd) {
/*
* Only mount owner can issue these ioctls. Information
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 63d14a9..ee24df5 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -105,7 +105,7 @@
/* This is used for a general mmap of a ncp file */
int ncp_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
DPRINTK("ncp_mmap: called\n");
diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h
index 54cc0cd..c51b2c5 100644
--- a/fs/ncpfs/ncp_fs_sb.h
+++ b/fs/ncpfs/ncp_fs_sb.h
@@ -23,15 +23,15 @@
unsigned long flags; /* NCP_MOUNT_* flags */
unsigned int int_flags; /* internal flags */
#define NCP_IMOUNT_LOGGEDIN_POSSIBLE 0x0001
- uid_t mounted_uid; /* Who may umount() this filesystem? */
+ kuid_t mounted_uid; /* Who may umount() this filesystem? */
struct pid *wdog_pid; /* Who cares for our watchdog packets? */
unsigned int ncp_fd; /* The socket to the ncp port */
unsigned int time_out; /* How long should I wait after
sending a NCP request? */
unsigned int retry_count; /* And how often should I retry? */
unsigned char mounted_vol[NCP_VOLNAME_LEN + 1];
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
umode_t file_mode;
umode_t dir_mode;
int info_fd;
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 4fa788c..434b93e 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -1273,6 +1273,7 @@
static struct pnfs_layoutdriver_type blocklayout_type = {
.id = LAYOUT_BLOCK_VOLUME,
.name = "LAYOUT_BLOCK_VOLUME",
+ .owner = THIS_MODULE,
.read_pagelist = bl_read_pagelist,
.write_pagelist = bl_write_pagelist,
.alloc_layout_hdr = bl_alloc_layout_hdr,
diff --git a/fs/nfs/blocklayout/blocklayoutdm.c b/fs/nfs/blocklayout/blocklayoutdm.c
index 737d839..6fc7b5c 100644
--- a/fs/nfs/blocklayout/blocklayoutdm.c
+++ b/fs/nfs/blocklayout/blocklayoutdm.c
@@ -55,7 +55,8 @@
bl_pipe_msg.bl_wq = &nn->bl_wq;
memset(msg, 0, sizeof(*msg));
- msg->data = kzalloc(1 + sizeof(bl_umount_request), GFP_NOFS);
+ msg->len = sizeof(bl_msg) + bl_msg.totallen;
+ msg->data = kzalloc(msg->len, GFP_NOFS);
if (!msg->data)
goto out;
@@ -66,7 +67,6 @@
memcpy(msg->data, &bl_msg, sizeof(bl_msg));
dataptr = (uint8_t *) msg->data;
memcpy(&dataptr[sizeof(bl_msg)], &bl_umount_request, sizeof(bl_umount_request));
- msg->len = sizeof(bl_msg) + bl_msg.totallen;
add_wait_queue(&nn->bl_wq, &wq);
if (rpc_queue_upcall(nn->bl_device_pipe, msg) < 0) {
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index 862a2f1..5f7b053 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -128,10 +128,13 @@
struct super_block *pipefs_sb;
int ret = 0;
+ sunrpc_init_cache_detail(cd);
pipefs_sb = rpc_get_sb_net(net);
if (pipefs_sb) {
ret = nfs_cache_register_sb(pipefs_sb, cd);
rpc_put_sb_net(net);
+ if (ret)
+ sunrpc_destroy_cache_detail(cd);
}
return ret;
}
@@ -151,14 +154,5 @@
nfs_cache_unregister_sb(pipefs_sb, cd);
rpc_put_sb_net(net);
}
-}
-
-void nfs_cache_init(struct cache_detail *cd)
-{
- sunrpc_init_cache_detail(cd);
-}
-
-void nfs_cache_destroy(struct cache_detail *cd)
-{
sunrpc_destroy_cache_detail(cd);
}
diff --git a/fs/nfs/cache_lib.h b/fs/nfs/cache_lib.h
index 317db95..4116d2c 100644
--- a/fs/nfs/cache_lib.h
+++ b/fs/nfs/cache_lib.h
@@ -23,8 +23,6 @@
extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq);
extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq);
-extern void nfs_cache_init(struct cache_detail *cd);
-extern void nfs_cache_destroy(struct cache_detail *cd);
extern int nfs_cache_register_net(struct net *net, struct cache_detail *cd);
extern void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd);
extern int nfs_cache_register_sb(struct super_block *sb,
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 264d1aa..2960512 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -183,60 +183,15 @@
static u32 initiate_bulk_draining(struct nfs_client *clp,
struct cb_layoutrecallargs *args)
{
- struct nfs_server *server;
- struct pnfs_layout_hdr *lo;
- struct inode *ino;
- u32 rv = NFS4ERR_NOMATCHING_LAYOUT;
- struct pnfs_layout_hdr *tmp;
- LIST_HEAD(recall_list);
- LIST_HEAD(free_me_list);
- struct pnfs_layout_range range = {
- .iomode = IOMODE_ANY,
- .offset = 0,
- .length = NFS4_MAX_UINT64,
- };
+ int stat;
- spin_lock(&clp->cl_lock);
- rcu_read_lock();
- list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
- if ((args->cbl_recall_type == RETURN_FSID) &&
- memcmp(&server->fsid, &args->cbl_fsid,
- sizeof(struct nfs_fsid)))
- continue;
-
- list_for_each_entry(lo, &server->layouts, plh_layouts) {
- ino = igrab(lo->plh_inode);
- if (!ino)
- continue;
- spin_lock(&ino->i_lock);
- /* Is this layout in the process of being freed? */
- if (NFS_I(ino)->layout != lo) {
- spin_unlock(&ino->i_lock);
- iput(ino);
- continue;
- }
- pnfs_get_layout_hdr(lo);
- spin_unlock(&ino->i_lock);
- list_add(&lo->plh_bulk_recall, &recall_list);
- }
- }
- rcu_read_unlock();
- spin_unlock(&clp->cl_lock);
-
- list_for_each_entry_safe(lo, tmp,
- &recall_list, plh_bulk_recall) {
- ino = lo->plh_inode;
- spin_lock(&ino->i_lock);
- set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
- if (pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, &range))
- rv = NFS4ERR_DELAY;
- list_del_init(&lo->plh_bulk_recall);
- spin_unlock(&ino->i_lock);
- pnfs_free_lseg_list(&free_me_list);
- pnfs_put_layout_hdr(lo);
- iput(ino);
- }
- return rv;
+ if (args->cbl_recall_type == RETURN_FSID)
+ stat = pnfs_destroy_layouts_byfsid(clp, &args->cbl_fsid, true);
+ else
+ stat = pnfs_destroy_layouts_byclid(clp, true);
+ if (stat != 0)
+ return NFS4ERR_DELAY;
+ return NFS4ERR_NOMATCHING_LAYOUT;
}
static u32 do_callback_layoutrecall(struct nfs_client *clp,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9f3c664..84d8eae 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -197,7 +197,6 @@
EXPORT_SYMBOL_GPL(nfs_alloc_client);
#if IS_ENABLED(CONFIG_NFS_V4)
-/* idr_remove_all is not needed as all id's are removed by nfs_put_client */
void nfs_cleanup_cb_ident_idr(struct net *net)
{
struct nfs_net *nn = net_generic(net, nfs_net_id);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 81c5eec..6390a4b 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -55,7 +55,8 @@
flags &= FMODE_READ|FMODE_WRITE;
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
- if (delegation != NULL && (delegation->type & flags) == flags) {
+ if (delegation != NULL && (delegation->type & flags) == flags &&
+ !test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
nfs_mark_delegation_referenced(delegation);
ret = 1;
}
@@ -70,8 +71,10 @@
int status = 0;
if (inode->i_flock == NULL)
- goto out;
+ return 0;
+ if (inode->i_flock == NULL)
+ goto out;
/* Protect inode->i_flock using the file locks lock */
lock_flocks();
for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
@@ -94,7 +97,9 @@
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_context *ctx;
+ struct nfs4_state_owner *sp;
struct nfs4_state *state;
+ unsigned int seq;
int err;
again:
@@ -109,9 +114,16 @@
continue;
get_nfs_open_context(ctx);
spin_unlock(&inode->i_lock);
+ sp = state->owner;
+ /* Block nfs4_proc_unlck */
+ mutex_lock(&sp->so_delegreturn_mutex);
+ seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
err = nfs4_open_delegation_recall(ctx, state, stateid);
- if (err >= 0)
+ if (!err)
err = nfs_delegation_claim_locks(ctx, state);
+ if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+ err = -EAGAIN;
+ mutex_unlock(&sp->so_delegreturn_mutex);
put_nfs_open_context(ctx);
if (err != 0)
return err;
@@ -182,39 +194,91 @@
}
static struct nfs_delegation *
-nfs_detach_delegation_locked(struct nfs_inode *nfsi,
- struct nfs_server *server)
+nfs_start_delegation_return_locked(struct nfs_inode *nfsi)
{
- struct nfs_delegation *delegation =
- rcu_dereference_protected(nfsi->delegation,
- lockdep_is_held(&server->nfs_client->cl_lock));
+ struct nfs_delegation *ret = NULL;
+ struct nfs_delegation *delegation = rcu_dereference(nfsi->delegation);
if (delegation == NULL)
- goto nomatch;
+ goto out;
+ spin_lock(&delegation->lock);
+ if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+ ret = delegation;
+ spin_unlock(&delegation->lock);
+out:
+ return ret;
+}
+
+static struct nfs_delegation *
+nfs_start_delegation_return(struct nfs_inode *nfsi)
+{
+ struct nfs_delegation *delegation;
+
+ rcu_read_lock();
+ delegation = nfs_start_delegation_return_locked(nfsi);
+ rcu_read_unlock();
+ return delegation;
+}
+
+static void
+nfs_abort_delegation_return(struct nfs_delegation *delegation,
+ struct nfs_client *clp)
+{
spin_lock(&delegation->lock);
+ clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
+ set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
+ spin_unlock(&delegation->lock);
+ set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
+}
+
+static struct nfs_delegation *
+nfs_detach_delegation_locked(struct nfs_inode *nfsi,
+ struct nfs_delegation *delegation,
+ struct nfs_client *clp)
+{
+ struct nfs_delegation *deleg_cur =
+ rcu_dereference_protected(nfsi->delegation,
+ lockdep_is_held(&clp->cl_lock));
+
+ if (deleg_cur == NULL || delegation != deleg_cur)
+ return NULL;
+
+ spin_lock(&delegation->lock);
+ set_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
list_del_rcu(&delegation->super_list);
delegation->inode = NULL;
nfsi->delegation_state = 0;
rcu_assign_pointer(nfsi->delegation, NULL);
spin_unlock(&delegation->lock);
return delegation;
-nomatch:
- return NULL;
}
static struct nfs_delegation *nfs_detach_delegation(struct nfs_inode *nfsi,
- struct nfs_server *server)
+ struct nfs_delegation *delegation,
+ struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
- struct nfs_delegation *delegation;
spin_lock(&clp->cl_lock);
- delegation = nfs_detach_delegation_locked(nfsi, server);
+ delegation = nfs_detach_delegation_locked(nfsi, delegation, clp);
spin_unlock(&clp->cl_lock);
return delegation;
}
+static struct nfs_delegation *
+nfs_inode_detach_delegation(struct inode *inode)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct nfs_delegation *delegation;
+
+ delegation = nfs_start_delegation_return(nfsi);
+ if (delegation == NULL)
+ return NULL;
+ return nfs_detach_delegation(nfsi, delegation, server);
+}
+
/**
* nfs_inode_set_delegation - set up a delegation on an inode
* @inode: inode to which delegation applies
@@ -268,7 +332,10 @@
delegation = NULL;
goto out;
}
- freeme = nfs_detach_delegation_locked(nfsi, server);
+ freeme = nfs_detach_delegation_locked(nfsi,
+ old_delegation, clp);
+ if (freeme == NULL)
+ goto out;
}
list_add_rcu(&delegation->super_list, &server->delegations);
nfsi->delegation_state = delegation->type;
@@ -292,19 +359,29 @@
/*
* Basic procedure for returning a delegation to the server
*/
-static int __nfs_inode_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
+static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync)
{
+ struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
struct nfs_inode *nfsi = NFS_I(inode);
int err;
- /*
- * Guard against new delegated open/lock/unlock calls and against
- * state recovery
- */
- down_write(&nfsi->rwsem);
- err = nfs_delegation_claim_opens(inode, &delegation->stateid);
- up_write(&nfsi->rwsem);
- if (err)
+ if (delegation == NULL)
+ return 0;
+ do {
+ err = nfs_delegation_claim_opens(inode, &delegation->stateid);
+ if (!issync || err != -EAGAIN)
+ break;
+ /*
+ * Guard against state recovery
+ */
+ err = nfs4_wait_clnt_recover(clp);
+ } while (err == 0);
+
+ if (err) {
+ nfs_abort_delegation_return(delegation, clp);
+ goto out;
+ }
+ if (!nfs_detach_delegation(nfsi, delegation, NFS_SERVER(inode)))
goto out;
err = nfs_do_return_delegation(inode, delegation, issync);
@@ -340,13 +417,10 @@
inode = nfs_delegation_grab_inode(delegation);
if (inode == NULL)
continue;
- delegation = nfs_detach_delegation(NFS_I(inode),
- server);
+ delegation = nfs_start_delegation_return_locked(NFS_I(inode));
rcu_read_unlock();
- if (delegation != NULL)
- err = __nfs_inode_return_delegation(inode,
- delegation, 0);
+ err = nfs_end_delegation_return(inode, delegation, 0);
iput(inode);
if (!err)
goto restart;
@@ -367,15 +441,11 @@
*/
void nfs_inode_return_delegation_noreclaim(struct inode *inode)
{
- struct nfs_server *server = NFS_SERVER(inode);
- struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_delegation *delegation;
- if (rcu_access_pointer(nfsi->delegation) != NULL) {
- delegation = nfs_detach_delegation(nfsi, server);
- if (delegation != NULL)
- nfs_do_return_delegation(inode, delegation, 0);
- }
+ delegation = nfs_inode_detach_delegation(inode);
+ if (delegation != NULL)
+ nfs_do_return_delegation(inode, delegation, 0);
}
/**
@@ -390,18 +460,14 @@
*/
int nfs4_inode_return_delegation(struct inode *inode)
{
- struct nfs_server *server = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_delegation *delegation;
int err = 0;
nfs_wb_all(inode);
- if (rcu_access_pointer(nfsi->delegation) != NULL) {
- delegation = nfs_detach_delegation(nfsi, server);
- if (delegation != NULL) {
- err = __nfs_inode_return_delegation(inode, delegation, 1);
- }
- }
+ delegation = nfs_start_delegation_return(nfsi);
+ if (delegation != NULL)
+ err = nfs_end_delegation_return(inode, delegation, 1);
return err;
}
@@ -471,7 +537,7 @@
{
struct nfs_delegation *delegation;
- delegation = nfs_detach_delegation(NFS_I(inode), NFS_SERVER(inode));
+ delegation = nfs_inode_detach_delegation(inode);
if (delegation) {
nfs_inode_find_state_and_recover(inode, &delegation->stateid);
nfs_free_delegation(delegation);
@@ -649,7 +715,7 @@
if (inode == NULL)
continue;
delegation = nfs_detach_delegation(NFS_I(inode),
- server);
+ delegation, server);
rcu_read_unlock();
if (delegation != NULL)
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index bbc6a4d..d54d4fc 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -29,6 +29,7 @@
NFS_DELEGATION_NEED_RECLAIM = 0,
NFS_DELEGATION_RETURN,
NFS_DELEGATION_REFERENCED,
+ NFS_DELEGATION_RETURNING,
};
int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 1b2d7eb..f23f455 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -281,7 +281,7 @@
for (i = 0; i < array->size; i++) {
if (array->array[i].cookie == *desc->dir_cookie) {
- struct nfs_inode *nfsi = NFS_I(desc->file->f_path.dentry->d_inode);
+ struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
struct nfs_open_dir_context *ctx = desc->file->private_data;
new_pos = desc->current_index + i;
@@ -629,7 +629,7 @@
static
int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
{
- struct inode *inode = desc->file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(desc->file);
int ret;
ret = nfs_readdir_xdr_to_array(desc, page, inode);
@@ -660,7 +660,7 @@
static
struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
{
- return read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping,
+ return read_cache_page(file_inode(desc->file)->i_mapping,
desc->page_index, (filler_t *)nfs_readdir_filler, desc);
}
@@ -764,7 +764,7 @@
{
struct page *page = NULL;
int status;
- struct inode *inode = desc->file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(desc->file);
struct nfs_open_dir_context *ctx = desc->file->private_data;
dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
@@ -1136,6 +1136,45 @@
}
/*
+ * A weaker form of d_revalidate for revalidating just the dentry->d_inode
+ * when we don't really care about the dentry name. This is called when a
+ * pathwalk ends on a dentry that was not found via a normal lookup in the
+ * parent dir (e.g.: ".", "..", procfs symlinks or mountpoint traversals).
+ *
+ * In this situation, we just want to verify that the inode itself is OK
+ * since the dentry might have changed on the server.
+ */
+static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ int error;
+ struct inode *inode = dentry->d_inode;
+
+ /*
+ * I believe we can only get a negative dentry here in the case of a
+ * procfs-style symlink. Just assume it's correct for now, but we may
+ * eventually need to do something more here.
+ */
+ if (!inode) {
+ dfprintk(LOOKUPCACHE, "%s: %s/%s has negative inode\n",
+ __func__, dentry->d_parent->d_name.name,
+ dentry->d_name.name);
+ return 1;
+ }
+
+ if (is_bad_inode(inode)) {
+ dfprintk(LOOKUPCACHE, "%s: %s/%s has dud inode\n",
+ __func__, dentry->d_parent->d_name.name,
+ dentry->d_name.name);
+ return 0;
+ }
+
+ error = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+ dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
+ __func__, inode->i_ino, error ? "invalid" : "valid");
+ return !error;
+}
+
+/*
* This is called from dput() when d_count is going to 0.
*/
static int nfs_dentry_delete(const struct dentry *dentry)
@@ -1202,6 +1241,7 @@
const struct dentry_operations nfs_dentry_operations = {
.d_revalidate = nfs_lookup_revalidate,
+ .d_weak_revalidate = nfs_weak_revalidate,
.d_delete = nfs_dentry_delete,
.d_iput = nfs_dentry_iput,
.d_automount = nfs_d_automount,
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index ca4b11e..9455270 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/dns_resolver.h>
#include "dns_resolve.h"
@@ -42,6 +43,7 @@
#include <linux/seq_file.h>
#include <linux/inet.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/cache.h>
#include <linux/sunrpc/svcauth.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
@@ -142,7 +144,7 @@
ret = nfs_cache_upcall(cd, key->hostname);
if (ret)
- ret = sunrpc_cache_pipe_upcall(cd, ch, nfs_dns_request);
+ ret = sunrpc_cache_pipe_upcall(cd, ch);
return ret;
}
@@ -351,60 +353,47 @@
}
EXPORT_SYMBOL_GPL(nfs_dns_resolve_name);
+static struct cache_detail nfs_dns_resolve_template = {
+ .owner = THIS_MODULE,
+ .hash_size = NFS_DNS_HASHTBL_SIZE,
+ .name = "dns_resolve",
+ .cache_put = nfs_dns_ent_put,
+ .cache_upcall = nfs_dns_upcall,
+ .cache_request = nfs_dns_request,
+ .cache_parse = nfs_dns_parse,
+ .cache_show = nfs_dns_show,
+ .match = nfs_dns_match,
+ .init = nfs_dns_ent_init,
+ .update = nfs_dns_ent_update,
+ .alloc = nfs_dns_ent_alloc,
+};
+
+
int nfs_dns_resolver_cache_init(struct net *net)
{
- int err = -ENOMEM;
+ int err;
struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct cache_detail *cd;
- struct cache_head **tbl;
- cd = kzalloc(sizeof(struct cache_detail), GFP_KERNEL);
- if (cd == NULL)
- goto err_cd;
+ nn->nfs_dns_resolve = cache_create_net(&nfs_dns_resolve_template, net);
+ if (IS_ERR(nn->nfs_dns_resolve))
+ return PTR_ERR(nn->nfs_dns_resolve);
- tbl = kzalloc(NFS_DNS_HASHTBL_SIZE * sizeof(struct cache_head *),
- GFP_KERNEL);
- if (tbl == NULL)
- goto err_tbl;
-
- cd->owner = THIS_MODULE,
- cd->hash_size = NFS_DNS_HASHTBL_SIZE,
- cd->hash_table = tbl,
- cd->name = "dns_resolve",
- cd->cache_put = nfs_dns_ent_put,
- cd->cache_upcall = nfs_dns_upcall,
- cd->cache_parse = nfs_dns_parse,
- cd->cache_show = nfs_dns_show,
- cd->match = nfs_dns_match,
- cd->init = nfs_dns_ent_init,
- cd->update = nfs_dns_ent_update,
- cd->alloc = nfs_dns_ent_alloc,
-
- nfs_cache_init(cd);
- err = nfs_cache_register_net(net, cd);
+ err = nfs_cache_register_net(net, nn->nfs_dns_resolve);
if (err)
goto err_reg;
- nn->nfs_dns_resolve = cd;
return 0;
err_reg:
- nfs_cache_destroy(cd);
- kfree(cd->hash_table);
-err_tbl:
- kfree(cd);
-err_cd:
+ cache_destroy_net(nn->nfs_dns_resolve, net);
return err;
}
void nfs_dns_resolver_cache_destroy(struct net *net)
{
struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct cache_detail *cd = nn->nfs_dns_resolve;
- nfs_cache_unregister_net(net, cd);
- nfs_cache_destroy(cd);
- kfree(cd->hash_table);
- kfree(cd);
+ nfs_cache_unregister_net(net, nn->nfs_dns_resolve);
+ cache_destroy_net(nn->nfs_dns_resolve, net);
}
static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 3c2b893..29f4a48 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -292,7 +292,7 @@
nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int ret;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
do {
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 033803c..44efaa8 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -126,8 +126,7 @@
}
spin_unlock(&ret->d_lock);
out:
- if (name)
- kfree(name);
+ kfree(name);
nfs_free_fattr(fsinfo.fattr);
return ret;
}
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index bc3968fa..c516da5 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -97,7 +97,7 @@
static bool nfs_fattr_map_owner_name(struct nfs_server *server, struct nfs_fattr *fattr)
{
struct nfs4_string *owner = fattr->owner_name;
- __u32 uid;
+ kuid_t uid;
if (!(fattr->valid & NFS_ATTR_FATTR_OWNER_NAME))
return false;
@@ -111,7 +111,7 @@
static bool nfs_fattr_map_group_name(struct nfs_server *server, struct nfs_fattr *fattr)
{
struct nfs4_string *group = fattr->group_name;
- __u32 gid;
+ kgid_t gid;
if (!(fattr->valid & NFS_ATTR_FATTR_GROUP_NAME))
return false;
@@ -193,7 +193,8 @@
if (!cred)
return -ENOMEM;
- keyring = keyring_alloc(".id_resolver", 0, 0, cred,
+ keyring = keyring_alloc(".id_resolver",
+ GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred,
(KEY_POS_ALL & ~KEY_POS_SETATTR) |
KEY_USR_VIEW | KEY_USR_READ,
KEY_ALLOC_NOT_IN_QUOTA, NULL);
@@ -725,9 +726,9 @@
return ret;
}
-static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data)
+static int nfs_idmap_instantiate(struct key *key, struct key *authkey, char *data, size_t datalen)
{
- return key_instantiate_and_link(key, data, strlen(data) + 1,
+ return key_instantiate_and_link(key, data, datalen,
id_resolver_cache->thread_keyring,
authkey);
}
@@ -737,6 +738,7 @@
struct key *key, struct key *authkey)
{
char id_str[NFS_UINT_MAXLEN];
+ size_t len;
int ret = -ENOKEY;
/* ret = -ENOKEY */
@@ -746,13 +748,15 @@
case IDMAP_CONV_NAMETOID:
if (strcmp(upcall->im_name, im->im_name) != 0)
break;
- sprintf(id_str, "%d", im->im_id);
- ret = nfs_idmap_instantiate(key, authkey, id_str);
+ /* Note: here we store the NUL terminator too */
+ len = sprintf(id_str, "%d", im->im_id) + 1;
+ ret = nfs_idmap_instantiate(key, authkey, id_str, len);
break;
case IDMAP_CONV_IDTONAME:
if (upcall->im_id != im->im_id)
break;
- ret = nfs_idmap_instantiate(key, authkey, im->im_name);
+ len = strlen(im->im_name);
+ ret = nfs_idmap_instantiate(key, authkey, im->im_name, len);
break;
default:
ret = -EINVAL;
@@ -764,7 +768,7 @@
static ssize_t
idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
{
- struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode);
+ struct rpc_inode *rpci = RPC_I(file_inode(filp));
struct idmap *idmap = (struct idmap *)rpci->private;
struct key_construction *cons;
struct idmap_msg im;
@@ -836,43 +840,61 @@
nfs_idmap_abort_pipe_upcall(idmap, -EPIPE);
}
-int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid)
+int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, kuid_t *uid)
{
struct idmap *idmap = server->nfs_client->cl_idmap;
+ __u32 id = -1;
+ int ret = 0;
- if (nfs_map_string_to_numeric(name, namelen, uid))
- return 0;
- return nfs_idmap_lookup_id(name, namelen, "uid", uid, idmap);
-}
-
-int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *gid)
-{
- struct idmap *idmap = server->nfs_client->cl_idmap;
-
- if (nfs_map_string_to_numeric(name, namelen, gid))
- return 0;
- return nfs_idmap_lookup_id(name, namelen, "gid", gid, idmap);
-}
-
-int nfs_map_uid_to_name(const struct nfs_server *server, __u32 uid, char *buf, size_t buflen)
-{
- struct idmap *idmap = server->nfs_client->cl_idmap;
- int ret = -EINVAL;
-
- if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
- ret = nfs_idmap_lookup_name(uid, "user", buf, buflen, idmap);
- if (ret < 0)
- ret = nfs_map_numeric_to_string(uid, buf, buflen);
+ if (!nfs_map_string_to_numeric(name, namelen, &id))
+ ret = nfs_idmap_lookup_id(name, namelen, "uid", &id, idmap);
+ if (ret == 0) {
+ *uid = make_kuid(&init_user_ns, id);
+ if (!uid_valid(*uid))
+ ret = -ERANGE;
+ }
return ret;
}
-int nfs_map_gid_to_group(const struct nfs_server *server, __u32 gid, char *buf, size_t buflen)
+
+int nfs_map_group_to_gid(const struct nfs_server *server, const char *name, size_t namelen, kgid_t *gid)
+{
+ struct idmap *idmap = server->nfs_client->cl_idmap;
+ __u32 id = -1;
+ int ret = 0;
+
+ if (!nfs_map_string_to_numeric(name, namelen, &id))
+ ret = nfs_idmap_lookup_id(name, namelen, "gid", &id, idmap);
+ if (ret == 0) {
+ *gid = make_kgid(&init_user_ns, id);
+ if (!gid_valid(*gid))
+ ret = -ERANGE;
+ }
+ return ret;
+}
+
+int nfs_map_uid_to_name(const struct nfs_server *server, kuid_t uid, char *buf, size_t buflen)
{
struct idmap *idmap = server->nfs_client->cl_idmap;
int ret = -EINVAL;
+ __u32 id;
+ id = from_kuid(&init_user_ns, uid);
if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
- ret = nfs_idmap_lookup_name(gid, "group", buf, buflen, idmap);
+ ret = nfs_idmap_lookup_name(id, "user", buf, buflen, idmap);
if (ret < 0)
- ret = nfs_map_numeric_to_string(gid, buf, buflen);
+ ret = nfs_map_numeric_to_string(id, buf, buflen);
+ return ret;
+}
+int nfs_map_gid_to_group(const struct nfs_server *server, kgid_t gid, char *buf, size_t buflen)
+{
+ struct idmap *idmap = server->nfs_client->cl_idmap;
+ int ret = -EINVAL;
+ __u32 id;
+
+ id = from_kgid(&init_user_ns, gid);
+ if (!(server->caps & NFS_CAP_UIDGID_NOMAP))
+ ret = nfs_idmap_lookup_name(id, "group", buf, buflen, idmap);
+ if (ret < 0)
+ ret = nfs_map_numeric_to_string(id, buf, buflen);
return ret;
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index ebeb94c..1f94167 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -237,6 +237,8 @@
if (NFS_FILEID(inode) != fattr->fileid)
return 0;
+ if ((S_IFMT & inode->i_mode) != (S_IFMT & fattr->mode))
+ return 0;
if (nfs_compare_fh(NFS_FH(inode), fh))
return 0;
if (is_bad_inode(inode) || NFS_STALE(inode))
@@ -332,8 +334,8 @@
inode->i_version = 0;
inode->i_size = 0;
clear_nlink(inode);
- inode->i_uid = -2;
- inode->i_gid = -2;
+ inode->i_uid = make_kuid(&init_user_ns, -2);
+ inode->i_gid = make_kgid(&init_user_ns, -2);
inode->i_blocks = 0;
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
nfsi->write_io = 0;
@@ -694,10 +696,7 @@
if (ctx->cred != NULL)
put_rpccred(ctx->cred);
dput(ctx->dentry);
- if (is_sync)
- nfs_sb_deactive(sb);
- else
- nfs_sb_deactive_async(sb);
+ nfs_sb_deactive(sb);
kfree(ctx->mdsthreshold);
kfree(ctx);
}
@@ -714,7 +713,7 @@
*/
void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct nfs_inode *nfsi = NFS_I(inode);
filp->private_data = get_nfs_open_context(ctx);
@@ -747,7 +746,7 @@
static void nfs_file_clear_open_context(struct file *filp)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct nfs_open_context *ctx = nfs_file_open_context(filp);
if (ctx) {
@@ -1009,9 +1008,9 @@
/* Have any file permissions changed? */
if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
- if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && inode->i_uid != fattr->uid)
+ if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid))
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
- if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && inode->i_gid != fattr->gid)
+ if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid))
invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL;
/* Has the link count changed? */
@@ -1440,7 +1439,7 @@
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
- if (inode->i_uid != fattr->uid) {
+ if (!uid_eq(inode->i_uid, fattr->uid)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_uid = fattr->uid;
}
@@ -1451,7 +1450,7 @@
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
- if (inode->i_gid != fattr->gid) {
+ if (!gid_eq(inode->i_gid, fattr->gid)) {
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
inode->i_gid = fattr->gid;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index f0e6c7d..541c9eb 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -329,7 +329,6 @@
extern void __exit unregister_nfs_fs(void);
extern void nfs_sb_active(struct super_block *sb);
extern void nfs_sb_deactive(struct super_block *sb);
-extern void nfs_sb_deactive_async(struct super_block *sb);
/* namespace.c */
#define NFS_PATH_CANONICAL 1
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index dd057bc..fc8dc20 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -177,11 +177,31 @@
return mnt;
}
+static int
+nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+ if (NFS_FH(dentry->d_inode)->size != 0)
+ return nfs_getattr(mnt, dentry, stat);
+ generic_fillattr(dentry->d_inode, stat);
+ return 0;
+}
+
+static int
+nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ if (NFS_FH(dentry->d_inode)->size != 0)
+ return nfs_setattr(dentry, attr);
+ return -EACCES;
+}
+
const struct inode_operations nfs_mountpoint_inode_operations = {
.getattr = nfs_getattr,
+ .setattr = nfs_setattr,
};
const struct inode_operations nfs_referral_inode_operations = {
+ .getattr = nfs_namespace_getattr,
+ .setattr = nfs_namespace_setattr,
};
static void nfs_expire_automounts(struct work_struct *work)
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 06b9df4..62db136 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -290,8 +290,13 @@
fattr->mode = be32_to_cpup(p++);
fattr->nlink = be32_to_cpup(p++);
- fattr->uid = be32_to_cpup(p++);
- fattr->gid = be32_to_cpup(p++);
+ fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++));
+ if (!uid_valid(fattr->uid))
+ goto out_uid;
+ fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++));
+ if (!gid_valid(fattr->gid))
+ goto out_gid;
+
fattr->size = be32_to_cpup(p++);
fattr->du.nfs2.blocksize = be32_to_cpup(p++);
@@ -313,6 +318,12 @@
fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
return 0;
+out_uid:
+ dprintk("NFS: returned invalid uid\n");
+ return -EINVAL;
+out_gid:
+ dprintk("NFS: returned invalid gid\n");
+ return -EINVAL;
out_overflow:
print_overflow_msg(__func__, xdr);
return -EIO;
@@ -351,11 +362,11 @@
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_UID)
- *p++ = cpu_to_be32(attr->ia_uid);
+ *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid));
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_GID)
- *p++ = cpu_to_be32(attr->ia_gid);
+ *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid));
else
*p++ = cpu_to_be32(NFS2_SATTR_NOT_SET);
if (attr->ia_valid & ATTR_SIZE)
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 70efb63..43ea96c 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -872,7 +872,7 @@
static int
nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
}
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index bffc324..fa6d721 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -592,13 +592,13 @@
if (attr->ia_valid & ATTR_UID) {
*p++ = xdr_one;
- *p++ = cpu_to_be32(attr->ia_uid);
+ *p++ = cpu_to_be32(from_kuid(&init_user_ns, attr->ia_uid));
} else
*p++ = xdr_zero;
if (attr->ia_valid & ATTR_GID) {
*p++ = xdr_one;
- *p++ = cpu_to_be32(attr->ia_gid);
+ *p++ = cpu_to_be32(from_kgid(&init_user_ns, attr->ia_gid));
} else
*p++ = xdr_zero;
@@ -657,8 +657,12 @@
fattr->mode = (be32_to_cpup(p++) & ~S_IFMT) | fmode;
fattr->nlink = be32_to_cpup(p++);
- fattr->uid = be32_to_cpup(p++);
- fattr->gid = be32_to_cpup(p++);
+ fattr->uid = make_kuid(&init_user_ns, be32_to_cpup(p++));
+ if (!uid_valid(fattr->uid))
+ goto out_uid;
+ fattr->gid = make_kgid(&init_user_ns, be32_to_cpup(p++));
+ if (!gid_valid(fattr->gid))
+ goto out_gid;
p = xdr_decode_size3(p, &fattr->size);
p = xdr_decode_size3(p, &fattr->du.nfs3.used);
@@ -675,6 +679,12 @@
fattr->valid |= NFS_ATTR_FATTR_V3;
return 0;
+out_uid:
+ dprintk("NFS: returned invalid uid\n");
+ return -EINVAL;
+out_gid:
+ dprintk("NFS: returned invalid gid\n");
+ return -EINVAL;
out_overflow:
print_overflow_msg(__func__, xdr);
return -EIO;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index a3f488b..944c9a5 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -13,6 +13,8 @@
#define NFS4_MAX_LOOP_ON_RECOVER (10)
+#include <linux/seqlock.h>
+
struct idmap;
enum nfs4_client_state {
@@ -90,6 +92,8 @@
unsigned long so_flags;
struct list_head so_states;
struct nfs_seqid_counter so_seqid;
+ seqcount_t so_reclaim_seqcount;
+ struct mutex so_delegreturn_mutex;
};
enum {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index acc3472..ac4fc9a 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -6,6 +6,7 @@
#include <linux/nfs_fs.h>
#include <linux/nfs_idmap.h>
#include <linux/nfs_mount.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/auth.h>
#include <linux/sunrpc/xprt.h>
#include <linux/sunrpc/bc_xprt.h>
@@ -29,15 +30,14 @@
if (clp->rpc_ops->version != 4 || minorversion != 0)
return ret;
-retry:
- if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL))
- return -ENOMEM;
+ idr_preload(GFP_KERNEL);
spin_lock(&nn->nfs_client_lock);
- ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident);
+ ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT);
+ if (ret >= 0)
+ clp->cl_cb_ident = ret;
spin_unlock(&nn->nfs_client_lock);
- if (ret == -EAGAIN)
- goto retry;
- return ret;
+ idr_preload_end();
+ return ret < 0 ? ret : 0;
}
#ifdef CONFIG_NFS_V4_1
@@ -236,11 +236,10 @@
error = nfs4_discover_server_trunking(clp, &old);
if (error < 0)
goto error;
+ nfs_put_client(clp);
if (clp != old) {
clp->cl_preserve_clid = true;
- nfs_put_client(clp);
clp = old;
- atomic_inc(&clp->cl_count);
}
return clp;
@@ -306,7 +305,7 @@
.clientid = new->cl_clientid,
.confirm = new->cl_confirm,
};
- int status;
+ int status = -NFS4ERR_STALE_CLIENTID;
spin_lock(&nn->nfs_client_lock);
list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -332,40 +331,33 @@
if (prev)
nfs_put_client(prev);
+ prev = pos;
status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
- if (status == 0) {
+ switch (status) {
+ case -NFS4ERR_STALE_CLIENTID:
+ break;
+ case 0:
nfs4_swap_callback_idents(pos, new);
- nfs_put_client(pos);
+ prev = NULL;
*result = pos;
dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
__func__, pos, atomic_read(&pos->cl_count));
- return 0;
- }
- if (status != -NFS4ERR_STALE_CLIENTID) {
- nfs_put_client(pos);
- dprintk("NFS: <-- %s status = %d, no result\n",
- __func__, status);
- return status;
+ default:
+ goto out;
}
spin_lock(&nn->nfs_client_lock);
- prev = pos;
}
+ spin_unlock(&nn->nfs_client_lock);
- /*
- * No matching nfs_client found. This should be impossible,
- * because the new nfs_client has already been added to
- * nfs_client_list by nfs_get_client().
- *
- * Don't BUG(), since the caller is holding a mutex.
- */
+ /* No match found. The server lost our clientid */
+out:
if (prev)
nfs_put_client(prev);
- spin_unlock(&nn->nfs_client_lock);
- pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
- return -NFS4ERR_STALE_CLIENTID;
+ dprintk("NFS: <-- %s status = %d\n", __func__, status);
+ return status;
}
#ifdef CONFIG_NFS_V4_1
@@ -432,7 +424,7 @@
{
struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
struct nfs_client *pos, *n, *prev = NULL;
- int error;
+ int status = -NFS4ERR_STALE_CLIENTID;
spin_lock(&nn->nfs_client_lock);
list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -448,14 +440,17 @@
nfs_put_client(prev);
prev = pos;
- error = nfs_wait_client_init_complete(pos);
- if (error < 0) {
+ nfs4_schedule_lease_recovery(pos);
+ status = nfs_wait_client_init_complete(pos);
+ if (status < 0) {
nfs_put_client(pos);
spin_lock(&nn->nfs_client_lock);
continue;
}
-
+ status = pos->cl_cons_state;
spin_lock(&nn->nfs_client_lock);
+ if (status < 0)
+ continue;
}
if (pos->rpc_ops != new->rpc_ops)
@@ -473,6 +468,7 @@
if (!nfs4_match_serverowners(pos, new))
continue;
+ atomic_inc(&pos->cl_count);
spin_unlock(&nn->nfs_client_lock);
dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
__func__, pos, atomic_read(&pos->cl_count));
@@ -481,16 +477,10 @@
return 0;
}
- /*
- * No matching nfs_client found. This should be impossible,
- * because the new nfs_client has already been added to
- * nfs_client_list by nfs_get_client().
- *
- * Don't BUG(), since the caller is holding a mutex.
- */
+ /* No matching nfs_client found. */
spin_unlock(&nn->nfs_client_lock);
- pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
- return -NFS4ERR_STALE_CLIENTID;
+ dprintk("NFS: <-- %s status = %d\n", __func__, status);
+ return status;
}
#endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 08ddccc..13e6bb3 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -94,7 +94,7 @@
nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
int ret;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
do {
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 194c484..4fb234d 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -99,7 +99,8 @@
task->tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
&hdr->pages,
- hdr->completion_ops);
+ hdr->completion_ops,
+ hdr->dreq);
}
}
@@ -119,7 +120,8 @@
task->tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
&hdr->pages,
- hdr->completion_ops);
+ hdr->completion_ops,
+ hdr->dreq);
}
}
@@ -127,7 +129,6 @@
{
if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return;
- clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags);
pnfs_return_layout(inode);
}
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 8c07241..b8da955 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -36,7 +36,7 @@
* Default data server connection timeout and retrans vaules.
* Set by module paramters dataserver_timeo and dataserver_retrans.
*/
-#define NFS4_DEF_DS_TIMEO 60
+#define NFS4_DEF_DS_TIMEO 600 /* in tenths of a second */
#define NFS4_DEF_DS_RETRANS 5
/*
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index b720064..1fe284f 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -31,6 +31,7 @@
#include <linux/nfs_fs.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
+#include <linux/sunrpc/addr.h>
#include "internal.h"
#include "nfs4session.h"
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 1e09eb7..0dd7660 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/vfs.h>
#include <linux/inet.h>
#include "internal.h"
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cf747ef..26431cf 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -93,6 +93,8 @@
return err;
switch (err) {
case -NFS4ERR_RESOURCE:
+ case -NFS4ERR_LAYOUTTRYLATER:
+ case -NFS4ERR_RECALLCONFLICT:
return -EREMOTEIO;
case -NFS4ERR_WRONGSEC:
return -EPERM;
@@ -896,6 +898,8 @@
return 0;
if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags))
return 0;
+ if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+ return 0;
nfs_mark_delegation_referenced(delegation);
return 1;
}
@@ -973,6 +977,7 @@
spin_lock(&deleg_cur->lock);
if (nfsi->delegation != deleg_cur ||
+ test_bit(NFS_DELEGATION_RETURNING, &deleg_cur->flags) ||
(deleg_cur->type & fmode) != fmode)
goto no_delegation_unlock;
@@ -1155,6 +1160,7 @@
data->o_arg.fmode);
iput(inode);
out:
+ nfs_release_seqid(data->o_arg.seqid);
return state;
err_put_inode:
iput(inode);
@@ -1352,19 +1358,18 @@
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
+ err = -EAGAIN;
goto out;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
case -NFS4ERR_EXPIRED:
/* Don't recall a delegation if it was lost */
nfs4_schedule_lease_recovery(server->nfs_client);
+ err = -EAGAIN;
goto out;
- case -ERESTARTSYS:
- /*
- * The show must go on: exit, but mark the
- * stateid as needing recovery.
- */
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
@@ -1375,6 +1380,7 @@
err = 0;
goto out;
}
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
out:
@@ -1463,7 +1469,7 @@
struct nfs4_state_owner *sp = data->owner;
if (nfs_wait_on_sequence(data->o_arg.seqid, task) != 0)
- return;
+ goto out_wait;
/*
* Check if we still need to send an OPEN call, or if we can use
* a delegation instead.
@@ -1498,6 +1504,7 @@
rcu_read_unlock();
out_no_action:
task->tk_action = NULL;
+out_wait:
nfs4_sequence_done(task, &data->o_res.seq_res);
}
@@ -1845,6 +1852,43 @@
sattr->ia_valid |= ATTR_MTIME;
}
+static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
+ fmode_t fmode,
+ int flags,
+ struct nfs4_state **res)
+{
+ struct nfs4_state_owner *sp = opendata->owner;
+ struct nfs_server *server = sp->so_server;
+ struct nfs4_state *state;
+ unsigned int seq;
+ int ret;
+
+ seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+
+ ret = _nfs4_proc_open(opendata);
+ if (ret != 0)
+ goto out;
+
+ state = nfs4_opendata_to_nfs4_state(opendata);
+ ret = PTR_ERR(state);
+ if (IS_ERR(state))
+ goto out;
+ if (server->caps & NFS_CAP_POSIX_LOCK)
+ set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
+
+ ret = nfs4_opendata_access(sp->so_cred, opendata, state, fmode, flags);
+ if (ret != 0)
+ goto out;
+
+ if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) {
+ nfs4_schedule_stateid_recovery(server, state);
+ nfs4_wait_clnt_recover(server->nfs_client);
+ }
+ *res = state;
+out:
+ return ret;
+}
+
/*
* Returns a referenced nfs4_state
*/
@@ -1889,18 +1933,7 @@
if (dentry->d_inode != NULL)
opendata->state = nfs4_get_open_state(dentry->d_inode, sp);
- status = _nfs4_proc_open(opendata);
- if (status != 0)
- goto err_opendata_put;
-
- state = nfs4_opendata_to_nfs4_state(opendata);
- status = PTR_ERR(state);
- if (IS_ERR(state))
- goto err_opendata_put;
- if (server->caps & NFS_CAP_POSIX_LOCK)
- set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
-
- status = nfs4_opendata_access(cred, opendata, state, fmode, flags);
+ status = _nfs4_open_and_get_state(opendata, fmode, flags, &state);
if (status != 0)
goto err_opendata_put;
@@ -2088,7 +2121,7 @@
nfs4_put_open_state(calldata->state);
nfs_free_seqid(calldata->arg.seqid);
nfs4_put_state_owner(sp);
- nfs_sb_deactive_async(sb);
+ nfs_sb_deactive(sb);
kfree(calldata);
}
@@ -2150,7 +2183,7 @@
dprintk("%s: begin!\n", __func__);
if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
- return;
+ goto out_wait;
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
@@ -2172,16 +2205,14 @@
if (!call_close) {
/* Note: exit _without_ calling nfs4_close_done */
- task->tk_action = NULL;
- nfs4_sequence_done(task, &calldata->res.seq_res);
- goto out;
+ goto out_no_action;
}
if (calldata->arg.fmode == 0) {
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
if (calldata->roc &&
pnfs_roc_drain(inode, &calldata->roc_barrier, task))
- goto out;
+ goto out_wait;
}
nfs_fattr_init(calldata->res.fattr);
@@ -2191,8 +2222,12 @@
&calldata->res.seq_res,
task) != 0)
nfs_release_seqid(calldata->arg.seqid);
-out:
dprintk("%s: done!\n", __func__);
+ return;
+out_no_action:
+ task->tk_action = NULL;
+out_wait:
+ nfs4_sequence_done(task, &calldata->res.seq_res);
}
static const struct rpc_call_ops nfs4_close_ops = {
@@ -2597,7 +2632,7 @@
int status;
if (pnfs_ld_layoutret_on_setattr(inode))
- pnfs_return_layout(inode);
+ pnfs_commit_and_return_layout(inode);
nfs_fattr_init(fattr);
@@ -4423,12 +4458,10 @@
struct nfs4_unlockdata *calldata = data;
if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
- return;
+ goto out_wait;
if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) {
/* Note: exit _without_ running nfs4_locku_done */
- task->tk_action = NULL;
- nfs4_sequence_done(task, &calldata->res.seq_res);
- return;
+ goto out_no_action;
}
calldata->timestamp = jiffies;
if (nfs4_setup_sequence(calldata->server,
@@ -4436,6 +4469,11 @@
&calldata->res.seq_res,
task) != 0)
nfs_release_seqid(calldata->arg.seqid);
+ return;
+out_no_action:
+ task->tk_action = NULL;
+out_wait:
+ nfs4_sequence_done(task, &calldata->res.seq_res);
}
static const struct rpc_call_ops nfs4_locku_ops = {
@@ -4482,7 +4520,9 @@
static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *request)
{
- struct nfs_inode *nfsi = NFS_I(state->inode);
+ struct inode *inode = state->inode;
+ struct nfs4_state_owner *sp = state->owner;
+ struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_seqid *seqid;
struct nfs4_lock_state *lsp;
struct rpc_task *task;
@@ -4492,12 +4532,17 @@
status = nfs4_set_lock_state(state, request);
/* Unlock _before_ we do the RPC call */
request->fl_flags |= FL_EXISTS;
+ /* Exclude nfs_delegation_claim_locks() */
+ mutex_lock(&sp->so_delegreturn_mutex);
+ /* Exclude nfs4_reclaim_open_stateid() - note nesting! */
down_read(&nfsi->rwsem);
if (do_vfs_lock(request->fl_file, request) == -ENOENT) {
up_read(&nfsi->rwsem);
+ mutex_unlock(&sp->so_delegreturn_mutex);
goto out;
}
up_read(&nfsi->rwsem);
+ mutex_unlock(&sp->so_delegreturn_mutex);
if (status != 0)
goto out;
/* Is this a delegated lock? */
@@ -4576,7 +4621,7 @@
dprintk("%s: begin!\n", __func__);
if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0)
- return;
+ goto out_wait;
/* Do we need to do an open_to_lock_owner? */
if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
@@ -4596,6 +4641,8 @@
nfs_release_seqid(data->arg.open_seqid);
out_release_lock_seqid:
nfs_release_seqid(data->arg.lock_seqid);
+out_wait:
+ nfs4_sequence_done(task, &data->res.seq_res);
dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
}
@@ -4813,8 +4860,10 @@
static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
+ struct nfs4_state_owner *sp = state->owner;
struct nfs_inode *nfsi = NFS_I(state->inode);
unsigned char fl_flags = request->fl_flags;
+ unsigned int seq;
int status = -ENOLCK;
if ((fl_flags & FL_POSIX) &&
@@ -4836,9 +4885,16 @@
status = do_vfs_lock(request->fl_file, request);
goto out_unlock;
}
+ seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+ up_read(&nfsi->rwsem);
status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
if (status != 0)
+ goto out;
+ down_read(&nfsi->rwsem);
+ if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) {
+ status = -NFS4ERR_DELAY;
goto out_unlock;
+ }
/* Note: we always want to sleep here! */
request->fl_flags = fl_flags | FL_SLEEP;
if (do_vfs_lock(request->fl_file, request) < 0)
@@ -4945,24 +5001,22 @@
case 0:
case -ESTALE:
goto out;
- case -NFS4ERR_EXPIRED:
- nfs4_schedule_stateid_recovery(server, state);
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
+ case -NFS4ERR_EXPIRED:
nfs4_schedule_lease_recovery(server->nfs_client);
+ err = -EAGAIN;
goto out;
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
+ err = -EAGAIN;
goto out;
- case -ERESTARTSYS:
- /*
- * The show must go on: exit, but mark the
- * stateid as needing recovery.
- */
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
@@ -4975,9 +5029,8 @@
/* kill_proc(fl->fl_pid, SIGLOST, 1); */
err = 0;
goto out;
- case -NFS4ERR_DELAY:
- break;
}
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
out:
@@ -5995,6 +6048,7 @@
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
struct nfs4_state *state = NULL;
+ unsigned long timeo, giveup;
dprintk("--> %s\n", __func__);
@@ -6006,7 +6060,10 @@
goto out;
case -NFS4ERR_LAYOUTTRYLATER:
case -NFS4ERR_RECALLCONFLICT:
- task->tk_status = -NFS4ERR_DELAY;
+ timeo = rpc_get_timeout(task->tk_client);
+ giveup = lgp->args.timestamp + timeo;
+ if (time_after(giveup, jiffies))
+ task->tk_status = -NFS4ERR_DELAY;
break;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
@@ -6079,11 +6136,13 @@
static void nfs4_layoutget_release(void *calldata)
{
struct nfs4_layoutget *lgp = calldata;
- struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+ struct inode *inode = lgp->args.inode;
+ struct nfs_server *server = NFS_SERVER(inode);
size_t max_pages = max_response_pages(server);
dprintk("--> %s\n", __func__);
nfs4_free_pages(lgp->args.layout.pages, max_pages);
+ pnfs_put_layout_hdr(NFS_I(inode)->layout);
put_nfs_open_context(lgp->args.ctx);
kfree(calldata);
dprintk("<-- %s\n", __func__);
@@ -6098,7 +6157,8 @@
struct pnfs_layout_segment *
nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
{
- struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+ struct inode *inode = lgp->args.inode;
+ struct nfs_server *server = NFS_SERVER(inode);
size_t max_pages = max_response_pages(server);
struct rpc_task *task;
struct rpc_message msg = {
@@ -6124,17 +6184,23 @@
return ERR_PTR(-ENOMEM);
}
lgp->args.layout.pglen = max_pages * PAGE_SIZE;
+ lgp->args.timestamp = jiffies;
lgp->res.layoutp = &lgp->args.layout;
lgp->res.seq_res.sr_slot = NULL;
nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
+
+ /* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+ pnfs_get_layout_hdr(NFS_I(inode)->layout);
+
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return ERR_CAST(task);
status = nfs4_wait_for_completion_rpc_task(task);
if (status == 0)
status = task->tk_status;
- if (status == 0)
+ /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
+ if (status == 0 && lgp->res.layoutp->len)
lseg = pnfs_layout_process(lgp);
rpc_put_task(task);
dprintk("<-- %s status=%d\n", __func__, status);
@@ -6350,22 +6416,8 @@
static void nfs4_layoutcommit_release(void *calldata)
{
struct nfs4_layoutcommit_data *data = calldata;
- struct pnfs_layout_segment *lseg, *tmp;
- unsigned long *bitlock = &NFS_I(data->args.inode)->flags;
pnfs_cleanup_layoutcommit(data);
- /* Matched by references in pnfs_set_layoutcommit */
- list_for_each_entry_safe(lseg, tmp, &data->lseg_list, pls_lc_list) {
- list_del_init(&lseg->pls_lc_list);
- if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT,
- &lseg->pls_flags))
- pnfs_put_lseg(lseg);
- }
-
- clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
- smp_mb__after_clear_bit();
- wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
-
put_rpccred(data->cred);
kfree(data);
}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9448c57..6ace365 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -136,16 +136,11 @@
clp->cl_confirm = clid.confirm;
status = nfs40_walk_client_list(clp, result, cred);
- switch (status) {
- case -NFS4ERR_STALE_CLIENTID:
- set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
- case 0:
+ if (status == 0) {
/* Sustain the lease, even if it's empty. If the clientid4
* goes stale it's of no use for trunking discovery. */
nfs4_schedule_state_renewal(*result);
- break;
}
-
out:
return status;
}
@@ -523,6 +518,8 @@
nfs4_init_seqid_counter(&sp->so_seqid);
atomic_set(&sp->so_count, 1);
INIT_LIST_HEAD(&sp->so_lru);
+ seqcount_init(&sp->so_reclaim_seqcount);
+ mutex_init(&sp->so_delegreturn_mutex);
return sp;
}
@@ -1395,8 +1392,9 @@
* recovering after a network partition or a reboot from a
* server that doesn't support a grace period.
*/
-restart:
spin_lock(&sp->so_lock);
+ write_seqcount_begin(&sp->so_reclaim_seqcount);
+restart:
list_for_each_entry(state, &sp->so_states, open_states) {
if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
continue;
@@ -1417,6 +1415,7 @@
}
spin_unlock(&state->state_lock);
nfs4_put_open_state(state);
+ spin_lock(&sp->so_lock);
goto restart;
}
}
@@ -1454,12 +1453,17 @@
goto out_err;
}
nfs4_put_open_state(state);
+ spin_lock(&sp->so_lock);
goto restart;
}
+ write_seqcount_end(&sp->so_reclaim_seqcount);
spin_unlock(&sp->so_lock);
return 0;
out_err:
nfs4_put_open_state(state);
+ spin_lock(&sp->so_lock);
+ write_seqcount_end(&sp->so_reclaim_seqcount);
+ spin_unlock(&sp->so_lock);
return status;
}
@@ -1863,6 +1867,7 @@
case -ETIMEDOUT:
case -EAGAIN:
ssleep(1);
+ case -NFS4ERR_STALE_CLIENTID:
dprintk("NFS: %s after status %d, retrying\n",
__func__, status);
goto again;
@@ -2022,8 +2027,18 @@
nfs4_begin_drain_session(clp);
cred = nfs4_get_exchange_id_cred(clp);
status = nfs4_proc_destroy_session(clp->cl_session, cred);
- if (status && status != -NFS4ERR_BADSESSION &&
- status != -NFS4ERR_DEADSESSION) {
+ switch (status) {
+ case 0:
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_DEADSESSION:
+ break;
+ case -NFS4ERR_BACK_CHAN_BUSY:
+ case -NFS4ERR_DELAY:
+ set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+ status = 0;
+ ssleep(1);
+ goto out;
+ default:
status = nfs4_recovery_handle_error(clp, status);
goto out;
}
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 84d2e9e..569b166 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -28,7 +28,7 @@
.name = "nfs4",
.mount = nfs4_remote_mount,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
static struct file_system_type nfs4_remote_referral_fs_type = {
@@ -36,7 +36,7 @@
.name = "nfs4",
.mount = nfs4_remote_referral_mount,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
struct file_system_type nfs4_referral_fs_type = {
@@ -44,7 +44,7 @@
.name = "nfs4",
.mount = nfs4_referral_mount,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
static const struct super_operations nfs4_sops = {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 26b1439..e3edda5 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1002,7 +1002,7 @@
owner_namelen = nfs_map_uid_to_name(server, iap->ia_uid, owner_name, IDMAP_NAMESZ);
if (owner_namelen < 0) {
dprintk("nfs: couldn't resolve uid %d to string\n",
- iap->ia_uid);
+ from_kuid(&init_user_ns, iap->ia_uid));
/* XXX */
strcpy(owner_name, "nobody");
owner_namelen = sizeof("nobody") - 1;
@@ -1014,7 +1014,7 @@
owner_grouplen = nfs_map_gid_to_group(server, iap->ia_gid, owner_group, IDMAP_NAMESZ);
if (owner_grouplen < 0) {
dprintk("nfs: couldn't resolve gid %d to string\n",
- iap->ia_gid);
+ from_kgid(&init_user_ns, iap->ia_gid));
strcpy(owner_group, "nobody");
owner_grouplen = sizeof("nobody") - 1;
/* goto out; */
@@ -3778,14 +3778,14 @@
}
static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap,
- const struct nfs_server *server, uint32_t *uid,
+ const struct nfs_server *server, kuid_t *uid,
struct nfs4_string *owner_name)
{
uint32_t len;
__be32 *p;
int ret = 0;
- *uid = -2;
+ *uid = make_kuid(&init_user_ns, -2);
if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U)))
return -EIO;
if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) {
@@ -3813,7 +3813,7 @@
__func__, len);
bitmap[1] &= ~FATTR4_WORD1_OWNER;
}
- dprintk("%s: uid=%d\n", __func__, (int)*uid);
+ dprintk("%s: uid=%d\n", __func__, (int)from_kuid(&init_user_ns, *uid));
return ret;
out_overflow:
print_overflow_msg(__func__, xdr);
@@ -3821,14 +3821,14 @@
}
static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
- const struct nfs_server *server, uint32_t *gid,
+ const struct nfs_server *server, kgid_t *gid,
struct nfs4_string *group_name)
{
uint32_t len;
__be32 *p;
int ret = 0;
- *gid = -2;
+ *gid = make_kgid(&init_user_ns, -2);
if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U)))
return -EIO;
if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) {
@@ -3856,7 +3856,7 @@
__func__, len);
bitmap[1] &= ~FATTR4_WORD1_OWNER_GROUP;
}
- dprintk("%s: gid=%d\n", __func__, (int)*gid);
+ dprintk("%s: gid=%d\n", __func__, (int)from_kgid(&init_user_ns, *gid));
return ret;
out_overflow:
print_overflow_msg(__func__, xdr);
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index c6f9906..88f9611 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -647,6 +647,7 @@
.flags = PNFS_LAYOUTRET_ON_SETATTR |
PNFS_LAYOUTRET_ON_ERROR,
+ .owner = THIS_MODULE,
.alloc_layout_hdr = objlayout_alloc_layout_hdr,
.free_layout_hdr = objlayout_free_layout_hdr,
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index d00260b..4bdffe0 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -417,6 +417,16 @@
lo_seg_intersecting(lseg_range, recall_range);
}
+static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
+ struct list_head *tmp_list)
+{
+ if (!atomic_dec_and_test(&lseg->pls_refcount))
+ return false;
+ pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
+ list_add(&lseg->pls_list, tmp_list);
+ return true;
+}
+
/* Returns 1 if lseg is removed from list, 0 otherwise */
static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
struct list_head *tmp_list)
@@ -430,11 +440,8 @@
*/
dprintk("%s: lseg %p ref %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount));
- if (atomic_dec_and_test(&lseg->pls_refcount)) {
- pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
- list_add(&lseg->pls_list, tmp_list);
+ if (pnfs_lseg_dec_and_remove_zero(lseg, tmp_list))
rv = 1;
- }
}
return rv;
}
@@ -505,6 +512,136 @@
}
EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
+static bool
+pnfs_layout_add_bulk_destroy_list(struct inode *inode,
+ struct list_head *layout_list)
+{
+ struct pnfs_layout_hdr *lo;
+ bool ret = false;
+
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (lo != NULL && list_empty(&lo->plh_bulk_destroy)) {
+ pnfs_get_layout_hdr(lo);
+ list_add(&lo->plh_bulk_destroy, layout_list);
+ ret = true;
+ }
+ spin_unlock(&inode->i_lock);
+ return ret;
+}
+
+/* Caller must hold rcu_read_lock and clp->cl_lock */
+static int
+pnfs_layout_bulk_destroy_byserver_locked(struct nfs_client *clp,
+ struct nfs_server *server,
+ struct list_head *layout_list)
+{
+ struct pnfs_layout_hdr *lo, *next;
+ struct inode *inode;
+
+ list_for_each_entry_safe(lo, next, &server->layouts, plh_layouts) {
+ inode = igrab(lo->plh_inode);
+ if (inode == NULL)
+ continue;
+ list_del_init(&lo->plh_layouts);
+ if (pnfs_layout_add_bulk_destroy_list(inode, layout_list))
+ continue;
+ rcu_read_unlock();
+ spin_unlock(&clp->cl_lock);
+ iput(inode);
+ spin_lock(&clp->cl_lock);
+ rcu_read_lock();
+ return -EAGAIN;
+ }
+ return 0;
+}
+
+static int
+pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
+ bool is_bulk_recall)
+{
+ struct pnfs_layout_hdr *lo;
+ struct inode *inode;
+ struct pnfs_layout_range range = {
+ .iomode = IOMODE_ANY,
+ .offset = 0,
+ .length = NFS4_MAX_UINT64,
+ };
+ LIST_HEAD(lseg_list);
+ int ret = 0;
+
+ while (!list_empty(layout_list)) {
+ lo = list_entry(layout_list->next, struct pnfs_layout_hdr,
+ plh_bulk_destroy);
+ dprintk("%s freeing layout for inode %lu\n", __func__,
+ lo->plh_inode->i_ino);
+ inode = lo->plh_inode;
+ spin_lock(&inode->i_lock);
+ list_del_init(&lo->plh_bulk_destroy);
+ lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
+ if (is_bulk_recall)
+ set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+ if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range))
+ ret = -EAGAIN;
+ spin_unlock(&inode->i_lock);
+ pnfs_free_lseg_list(&lseg_list);
+ pnfs_put_layout_hdr(lo);
+ iput(inode);
+ }
+ return ret;
+}
+
+int
+pnfs_destroy_layouts_byfsid(struct nfs_client *clp,
+ struct nfs_fsid *fsid,
+ bool is_recall)
+{
+ struct nfs_server *server;
+ LIST_HEAD(layout_list);
+
+ spin_lock(&clp->cl_lock);
+ rcu_read_lock();
+restart:
+ list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+ if (memcmp(&server->fsid, fsid, sizeof(*fsid)) != 0)
+ continue;
+ if (pnfs_layout_bulk_destroy_byserver_locked(clp,
+ server,
+ &layout_list) != 0)
+ goto restart;
+ }
+ rcu_read_unlock();
+ spin_unlock(&clp->cl_lock);
+
+ if (list_empty(&layout_list))
+ return 0;
+ return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall);
+}
+
+int
+pnfs_destroy_layouts_byclid(struct nfs_client *clp,
+ bool is_recall)
+{
+ struct nfs_server *server;
+ LIST_HEAD(layout_list);
+
+ spin_lock(&clp->cl_lock);
+ rcu_read_lock();
+restart:
+ list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
+ if (pnfs_layout_bulk_destroy_byserver_locked(clp,
+ server,
+ &layout_list) != 0)
+ goto restart;
+ }
+ rcu_read_unlock();
+ spin_unlock(&clp->cl_lock);
+
+ if (list_empty(&layout_list))
+ return 0;
+ return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall);
+}
+
/*
* Called by the state manger to remove all layouts established under an
* expired lease.
@@ -512,30 +649,10 @@
void
pnfs_destroy_all_layouts(struct nfs_client *clp)
{
- struct nfs_server *server;
- struct pnfs_layout_hdr *lo;
- LIST_HEAD(tmp_list);
-
nfs4_deviceid_mark_client_invalid(clp);
nfs4_deviceid_purge_client(clp);
- spin_lock(&clp->cl_lock);
- rcu_read_lock();
- list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
- if (!list_empty(&server->layouts))
- list_splice_init(&server->layouts, &tmp_list);
- }
- rcu_read_unlock();
- spin_unlock(&clp->cl_lock);
-
- while (!list_empty(&tmp_list)) {
- lo = list_entry(tmp_list.next, struct pnfs_layout_hdr,
- plh_layouts);
- dprintk("%s freeing layout for inode %lu\n", __func__,
- lo->plh_inode->i_ino);
- list_del_init(&lo->plh_layouts);
- pnfs_destroy_layout(NFS_I(lo->plh_inode));
- }
+ pnfs_destroy_layouts_byclid(clp, false);
}
/*
@@ -667,6 +784,21 @@
return lseg;
}
+static void pnfs_clear_layoutcommit(struct inode *inode,
+ struct list_head *head)
+{
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct pnfs_layout_segment *lseg, *tmp;
+
+ if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
+ return;
+ list_for_each_entry_safe(lseg, tmp, &nfsi->layout->plh_segs, pls_list) {
+ if (!test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+ continue;
+ pnfs_lseg_dec_and_remove_zero(lseg, head);
+ }
+}
+
/*
* Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
* when the layout segment list is empty.
@@ -698,6 +830,7 @@
/* Reference matched in nfs4_layoutreturn_release */
pnfs_get_layout_hdr(lo);
empty = list_empty(&lo->plh_segs);
+ pnfs_clear_layoutcommit(ino, &tmp_list);
pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
/* Don't send a LAYOUTRETURN if list was initially empty */
if (empty) {
@@ -710,8 +843,6 @@
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&tmp_list);
- WARN_ON(test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags));
-
lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
if (unlikely(lrp == NULL)) {
status = -ENOMEM;
@@ -735,6 +866,33 @@
}
EXPORT_SYMBOL_GPL(_pnfs_return_layout);
+int
+pnfs_commit_and_return_layout(struct inode *inode)
+{
+ struct pnfs_layout_hdr *lo;
+ int ret;
+
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (lo == NULL) {
+ spin_unlock(&inode->i_lock);
+ return 0;
+ }
+ pnfs_get_layout_hdr(lo);
+ /* Block new layoutgets and read/write to ds */
+ lo->plh_block_lgets++;
+ spin_unlock(&inode->i_lock);
+ filemap_fdatawait(inode->i_mapping);
+ ret = pnfs_layoutcommit_inode(inode, true);
+ if (ret == 0)
+ ret = _pnfs_return_layout(inode);
+ spin_lock(&inode->i_lock);
+ lo->plh_block_lgets--;
+ spin_unlock(&inode->i_lock);
+ pnfs_put_layout_hdr(lo);
+ return ret;
+}
+
bool pnfs_roc(struct inode *ino)
{
struct pnfs_layout_hdr *lo;
@@ -888,7 +1046,7 @@
atomic_set(&lo->plh_refcount, 1);
INIT_LIST_HEAD(&lo->plh_layouts);
INIT_LIST_HEAD(&lo->plh_segs);
- INIT_LIST_HEAD(&lo->plh_bulk_recall);
+ INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
lo->plh_lc_cred = get_rpccred(ctx->state->owner->so_cred);
return lo;
@@ -1071,7 +1229,7 @@
struct nfs_client *clp = server->nfs_client;
struct pnfs_layout_hdr *lo;
struct pnfs_layout_segment *lseg = NULL;
- bool first = false;
+ bool first;
if (!pnfs_enabled_sb(NFS_SERVER(ino)))
goto out;
@@ -1105,10 +1263,9 @@
goto out_unlock;
atomic_inc(&lo->plh_outstanding);
- if (list_empty(&lo->plh_segs))
- first = true;
-
+ first = list_empty(&lo->plh_layouts) ? true : false;
spin_unlock(&ino->i_lock);
+
if (first) {
/* The lo must be on the clp list if there is any
* chance of a CB_LAYOUTRECALL(FILE) coming in.
@@ -1312,13 +1469,15 @@
int pnfs_write_done_resend_to_mds(struct inode *inode,
struct list_head *head,
- const struct nfs_pgio_completion_ops *compl_ops)
+ const struct nfs_pgio_completion_ops *compl_ops,
+ struct nfs_direct_req *dreq)
{
struct nfs_pageio_descriptor pgio;
LIST_HEAD(failed);
/* Resend all requests through the MDS */
nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
+ pgio.pg_dreq = dreq;
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
@@ -1347,13 +1506,13 @@
dprintk("pnfs write error = %d\n", hdr->pnfs_error);
if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
- clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
pnfs_return_layout(hdr->inode);
}
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
&hdr->pages,
- hdr->completion_ops);
+ hdr->completion_ops,
+ hdr->dreq);
}
/*
@@ -1468,13 +1627,15 @@
int pnfs_read_done_resend_to_mds(struct inode *inode,
struct list_head *head,
- const struct nfs_pgio_completion_ops *compl_ops)
+ const struct nfs_pgio_completion_ops *compl_ops,
+ struct nfs_direct_req *dreq)
{
struct nfs_pageio_descriptor pgio;
LIST_HEAD(failed);
/* Resend all requests through the MDS */
nfs_pageio_init_read(&pgio, inode, compl_ops);
+ pgio.pg_dreq = dreq;
while (!list_empty(head)) {
struct nfs_page *req = nfs_list_entry(head->next);
@@ -1499,13 +1660,13 @@
dprintk("pnfs read error = %d\n", hdr->pnfs_error);
if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
- clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
pnfs_return_layout(hdr->inode);
}
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
&hdr->pages,
- hdr->completion_ops);
+ hdr->completion_ops,
+ hdr->dreq);
}
/*
@@ -1631,11 +1792,27 @@
list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
if (lseg->pls_range.iomode == IOMODE_RW &&
- test_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
+ test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
list_add(&lseg->pls_lc_list, listp);
}
}
+static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp)
+{
+ struct pnfs_layout_segment *lseg, *tmp;
+ unsigned long *bitlock = &NFS_I(inode)->flags;
+
+ /* Matched by references in pnfs_set_layoutcommit */
+ list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) {
+ list_del_init(&lseg->pls_lc_list);
+ pnfs_put_lseg(lseg);
+ }
+
+ clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
+}
+
void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
{
pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode);
@@ -1680,6 +1857,7 @@
if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
+ pnfs_list_write_lseg_done(data->args.inode, &data->lseg_list);
}
/*
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index dbf7bba..f5f8a47 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -132,7 +132,7 @@
struct pnfs_layout_hdr {
atomic_t plh_refcount;
struct list_head plh_layouts; /* other client layouts */
- struct list_head plh_bulk_recall; /* clnt list of bulk recalls */
+ struct list_head plh_bulk_destroy;
struct list_head plh_segs; /* layout segments list */
nfs4_stateid plh_stateid;
atomic_t plh_outstanding; /* number of RPCs out */
@@ -196,6 +196,11 @@
void pnfs_free_lseg_list(struct list_head *tmp_list);
void pnfs_destroy_layout(struct nfs_inode *);
void pnfs_destroy_all_layouts(struct nfs_client *);
+int pnfs_destroy_layouts_byfsid(struct nfs_client *clp,
+ struct nfs_fsid *fsid,
+ bool is_recall);
+int pnfs_destroy_layouts_byclid(struct nfs_client *clp,
+ bool is_recall);
void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
const nfs4_stateid *new,
@@ -214,6 +219,7 @@
void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
int _pnfs_return_layout(struct inode *);
+int pnfs_commit_and_return_layout(struct inode *);
void pnfs_ld_write_done(struct nfs_write_data *);
void pnfs_ld_read_done(struct nfs_read_data *);
struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
@@ -225,9 +231,11 @@
void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head,
- const struct nfs_pgio_completion_ops *compl_ops);
+ const struct nfs_pgio_completion_ops *compl_ops,
+ struct nfs_direct_req *dreq);
int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head,
- const struct nfs_pgio_completion_ops *compl_ops);
+ const struct nfs_pgio_completion_ops *compl_ops,
+ struct nfs_direct_req *dreq);
struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
/* nfs4_deviceid_flags */
@@ -400,6 +408,11 @@
return 0;
}
+static inline int pnfs_commit_and_return_layout(struct inode *inode)
+{
+ return 0;
+}
+
static inline bool
pnfs_ld_layoutret_on_setattr(struct inode *inode)
{
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index d35b62e..6da209b 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -77,9 +77,8 @@
long hash)
{
struct nfs4_deviceid_node *d;
- struct hlist_node *n;
- hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+ hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node)
if (d->ld == ld && d->nfs_client == clp &&
!memcmp(&d->deviceid, id, sizeof(*id))) {
if (atomic_read(&d->ref))
@@ -248,12 +247,11 @@
_deviceid_purge_client(const struct nfs_client *clp, long hash)
{
struct nfs4_deviceid_node *d;
- struct hlist_node *n;
HLIST_HEAD(tmp);
spin_lock(&nfs4_deviceid_lock);
rcu_read_lock();
- hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+ hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[hash], node)
if (d->nfs_client == clp && atomic_read(&d->ref)) {
hlist_del_init_rcu(&d->node);
hlist_add_head(&d->tmpnode, &tmp);
@@ -291,12 +289,11 @@
nfs4_deviceid_mark_client_invalid(struct nfs_client *clp)
{
struct nfs4_deviceid_node *d;
- struct hlist_node *n;
int i;
rcu_read_lock();
for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i ++){
- hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[i], node)
+ hlist_for_each_entry_rcu(d, &nfs4_deviceid_cache[i], node)
if (d->nfs_client == clp)
set_bit(NFS_DEVICEID_INVALID, &d->flags);
}
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index f084dac..fc8de90 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -662,7 +662,7 @@
static int
nfs_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2e7e8c8..2f8a29d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -31,6 +31,7 @@
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/stats.h>
#include <linux/sunrpc/metrics.h>
#include <linux/sunrpc/xprtsock.h>
@@ -54,7 +55,6 @@
#include <linux/parser.h>
#include <linux/nsproxy.h>
#include <linux/rcupdate.h>
-#include <linux/kthread.h>
#include <asm/uaccess.h>
@@ -292,8 +292,9 @@
.name = "nfs",
.mount = nfs_fs_mount,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
+MODULE_ALIAS_FS("nfs");
EXPORT_SYMBOL_GPL(nfs_fs_type);
struct file_system_type nfs_xdev_fs_type = {
@@ -301,7 +302,7 @@
.name = "nfs",
.mount = nfs_xdev_mount,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
const struct super_operations nfs_sops = {
@@ -331,8 +332,10 @@
.name = "nfs4",
.mount = nfs_fs_mount,
.kill_sb = nfs_kill_super,
- .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
+ .fs_flags = FS_RENAME_DOES_D_MOVE|FS_BINARY_MOUNTDATA,
};
+MODULE_ALIAS_FS("nfs4");
+MODULE_ALIAS("nfs4");
EXPORT_SYMBOL_GPL(nfs4_fs_type);
static int __init register_nfs4_fs(void)
@@ -418,54 +421,6 @@
}
EXPORT_SYMBOL_GPL(nfs_sb_deactive);
-static int nfs_deactivate_super_async_work(void *ptr)
-{
- struct super_block *sb = ptr;
-
- deactivate_super(sb);
- module_put_and_exit(0);
- return 0;
-}
-
-/*
- * same effect as deactivate_super, but will do final unmount in kthread
- * context
- */
-static void nfs_deactivate_super_async(struct super_block *sb)
-{
- struct task_struct *task;
- char buf[INET6_ADDRSTRLEN + 1];
- struct nfs_server *server = NFS_SB(sb);
- struct nfs_client *clp = server->nfs_client;
-
- if (!atomic_add_unless(&sb->s_active, -1, 1)) {
- rcu_read_lock();
- snprintf(buf, sizeof(buf),
- rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR));
- rcu_read_unlock();
-
- __module_get(THIS_MODULE);
- task = kthread_run(nfs_deactivate_super_async_work, sb,
- "%s-deactivate-super", buf);
- if (IS_ERR(task)) {
- pr_err("%s: kthread_run: %ld\n",
- __func__, PTR_ERR(task));
- /* make synchronous call and hope for the best */
- deactivate_super(sb);
- module_put(THIS_MODULE);
- }
- }
-}
-
-void nfs_sb_deactive_async(struct super_block *sb)
-{
- struct nfs_server *server = NFS_SB(sb);
-
- if (atomic_dec_and_test(&server->active))
- nfs_deactivate_super_async(sb);
-}
-EXPORT_SYMBOL_GPL(nfs_sb_deactive_async);
-
/*
* Deliver file system statistics to userspace
*/
@@ -2589,27 +2544,23 @@
struct nfs_server *server;
struct dentry *mntroot = ERR_PTR(-ENOMEM);
struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
- int error;
- dprintk("--> nfs_xdev_mount_common()\n");
+ dprintk("--> nfs_xdev_mount()\n");
mount_info.mntfh = mount_info.cloned->fh;
/* create a new volume representation */
server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
- if (IS_ERR(server)) {
- error = PTR_ERR(server);
- goto out_err;
- }
- mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod);
- dprintk("<-- nfs_xdev_mount_common() = 0\n");
-out:
+ if (IS_ERR(server))
+ mntroot = ERR_CAST(server);
+ else
+ mntroot = nfs_fs_mount_common(server, flags,
+ dev_name, &mount_info, nfs_mod);
+
+ dprintk("<-- nfs_xdev_mount() = %ld\n",
+ IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L);
return mntroot;
-
-out_err:
- dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error);
- goto out;
}
#if IS_ENABLED(CONFIG_NFS_V4)
@@ -2769,6 +2720,5 @@
MODULE_PARM_DESC(send_implementation_id,
"Send implementation ID with NFSv4.1 exchange_id");
MODULE_PARM_DESC(nfs4_unique_id, "nfs_client_id4 uniquifier string");
-MODULE_ALIAS("nfs4");
#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 3f79c77..1f1f38f 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -95,7 +95,7 @@
nfs_dec_sillycount(data->dir);
nfs_free_unlinkdata(data);
- nfs_sb_deactive_async(sb);
+ nfs_sb_deactive(sb);
}
static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
@@ -268,8 +268,7 @@
* point dentry is definitely not a root, so we won't need
* that anymore.
*/
- if (devname_garbage)
- kfree(devname_garbage);
+ kfree(devname_garbage);
return 0;
out_unlock:
spin_unlock(&dentry->d_lock);
@@ -336,20 +335,14 @@
struct inode *old_dir = data->old_dir;
struct inode *new_dir = data->new_dir;
struct dentry *old_dentry = data->old_dentry;
- struct dentry *new_dentry = data->new_dentry;
if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
rpc_restart_call_prepare(task);
return;
}
- if (task->tk_status != 0) {
+ if (task->tk_status != 0)
nfs_cancel_async_unlink(old_dentry);
- return;
- }
-
- d_drop(old_dentry);
- d_drop(new_dentry);
}
/**
@@ -550,6 +543,18 @@
error = rpc_wait_for_completion_task(task);
if (error == 0)
error = task->tk_status;
+ switch (error) {
+ case 0:
+ /* The rename succeeded */
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ d_move(dentry, sdentry);
+ break;
+ case -ERESTARTSYS:
+ /* The result of the rename is unknown. Play it safe by
+ * forcing a new lookup */
+ d_drop(dentry);
+ d_drop(sdentry);
+ }
rpc_put_task(task);
out_dput:
dput(sdentry);
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index 6940439..ed628f7 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -38,8 +38,8 @@
unsigned int count;
struct posix_acl *acl;
int typeflag;
- uid_t uid;
- gid_t gid;
+ kuid_t uid;
+ kgid_t gid;
};
struct nfsacl_simple_acl {
@@ -60,14 +60,16 @@
*p++ = htonl(entry->e_tag | nfsacl_desc->typeflag);
switch(entry->e_tag) {
case ACL_USER_OBJ:
- *p++ = htonl(nfsacl_desc->uid);
+ *p++ = htonl(from_kuid(&init_user_ns, nfsacl_desc->uid));
break;
case ACL_GROUP_OBJ:
- *p++ = htonl(nfsacl_desc->gid);
+ *p++ = htonl(from_kgid(&init_user_ns, nfsacl_desc->gid));
break;
case ACL_USER:
+ *p++ = htonl(from_kuid(&init_user_ns, entry->e_uid));
+ break;
case ACL_GROUP:
- *p++ = htonl(entry->e_id);
+ *p++ = htonl(from_kgid(&init_user_ns, entry->e_gid));
break;
default: /* Solaris depends on that! */
*p++ = 0;
@@ -148,6 +150,7 @@
(struct nfsacl_decode_desc *) desc;
__be32 *p = elem;
struct posix_acl_entry *entry;
+ unsigned int id;
if (!nfsacl_desc->acl) {
if (desc->array_len > NFS_ACL_MAX_ENTRIES)
@@ -160,14 +163,22 @@
entry = &nfsacl_desc->acl->a_entries[nfsacl_desc->count++];
entry->e_tag = ntohl(*p++) & ~NFS_ACL_DEFAULT;
- entry->e_id = ntohl(*p++);
+ id = ntohl(*p++);
entry->e_perm = ntohl(*p++);
switch(entry->e_tag) {
- case ACL_USER_OBJ:
case ACL_USER:
- case ACL_GROUP_OBJ:
+ entry->e_uid = make_kuid(&init_user_ns, id);
+ if (!uid_valid(entry->e_uid))
+ return -EINVAL;
+ break;
case ACL_GROUP:
+ entry->e_gid = make_kgid(&init_user_ns, id);
+ if (!gid_valid(entry->e_gid))
+ return -EINVAL;
+ break;
+ case ACL_USER_OBJ:
+ case ACL_GROUP_OBJ:
case ACL_OTHER:
if (entry->e_perm & ~S_IRWXO)
return -EINVAL;
@@ -190,9 +201,13 @@
if (a->e_tag != b->e_tag)
return a->e_tag - b->e_tag;
- else if (a->e_id > b->e_id)
+ else if ((a->e_tag == ACL_USER) && uid_gt(a->e_uid, b->e_uid))
return 1;
- else if (a->e_id < b->e_id)
+ else if ((a->e_tag == ACL_USER) && uid_lt(a->e_uid, b->e_uid))
+ return -1;
+ else if ((a->e_tag == ACL_GROUP) && gid_gt(a->e_gid, b->e_gid))
+ return 1;
+ else if ((a->e_tag == ACL_GROUP) && gid_lt(a->e_gid, b->e_gid))
return -1;
else
return 0;
@@ -213,22 +228,18 @@
sort(acl->a_entries, acl->a_count, sizeof(struct posix_acl_entry),
cmp_acl_entry, NULL);
- /* Clear undefined identifier fields and find the ACL_GROUP_OBJ
- and ACL_MASK entries. */
+ /* Find the ACL_GROUP_OBJ and ACL_MASK entries. */
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch(pa->e_tag) {
case ACL_USER_OBJ:
- pa->e_id = ACL_UNDEFINED_ID;
break;
case ACL_GROUP_OBJ:
- pa->e_id = ACL_UNDEFINED_ID;
group_obj = pa;
break;
case ACL_MASK:
mask = pa;
/* fall through */
case ACL_OTHER:
- pa->e_id = ACL_UNDEFINED_ID;
break;
}
}
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 8df1ea4..430b687 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -65,8 +65,8 @@
If unsure, say N.
config NFSD_V4
- bool "NFS server support for NFS version 4 (EXPERIMENTAL)"
- depends on NFSD && PROC_FS && EXPERIMENTAL
+ bool "NFS server support for NFS version 4"
+ depends on NFSD && PROC_FS
select NFSD_V3
select FS_POSIX_ACL
select SUNRPC_GSS
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
index 34e5c40..8b186a4 100644
--- a/fs/nfsd/acl.h
+++ b/fs/nfsd/acl.h
@@ -44,8 +44,6 @@
struct nfs4_acl *nfs4_acl_new(int);
int nfs4_acl_get_whotype(char *, u32);
int nfs4_acl_write_who(int who, char *p);
-int nfs4_acl_permission(struct nfs4_acl *acl, uid_t owner, gid_t group,
- uid_t who, u32 mask);
#define NFS4_ACL_TYPE_DEFAULT 0x01
#define NFS4_ACL_DIR 0x02
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 34a10d7..06cddd5 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -47,9 +47,9 @@
if (!gi)
goto oom;
} else if (flags & NFSEXP_ROOTSQUASH) {
- if (!new->fsuid)
+ if (uid_eq(new->fsuid, GLOBAL_ROOT_UID))
new->fsuid = exp->ex_anon_uid;
- if (!new->fsgid)
+ if (gid_eq(new->fsgid, GLOBAL_ROOT_GID))
new->fsgid = exp->ex_anon_gid;
gi = groups_alloc(rqgi->ngroups);
@@ -58,7 +58,7 @@
for (i = 0; i < rqgi->ngroups; i++) {
if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i)))
- GROUP_AT(gi, i) = make_kgid(&init_user_ns, exp->ex_anon_gid);
+ GROUP_AT(gi, i) = exp->ex_anon_gid;
else
GROUP_AT(gi, i) = GROUP_AT(rqgi, i);
}
@@ -66,9 +66,9 @@
gi = get_group_info(rqgi);
}
- if (new->fsuid == (uid_t) -1)
+ if (uid_eq(new->fsuid, INVALID_UID))
new->fsuid = exp->ex_anon_uid;
- if (new->fsgid == (gid_t) -1)
+ if (gid_eq(new->fsgid, INVALID_GID))
new->fsgid = exp->ex_anon_gid;
ret = set_groups(new, gi);
@@ -76,7 +76,7 @@
if (ret < 0)
goto error;
- if (new->fsuid)
+ if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
else
new->cap_effective = cap_raise_nfsd_set(new->cap_effective,
diff --git a/fs/nfsd/auth.h b/fs/nfsd/auth.h
index 78b3c0e..53325a1 100644
--- a/fs/nfsd/auth.h
+++ b/fs/nfsd/auth.h
@@ -1,6 +1,5 @@
/*
* nfsd-specific authentication stuff.
- * uid/gid mapping not yet implemented.
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
@@ -8,11 +7,6 @@
#ifndef LINUX_NFSD_AUTH_H
#define LINUX_NFSD_AUTH_H
-#define nfsd_luid(rq, uid) ((u32)(uid))
-#define nfsd_lgid(rq, gid) ((u32)(gid))
-#define nfsd_ruid(rq, uid) ((u32)(uid))
-#define nfsd_rgid(rq, gid) ((u32)(gid))
-
/*
* Set the current process's fsuid/fsgid etc to those of the NFS
* client user
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index 93cc9d3..87fd141 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -12,6 +12,10 @@
/*
* Representation of a reply cache entry.
+ *
+ * Note that we use a sockaddr_in6 to hold the address instead of the more
+ * typical sockaddr_storage. This is for space reasons, since sockaddr_storage
+ * is much larger than a sockaddr_in6.
*/
struct svc_cacherep {
struct hlist_node c_hash;
@@ -20,11 +24,13 @@
unsigned char c_state, /* unused, inprog, done */
c_type, /* status, buffer */
c_secure : 1; /* req came from port < 1024 */
- struct sockaddr_in c_addr;
+ struct sockaddr_in6 c_addr;
__be32 c_xid;
u32 c_prot;
u32 c_proc;
u32 c_vers;
+ unsigned int c_len;
+ __wsum c_csum;
unsigned long c_timestamp;
union {
struct kvec u_vec;
@@ -46,8 +52,7 @@
enum {
RC_DROPIT,
RC_REPLY,
- RC_DOIT,
- RC_INTR
+ RC_DOIT
};
/*
@@ -67,6 +72,12 @@
*/
#define RC_DELAY (HZ/5)
+/* Cache entries expire after this time period */
+#define RC_EXPIRE (120 * HZ)
+
+/* Checksum this amount of the request */
+#define RC_CSUMLEN (256U)
+
int nfsd_reply_cache_init(void);
void nfsd_reply_cache_shutdown(void);
int nfsd_cache_lookup(struct svc_rqst *);
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index a3946cf..5f38ea3 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -67,11 +67,6 @@
(*bpp)[-1] = '\n';
}
-static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
-{
- return sunrpc_cache_pipe_upcall(cd, h, expkey_request);
-}
-
static struct svc_expkey *svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new,
struct svc_expkey *old);
static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *);
@@ -245,7 +240,7 @@
.hash_size = EXPKEY_HASHMAX,
.name = "nfsd.fh",
.cache_put = expkey_put,
- .cache_upcall = expkey_upcall,
+ .cache_request = expkey_request,
.cache_parse = expkey_parse,
.cache_show = expkey_show,
.match = expkey_match,
@@ -315,6 +310,7 @@
path_put(&exp->ex_path);
auth_domain_put(exp->ex_client);
nfsd4_fslocs_free(&exp->ex_fslocs);
+ kfree(exp->ex_uuid);
kfree(exp);
}
@@ -337,11 +333,6 @@
(*bpp)[-1] = '\n';
}
-static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
-{
- return sunrpc_cache_pipe_upcall(cd, h, svc_export_request);
-}
-
static struct svc_export *svc_export_update(struct svc_export *new,
struct svc_export *old);
static struct svc_export *svc_export_lookup(struct svc_export *);
@@ -544,13 +535,17 @@
err = get_int(&mesg, &an_int);
if (err)
goto out3;
- exp.ex_anon_uid= an_int;
+ exp.ex_anon_uid= make_kuid(&init_user_ns, an_int);
+ if (!uid_valid(exp.ex_anon_uid))
+ goto out3;
/* anon gid */
err = get_int(&mesg, &an_int);
if (err)
goto out3;
- exp.ex_anon_gid= an_int;
+ exp.ex_anon_gid= make_kgid(&init_user_ns, an_int);
+ if (!gid_valid(exp.ex_anon_gid))
+ goto out3;
/* fsid */
err = get_int(&mesg, &an_int);
@@ -613,7 +608,7 @@
}
static void exp_flags(struct seq_file *m, int flag, int fsid,
- uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fslocs);
+ kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fslocs);
static void show_secinfo(struct seq_file *m, struct svc_export *exp);
static int svc_export_show(struct seq_file *m,
@@ -670,6 +665,7 @@
new->ex_fslocs.locations = NULL;
new->ex_fslocs.locations_count = 0;
new->ex_fslocs.migrated = 0;
+ new->ex_uuid = NULL;
new->cd = item->cd;
}
@@ -711,7 +707,7 @@
.hash_size = EXPORT_HASHMAX,
.name = "nfsd.export",
.cache_put = svc_export_put,
- .cache_upcall = svc_export_upcall,
+ .cache_request = svc_export_request,
.cache_parse = svc_export_parse,
.cache_show = svc_export_show,
.match = svc_export_match,
@@ -1179,15 +1175,17 @@
}
static void exp_flags(struct seq_file *m, int flag, int fsid,
- uid_t anonu, uid_t anong, struct nfsd4_fs_locations *fsloc)
+ kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fsloc)
{
show_expflags(m, flag, NFSEXP_ALLFLAGS);
if (flag & NFSEXP_FSID)
seq_printf(m, ",fsid=%d", fsid);
- if (anonu != (uid_t)-2 && anonu != (0x10000-2))
- seq_printf(m, ",anonuid=%u", anonu);
- if (anong != (gid_t)-2 && anong != (0x10000-2))
- seq_printf(m, ",anongid=%u", anong);
+ if (!uid_eq(anonu, make_kuid(&init_user_ns, (uid_t)-2)) &&
+ !uid_eq(anonu, make_kuid(&init_user_ns, 0x10000-2)))
+ seq_printf(m, ",anonuid=%u", from_kuid(&init_user_ns, anonu));
+ if (!gid_eq(anong, make_kgid(&init_user_ns, (gid_t)-2)) &&
+ !gid_eq(anong, make_kgid(&init_user_ns, 0x10000-2)))
+ seq_printf(m, ",anongid=%u", from_kgid(&init_user_ns, anong));
if (fsloc && fsloc->locations_count > 0) {
char *loctype = (fsloc->migrated) ? "refer" : "replicas";
int i;
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index e761ee9..d620e7f 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -9,7 +9,7 @@
#include <linux/debugfs.h>
#include <linux/module.h>
#include <linux/nsproxy.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <asm/uaccess.h>
#include "state.h"
@@ -101,7 +101,7 @@
loff_t pos = *ppos;
if (!pos)
- nfsd_inject_get(file->f_dentry->d_inode->i_private, &val);
+ nfsd_inject_get(file_inode(file)->i_private, &val);
size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
if (pos < 0)
@@ -133,10 +133,10 @@
size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
if (size > 0)
- nfsd_inject_set_client(file->f_dentry->d_inode->i_private, &sa, size);
+ nfsd_inject_set_client(file_inode(file)->i_private, &sa, size);
else {
val = simple_strtoll(write_buf, NULL, 0);
- nfsd_inject_set(file->f_dentry->d_inode->i_private, val);
+ nfsd_inject_set(file_inode(file)->i_private, val);
}
return len; /* on success, claim we got the whole input */
}
diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h
index 9d513ef..bf95f6b 100644
--- a/fs/nfsd/idmap.h
+++ b/fs/nfsd/idmap.h
@@ -54,9 +54,9 @@
}
#endif
-__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, __u32 *);
-__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, __u32 *);
-int nfsd_map_uid_to_name(struct svc_rqst *, __u32, char *);
-int nfsd_map_gid_to_name(struct svc_rqst *, __u32, char *);
+__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
+__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
+int nfsd_map_uid_to_name(struct svc_rqst *, kuid_t, char *);
+int nfsd_map_gid_to_name(struct svc_rqst *, kgid_t, char *);
#endif /* LINUX_NFSD_IDMAP_H */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 9170861..95d76dc 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -45,6 +45,10 @@
RETURN_STATUS(nfserr_inval);
resp->mask = argp->mask;
+ nfserr = fh_getattr(fh, &resp->stat);
+ if (nfserr)
+ goto fail;
+
if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
acl = nfsd_get_posix_acl(fh, ACL_TYPE_ACCESS);
if (IS_ERR(acl)) {
@@ -115,6 +119,9 @@
nfserr = nfserrno( nfsd_set_posix_acl(
fh, ACL_TYPE_DEFAULT, argp->acl_default) );
}
+ if (!nfserr) {
+ nfserr = fh_getattr(fh, &resp->stat);
+ }
/* argp->acl_{access,default} may have been allocated in
nfssvc_decode_setaclargs. */
@@ -129,10 +136,15 @@
static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
struct nfsd_fhandle *argp, struct nfsd_attrstat *resp)
{
+ __be32 nfserr;
dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh));
fh_copy(&resp->fh, &argp->fh);
- return fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+ nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP);
+ if (nfserr)
+ return nfserr;
+ nfserr = fh_getattr(&resp->fh, &resp->stat);
+ return nfserr;
}
/*
@@ -150,6 +162,9 @@
fh_copy(&resp->fh, &argp->fh);
resp->access = argp->access;
nfserr = nfsd_access(rqstp, &resp->fh, &resp->access, NULL);
+ if (nfserr)
+ return nfserr;
+ nfserr = fh_getattr(&resp->fh, &resp->stat);
return nfserr;
}
@@ -243,7 +258,7 @@
return 0;
inode = dentry->d_inode;
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh);
+ p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
*p++ = htonl(resp->mask);
if (!xdr_ressize_check(rqstp, p))
return 0;
@@ -274,7 +289,7 @@
static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd_attrstat *resp)
{
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh);
+ p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
return xdr_ressize_check(rqstp, p);
}
@@ -282,7 +297,7 @@
static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_accessres *resp)
{
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh);
+ p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
*p++ = htonl(resp->access);
return xdr_ressize_check(rqstp, p);
}
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 1fc02df..4012899 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -43,7 +43,6 @@
nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp,
struct nfsd3_attrstat *resp)
{
- int err;
__be32 nfserr;
dprintk("nfsd: GETATTR(3) %s\n",
@@ -55,9 +54,7 @@
if (nfserr)
RETURN_STATUS(nfserr);
- err = vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry, &resp->stat);
- nfserr = nfserrno(err);
+ nfserr = fh_getattr(&resp->fh, &resp->stat);
RETURN_STATUS(nfserr);
}
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 324c0ba..14d9ecb 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -11,6 +11,7 @@
#include "xdr3.h"
#include "auth.h"
#include "netns.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
@@ -105,12 +106,14 @@
iap->ia_mode = ntohl(*p++);
}
if (*p++) {
- iap->ia_valid |= ATTR_UID;
- iap->ia_uid = ntohl(*p++);
+ iap->ia_uid = make_kuid(&init_user_ns, ntohl(*p++));
+ if (uid_valid(iap->ia_uid))
+ iap->ia_valid |= ATTR_UID;
}
if (*p++) {
- iap->ia_valid |= ATTR_GID;
- iap->ia_gid = ntohl(*p++);
+ iap->ia_gid = make_kgid(&init_user_ns, ntohl(*p++));
+ if (gid_valid(iap->ia_gid))
+ iap->ia_valid |= ATTR_GID;
}
if (*p++) {
u64 newsize;
@@ -167,8 +170,8 @@
*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
*p++ = htonl((u32) stat->mode);
*p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) nfsd_ruid(rqstp, stat->uid));
- *p++ = htonl((u32) nfsd_rgid(rqstp, stat->gid));
+ *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
+ *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) {
p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN);
} else {
@@ -204,10 +207,10 @@
{
struct dentry *dentry = fhp->fh_dentry;
if (dentry && dentry->d_inode) {
- int err;
+ __be32 err;
struct kstat stat;
- err = vfs_getattr(fhp->fh_export->ex_path.mnt, dentry, &stat);
+ err = fh_getattr(fhp, &stat);
if (!err) {
*p++ = xdr_one; /* attributes follow */
lease_get_mtime(dentry->d_inode, &stat.mtime);
@@ -254,13 +257,12 @@
*/
void fill_post_wcc(struct svc_fh *fhp)
{
- int err;
+ __be32 err;
if (fhp->fh_post_saved)
printk("nfsd: inode locked twice during operation.\n");
- err = vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry,
- &fhp->fh_post_attr);
+ err = fh_getattr(fhp, &fhp->fh_post_attr);
fhp->fh_post_change = fhp->fh_dentry->d_inode->i_version;
if (err) {
fhp->fh_post_saved = 0;
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 9c51aff..8a50b3c 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -264,7 +264,7 @@
ace->flag = eflag;
ace->access_mask = deny_mask_from_posix(deny, flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_uid = pa->e_uid;
ace++;
acl->naces++;
}
@@ -273,7 +273,7 @@
ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_uid = pa->e_uid;
ace++;
acl->naces++;
pa++;
@@ -300,7 +300,7 @@
ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_gid = pa->e_gid;
ace++;
acl->naces++;
pa++;
@@ -329,7 +329,7 @@
ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
ace->access_mask = deny_mask_from_posix(deny, flags);
ace->whotype = NFS4_ACL_WHO_NAMED;
- ace->who = pa->e_id;
+ ace->who_gid = pa->e_gid;
ace++;
acl->naces++;
}
@@ -345,6 +345,18 @@
acl->naces++;
}
+static bool
+pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2)
+{
+ if (pace1->e_tag != pace2->e_tag)
+ return pace1->e_tag > pace2->e_tag;
+ if (pace1->e_tag == ACL_USER)
+ return uid_gt(pace1->e_uid, pace2->e_uid);
+ if (pace1->e_tag == ACL_GROUP)
+ return gid_gt(pace1->e_gid, pace2->e_gid);
+ return false;
+}
+
static void
sort_pacl_range(struct posix_acl *pacl, int start, int end) {
int sorted = 0, i;
@@ -355,8 +367,8 @@
while (!sorted) {
sorted = 1;
for (i = start; i < end; i++) {
- if (pacl->a_entries[i].e_id
- > pacl->a_entries[i+1].e_id) {
+ if (pace_gt(&pacl->a_entries[i],
+ &pacl->a_entries[i+1])) {
sorted = 0;
tmp = pacl->a_entries[i];
pacl->a_entries[i] = pacl->a_entries[i+1];
@@ -398,7 +410,10 @@
};
struct posix_user_ace_state {
- uid_t uid;
+ union {
+ kuid_t uid;
+ kgid_t gid;
+ };
struct posix_ace_state perms;
};
@@ -521,7 +536,6 @@
if (error)
goto out_err;
low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
for (i=0; i < state->users->n; i++) {
pace++;
@@ -531,7 +545,7 @@
goto out_err;
low_mode_from_nfs4(state->users->aces[i].perms.allow,
&pace->e_perm, flags);
- pace->e_id = state->users->aces[i].uid;
+ pace->e_uid = state->users->aces[i].uid;
add_to_mask(state, &state->users->aces[i].perms);
}
@@ -541,7 +555,6 @@
if (error)
goto out_err;
low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
add_to_mask(state, &state->group);
for (i=0; i < state->groups->n; i++) {
@@ -552,14 +565,13 @@
goto out_err;
low_mode_from_nfs4(state->groups->aces[i].perms.allow,
&pace->e_perm, flags);
- pace->e_id = state->groups->aces[i].uid;
+ pace->e_gid = state->groups->aces[i].gid;
add_to_mask(state, &state->groups->aces[i].perms);
}
pace++;
pace->e_tag = ACL_MASK;
low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
pace++;
pace->e_tag = ACL_OTHER;
@@ -567,7 +579,6 @@
if (error)
goto out_err;
low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags);
- pace->e_id = ACL_UNDEFINED_ID;
return pacl;
out_err:
@@ -587,12 +598,13 @@
astate->deny |= mask & ~astate->allow;
}
-static int find_uid(struct posix_acl_state *state, struct posix_ace_state_array *a, uid_t uid)
+static int find_uid(struct posix_acl_state *state, kuid_t uid)
{
+ struct posix_ace_state_array *a = state->users;
int i;
for (i = 0; i < a->n; i++)
- if (a->aces[i].uid == uid)
+ if (uid_eq(a->aces[i].uid, uid))
return i;
/* Not found: */
a->n++;
@@ -603,6 +615,23 @@
return i;
}
+static int find_gid(struct posix_acl_state *state, kgid_t gid)
+{
+ struct posix_ace_state_array *a = state->groups;
+ int i;
+
+ for (i = 0; i < a->n; i++)
+ if (gid_eq(a->aces[i].gid, gid))
+ return i;
+ /* Not found: */
+ a->n++;
+ a->aces[i].gid = gid;
+ a->aces[i].perms.allow = state->everyone.allow;
+ a->aces[i].perms.deny = state->everyone.deny;
+
+ return i;
+}
+
static void deny_bits_array(struct posix_ace_state_array *a, u32 mask)
{
int i;
@@ -636,7 +665,7 @@
}
break;
case ACL_USER:
- i = find_uid(state, state->users, ace->who);
+ i = find_uid(state, ace->who_uid);
if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
allow_bits(&state->users->aces[i].perms, mask);
} else {
@@ -658,7 +687,7 @@
}
break;
case ACL_GROUP:
- i = find_uid(state, state->groups, ace->who);
+ i = find_gid(state, ace->who_gid);
if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
allow_bits(&state->groups->aces[i].perms, mask);
} else {
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index a1f10c0..4832fd8 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -65,7 +65,7 @@
struct ent {
struct cache_head h;
int type; /* User / Group */
- uid_t id;
+ u32 id;
char name[IDMAP_NAMESZ];
char authname[IDMAP_NAMESZ];
};
@@ -140,12 +140,6 @@
}
static int
-idtoname_upcall(struct cache_detail *cd, struct cache_head *ch)
-{
- return sunrpc_cache_pipe_upcall(cd, ch, idtoname_request);
-}
-
-static int
idtoname_match(struct cache_head *ca, struct cache_head *cb)
{
struct ent *a = container_of(ca, struct ent, h);
@@ -192,7 +186,7 @@
.hash_size = ENT_HASHMAX,
.name = "nfs4.idtoname",
.cache_put = ent_put,
- .cache_upcall = idtoname_upcall,
+ .cache_request = idtoname_request,
.cache_parse = idtoname_parse,
.cache_show = idtoname_show,
.warn_no_listener = warn_no_idmapd,
@@ -321,12 +315,6 @@
}
static int
-nametoid_upcall(struct cache_detail *cd, struct cache_head *ch)
-{
- return sunrpc_cache_pipe_upcall(cd, ch, nametoid_request);
-}
-
-static int
nametoid_match(struct cache_head *ca, struct cache_head *cb)
{
struct ent *a = container_of(ca, struct ent, h);
@@ -365,7 +353,7 @@
.hash_size = ENT_HASHMAX,
.name = "nfs4.nametoid",
.cache_put = ent_put,
- .cache_upcall = nametoid_upcall,
+ .cache_request = nametoid_request,
.cache_parse = nametoid_parse,
.cache_show = nametoid_show,
.warn_no_listener = warn_no_idmapd,
@@ -540,7 +528,7 @@
static __be32
idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
- uid_t *id)
+ u32 *id)
{
struct ent *item, key = {
.type = type,
@@ -564,7 +552,7 @@
}
static int
-idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
+idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, char *name)
{
struct ent *item, key = {
.id = id,
@@ -587,7 +575,7 @@
}
static bool
-numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
{
int ret;
char buf[11];
@@ -603,7 +591,7 @@
}
static __be32
-do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id)
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
{
if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
if (numeric_name_to_id(rqstp, type, name, namelen, id))
@@ -616,7 +604,7 @@
}
static int
-do_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name)
+do_id_to_name(struct svc_rqst *rqstp, int type, u32 id, char *name)
{
if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
return sprintf(name, "%u", id);
@@ -625,26 +613,40 @@
__be32
nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
- __u32 *id)
+ kuid_t *uid)
{
- return do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, id);
+ __be32 status;
+ u32 id = -1;
+ status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id);
+ *uid = make_kuid(&init_user_ns, id);
+ if (!uid_valid(*uid))
+ status = nfserr_badowner;
+ return status;
}
__be32
nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
- __u32 *id)
+ kgid_t *gid)
{
- return do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, id);
+ __be32 status;
+ u32 id = -1;
+ status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id);
+ *gid = make_kgid(&init_user_ns, id);
+ if (!gid_valid(*gid))
+ status = nfserr_badowner;
+ return status;
}
int
-nfsd_map_uid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
+nfsd_map_uid_to_name(struct svc_rqst *rqstp, kuid_t uid, char *name)
{
+ u32 id = from_kuid(&init_user_ns, uid);
return do_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
}
int
-nfsd_map_gid_to_name(struct svc_rqst *rqstp, __u32 id, char *name)
+nfsd_map_gid_to_name(struct svc_rqst *rqstp, kgid_t gid, char *name)
{
+ u32 id = from_kgid(&init_user_ns, gid);
return do_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9d1c5db..ae73175 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -993,14 +993,15 @@
if (!buf)
return nfserr_jukebox;
+ p = buf;
status = nfsd4_encode_fattr(&cstate->current_fh,
cstate->current_fh.fh_export,
- cstate->current_fh.fh_dentry, buf,
- &count, verify->ve_bmval,
+ cstate->current_fh.fh_dentry, &p,
+ count, verify->ve_bmval,
rqstp, 0);
/* this means that nfsd4_encode_fattr() ran out of space */
- if (status == nfserr_resource && count == 0)
+ if (status == nfserr_resource)
status = nfserr_not_same;
if (status)
goto out_kfree;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index ba6fdd4..899ca26 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -73,8 +73,8 @@
if (!new)
return -ENOMEM;
- new->fsuid = 0;
- new->fsgid = 0;
+ new->fsuid = GLOBAL_ROOT_UID;
+ new->fsgid = GLOBAL_ROOT_GID;
*original_creds = override_creds(new);
put_cred(new);
return 0;
@@ -1185,6 +1185,12 @@
static int
nfsd4_umh_cltrack_init(struct net __attribute__((unused)) *net)
{
+ /* XXX: The usermode helper s not working in container yet. */
+ if (net != &init_net) {
+ WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
+ "tracking in a container!\n");
+ return -EINVAL;
+ }
return nfsd4_umh_cltrack_upcall("init", NULL, NULL);
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ac8ed96..2e27430 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -40,7 +40,7 @@
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/sunrpc/svcauth_gss.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include "xdr4.h"
#include "vfs.h"
#include "current_stateid.h"
@@ -151,7 +151,7 @@
}
static int num_delegations;
-unsigned int max_delegations;
+unsigned long max_delegations;
/*
* Open owner state (share locks)
@@ -230,21 +230,28 @@
__nfs4_file_put_access(fp, oflag);
}
-static inline int get_new_stid(struct nfs4_stid *stid)
+static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
+kmem_cache *slab)
{
+ struct idr *stateids = &cl->cl_stateids;
static int min_stateid = 0;
- struct idr *stateids = &stid->sc_client->cl_stateids;
- int new_stid;
- int error;
+ struct nfs4_stid *stid;
+ int new_id;
- error = idr_get_new_above(stateids, stid, min_stateid, &new_stid);
- /*
- * Note: the necessary preallocation was done in
- * nfs4_alloc_stateid(). The idr code caps the number of
- * preallocations that can exist at a time, but the state lock
- * prevents anyone from using ours before we get here:
- */
- WARN_ON_ONCE(error);
+ stid = kmem_cache_alloc(slab, GFP_KERNEL);
+ if (!stid)
+ return NULL;
+
+ new_id = idr_alloc(stateids, stid, min_stateid, 0, GFP_KERNEL);
+ if (new_id < 0)
+ goto out_free;
+ stid->sc_client = cl;
+ stid->sc_type = 0;
+ stid->sc_stateid.si_opaque.so_id = new_id;
+ stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
+ /* Will be incremented before return to client: */
+ stid->sc_stateid.si_generation = 0;
+
/*
* It shouldn't be a problem to reuse an opaque stateid value.
* I don't think it is for 4.1. But with 4.0 I worry that, for
@@ -255,39 +262,13 @@
* "increase" (mod INT_MAX):
*/
- min_stateid = new_stid+1;
+ min_stateid = new_id+1;
if (min_stateid == INT_MAX)
min_stateid = 0;
- return new_stid;
-}
-
-static void init_stid(struct nfs4_stid *stid, struct nfs4_client *cl, unsigned char type)
-{
- stateid_t *s = &stid->sc_stateid;
- int new_id;
-
- stid->sc_type = type;
- stid->sc_client = cl;
- s->si_opaque.so_clid = cl->cl_clientid;
- new_id = get_new_stid(stid);
- s->si_opaque.so_id = (u32)new_id;
- /* Will be incremented before return to client: */
- s->si_generation = 0;
-}
-
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab)
-{
- struct idr *stateids = &cl->cl_stateids;
-
- if (!idr_pre_get(stateids, GFP_KERNEL))
- return NULL;
- /*
- * Note: if we fail here (or any time between now and the time
- * we actually get the new idr), we won't need to undo the idr
- * preallocation, since the idr code caps the number of
- * preallocated entries.
- */
- return kmem_cache_alloc(slab, GFP_KERNEL);
+ return stid;
+out_free:
+ kfree(stid);
+ return NULL;
}
static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
@@ -316,7 +297,7 @@
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
return dp;
- init_stid(&dp->dl_stid, clp, NFS4_DELEG_STID);
+ dp->dl_stid.sc_type = NFS4_DELEG_STID;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -337,13 +318,21 @@
return dp;
}
+static void free_stid(struct nfs4_stid *s, struct kmem_cache *slab)
+{
+ struct idr *stateids = &s->sc_client->cl_stateids;
+
+ idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ kmem_cache_free(slab, s);
+}
+
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
- kmem_cache_free(deleg_slab, dp);
+ free_stid(&dp->dl_stid, deleg_slab);
num_delegations--;
}
}
@@ -360,9 +349,7 @@
static void unhash_stid(struct nfs4_stid *s)
{
- struct idr *stateids = &s->sc_client->cl_stateids;
-
- idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ s->sc_type = 0;
}
/* Called under the state lock. */
@@ -519,7 +506,7 @@
static void free_generic_stateid(struct nfs4_ol_stateid *stp)
{
- kmem_cache_free(stateid_slab, stp);
+ free_stid(&stp->st_stid, stateid_slab);
}
static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -700,8 +687,8 @@
num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION);
spin_lock(&nfsd_drc_lock);
- avail = min_t(int, NFSD_MAX_MEM_PER_SESSION,
- nfsd_drc_max_mem - nfsd_drc_mem_used);
+ avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION,
+ nfsd_drc_max_mem - nfsd_drc_mem_used);
num = min_t(int, num, avail / slotsize);
nfsd_drc_mem_used += num * slotsize;
spin_unlock(&nfsd_drc_lock);
@@ -905,7 +892,7 @@
new = __alloc_session(slotsize, numslots);
if (!new) {
- nfsd4_put_drc_mem(slotsize, fchan->maxreqs);
+ nfsd4_put_drc_mem(slotsize, numslots);
return NULL;
}
init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize, nn);
@@ -1048,7 +1035,7 @@
static inline void
free_client(struct nfs4_client *clp)
{
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id);
lockdep_assert_held(&nn->client_lock);
while (!list_empty(&clp->cl_sessions)) {
@@ -1060,6 +1047,7 @@
}
free_svc_cred(&clp->cl_cred);
kfree(clp->cl_name.data);
+ idr_destroy(&clp->cl_stateids);
kfree(clp);
}
@@ -1202,7 +1190,7 @@
if (g1->ngroups != g2->ngroups)
return false;
for (i=0; i<g1->ngroups; i++)
- if (GROUP_AT(g1, i) != GROUP_AT(g2, i))
+ if (!gid_eq(GROUP_AT(g1, i), GROUP_AT(g2, i)))
return false;
return true;
}
@@ -1227,8 +1215,8 @@
same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
{
if ((is_gss_cred(cr1) != is_gss_cred(cr2))
- || (cr1->cr_uid != cr2->cr_uid)
- || (cr1->cr_gid != cr2->cr_gid)
+ || (!uid_eq(cr1->cr_uid, cr2->cr_uid))
+ || (!gid_eq(cr1->cr_gid, cr2->cr_gid))
|| !groups_equal(cr1->cr_group_info, cr2->cr_group_info))
return false;
if (cr1->cr_principal == cr2->cr_principal)
@@ -1258,7 +1246,12 @@
static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
{
- return idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ struct nfs4_stid *ret;
+
+ ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ if (!ret || !ret->sc_type)
+ return NULL;
+ return ret;
}
static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
@@ -1844,11 +1837,12 @@
/* cache solo and embedded create sessions under the state lock */
nfsd4_cache_create_session(cr_ses, cs_slot, status);
-out:
nfs4_unlock_state();
+out:
dprintk("%s returns %d\n", __func__, ntohl(status));
return status;
out_free_conn:
+ nfs4_unlock_state();
free_conn(conn);
out_free_session:
__free_session(new);
@@ -2443,9 +2437,8 @@
static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
struct nfs4_openowner *oo = open->op_openowner;
- struct nfs4_client *clp = oo->oo_owner.so_client;
- init_stid(&stp->st_stid, clp, NFS4_OPEN_STID);
+ stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_lockowners);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
@@ -4031,7 +4024,7 @@
stp = nfs4_alloc_stateid(clp);
if (stp == NULL)
return NULL;
- init_stid(&stp->st_stid, clp, NFS4_LOCK_STID);
+ stp->st_stid.sc_type = NFS4_LOCK_STID;
list_add(&stp->st_perfile, &fp->fi_stateids);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
stp->st_stateowner = &lo->lo_owner;
@@ -4913,16 +4906,6 @@
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
- /*
- * FIXME: For now, we hang most of the pernet global stuff off of
- * init_net until nfsd is fully containerized. Eventually, we'll
- * need to pass a net pointer into this function, take a reference
- * to that instead and then do most of the rest of this on a per-net
- * basis.
- */
- if (net != &init_net)
- return -EINVAL;
-
ret = nfs4_state_create_net(net);
if (ret)
return ret;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0dc1158..0116886 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -293,13 +293,13 @@
ace->whotype = nfs4_acl_get_whotype(buf, dummy32);
status = nfs_ok;
if (ace->whotype != NFS4_ACL_WHO_NAMED)
- ace->who = 0;
+ ;
else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
status = nfsd_map_name_to_gid(argp->rqstp,
- buf, dummy32, &ace->who);
+ buf, dummy32, &ace->who_gid);
else
status = nfsd_map_name_to_uid(argp->rqstp,
- buf, dummy32, &ace->who);
+ buf, dummy32, &ace->who_uid);
if (status)
return status;
}
@@ -464,9 +464,16 @@
READ32(dummy);
READ_BUF(dummy * 4);
if (cbs->flavor == (u32)(-1)) {
- cbs->uid = uid;
- cbs->gid = gid;
- cbs->flavor = RPC_AUTH_UNIX;
+ kuid_t kuid = make_kuid(&init_user_ns, uid);
+ kgid_t kgid = make_kgid(&init_user_ns, gid);
+ if (uid_valid(kuid) && gid_valid(kgid)) {
+ cbs->uid = kuid;
+ cbs->gid = kgid;
+ cbs->flavor = RPC_AUTH_UNIX;
+ } else {
+ dprintk("RPC_AUTH_UNIX with invalid"
+ "uid or gid ignoring!\n");
+ }
}
break;
case RPC_AUTH_GSS:
@@ -1926,7 +1933,7 @@
}
static __be32
-nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
+nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, kuid_t uid, kgid_t gid,
__be32 **p, int *buflen)
{
int status;
@@ -1935,10 +1942,10 @@
return nfserr_resource;
if (whotype != NFS4_ACL_WHO_NAMED)
status = nfs4_acl_write_who(whotype, (u8 *)(*p + 1));
- else if (group)
- status = nfsd_map_gid_to_name(rqstp, id, (u8 *)(*p + 1));
+ else if (gid_valid(gid))
+ status = nfsd_map_gid_to_name(rqstp, gid, (u8 *)(*p + 1));
else
- status = nfsd_map_uid_to_name(rqstp, id, (u8 *)(*p + 1));
+ status = nfsd_map_uid_to_name(rqstp, uid, (u8 *)(*p + 1));
if (status < 0)
return nfserrno(status);
*p = xdr_encode_opaque(*p, NULL, status);
@@ -1948,22 +1955,33 @@
}
static inline __be32
-nfsd4_encode_user(struct svc_rqst *rqstp, uid_t uid, __be32 **p, int *buflen)
+nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t user, __be32 **p, int *buflen)
{
- return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, uid, 0, p, buflen);
+ return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, user, INVALID_GID,
+ p, buflen);
}
static inline __be32
-nfsd4_encode_group(struct svc_rqst *rqstp, uid_t gid, __be32 **p, int *buflen)
+nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t group, __be32 **p, int *buflen)
{
- return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, gid, 1, p, buflen);
+ return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, INVALID_UID, group,
+ p, buflen);
}
static inline __be32
-nfsd4_encode_aclname(struct svc_rqst *rqstp, int whotype, uid_t id, int group,
+nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
__be32 **p, int *buflen)
{
- return nfsd4_encode_name(rqstp, whotype, id, group, p, buflen);
+ kuid_t uid = INVALID_UID;
+ kgid_t gid = INVALID_GID;
+
+ if (ace->whotype == NFS4_ACL_WHO_NAMED) {
+ if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
+ gid = ace->who_gid;
+ else
+ uid = ace->who_uid;
+ }
+ return nfsd4_encode_name(rqstp, ace->whotype, uid, gid, p, buflen);
}
#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
@@ -1997,7 +2015,7 @@
if (path.dentry != path.mnt->mnt_root)
break;
}
- err = vfs_getattr(path.mnt, path.dentry, stat);
+ err = vfs_getattr(&path, stat);
path_put(&path);
return err;
}
@@ -2006,12 +2024,11 @@
* Note: @fhp can be NULL; in this case, we might have to compose the filehandle
* ourselves.
*
- * @countp is the buffer size in _words_; upon successful return this becomes
- * replaced with the number of words written.
+ * countp is the buffer size in _words_
*/
__be32
nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 *buffer, int *countp, u32 *bmval,
+ struct dentry *dentry, __be32 **buffer, int count, u32 *bmval,
struct svc_rqst *rqstp, int ignore_crossmnt)
{
u32 bmval0 = bmval[0];
@@ -2020,12 +2037,12 @@
struct kstat stat;
struct svc_fh tempfh;
struct kstatfs statfs;
- int buflen = *countp << 2;
+ int buflen = count << 2;
__be32 *attrlenp;
u32 dummy;
u64 dummy64;
u32 rdattr_err = 0;
- __be32 *p = buffer;
+ __be32 *p = *buffer;
__be32 status;
int err;
int aclsupport = 0;
@@ -2050,7 +2067,7 @@
goto out;
}
- err = vfs_getattr(exp->ex_path.mnt, dentry, &stat);
+ err = vfs_getattr(&path, &stat);
if (err)
goto out_nfserr;
if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
@@ -2224,9 +2241,7 @@
WRITE32(ace->type);
WRITE32(ace->flag);
WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL);
- status = nfsd4_encode_aclname(rqstp, ace->whotype,
- ace->who, ace->flag & NFS4_ACE_IDENTIFIER_GROUP,
- &p, &buflen);
+ status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen);
if (status == nfserr_resource)
goto out_resource;
if (status)
@@ -2431,7 +2446,7 @@
}
*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
- *countp = p - buffer;
+ *buffer = p;
status = nfs_ok;
out:
@@ -2443,7 +2458,6 @@
status = nfserrno(err);
goto out;
out_resource:
- *countp = 0;
status = nfserr_resource;
goto out;
out_serverfault:
@@ -2462,7 +2476,7 @@
static __be32
nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
- const char *name, int namlen, __be32 *p, int *buflen)
+ const char *name, int namlen, __be32 **p, int buflen)
{
struct svc_export *exp = cd->rd_fhp->fh_export;
struct dentry *dentry;
@@ -2568,10 +2582,9 @@
p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */
p = xdr_encode_array(p, name, namlen); /* name length & name */
- nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, p, &buflen);
+ nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, &p, buflen);
switch (nfserr) {
case nfs_ok:
- p += buflen;
break;
case nfserr_resource:
nfserr = nfserr_toosmall;
@@ -2698,10 +2711,8 @@
buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2);
nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry,
- resp->p, &buflen, getattr->ga_bmval,
+ &resp->p, buflen, getattr->ga_bmval,
resp->rqstp, 0);
- if (!nfserr)
- resp->p += buflen;
return nfserr;
}
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 2cbac34..ca05f6d 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -9,22 +9,22 @@
*/
#include <linux/slab.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/highmem.h>
+#include <net/checksum.h>
#include "nfsd.h"
#include "cache.h"
-/* Size of reply cache. Common values are:
- * 4.3BSD: 128
- * 4.4BSD: 256
- * Solaris2: 1024
- * DEC Unix: 512-4096
- */
-#define CACHESIZE 1024
+#define NFSDDBG_FACILITY NFSDDBG_REPCACHE
+
#define HASHSIZE 64
static struct hlist_head * cache_hash;
static struct list_head lru_head;
-static int cache_disabled = 1;
+static struct kmem_cache *drc_slab;
+static unsigned int num_drc_entries;
+static unsigned int max_drc_entries;
/*
* Calculate the hash index from an XID.
@@ -37,6 +37,14 @@
}
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
+static void cache_cleaner_func(struct work_struct *unused);
+static int nfsd_reply_cache_shrink(struct shrinker *shrink,
+ struct shrink_control *sc);
+
+struct shrinker nfsd_reply_cache_shrinker = {
+ .shrink = nfsd_reply_cache_shrink,
+ .seeks = 1,
+};
/*
* locking for the reply cache:
@@ -44,30 +52,87 @@
* Otherwise, it when accessing _prev or _next, the lock must be held.
*/
static DEFINE_SPINLOCK(cache_lock);
+static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
+
+/*
+ * Put a cap on the size of the DRC based on the amount of available
+ * low memory in the machine.
+ *
+ * 64MB: 8192
+ * 128MB: 11585
+ * 256MB: 16384
+ * 512MB: 23170
+ * 1GB: 32768
+ * 2GB: 46340
+ * 4GB: 65536
+ * 8GB: 92681
+ * 16GB: 131072
+ *
+ * ...with a hard cap of 256k entries. In the worst case, each entry will be
+ * ~1k, so the above numbers should give a rough max of the amount of memory
+ * used in k.
+ */
+static unsigned int
+nfsd_cache_size_limit(void)
+{
+ unsigned int limit;
+ unsigned long low_pages = totalram_pages - totalhigh_pages;
+
+ limit = (16 * int_sqrt(low_pages)) << (PAGE_SHIFT-10);
+ return min_t(unsigned int, limit, 256*1024);
+}
+
+static struct svc_cacherep *
+nfsd_reply_cache_alloc(void)
+{
+ struct svc_cacherep *rp;
+
+ rp = kmem_cache_alloc(drc_slab, GFP_KERNEL);
+ if (rp) {
+ rp->c_state = RC_UNUSED;
+ rp->c_type = RC_NOCACHE;
+ INIT_LIST_HEAD(&rp->c_lru);
+ INIT_HLIST_NODE(&rp->c_hash);
+ }
+ return rp;
+}
+
+static void
+nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
+{
+ if (rp->c_type == RC_REPLBUFF)
+ kfree(rp->c_replvec.iov_base);
+ if (!hlist_unhashed(&rp->c_hash))
+ hlist_del(&rp->c_hash);
+ list_del(&rp->c_lru);
+ --num_drc_entries;
+ kmem_cache_free(drc_slab, rp);
+}
+
+static void
+nfsd_reply_cache_free(struct svc_cacherep *rp)
+{
+ spin_lock(&cache_lock);
+ nfsd_reply_cache_free_locked(rp);
+ spin_unlock(&cache_lock);
+}
int nfsd_reply_cache_init(void)
{
- struct svc_cacherep *rp;
- int i;
-
INIT_LIST_HEAD(&lru_head);
- i = CACHESIZE;
- while (i) {
- rp = kmalloc(sizeof(*rp), GFP_KERNEL);
- if (!rp)
- goto out_nomem;
- list_add(&rp->c_lru, &lru_head);
- rp->c_state = RC_UNUSED;
- rp->c_type = RC_NOCACHE;
- INIT_HLIST_NODE(&rp->c_hash);
- i--;
- }
+ max_drc_entries = nfsd_cache_size_limit();
+ num_drc_entries = 0;
- cache_hash = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
+ register_shrinker(&nfsd_reply_cache_shrinker);
+ drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
+ 0, 0, NULL);
+ if (!drc_slab)
+ goto out_nomem;
+
+ cache_hash = kcalloc(HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
if (!cache_hash)
goto out_nomem;
- cache_disabled = 0;
return 0;
out_nomem:
printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
@@ -79,27 +144,33 @@
{
struct svc_cacherep *rp;
+ unregister_shrinker(&nfsd_reply_cache_shrinker);
+ cancel_delayed_work_sync(&cache_cleaner);
+
while (!list_empty(&lru_head)) {
rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
- if (rp->c_state == RC_DONE && rp->c_type == RC_REPLBUFF)
- kfree(rp->c_replvec.iov_base);
- list_del(&rp->c_lru);
- kfree(rp);
+ nfsd_reply_cache_free_locked(rp);
}
- cache_disabled = 1;
-
kfree (cache_hash);
cache_hash = NULL;
+
+ if (drc_slab) {
+ kmem_cache_destroy(drc_slab);
+ drc_slab = NULL;
+ }
}
/*
- * Move cache entry to end of LRU list
+ * Move cache entry to end of LRU list, and queue the cleaner to run if it's
+ * not already scheduled.
*/
static void
lru_put_end(struct svc_cacherep *rp)
{
+ rp->c_timestamp = jiffies;
list_move_tail(&rp->c_lru, &lru_head);
+ schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
}
/*
@@ -112,83 +183,214 @@
hlist_add_head(&rp->c_hash, cache_hash + request_hash(rp->c_xid));
}
-/*
- * Try to find an entry matching the current call in the cache. When none
- * is found, we grab the oldest unlocked entry off the LRU list.
- * Note that no operation within the loop may sleep.
- */
-int
-nfsd_cache_lookup(struct svc_rqst *rqstp)
+static inline bool
+nfsd_cache_entry_expired(struct svc_cacherep *rp)
{
- struct hlist_node *hn;
- struct hlist_head *rh;
+ return rp->c_state != RC_INPROG &&
+ time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static void
+prune_cache_entries(void)
+{
+ struct svc_cacherep *rp, *tmp;
+
+ list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
+ if (!nfsd_cache_entry_expired(rp) &&
+ num_drc_entries <= max_drc_entries)
+ break;
+ nfsd_reply_cache_free_locked(rp);
+ }
+
+ /*
+ * Conditionally rearm the job. If we cleaned out the list, then
+ * cancel any pending run (since there won't be any work to do).
+ * Otherwise, we rearm the job or modify the existing one to run in
+ * RC_EXPIRE since we just ran the pruner.
+ */
+ if (list_empty(&lru_head))
+ cancel_delayed_work(&cache_cleaner);
+ else
+ mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+}
+
+static void
+cache_cleaner_func(struct work_struct *unused)
+{
+ spin_lock(&cache_lock);
+ prune_cache_entries();
+ spin_unlock(&cache_lock);
+}
+
+static int
+nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned int num;
+
+ spin_lock(&cache_lock);
+ if (sc->nr_to_scan)
+ prune_cache_entries();
+ num = num_drc_entries;
+ spin_unlock(&cache_lock);
+
+ return num;
+}
+
+/*
+ * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+ */
+static __wsum
+nfsd_cache_csum(struct svc_rqst *rqstp)
+{
+ int idx;
+ unsigned int base;
+ __wsum csum;
+ struct xdr_buf *buf = &rqstp->rq_arg;
+ const unsigned char *p = buf->head[0].iov_base;
+ size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
+ RC_CSUMLEN);
+ size_t len = min(buf->head[0].iov_len, csum_len);
+
+ /* rq_arg.head first */
+ csum = csum_partial(p, len, 0);
+ csum_len -= len;
+
+ /* Continue into page array */
+ idx = buf->page_base / PAGE_SIZE;
+ base = buf->page_base & ~PAGE_MASK;
+ while (csum_len) {
+ p = page_address(buf->pages[idx]) + base;
+ len = min_t(size_t, PAGE_SIZE - base, csum_len);
+ csum = csum_partial(p, len, csum);
+ csum_len -= len;
+ base = 0;
+ ++idx;
+ }
+ return csum;
+}
+
+/*
+ * Search the request hash for an entry that matches the given rqstp.
+ * Must be called with cache_lock held. Returns the found entry or
+ * NULL on failure.
+ */
+static struct svc_cacherep *
+nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
+{
struct svc_cacherep *rp;
+ struct hlist_head *rh;
__be32 xid = rqstp->rq_xid;
u32 proto = rqstp->rq_prot,
vers = rqstp->rq_vers,
proc = rqstp->rq_proc;
+
+ rh = &cache_hash[request_hash(xid)];
+ hlist_for_each_entry(rp, rh, c_hash) {
+ if (xid == rp->c_xid && proc == rp->c_proc &&
+ proto == rp->c_prot && vers == rp->c_vers &&
+ rqstp->rq_arg.len == rp->c_len && csum == rp->c_csum &&
+ rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) &&
+ rpc_get_port(svc_addr(rqstp)) == rpc_get_port((struct sockaddr *)&rp->c_addr))
+ return rp;
+ }
+ return NULL;
+}
+
+/*
+ * Try to find an entry matching the current call in the cache. When none
+ * is found, we try to grab the oldest expired entry off the LRU list. If
+ * a suitable one isn't there, then drop the cache_lock and allocate a
+ * new one, then search again in case one got inserted while this thread
+ * didn't hold the lock.
+ */
+int
+nfsd_cache_lookup(struct svc_rqst *rqstp)
+{
+ struct svc_cacherep *rp, *found;
+ __be32 xid = rqstp->rq_xid;
+ u32 proto = rqstp->rq_prot,
+ vers = rqstp->rq_vers,
+ proc = rqstp->rq_proc;
+ __wsum csum;
unsigned long age;
int type = rqstp->rq_cachetype;
int rtn;
rqstp->rq_cacherep = NULL;
- if (cache_disabled || type == RC_NOCACHE) {
+ if (type == RC_NOCACHE) {
nfsdstats.rcnocache++;
return RC_DOIT;
}
+ csum = nfsd_cache_csum(rqstp);
+
spin_lock(&cache_lock);
rtn = RC_DOIT;
- rh = &cache_hash[request_hash(xid)];
- hlist_for_each_entry(rp, hn, rh, c_hash) {
- if (rp->c_state != RC_UNUSED &&
- xid == rp->c_xid && proc == rp->c_proc &&
- proto == rp->c_prot && vers == rp->c_vers &&
- time_before(jiffies, rp->c_timestamp + 120*HZ) &&
- memcmp((char*)&rqstp->rq_addr, (char*)&rp->c_addr, sizeof(rp->c_addr))==0) {
- nfsdstats.rchits++;
- goto found_entry;
+ rp = nfsd_cache_search(rqstp, csum);
+ if (rp)
+ goto found_entry;
+
+ /* Try to use the first entry on the LRU */
+ if (!list_empty(&lru_head)) {
+ rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
+ if (nfsd_cache_entry_expired(rp) ||
+ num_drc_entries >= max_drc_entries) {
+ lru_put_end(rp);
+ prune_cache_entries();
+ goto setup_entry;
}
}
+
+ /* Drop the lock and allocate a new entry */
+ spin_unlock(&cache_lock);
+ rp = nfsd_reply_cache_alloc();
+ if (!rp) {
+ dprintk("nfsd: unable to allocate DRC entry!\n");
+ return RC_DOIT;
+ }
+ spin_lock(&cache_lock);
+ ++num_drc_entries;
+
+ /*
+ * Must search again just in case someone inserted one
+ * after we dropped the lock above.
+ */
+ found = nfsd_cache_search(rqstp, csum);
+ if (found) {
+ nfsd_reply_cache_free_locked(rp);
+ rp = found;
+ goto found_entry;
+ }
+
+ /*
+ * We're keeping the one we just allocated. Are we now over the
+ * limit? Prune one off the tip of the LRU in trade for the one we
+ * just allocated if so.
+ */
+ if (num_drc_entries >= max_drc_entries)
+ nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
+ struct svc_cacherep, c_lru));
+
+setup_entry:
nfsdstats.rcmisses++;
-
- /* This loop shouldn't take more than a few iterations normally */
- {
- int safe = 0;
- list_for_each_entry(rp, &lru_head, c_lru) {
- if (rp->c_state != RC_INPROG)
- break;
- if (safe++ > CACHESIZE) {
- printk("nfsd: loop in repcache LRU list\n");
- cache_disabled = 1;
- goto out;
- }
- }
- }
-
- /* All entries on the LRU are in-progress. This should not happen */
- if (&rp->c_lru == &lru_head) {
- static int complaints;
-
- printk(KERN_WARNING "nfsd: all repcache entries locked!\n");
- if (++complaints > 5) {
- printk(KERN_WARNING "nfsd: disabling repcache.\n");
- cache_disabled = 1;
- }
- goto out;
- }
-
rqstp->rq_cacherep = rp;
rp->c_state = RC_INPROG;
rp->c_xid = xid;
rp->c_proc = proc;
- memcpy(&rp->c_addr, svc_addr_in(rqstp), sizeof(rp->c_addr));
+ rpc_copy_addr((struct sockaddr *)&rp->c_addr, svc_addr(rqstp));
+ rpc_set_port((struct sockaddr *)&rp->c_addr, rpc_get_port(svc_addr(rqstp)));
rp->c_prot = proto;
rp->c_vers = vers;
- rp->c_timestamp = jiffies;
+ rp->c_len = rqstp->rq_arg.len;
+ rp->c_csum = csum;
hash_refile(rp);
+ lru_put_end(rp);
/* release any buffer */
if (rp->c_type == RC_REPLBUFF) {
@@ -201,9 +403,9 @@
return rtn;
found_entry:
+ nfsdstats.rchits++;
/* We found a matching entry which is either in progress or done. */
age = jiffies - rp->c_timestamp;
- rp->c_timestamp = jiffies;
lru_put_end(rp);
rtn = RC_DROPIT;
@@ -232,7 +434,7 @@
break;
default:
printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free_locked(rp);
}
goto out;
@@ -257,11 +459,11 @@
void
nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp = rqstp->rq_cacherep;
struct kvec *resv = &rqstp->rq_res.head[0], *cachv;
int len;
- if (!(rp = rqstp->rq_cacherep) || cache_disabled)
+ if (!rp)
return;
len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
@@ -269,7 +471,7 @@
/* Don't cache excessive amounts of data and XDR failures */
if (!statp || len > (256 >> 2)) {
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free(rp);
return;
}
@@ -283,21 +485,21 @@
cachv = &rp->c_replvec;
cachv->iov_base = kmalloc(len << 2, GFP_KERNEL);
if (!cachv->iov_base) {
- spin_lock(&cache_lock);
- rp->c_state = RC_UNUSED;
- spin_unlock(&cache_lock);
+ nfsd_reply_cache_free(rp);
return;
}
cachv->iov_len = len << 2;
memcpy(cachv->iov_base, statp, len << 2);
break;
+ case RC_NOCACHE:
+ nfsd_reply_cache_free(rp);
+ return;
}
spin_lock(&cache_lock);
lru_put_end(rp);
rp->c_secure = rqstp->rq_secure;
rp->c_type = cachetype;
rp->c_state = RC_DONE;
- rp->c_timestamp = jiffies;
spin_unlock(&cache_lock);
return;
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7493428..f33455b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -10,7 +10,7 @@
#include <linux/sunrpc/svcsock.h>
#include <linux/lockd/lockd.h>
-#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/gss_krb5_enctypes.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
@@ -85,7 +85,7 @@
static ssize_t nfsctl_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos)
{
- ino_t ino = file->f_path.dentry->d_inode->i_ino;
+ ino_t ino = file_inode(file)->i_ino;
char *data;
ssize_t rv;
@@ -125,11 +125,11 @@
.llseek = default_llseek,
};
-static int exports_open(struct inode *inode, struct file *file)
+static int exports_net_open(struct net *net, struct file *file)
{
int err;
struct seq_file *seq;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
err = seq_open(file, &nfs_exports_op);
if (err)
@@ -140,8 +140,26 @@
return 0;
}
-static const struct file_operations exports_operations = {
- .open = exports_open,
+static int exports_proc_open(struct inode *inode, struct file *file)
+{
+ return exports_net_open(current->nsproxy->net_ns, file);
+}
+
+static const struct file_operations exports_proc_operations = {
+ .open = exports_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+ .owner = THIS_MODULE,
+};
+
+static int exports_nfsd_open(struct inode *inode, struct file *file)
+{
+ return exports_net_open(inode->i_sb->s_fs_info, file);
+}
+
+static const struct file_operations exports_nfsd_operations = {
+ .open = exports_nfsd_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
@@ -220,6 +238,7 @@
struct sockaddr *sap = (struct sockaddr *)&address;
size_t salen = sizeof(address);
char *fo_path;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
/* sanity check */
if (size == 0)
@@ -232,7 +251,7 @@
if (qword_get(&buf, fo_path, size) < 0)
return -EINVAL;
- if (rpc_pton(&init_net, fo_path, size, sap, salen) == 0)
+ if (rpc_pton(net, fo_path, size, sap, salen) == 0)
return -EINVAL;
return nlmsvc_unlock_all_by_ip(sap);
@@ -317,6 +336,7 @@
int len;
struct auth_domain *dom;
struct knfsd_fh fh;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
if (size == 0)
return -EINVAL;
@@ -352,7 +372,7 @@
if (!dom)
return -ENOMEM;
- len = exp_rootfh(&init_net, dom, path, &fh, maxsize);
+ len = exp_rootfh(net, dom, path, &fh, maxsize);
auth_domain_put(dom);
if (len)
return len;
@@ -396,7 +416,7 @@
{
char *mesg = buf;
int rv;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
if (size > 0) {
int newthreads;
@@ -447,7 +467,7 @@
int len;
int npools;
int *nthreads;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
npools = nfsd_nrpools(net);
@@ -510,7 +530,7 @@
unsigned minor;
ssize_t tlen = 0;
char *sep;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size>0) {
@@ -534,7 +554,7 @@
else
num = simple_strtol(vers, &minorp, 0);
if (*minorp == '.') {
- if (num < 4)
+ if (num != 4)
return -EINVAL;
minor = simple_strtoul(minorp+1, NULL, 0);
if (minor == 0)
@@ -792,7 +812,7 @@
static ssize_t write_ports(struct file *file, char *buf, size_t size)
{
ssize_t rv;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
rv = __write_ports(file, buf, size, net);
@@ -827,7 +847,7 @@
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
{
char *mesg = buf;
- struct net *net = &init_net;
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (size > 0) {
@@ -923,7 +943,8 @@
*/
static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
{
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
}
@@ -939,7 +960,8 @@
*/
static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
{
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}
@@ -995,7 +1017,8 @@
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
{
ssize_t rv;
- struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id);
+ struct net *net = file->f_dentry->d_sb->s_fs_info;
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
mutex_lock(&nfsd_mutex);
rv = __write_recoverydir(file, buf, size, nn);
@@ -1013,7 +1036,7 @@
static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
{
static struct tree_descr nfsd_files[] = {
- [NFSD_List] = {"exports", &exports_operations, S_IRUGO},
+ [NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO},
[NFSD_Export_features] = {"export_features",
&export_features_operations, S_IRUGO},
[NFSD_FO_UnlockIP] = {"unlock_ip",
@@ -1037,21 +1060,37 @@
#endif
/* last one */ {""}
};
- return simple_fill_super(sb, 0x6e667364, nfsd_files);
+ struct net *net = data;
+ int ret;
+
+ ret = simple_fill_super(sb, 0x6e667364, nfsd_files);
+ if (ret)
+ return ret;
+ sb->s_fs_info = get_net(net);
+ return 0;
}
static struct dentry *nfsd_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- return mount_single(fs_type, flags, data, nfsd_fill_super);
+ return mount_ns(fs_type, flags, current->nsproxy->net_ns, nfsd_fill_super);
+}
+
+static void nfsd_umount(struct super_block *sb)
+{
+ struct net *net = sb->s_fs_info;
+
+ kill_litter_super(sb);
+ put_net(net);
}
static struct file_system_type nfsd_fs_type = {
.owner = THIS_MODULE,
.name = "nfsd",
.mount = nfsd_mount,
- .kill_sb = kill_litter_super,
+ .kill_sb = nfsd_umount,
};
+MODULE_ALIAS_FS("nfsd");
#ifdef CONFIG_PROC_FS
static int create_proc_exports_entry(void)
@@ -1061,7 +1100,8 @@
entry = proc_mkdir("fs/nfs", NULL);
if (!entry)
return -ENOMEM;
- entry = proc_create("exports", 0, entry, &exports_operations);
+ entry = proc_create("exports", 0, entry,
+ &exports_proc_operations);
if (!entry)
return -ENOMEM;
return 0;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index de23db2..07a473f 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -56,8 +56,8 @@
extern u32 nfsd_supported_minorversion;
extern struct mutex nfsd_mutex;
extern spinlock_t nfsd_drc_lock;
-extern unsigned int nfsd_drc_max_mem;
-extern unsigned int nfsd_drc_mem_used;
+extern unsigned long nfsd_drc_max_mem;
+extern unsigned long nfsd_drc_mem_used;
extern const struct seq_operations nfs_exports_op;
@@ -106,7 +106,7 @@
* NFSv4 State
*/
#ifdef CONFIG_NFSD_V4
-extern unsigned int max_delegations;
+extern unsigned long max_delegations;
void nfs4_state_init(void);
int nfsd4_init_slabs(void);
void nfsd4_free_slabs(void);
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index aad6d45..54c6b3d 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -26,17 +26,13 @@
nfsd_return_attrs(__be32 err, struct nfsd_attrstat *resp)
{
if (err) return err;
- return nfserrno(vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry,
- &resp->stat));
+ return fh_getattr(&resp->fh, &resp->stat);
}
static __be32
nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp)
{
if (err) return err;
- return nfserrno(vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry,
- &resp->stat));
+ return fh_getattr(&resp->fh, &resp->stat);
}
/*
* Get a file's attributes
@@ -150,9 +146,7 @@
&resp->count);
if (nfserr) return nfserr;
- return nfserrno(vfs_getattr(resp->fh.fh_export->ex_path.mnt,
- resp->fh.fh_dentry,
- &resp->stat));
+ return fh_getattr(&resp->fh, &resp->stat);
}
/*
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index cee62ab..262df5c 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -59,8 +59,8 @@
* nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
*/
spinlock_t nfsd_drc_lock;
-unsigned int nfsd_drc_max_mem;
-unsigned int nfsd_drc_mem_used;
+unsigned long nfsd_drc_max_mem;
+unsigned long nfsd_drc_mem_used;
#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
static struct svc_stat nfsd_acl_svcstats;
@@ -342,7 +342,7 @@
>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
nfsd_drc_mem_used = 0;
spin_lock_init(&nfsd_drc_lock);
- dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
+ dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
}
static int nfsd_get_default_max_blksize(void)
@@ -652,7 +652,6 @@
/* Check whether we have this call in the cache. */
switch (nfsd_cache_lookup(rqstp)) {
- case RC_INTR:
case RC_DROPIT:
return 0;
case RC_REPLY:
@@ -703,8 +702,7 @@
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
{
int ret;
- struct net *net = &init_net;
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(inode->i_sb->s_fs_info, nfsd_net_id);
mutex_lock(&nfsd_mutex);
if (nn->nfsd_serv == NULL) {
@@ -721,7 +719,7 @@
int nfsd_pool_stats_release(struct inode *inode, struct file *file)
{
int ret = seq_release(inode, file);
- struct net *net = &init_net;
+ struct net *net = inode->i_sb->s_fs_info;
mutex_lock(&nfsd_mutex);
/* this function really, really should have been called svc_put() */
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 979b421..9c769a4 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -4,6 +4,7 @@
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
+#include "vfs.h"
#include "xdr.h"
#include "auth.h"
@@ -100,12 +101,14 @@
iap->ia_mode = tmp;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
- iap->ia_valid |= ATTR_UID;
- iap->ia_uid = tmp;
+ iap->ia_uid = make_kuid(&init_user_ns, tmp);
+ if (uid_valid(iap->ia_uid))
+ iap->ia_valid |= ATTR_UID;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
- iap->ia_valid |= ATTR_GID;
- iap->ia_gid = tmp;
+ iap->ia_gid = make_kgid(&init_user_ns, tmp);
+ if (gid_valid(iap->ia_gid))
+ iap->ia_valid |= ATTR_GID;
}
if ((tmp = ntohl(*p++)) != (u32)-1) {
iap->ia_valid |= ATTR_SIZE;
@@ -151,8 +154,8 @@
*p++ = htonl(nfs_ftypes[type >> 12]);
*p++ = htonl((u32) stat->mode);
*p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) nfsd_ruid(rqstp, stat->uid));
- *p++ = htonl((u32) nfsd_rgid(rqstp, stat->gid));
+ *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
+ *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
*p++ = htonl(NFS_MAXPATHLEN);
@@ -194,11 +197,9 @@
}
/* Helper function for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
{
- struct kstat stat;
- vfs_getattr(fhp->fh_export->ex_path.mnt, fhp->fh_dentry, &stat);
- return encode_fattr(rqstp, p, fhp, &stat);
+ return encode_fattr(rqstp, p, fhp, stat);
}
/*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index d1c229f..1a8c739 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -152,8 +152,8 @@
struct nfsd4_cb_sec {
u32 flavor; /* (u32)(-1) used to mean "no valid flavor" */
- u32 uid;
- u32 gid;
+ kuid_t uid;
+ kgid_t gid;
};
struct nfsd4_create_session {
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index d586117..2b2e239 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -401,8 +401,8 @@
/* Revoke setuid/setgid on chown */
if (!S_ISDIR(inode->i_mode) &&
- (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
- ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid))) {
+ (((iap->ia_valid & ATTR_UID) && !uid_eq(iap->ia_uid, inode->i_uid)) ||
+ ((iap->ia_valid & ATTR_GID) && !gid_eq(iap->ia_gid, inode->i_gid)))) {
iap->ia_valid |= ATTR_KILL_PRIV;
if (iap->ia_valid & ATTR_MODE) {
/* we're setting mode too, just clear the s*id bits */
@@ -979,7 +979,7 @@
*/
static int wait_for_concurrent_writes(struct file *file)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
static ino_t last_ino;
static dev_t last_dev;
int err = 0;
@@ -1013,6 +1013,7 @@
int host_err;
int stable = *stablep;
int use_wgather;
+ loff_t pos = offset;
dentry = file->f_path.dentry;
inode = dentry->d_inode;
@@ -1025,7 +1026,7 @@
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
- host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &offset);
+ host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
set_fs(oldfs);
if (host_err < 0)
goto out_nfserr;
@@ -1070,7 +1071,7 @@
if (err)
return err;
- inode = file->f_path.dentry->d_inode;
+ inode = file_inode(file);
/* Get readahead parameters */
ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
@@ -1205,7 +1206,7 @@
* send along the gid on create when it tries to implement
* setgid directories via NFS:
*/
- if (current_fsuid() != 0)
+ if (!uid_eq(current_fsuid(), GLOBAL_ROOT_UID))
iap->ia_valid &= ~(ATTR_UID|ATTR_GID);
if (iap->ia_valid)
return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0);
@@ -1957,7 +1958,7 @@
offset = *offsetp;
while (1) {
- struct inode *dir_inode = file->f_path.dentry->d_inode;
+ struct inode *dir_inode = file_inode(file);
unsigned int reclen;
cdp->err = nfserr_eof; /* will be cleared on successful read */
@@ -2150,7 +2151,7 @@
* with NFSv3.
*/
if ((acc & NFSD_MAY_OWNER_OVERRIDE) &&
- inode->i_uid == current_fsuid())
+ uid_eq(inode->i_uid, current_fsuid()))
return 0;
/* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 359594c..5b58941 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -6,6 +6,7 @@
#define LINUX_NFSD_VFS_H
#include "nfsfh.h"
+#include "nfsd.h"
/*
* Flags for nfsd_permission
@@ -125,4 +126,11 @@
}
}
+static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
+{
+ struct path p = {.mnt = fh->fh_export->ex_path.mnt,
+ .dentry = fh->fh_dentry};
+ return nfserrno(vfs_getattr(&p, stat));
+}
+
#endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 53b1863..4f0481d 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -167,7 +167,7 @@
int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
/* Helper functions for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp);
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp);
#endif /* LINUX_NFSD_H */
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 7df980e..b6d5542 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -136,6 +136,7 @@
__be32 status;
struct svc_fh fh;
__u32 access;
+ struct kstat stat;
};
struct nfsd3_readlinkres {
@@ -225,6 +226,7 @@
int mask;
struct posix_acl *acl_access;
struct posix_acl *acl_default;
+ struct kstat stat;
};
/* dummy type for release */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 0889bfb..546f898 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -563,7 +563,7 @@
void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op);
__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
- struct dentry *dentry, __be32 *buffer, int *countp,
+ struct dentry *dentry, __be32 **buffer, int countp,
u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *,
diff --git a/fs/nilfs2/Kconfig b/fs/nilfs2/Kconfig
index 251da07..80da8eb 100644
--- a/fs/nilfs2/Kconfig
+++ b/fs/nilfs2/Kconfig
@@ -1,6 +1,5 @@
config NILFS2_FS
- tristate "NILFS2 file system support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ tristate "NILFS2 file system support"
select CRC32
help
NILFS2 is a log-structured file system (LFS) supporting continuous
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index df1a7fb..f30b017 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -259,7 +259,7 @@
static int nilfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
loff_t pos = filp->f_pos;
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
unsigned int offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 6194688..08fdb77 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -67,7 +67,7 @@
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
int ret = 0;
@@ -126,7 +126,7 @@
nilfs_transaction_commit(inode->i_sb);
mapped:
- wait_on_page_writeback(page);
+ wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index fdb1807..b44bdb2 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -664,8 +664,11 @@
if (ret < 0)
printk(KERN_ERR "NILFS: GC failed during preparation: "
"cannot read source blocks: err=%d\n", ret);
- else
+ else {
+ if (nilfs_sb_need_update(nilfs))
+ set_nilfs_discontinued(nilfs);
ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
+ }
nilfs_remove_all_gcinodes(nilfs);
clear_nilfs_gc_running(nilfs);
@@ -793,7 +796,7 @@
long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
void __user *argp = (void __user *)arg;
switch (cmd) {
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1d0c0b8..9de78f0 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -517,11 +517,11 @@
if (parent && *lenp < NILFS_FID_SIZE_CONNECTABLE) {
*lenp = NILFS_FID_SIZE_CONNECTABLE;
- return 255;
+ return FILEID_INVALID;
}
if (*lenp < NILFS_FID_SIZE_NON_CONNECTABLE) {
*lenp = NILFS_FID_SIZE_NON_CONNECTABLE;
- return 255;
+ return FILEID_INVALID;
}
fid->cno = root->cno;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 3c991dc..c7d1f9f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1361,6 +1361,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("nilfs2");
static void nilfs_inode_init_once(void *obj)
{
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 08b886f..2bfe6dc 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -174,7 +174,7 @@
struct dnotify_struct **prev;
struct inode *inode;
- inode = filp->f_path.dentry->d_inode;
+ inode = file_inode(filp);
if (!S_ISDIR(inode->i_mode))
return;
@@ -296,7 +296,7 @@
}
/* dnotify only works on directories */
- inode = filp->f_path.dentry->d_inode;
+ inode = file_inode(filp);
if (!S_ISDIR(inode->i_mode)) {
error = -ENOTDIR;
goto out_err;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9ff4a5e..5d84442 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -466,7 +466,7 @@
ret = -ENOTDIR;
if ((flags & FAN_MARK_ONLYDIR) &&
- !(S_ISDIR(f.file->f_path.dentry->d_inode->i_mode))) {
+ !(S_ISDIR(file_inode(f.file)->i_mode))) {
fdput(f);
goto out;
}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 6baadb5..4bb21d6 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -52,7 +52,6 @@
void __fsnotify_update_child_dentry_flags(struct inode *inode)
{
struct dentry *alias;
- struct hlist_node *p;
int watched;
if (!S_ISDIR(inode->i_mode))
@@ -64,7 +63,7 @@
spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
- hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
struct dentry *child;
/* run all of the children of the original inode and fix their
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index f31e90f..74825be 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -36,12 +36,11 @@
static void fsnotify_recalc_inode_mask_locked(struct inode *inode)
{
struct fsnotify_mark *mark;
- struct hlist_node *pos;
__u32 new_mask = 0;
assert_spin_locked(&inode->i_lock);
- hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list)
+ hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list)
new_mask |= mark->mask;
inode->i_fsnotify_mask = new_mask;
}
@@ -87,11 +86,11 @@
void fsnotify_clear_marks_by_inode(struct inode *inode)
{
struct fsnotify_mark *mark, *lmark;
- struct hlist_node *pos, *n;
+ struct hlist_node *n;
LIST_HEAD(free_list);
spin_lock(&inode->i_lock);
- hlist_for_each_entry_safe(mark, pos, n, &inode->i_fsnotify_marks, i.i_list) {
+ hlist_for_each_entry_safe(mark, n, &inode->i_fsnotify_marks, i.i_list) {
list_add(&mark->i.free_i_list, &free_list);
hlist_del_init_rcu(&mark->i.i_list);
fsnotify_get_mark(mark);
@@ -129,11 +128,10 @@
struct inode *inode)
{
struct fsnotify_mark *mark;
- struct hlist_node *pos;
assert_spin_locked(&inode->i_lock);
- hlist_for_each_entry(mark, pos, &inode->i_fsnotify_marks, i.i_list) {
+ hlist_for_each_entry(mark, &inode->i_fsnotify_marks, i.i_list) {
if (mark->group == group) {
fsnotify_get_mark(mark);
return mark;
@@ -194,8 +192,7 @@
struct fsnotify_group *group, struct inode *inode,
int allow_dups)
{
- struct fsnotify_mark *lmark;
- struct hlist_node *node, *last = NULL;
+ struct fsnotify_mark *lmark, *last = NULL;
int ret = 0;
mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
@@ -214,8 +211,8 @@
}
/* should mark be in the middle of the current list? */
- hlist_for_each_entry(lmark, node, &inode->i_fsnotify_marks, i.i_list) {
- last = node;
+ hlist_for_each_entry(lmark, &inode->i_fsnotify_marks, i.i_list) {
+ last = lmark;
if ((lmark->group == group) && !allow_dups) {
ret = -EEXIST;
@@ -235,7 +232,7 @@
BUG_ON(last == NULL);
/* mark should be the last entry. last is the current last entry */
- hlist_add_after_rcu(last, &mark->i.i_list);
+ hlist_add_after_rcu(&last->i.i_list, &mark->i.i_list);
out:
fsnotify_recalc_inode_mask_locked(inode);
spin_unlock(&inode->i_lock);
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 871569c..4216308 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -197,7 +197,6 @@
{
/* ideally the idr is empty and we won't hit the BUG in the callback */
idr_for_each(&group->inotify_data.idr, idr_callback, group);
- idr_remove_all(&group->inotify_data.idr);
idr_destroy(&group->inotify_data.idr);
atomic_dec(&group->inotify_data.user->inotify_devs);
free_uid(group->inotify_data.user);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 228a2c2..e0f7c12 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -364,22 +364,20 @@
{
int ret;
- do {
- if (unlikely(!idr_pre_get(idr, GFP_KERNEL)))
- return -ENOMEM;
+ idr_preload(GFP_KERNEL);
+ spin_lock(idr_lock);
- spin_lock(idr_lock);
- ret = idr_get_new_above(idr, i_mark, *last_wd + 1,
- &i_mark->wd);
+ ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT);
+ if (ret >= 0) {
/* we added the mark to the idr, take a reference */
- if (!ret) {
- *last_wd = i_mark->wd;
- fsnotify_get_mark(&i_mark->fsn_mark);
- }
- spin_unlock(idr_lock);
- } while (ret == -EAGAIN);
+ i_mark->wd = ret;
+ *last_wd = i_mark->wd;
+ fsnotify_get_mark(&i_mark->fsn_mark);
+ }
- return ret;
+ spin_unlock(idr_lock);
+ idr_preload_end();
+ return ret < 0 ? ret : 0;
}
static struct inotify_inode_mark *inotify_idr_find_locked(struct fsnotify_group *group,
@@ -576,8 +574,6 @@
/* don't allow invalid bits: we don't want flags set */
mask = inotify_arg_to_mask(arg);
- if (unlikely(!(mask & IN_ALL_EVENTS)))
- return -EINVAL;
fsn_mark = fsnotify_find_inode_mark(group, inode);
if (!fsn_mark)
@@ -629,8 +625,6 @@
/* don't allow invalid bits: we don't want flags set */
mask = inotify_arg_to_mask(arg);
- if (unlikely(!(mask & IN_ALL_EVENTS)))
- return -EINVAL;
tmp_i_mark = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
if (unlikely(!tmp_i_mark))
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index 4df58b8..68ca5a8 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -33,12 +33,12 @@
void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
{
struct fsnotify_mark *mark, *lmark;
- struct hlist_node *pos, *n;
+ struct hlist_node *n;
struct mount *m = real_mount(mnt);
LIST_HEAD(free_list);
spin_lock(&mnt->mnt_root->d_lock);
- hlist_for_each_entry_safe(mark, pos, n, &m->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry_safe(mark, n, &m->mnt_fsnotify_marks, m.m_list) {
list_add(&mark->m.free_m_list, &free_list);
hlist_del_init_rcu(&mark->m.m_list);
fsnotify_get_mark(mark);
@@ -71,12 +71,11 @@
{
struct mount *m = real_mount(mnt);
struct fsnotify_mark *mark;
- struct hlist_node *pos;
__u32 new_mask = 0;
assert_spin_locked(&mnt->mnt_root->d_lock);
- hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list)
+ hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list)
new_mask |= mark->mask;
m->mnt_fsnotify_mask = new_mask;
}
@@ -114,11 +113,10 @@
{
struct mount *m = real_mount(mnt);
struct fsnotify_mark *mark;
- struct hlist_node *pos;
assert_spin_locked(&mnt->mnt_root->d_lock);
- hlist_for_each_entry(mark, pos, &m->mnt_fsnotify_marks, m.m_list) {
+ hlist_for_each_entry(mark, &m->mnt_fsnotify_marks, m.m_list) {
if (mark->group == group) {
fsnotify_get_mark(mark);
return mark;
@@ -153,8 +151,7 @@
int allow_dups)
{
struct mount *m = real_mount(mnt);
- struct fsnotify_mark *lmark;
- struct hlist_node *node, *last = NULL;
+ struct fsnotify_mark *lmark, *last = NULL;
int ret = 0;
mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
@@ -173,8 +170,8 @@
}
/* should mark be in the middle of the current list? */
- hlist_for_each_entry(lmark, node, &m->mnt_fsnotify_marks, m.m_list) {
- last = node;
+ hlist_for_each_entry(lmark, &m->mnt_fsnotify_marks, m.m_list) {
+ last = lmark;
if ((lmark->group == group) && !allow_dups) {
ret = -EEXIST;
@@ -194,7 +191,7 @@
BUG_ON(last == NULL);
/* mark should be the last entry. last is the current last entry */
- hlist_add_after_rcu(last, &mark->m.m_list);
+ hlist_add_after_rcu(&last->m.m_list, &mark->m.m_list);
out:
fsnotify_recalc_vfsmount_mask_locked(mnt);
spin_unlock(&mnt->mnt_root->d_lock);
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 99e3610..aa411c3 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -1101,7 +1101,7 @@
{
s64 ia_pos, ia_start, prev_ia_pos, bmp_pos;
loff_t fpos, i_size;
- struct inode *bmp_vi, *vdir = filp->f_path.dentry->d_inode;
+ struct inode *bmp_vi, *vdir = file_inode(filp);
struct super_block *sb = vdir->i_sb;
ntfs_inode *ndir = NTFS_I(vdir);
ntfs_volume *vol = NTFS_SB(sb);
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 4a8289f8..82650d5 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -3079,6 +3079,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ntfs");
/* Stable names for the slab caches. */
static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 260b162..8a40457 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -65,7 +65,20 @@
acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag);
acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
- acl->a_entries[n].e_id = le32_to_cpu(entry->e_id);
+ switch(acl->a_entries[n].e_tag) {
+ case ACL_USER:
+ acl->a_entries[n].e_uid =
+ make_kuid(&init_user_ns,
+ le32_to_cpu(entry->e_id));
+ break;
+ case ACL_GROUP:
+ acl->a_entries[n].e_gid =
+ make_kgid(&init_user_ns,
+ le32_to_cpu(entry->e_id));
+ break;
+ default:
+ break;
+ }
value += sizeof(struct posix_acl_entry);
}
@@ -91,7 +104,21 @@
for (n = 0; n < acl->a_count; n++, entry++) {
entry->e_tag = cpu_to_le16(acl->a_entries[n].e_tag);
entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
- entry->e_id = cpu_to_le32(acl->a_entries[n].e_id);
+ switch(acl->a_entries[n].e_tag) {
+ case ACL_USER:
+ entry->e_id = cpu_to_le32(
+ from_kuid(&init_user_ns,
+ acl->a_entries[n].e_uid));
+ break;
+ case ACL_GROUP:
+ entry->e_id = cpu_to_le32(
+ from_kgid(&init_user_ns,
+ acl->a_entries[n].e_gid));
+ break;
+ default:
+ entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID);
+ break;
+ }
}
return ocfs2_acl;
}
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 31b9463..b8a9d87 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -6751,8 +6751,7 @@
mlog_errno(ret);
out:
- if (pages)
- kfree(pages);
+ kfree(pages);
return ret;
}
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 6577432..20dfec7 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -569,7 +569,7 @@
int ret,
bool is_async)
{
- struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(iocb->ki_filp);
int level;
wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
@@ -593,9 +593,9 @@
level = ocfs2_iocb_rw_locked_level(iocb);
ocfs2_rw_unlock(inode, level);
+ inode_dio_done(inode);
if (is_async)
aio_complete(iocb, ret, 0);
- inode_dio_done(inode);
}
/*
@@ -626,7 +626,7 @@
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
+ struct inode *inode = file_inode(file)->i_mapping->host;
/*
* Fallback to buffered I/O if we see an inode without
@@ -1194,6 +1194,7 @@
goto out;
}
}
+ wait_for_stable_page(wc->w_pages[i]);
if (index == target_index)
wc->w_target_page = wc->w_pages[i];
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index f7c648d..42252bf 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1471,8 +1471,7 @@
mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name);
- if (reg->hr_tmp_block)
- kfree(reg->hr_tmp_block);
+ kfree(reg->hr_tmp_block);
if (reg->hr_slot_data) {
for (i = 0; i < reg->hr_num_pages; i++) {
@@ -1486,8 +1485,7 @@
if (reg->hr_bdev)
blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);
- if (reg->hr_slots)
- kfree(reg->hr_slots);
+ kfree(reg->hr_slots);
kfree(reg->hr_db_regnum);
kfree(reg->hr_db_livenodes);
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 1bfe880..aa88bd8 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -304,28 +304,22 @@
static int o2net_prep_nsw(struct o2net_node *nn, struct o2net_status_wait *nsw)
{
- int ret = 0;
+ int ret;
- do {
- if (!idr_pre_get(&nn->nn_status_idr, GFP_ATOMIC)) {
- ret = -EAGAIN;
- break;
- }
- spin_lock(&nn->nn_lock);
- ret = idr_get_new(&nn->nn_status_idr, nsw, &nsw->ns_id);
- if (ret == 0)
- list_add_tail(&nsw->ns_node_item,
- &nn->nn_status_list);
- spin_unlock(&nn->nn_lock);
- } while (ret == -EAGAIN);
-
- if (ret == 0) {
- init_waitqueue_head(&nsw->ns_wq);
- nsw->ns_sys_status = O2NET_ERR_NONE;
- nsw->ns_status = 0;
+ spin_lock(&nn->nn_lock);
+ ret = idr_alloc(&nn->nn_status_idr, nsw, 0, 0, GFP_ATOMIC);
+ if (ret >= 0) {
+ nsw->ns_id = ret;
+ list_add_tail(&nsw->ns_node_item, &nn->nn_status_list);
}
+ spin_unlock(&nn->nn_lock);
+ if (ret < 0)
+ return ret;
- return ret;
+ init_waitqueue_head(&nsw->ns_wq);
+ nsw->ns_sys_status = O2NET_ERR_NONE;
+ nsw->ns_status = 0;
+ return 0;
}
static void o2net_complete_nsw_locked(struct o2net_node *nn,
@@ -870,7 +864,7 @@
/* we've had some trouble with handlers seemingly vanishing. */
mlog_bug_on_msg(o2net_handler_tree_lookup(msg_type, key, &p,
&parent) == NULL,
- "couldn't find handler we *just* registerd "
+ "couldn't find handler we *just* registered "
"for type %u key %08x\n", msg_type, key);
}
write_unlock(&o2net_handler_lock);
@@ -1165,10 +1159,8 @@
o2net_debug_del_nst(&nst); /* must be before dropping sc and node */
if (sc)
sc_put(sc);
- if (vec)
- kfree(vec);
- if (msg)
- kfree(msg);
+ kfree(vec);
+ kfree(msg);
o2net_complete_nsw(nn, &nsw, 0, 0, 0);
return ret;
}
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 8db4b58..ef99972 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -169,11 +169,10 @@
u64 parent_blkno,
int skip_unhashed)
{
- struct hlist_node *p;
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
trace_ocfs2_find_local_alias(dentry->d_name.len,
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 8fe4e28..f1e1aed 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -67,7 +67,6 @@
#define NAMEI_RA_CHUNKS 2
#define NAMEI_RA_BLOCKS 4
#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
-#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
static unsigned char ocfs2_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
@@ -2015,12 +2014,12 @@
int ocfs2_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
int error = 0;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int lock_level = 0;
trace_ocfs2_readdir((unsigned long long)OCFS2_I(inode)->ip_blkno);
- error = ocfs2_inode_lock_atime(inode, filp->f_vfsmnt, &lock_level);
+ error = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level);
if (lock_level && error >= 0) {
/* We release EX lock which used to update atime
* and get PR lock again to reduce contention
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 9e89d70..dbb17c0 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -319,9 +319,7 @@
if (dlm->master_hash)
dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES);
- if (dlm->name)
- kfree(dlm->name);
-
+ kfree(dlm->name);
kfree(dlm);
}
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 005261c..33ecbe0 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2020,7 +2020,7 @@
int ignore_higher, u8 request_from, u32 flags)
{
struct dlm_work_item *item;
- item = kzalloc(sizeof(*item), GFP_NOFS);
+ item = kzalloc(sizeof(*item), GFP_ATOMIC);
if (!item)
return -ENOMEM;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 01ebfd0..eeac97b 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2083,7 +2083,6 @@
u8 dead_node, u8 new_master)
{
int i;
- struct hlist_node *hash_iter;
struct hlist_head *bucket;
struct dlm_lock_resource *res, *next;
@@ -2114,7 +2113,7 @@
* if necessary */
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_lockres_hash(dlm, i);
- hlist_for_each_entry(res, hash_iter, bucket, hash_node) {
+ hlist_for_each_entry(res, bucket, hash_node) {
if (!(res->state & DLM_LOCK_RES_RECOVERING))
continue;
@@ -2273,7 +2272,6 @@
static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
{
- struct hlist_node *iter;
struct dlm_lock_resource *res;
int i;
struct hlist_head *bucket;
@@ -2299,7 +2297,7 @@
*/
for (i = 0; i < DLM_HASH_BUCKETS; i++) {
bucket = dlm_lockres_hash(dlm, i);
- hlist_for_each_entry(res, iter, bucket, hash_node) {
+ hlist_for_each_entry(res, bucket, hash_node) {
/* always prune any $RECOVERY entries for dead nodes,
* otherwise hangs can occur during later recovery */
if (dlm_is_recovery_lock(res->lockname.name,
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 16b712d..12bafb7 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -224,7 +224,7 @@
static unsigned int dlmfs_file_poll(struct file *file, poll_table *wait)
{
int event = 0;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct dlmfs_inode_private *ip = DLMFS_I(inode);
poll_wait(file, &ip->ip_lockres.l_event, wait);
@@ -245,7 +245,7 @@
int bytes_left;
ssize_t readlen, got;
char *lvb_buf;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
mlog(0, "inode %lu, count = %zu, *ppos = %llu\n",
inode->i_ino, count, *ppos);
@@ -293,7 +293,7 @@
int bytes_left;
ssize_t writelen;
char *lvb_buf;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
mlog(0, "inode %lu, count = %zu, *ppos = %llu\n",
inode->i_ino, count, *ppos);
@@ -640,6 +640,7 @@
.mount = dlmfs_mount,
.kill_sb = kill_litter_super,
};
+MODULE_ALIAS_FS("ocfs2_dlmfs");
static int __init init_dlmfs_fs(void)
{
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 4f7795f..12ae194 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2045,8 +2045,8 @@
lvb->lvb_version = OCFS2_LVB_VERSION;
lvb->lvb_isize = cpu_to_be64(i_size_read(inode));
lvb->lvb_iclusters = cpu_to_be32(oi->ip_clusters);
- lvb->lvb_iuid = cpu_to_be32(inode->i_uid);
- lvb->lvb_igid = cpu_to_be32(inode->i_gid);
+ lvb->lvb_iuid = cpu_to_be32(i_uid_read(inode));
+ lvb->lvb_igid = cpu_to_be32(i_gid_read(inode));
lvb->lvb_imode = cpu_to_be16(inode->i_mode);
lvb->lvb_inlink = cpu_to_be16(inode->i_nlink);
lvb->lvb_iatime_packed =
@@ -2095,8 +2095,8 @@
else
inode->i_blocks = ocfs2_inode_sector_count(inode);
- inode->i_uid = be32_to_cpu(lvb->lvb_iuid);
- inode->i_gid = be32_to_cpu(lvb->lvb_igid);
+ i_uid_write(inode, be32_to_cpu(lvb->lvb_iuid));
+ i_gid_write(inode, be32_to_cpu(lvb->lvb_igid));
inode->i_mode = be16_to_cpu(lvb->lvb_imode);
set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
ocfs2_unpack_timespec(&inode->i_atime,
@@ -2545,6 +2545,7 @@
* everything is up to the caller :) */
status = ocfs2_should_refresh_lock_res(lockres);
if (status < 0) {
+ ocfs2_cluster_unlock(osb, lockres, level);
mlog_errno(status);
goto bail;
}
@@ -2553,8 +2554,10 @@
ocfs2_complete_lock_res_refresh(lockres, status);
- if (status < 0)
+ if (status < 0) {
+ ocfs2_cluster_unlock(osb, lockres, level);
mlog_errno(status);
+ }
ocfs2_track_lock_refresh(lockres);
}
bail:
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 322216a..2965116 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -195,11 +195,11 @@
if (parent && (len < 6)) {
*max_len = 6;
- type = 255;
+ type = FILEID_INVALID;
goto bail;
} else if (len < 3) {
*max_len = 3;
- type = 255;
+ type = FILEID_INVALID;
goto bail;
}
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index f487aa3..1c39efb 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -282,8 +282,7 @@
spin_unlock(&oi->ip_lock);
out:
- if (new_emi)
- kfree(new_emi);
+ kfree(new_emi);
}
static int ocfs2_last_eb_is_empty(struct inode *inode,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 37d313e..6474cb4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1116,7 +1116,8 @@
(unsigned long long)OCFS2_I(inode)->ip_blkno,
dentry->d_name.len, dentry->d_name.name,
attr->ia_valid, attr->ia_mode,
- attr->ia_uid, attr->ia_gid);
+ from_kuid(&init_user_ns, attr->ia_uid),
+ from_kgid(&init_user_ns, attr->ia_gid));
/* ensuring we don't even attempt to truncate a symlink */
if (S_ISLNK(inode->i_mode))
@@ -1174,14 +1175,14 @@
}
}
- if ((attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
- (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+ if ((attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
+ (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
/*
* Gather pointers to quota structures so that allocation /
* freeing of quota structures happens here and not inside
* dquot_transfer() where we have problems with lock ordering
*/
- if (attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid
+ if (attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)
&& OCFS2_HAS_RO_COMPAT_FEATURE(sb,
OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
@@ -1190,7 +1191,7 @@
goto bail_unlock;
}
}
- if (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid
+ if (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid)
&& OCFS2_HAS_RO_COMPAT_FEATURE(sb,
OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) {
transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
@@ -1949,7 +1950,7 @@
int ocfs2_change_file_space(struct file *file, unsigned int cmd,
struct ocfs2_space_resv *sr)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int ret;
@@ -1977,7 +1978,7 @@
static long ocfs2_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_space_resv sr;
int change_size = 1;
@@ -2232,7 +2233,7 @@
loff_t old_size, *ppos = &iocb->ki_pos;
u32 old_clusters;
struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int full_coherency = !(osb->s_mount_opt &
OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2516,7 +2517,7 @@
unsigned int flags)
{
int ret = 0, lock_level = 0;
- struct inode *inode = in->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(in);
trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2526,7 +2527,7 @@
/*
* See the comment in ocfs2_file_aio_read()
*/
- ret = ocfs2_inode_lock_atime(inode, in->f_vfsmnt, &lock_level);
+ ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
if (ret < 0) {
mlog_errno(ret);
goto bail;
@@ -2546,7 +2547,7 @@
{
int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
struct file *filp = iocb->ki_filp;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2589,7 +2590,7 @@
* like i_size. This allows the checks down below
* generic_file_aio_read() a chance of actually working.
*/
- ret = ocfs2_inode_lock_atime(inode, filp->f_vfsmnt, &lock_level);
+ ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level);
if (ret < 0) {
mlog_errno(ret);
goto bail;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index d89e08a..f87f9bd 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -269,8 +269,8 @@
inode->i_generation = le32_to_cpu(fe->i_generation);
inode->i_rdev = huge_decode_dev(le64_to_cpu(fe->id1.dev1.i_rdev));
inode->i_mode = le16_to_cpu(fe->i_mode);
- inode->i_uid = le32_to_cpu(fe->i_uid);
- inode->i_gid = le32_to_cpu(fe->i_gid);
+ i_uid_write(inode, le32_to_cpu(fe->i_uid));
+ i_gid_write(inode, le32_to_cpu(fe->i_gid));
/* Fast symlinks will have i_size but no allocated clusters. */
if (S_ISLNK(inode->i_mode) && !fe->i_clusters) {
@@ -1259,8 +1259,8 @@
fe->i_size = cpu_to_le64(i_size_read(inode));
ocfs2_set_links_count(fe, inode->i_nlink);
- fe->i_uid = cpu_to_le32(inode->i_uid);
- fe->i_gid = cpu_to_le32(inode->i_gid);
+ fe->i_uid = cpu_to_le32(i_uid_read(inode));
+ fe->i_gid = cpu_to_le32(i_gid_read(inode));
fe->i_mode = cpu_to_le16(inode->i_mode);
fe->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
fe->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
@@ -1290,8 +1290,8 @@
ocfs2_set_inode_flags(inode);
i_size_write(inode, le64_to_cpu(fe->i_size));
set_nlink(inode, ocfs2_read_links_count(fe));
- inode->i_uid = le32_to_cpu(fe->i_uid);
- inode->i_gid = le32_to_cpu(fe->i_gid);
+ i_uid_write(inode, le32_to_cpu(fe->i_uid));
+ i_gid_write(inode, le32_to_cpu(fe->i_gid));
inode->i_mode = le16_to_cpu(fe->i_mode);
if (S_ISLNK(inode->i_mode) && le32_to_cpu(fe->i_clusters) == 0)
inode->i_blocks = 0;
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index f20edcb..752f0b2 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -881,7 +881,7 @@
long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
unsigned int flags;
int new_clusters;
int status;
@@ -994,7 +994,7 @@
{
bool preserve;
struct reflink_arguments args;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ocfs2_info info;
void __user *argp = (void __user *)arg;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 2dd36af..8eccfab 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1234,11 +1234,8 @@
/* Though we wish to avoid it, we are in fact safe in
* skipping local alloc cleanup as fsck.ocfs2 is more
* than capable of reclaiming unused space. */
- if (la_dinode)
- kfree(la_dinode);
-
- if (tl_dinode)
- kfree(tl_dinode);
+ kfree(la_dinode);
+ kfree(tl_dinode);
if (qrec)
ocfs2_free_quota_recovery(qrec);
@@ -1408,8 +1405,7 @@
mutex_unlock(&osb->recovery_lock);
- if (rm_quota)
- kfree(rm_quota);
+ kfree(rm_quota);
/* no one is callint kthread_stop() for us so the kthread() api
* requires that we call do_exit(). And it isn't exported, but
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index a9f78c7..aebeacd 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -476,8 +476,7 @@
if (local_alloc_inode)
iput(local_alloc_inode);
- if (alloc_copy)
- kfree(alloc_copy);
+ kfree(alloc_copy);
}
/*
@@ -534,7 +533,7 @@
mlog_errno(status);
bail:
- if ((status < 0) && (*alloc_copy)) {
+ if (status < 0) {
kfree(*alloc_copy);
*alloc_copy = NULL;
}
@@ -1290,8 +1289,7 @@
if (main_bm_inode)
iput(main_bm_inode);
- if (alloc_copy)
- kfree(alloc_copy);
+ kfree(alloc_copy);
if (ac)
ocfs2_free_alloc_context(ac);
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 47a87dd..10d66c7 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -62,7 +62,7 @@
struct page *page)
{
int ret = VM_FAULT_NOPAGE;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
loff_t pos = page_offset(page);
unsigned int len = PAGE_CACHE_SIZE;
@@ -131,7 +131,7 @@
static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct buffer_head *di_bh = NULL;
sigset_t oldset;
int ret;
@@ -180,13 +180,13 @@
{
int ret = 0, lock_level = 0;
- ret = ocfs2_inode_lock_atime(file->f_dentry->d_inode,
- file->f_vfsmnt, &lock_level);
+ ret = ocfs2_inode_lock_atime(file_inode(file),
+ file->f_path.mnt, &lock_level);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
- ocfs2_inode_unlock(file->f_dentry->d_inode, lock_level);
+ ocfs2_inode_unlock(file_inode(file), lock_level);
out:
vma->vm_ops = &ocfs2_file_vm_ops;
return 0;
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 6083432..9f8dcad 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -1055,7 +1055,7 @@
{
int status;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ocfs2_move_extents range;
struct ocfs2_move_extents_context *context = NULL;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f1fd074..04ee1b5 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -512,8 +512,8 @@
fe->i_suballoc_loc = cpu_to_le64(suballoc_loc);
fe->i_suballoc_bit = cpu_to_le16(suballoc_bit);
fe->i_suballoc_slot = cpu_to_le16(inode_ac->ac_alloc_slot);
- fe->i_uid = cpu_to_le32(inode->i_uid);
- fe->i_gid = cpu_to_le32(inode->i_gid);
+ fe->i_uid = cpu_to_le32(i_uid_read(inode));
+ fe->i_gid = cpu_to_le32(i_gid_read(inode));
fe->i_mode = cpu_to_le16(inode->i_mode);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev));
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 30a0550..998b17e 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2927,7 +2927,7 @@
u32 new_cluster, u32 new_len)
{
int ret = 0, partial;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct ocfs2_caching_info *ci = INODE_CACHE(inode);
struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
@@ -3020,7 +3020,7 @@
u32 new_cluster, u32 new_len)
{
int ret = 0;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
struct ocfs2_caching_info *ci = INODE_CACHE(inode);
int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
@@ -4407,7 +4407,7 @@
* rights to do so.
*/
if (preserve) {
- if ((current_fsuid() != inode->i_uid) && !capable(CAP_CHOWN))
+ if (!uid_eq(current_fsuid(), inode->i_uid) && !capable(CAP_CHOWN))
return -EPERM;
if (!in_group_p(inode->i_gid) && !capable(CAP_CHOWN))
return -EPERM;
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 9436801..bf1f893 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -376,7 +376,7 @@
dlm_register_eviction_cb(dlm, &priv->op_eviction_cb);
out_free:
- if (rc && conn->cc_private)
+ if (rc)
kfree(conn->cc_private);
out:
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f169da4..b7e74b5 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -642,7 +642,7 @@
* cluster groups will be staying in cache for the duration of
* this operation.
*/
- ac->ac_allow_chain_relink = 0;
+ ac->ac_disable_chain_relink = 1;
/* Claim the first region */
status = ocfs2_block_group_claim_bits(osb, handle, ac, min_bits,
@@ -1823,7 +1823,7 @@
* Do this *after* figuring out how many bits we're taking out
* of our target group.
*/
- if (ac->ac_allow_chain_relink &&
+ if (!ac->ac_disable_chain_relink &&
(prev_group_bh) &&
(ocfs2_block_group_reasonably_empty(bg, res->sr_bits))) {
status = ocfs2_relink_block_group(handle, alloc_inode,
@@ -1928,7 +1928,6 @@
victim = ocfs2_find_victim_chain(cl);
ac->ac_chain = victim;
- ac->ac_allow_chain_relink = 1;
status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
res, &bits_left);
@@ -1947,7 +1946,7 @@
* searching each chain in order. Don't allow chain relinking
* because we only calculate enough journal credits for one
* relink per alloc. */
- ac->ac_allow_chain_relink = 0;
+ ac->ac_disable_chain_relink = 1;
for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
if (i == victim)
continue;
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index b8afabf..a36d0aa 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -49,7 +49,7 @@
/* these are used by the chain search */
u16 ac_chain;
- int ac_allow_chain_relink;
+ int ac_disable_chain_relink;
group_search_t *ac_group_search;
u64 ac_last_group;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 0e91ec2..01b8516 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1266,6 +1266,7 @@
.fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
.next = NULL
};
+MODULE_ALIAS_FS("ocfs2");
static int ocfs2_check_set_options(struct super_block *sb,
struct mount_options *options)
@@ -2525,8 +2526,7 @@
mlog_errno(status);
finally:
- if (local_alloc)
- kfree(local_alloc);
+ kfree(local_alloc);
if (status)
mlog_errno(status);
@@ -2553,8 +2553,7 @@
* we free it here.
*/
kfree(osb->journal);
- if (osb->local_alloc_copy)
- kfree(osb->local_alloc_copy);
+ kfree(osb->local_alloc_copy);
kfree(osb->uuid_str);
ocfs2_put_dlm_debug(osb->osb_dlm_debug);
memset(osb, 0, sizeof(struct ocfs2_super));
diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c
index f1fbb4b..66edce7e 100644
--- a/fs/ocfs2/symlink.c
+++ b/fs/ocfs2/symlink.c
@@ -57,7 +57,7 @@
static int ocfs2_fast_symlink_readpage(struct file *unused, struct page *page)
{
struct inode *inode = page->mapping->host;
- struct buffer_head *bh;
+ struct buffer_head *bh = NULL;
int status = ocfs2_read_inode_block(inode, &bh);
struct ocfs2_dinode *fe;
const char *link;
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index 3d635f4..f053688 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -91,8 +91,7 @@
} else
osb->local_system_inodes = local_system_inodes;
spin_unlock(&osb->osb_lock);
- if (unlikely(free))
- kfree(free);
+ kfree(free);
}
index = (slot * NUM_LOCAL_SYSTEM_INODES) +
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 0ba9ea1..2e3ea30 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -7189,7 +7189,7 @@
struct buffer_head *dir_bh = NULL;
ret = ocfs2_init_security_get(inode, dir, qstr, NULL);
- if (!ret) {
+ if (ret) {
mlog_errno(ret);
goto leave;
}
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index fb5b3ff..acbaebc 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -330,7 +330,7 @@
static int omfs_fill_chain(struct file *filp, void *dirent, filldir_t filldir,
u64 fsblock, int hindex)
{
- struct inode *dir = filp->f_dentry->d_inode;
+ struct inode *dir = file_inode(filp);
struct buffer_head *bh;
struct omfs_inode *oi;
u64 self;
@@ -405,7 +405,7 @@
static int omfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *dir = filp->f_dentry->d_inode;
+ struct inode *dir = file_inode(filp);
struct buffer_head *bh;
loff_t offset, res;
unsigned int hchain, hindex;
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 25d715c..d8b0afd 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -572,6 +572,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("omfs");
static int __init init_omfs_fs(void)
{
diff --git a/fs/open.c b/fs/open.c
index 9b33c0c..6835446 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -30,6 +30,7 @@
#include <linux/fs_struct.h>
#include <linux/ima.h>
#include <linux/dnotify.h>
+#include <linux/compat.h>
#include "internal.h"
@@ -140,6 +141,13 @@
return do_sys_truncate(path, length);
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length)
+{
+ return do_sys_truncate(path, length);
+}
+#endif
+
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
@@ -195,6 +203,13 @@
return ret;
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length)
+{
+ return do_sys_ftruncate(fd, length, 1);
+}
+#endif
+
/* LFS versions of truncate are only needed on 32 bit machines */
#if BITS_PER_LONG == 32
SYSCALL_DEFINE(truncate64)(const char __user * path, loff_t length)
@@ -228,7 +243,7 @@
int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
@@ -426,7 +441,7 @@
if (!f.file)
goto out;
- inode = f.file->f_path.dentry->d_inode;
+ inode = file_inode(f.file);
error = -ENOTDIR;
if (!S_ISDIR(inode->i_mode))
@@ -689,7 +704,7 @@
f->f_mode = FMODE_PATH;
path_get(&f->f_path);
- inode = f->f_path.dentry->d_inode;
+ inode = f->f_inode = f->f_path.dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = __get_file_write_access(inode, f->f_path.mnt);
if (error)
@@ -699,7 +714,6 @@
}
f->f_mapping = inode->i_mapping;
- f->f_pos = 0;
file_sb_list_add(f, inode->i_sb);
if (unlikely(f->f_mode & FMODE_PATH)) {
@@ -753,6 +767,7 @@
path_put(&f->f_path);
f->f_path.mnt = NULL;
f->f_path.dentry = NULL;
+ f->f_inode = NULL;
return error;
}
@@ -810,23 +825,22 @@
/* We must always pass in a valid mount pointer. */
BUG_ON(!path->mnt);
- error = -ENFILE;
f = get_empty_filp();
- if (f == NULL)
- return ERR_PTR(error);
-
- f->f_flags = flags;
- f->f_path = *path;
- error = do_dentry_open(f, NULL, cred);
- if (!error) {
- error = open_check_o_direct(f);
- if (error) {
- fput(f);
+ if (!IS_ERR(f)) {
+ f->f_flags = flags;
+ f->f_path = *path;
+ error = do_dentry_open(f, NULL, cred);
+ if (!error) {
+ /* from now on we need fput() to dispose of f */
+ error = open_check_o_direct(f);
+ if (error) {
+ fput(f);
+ f = ERR_PTR(error);
+ }
+ } else {
+ put_filp(f);
f = ERR_PTR(error);
}
- } else {
- put_filp(f);
- f = ERR_PTR(error);
}
return f;
}
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 2ad080f..75885ff 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -262,7 +262,7 @@
static int openpromfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct op_inode_info *oi = OP_I(inode);
struct device_node *dp = oi->u.node;
struct device_node *child;
@@ -432,6 +432,7 @@
.mount = openprom_mount,
.kill_sb = kill_anon_super,
};
+MODULE_ALIAS_FS("openpromfs");
static void op_inode_init_once(void *data)
{
diff --git a/fs/pipe.c b/fs/pipe.c
index bd3479d..2234f3f 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -361,7 +361,7 @@
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct pipe_inode_info *pipe;
int do_wakeup;
ssize_t ret;
@@ -486,7 +486,7 @@
unsigned long nr_segs, loff_t ppos)
{
struct file *filp = iocb->ki_filp;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct pipe_inode_info *pipe;
ssize_t ret;
int do_wakeup;
@@ -677,7 +677,7 @@
static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct pipe_inode_info *pipe;
int count, buf, nrbufs;
@@ -705,7 +705,7 @@
pipe_poll(struct file *filp, poll_table *wait)
{
unsigned int mask;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct pipe_inode_info *pipe = inode->i_pipe;
int nrbufs;
@@ -758,7 +758,7 @@
static int
pipe_read_fasync(int fd, struct file *filp, int on)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int retval;
mutex_lock(&inode->i_mutex);
@@ -772,7 +772,7 @@
static int
pipe_write_fasync(int fd, struct file *filp, int on)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int retval;
mutex_lock(&inode->i_mutex);
@@ -786,7 +786,7 @@
static int
pipe_rdwr_fasync(int fd, struct file *filp, int on)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct pipe_inode_info *pipe = inode->i_pipe;
int retval;
@@ -863,6 +863,9 @@
{
int ret = -ENOENT;
+ if (!(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
+ return -EINVAL;
+
mutex_lock(&inode->i_mutex);
if (inode->i_pipe) {
@@ -1037,13 +1040,13 @@
err = -ENFILE;
f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops);
- if (!f)
+ if (IS_ERR(f))
goto err_dentry;
f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
res[0] = alloc_file(&path, FMODE_READ, &read_pipefifo_fops);
- if (!res[0])
+ if (IS_ERR(res[0]))
goto err_file;
path_get(&path);
@@ -1226,7 +1229,7 @@
*/
struct pipe_inode_info *get_pipe_info(struct file *file)
{
- struct inode *i = file->f_path.dentry->d_inode;
+ struct inode *i = file_inode(file);
return S_ISFIFO(i->i_mode) ? i->i_pipe : NULL;
}
diff --git a/fs/pnode.c b/fs/pnode.c
index 3e000a5..8b29d21 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -9,6 +9,7 @@
#include <linux/mnt_namespace.h>
#include <linux/mount.h>
#include <linux/fs.h>
+#include <linux/nsproxy.h>
#include "internal.h"
#include "pnode.h"
@@ -220,6 +221,7 @@
int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry,
struct mount *source_mnt, struct list_head *tree_list)
{
+ struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
struct mount *m, *child;
int ret = 0;
struct mount *prev_dest_mnt = dest_mnt;
@@ -237,6 +239,10 @@
source = get_source(m, prev_dest_mnt, prev_src_mnt, &type);
+ /* Notice when we are propagating across user namespaces */
+ if (m->mnt_ns->user_ns != user_ns)
+ type |= CL_UNPRIVILEGED;
+
child = copy_tree(source, source->mnt.mnt_root, type);
if (IS_ERR(child)) {
ret = PTR_ERR(child);
diff --git a/fs/pnode.h b/fs/pnode.h
index 19b853a3..a0493d5 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -23,6 +23,7 @@
#define CL_MAKE_SHARED 0x08
#define CL_PRIVATE 0x10
#define CL_SHARED_TO_SLAVE 0x20
+#define CL_UNPRIVILEGED 0x40
static inline void set_mnt_shared(struct mount *mnt)
{
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 981b056..712f24d 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -8,7 +8,8 @@
proc-$(CONFIG_MMU) := mmu.o task_mmu.o
proc-y += inode.o root.o base.o generic.o array.o \
- proc_tty.o fd.o
+ fd.o
+proc-$(CONFIG_TTY) += proc_tty.o
proc-y += cmdline.o
proc-y += consoles.o
proc-y += cpuinfo.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 6a91e6f..f7ed9ee 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -449,7 +449,7 @@
do {
min_flt += t->min_flt;
maj_flt += t->maj_flt;
- gtime += t->gtime;
+ gtime += task_gtime(t);
t = next_thread(t);
} while (t != task);
@@ -472,7 +472,7 @@
min_flt = task->min_flt;
maj_flt = task->maj_flt;
task_cputime_adjusted(task, &utime, &stime);
- gtime = task->gtime;
+ gtime = task_gtime(task);
}
/* scale priority and nice values from timeslices to -20..20 */
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 9b43ff77..69078c7 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -73,6 +73,7 @@
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/tracehook.h>
+#include <linux/printk.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
@@ -383,7 +384,7 @@
static ssize_t lstats_write(struct file *file, const char __user *buf,
size_t count, loff_t *offs)
{
- struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+ struct task_struct *task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
@@ -602,7 +603,7 @@
static ssize_t proc_info_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
unsigned long page;
ssize_t length;
struct task_struct *task = get_proc_task(inode);
@@ -668,7 +669,7 @@
static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
{
- struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ struct task_struct *task = get_proc_task(file_inode(file));
struct mm_struct *mm;
if (!task)
@@ -869,7 +870,7 @@
static ssize_t oom_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);
+ struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
int oom_adj = OOM_ADJUST_MIN;
size_t len;
@@ -916,7 +917,7 @@
goto out;
}
- task = get_proc_task(file->f_path.dentry->d_inode);
+ task = get_proc_task(file_inode(file));
if (!task) {
err = -ESRCH;
goto out;
@@ -952,7 +953,7 @@
* /proc/pid/oom_adj is provided for legacy purposes, ask users to use
* /proc/pid/oom_score_adj instead.
*/
- printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+ pr_warn_once("%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));
@@ -976,7 +977,7 @@
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);
+ struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
short oom_score_adj = OOM_SCORE_ADJ_MIN;
unsigned long flags;
@@ -1019,7 +1020,7 @@
goto out;
}
- task = get_proc_task(file->f_path.dentry->d_inode);
+ task = get_proc_task(file_inode(file));
if (!task) {
err = -ESRCH;
goto out;
@@ -1067,7 +1068,7 @@
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
struct task_struct *task = get_proc_task(inode);
ssize_t length;
char tmpbuf[TMPBUFLEN];
@@ -1084,7 +1085,7 @@
static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
char *page, *tmp;
ssize_t length;
uid_t loginuid;
@@ -1142,7 +1143,7 @@
static ssize_t proc_sessionid_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
struct task_struct *task = get_proc_task(inode);
ssize_t length;
char tmpbuf[TMPBUFLEN];
@@ -1165,7 +1166,7 @@
static ssize_t proc_fault_inject_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+ struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
size_t len;
int make_it_fail;
@@ -1197,7 +1198,7 @@
make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
- task = get_proc_task(file->f_dentry->d_inode);
+ task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
task->make_it_fail = make_it_fail;
@@ -1237,7 +1238,7 @@
sched_write(struct file *file, const char __user *buf,
size_t count, loff_t *offset)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct task_struct *p;
p = get_proc_task(inode);
@@ -1288,7 +1289,7 @@
sched_autogroup_write(struct file *file, const char __user *buf,
size_t count, loff_t *offset)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct task_struct *p;
char buffer[PROC_NUMBUF];
int nice;
@@ -1343,7 +1344,7 @@
static ssize_t comm_write(struct file *file, const char __user *buf,
size_t count, loff_t *offset)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct task_struct *p;
char buffer[TASK_COMM_LEN];
@@ -1711,7 +1712,7 @@
return -ECHILD;
if (!capable(CAP_SYS_ADMIN)) {
- status = -EACCES;
+ status = -EPERM;
goto out_notask;
}
@@ -1844,7 +1845,7 @@
struct dentry *result;
struct mm_struct *mm;
- result = ERR_PTR(-EACCES);
+ result = ERR_PTR(-EPERM);
if (!capable(CAP_SYS_ADMIN))
goto out;
@@ -1900,7 +1901,7 @@
ino_t ino;
int ret;
- ret = -EACCES;
+ ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out;
@@ -2146,7 +2147,7 @@
static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
char *p = NULL;
ssize_t length;
struct task_struct *task = get_proc_task(inode);
@@ -2167,7 +2168,7 @@
static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
size_t count, loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
char *page;
ssize_t length;
struct task_struct *task = get_proc_task(inode);
@@ -2256,7 +2257,7 @@
static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+ struct task_struct *task = get_proc_task(file_inode(file));
struct mm_struct *mm;
char buffer[PROC_NUMBUF];
size_t len;
@@ -2308,7 +2309,7 @@
goto out_no_task;
ret = -ESRCH;
- task = get_proc_task(file->f_dentry->d_inode);
+ task = get_proc_task(file_inode(file));
if (!task)
goto out_no_task;
@@ -2618,6 +2619,7 @@
name.name = buf;
name.len = snprintf(buf, sizeof(buf), "%d", pid);
+ /* no ->d_hash() rejects on procfs */
dentry = d_hash_and_lookup(mnt->mnt_root, &name);
if (dentry) {
shrink_dcache_parent(dentry);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 76ddae8..4b3b3ff 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -15,6 +15,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/printk.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/idr.h>
@@ -42,7 +43,7 @@
__proc_file_read(struct file *file, char __user *buf, size_t nbytes,
loff_t *ppos)
{
- struct inode * inode = file->f_path.dentry->d_inode;
+ struct inode * inode = file_inode(file);
char *page;
ssize_t retval=0;
int eof=0;
@@ -132,11 +133,8 @@
}
if (start == NULL) {
- if (n > PAGE_SIZE) {
- printk(KERN_ERR
- "proc_file_read: Apparent buffer overflow!\n");
+ if (n > PAGE_SIZE) /* Apparent buffer overflow */
n = PAGE_SIZE;
- }
n -= *ppos;
if (n <= 0)
break;
@@ -144,26 +142,19 @@
n = count;
start = page + *ppos;
} else if (start < page) {
- if (n > PAGE_SIZE) {
- printk(KERN_ERR
- "proc_file_read: Apparent buffer overflow!\n");
+ if (n > PAGE_SIZE) /* Apparent buffer overflow */
n = PAGE_SIZE;
- }
if (n > count) {
/*
* Don't reduce n because doing so might
* cut off part of a data block.
*/
- printk(KERN_WARNING
- "proc_file_read: Read count exceeded\n");
+ pr_warn("proc_file_read: count exceeded\n");
}
} else /* start >= page */ {
unsigned long startoff = (unsigned long)(start - page);
- if (n > (PAGE_SIZE - startoff)) {
- printk(KERN_ERR
- "proc_file_read: Apparent buffer overflow!\n");
+ if (n > (PAGE_SIZE - startoff)) /* buffer overflow? */
n = PAGE_SIZE - startoff;
- }
if (n > count)
n = count;
}
@@ -188,7 +179,7 @@
proc_file_read(struct file *file, char __user *buf, size_t nbytes,
loff_t *ppos)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
spin_lock(&pde->pde_unload_lock);
@@ -209,7 +200,7 @@
proc_file_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
if (pde->write_proc) {
@@ -412,8 +403,7 @@
struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
struct dentry *dentry)
{
- struct inode *inode = NULL;
- int error = -ENOENT;
+ struct inode *inode;
spin_lock(&proc_subdir_lock);
for (de = de->subdir; de ; de = de->next) {
@@ -422,22 +412,16 @@
if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
pde_get(de);
spin_unlock(&proc_subdir_lock);
- error = -ENOMEM;
inode = proc_get_inode(dir->i_sb, de);
- goto out_unlock;
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ d_set_d_op(dentry, &proc_dentry_operations);
+ d_add(dentry, inode);
+ return NULL;
}
}
spin_unlock(&proc_subdir_lock);
-out_unlock:
-
- if (inode) {
- d_set_d_op(dentry, &proc_dentry_operations);
- d_add(dentry, inode);
- return NULL;
- }
- if (de)
- pde_put(de);
- return ERR_PTR(error);
+ return ERR_PTR(-ENOENT);
}
struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
@@ -460,7 +444,7 @@
{
unsigned int ino;
int i;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
int ret = 0;
ino = inode->i_ino;
@@ -522,7 +506,7 @@
int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
return proc_readdir_de(PDE(inode), filp, dirent, filldir);
}
@@ -576,7 +560,7 @@
for (tmp = dir->subdir; tmp; tmp = tmp->next)
if (strcmp(tmp->name, dp->name) == 0) {
- WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n",
+ WARN(1, "proc_dir_entry '%s/%s' already registered\n",
dir->name, dp->name);
break;
}
@@ -837,9 +821,9 @@
if (S_ISDIR(de->mode))
parent->nlink--;
de->nlink = 0;
- WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
- "'%s/%s', leaking at least '%s'\n", __func__,
- de->parent->name, de->name, de->subdir->name);
+ WARN(de->subdir, "%s: removing non-empty directory "
+ "'%s/%s', leaking at least '%s'\n", __func__,
+ de->parent->name, de->name, de->subdir->name);
pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 439ae688..869116c 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -13,6 +13,7 @@
#include <linux/stat.h>
#include <linux/completion.h>
#include <linux/poll.h>
+#include <linux/printk.h>
#include <linux/file.h>
#include <linux/limits.h>
#include <linux/init.h>
@@ -144,7 +145,7 @@
static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
loff_t rv = -EINVAL;
loff_t (*llseek)(struct file *, loff_t, int);
@@ -179,7 +180,7 @@
static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
@@ -201,7 +202,7 @@
static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
ssize_t rv = -EIO;
ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
@@ -223,7 +224,7 @@
static unsigned int proc_reg_poll(struct file *file, struct poll_table_struct *pts)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
unsigned int rv = DEFAULT_POLLMASK;
unsigned int (*poll)(struct file *, struct poll_table_struct *);
@@ -245,7 +246,7 @@
static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
long rv = -ENOTTY;
long (*ioctl)(struct file *, unsigned int, unsigned long);
@@ -268,7 +269,7 @@
#ifdef CONFIG_COMPAT
static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
long rv = -ENOTTY;
long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
@@ -291,7 +292,7 @@
static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
{
- struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode);
+ struct proc_dir_entry *pde = PDE(file_inode(file));
int rv = -EIO;
int (*mmap)(struct file *, struct vm_area_struct *);
@@ -445,12 +446,10 @@
struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
{
- struct inode * inode;
+ struct inode *inode = new_inode_pseudo(sb);
- inode = iget_locked(sb, de->low_ino);
- if (!inode)
- return NULL;
- if (inode->i_state & I_NEW) {
+ if (inode) {
+ inode->i_ino = de->low_ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
PROC_I(inode)->pde = de;
@@ -478,14 +477,15 @@
inode->i_fop = de->proc_fops;
}
}
- unlock_new_inode(inode);
} else
pde_put(de);
return inode;
-}
+}
int proc_fill_super(struct super_block *s)
{
+ struct inode *root_inode;
+
s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
@@ -494,11 +494,17 @@
s->s_time_gran = 1;
pde_get(&proc_root);
- s->s_root = d_make_root(proc_get_inode(s, &proc_root));
- if (s->s_root)
- return 0;
+ root_inode = proc_get_inode(s, &proc_root);
+ if (!root_inode) {
+ pr_err("proc_fill_super: get root inode failed\n");
+ return -ENOMEM;
+ }
- printk("proc_read_super: get root inode failed\n");
- pde_put(&proc_root);
- return -ENOMEM;
+ s->s_root = d_make_root(root_inode);
+ if (!s->s_root) {
+ pr_err("proc_fill_super: allocate dentry failed\n");
+ return -ENOMEM;
+ }
+
+ return 0;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 252544c..85ff3a4 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -11,6 +11,7 @@
#include <linux/sched.h>
#include <linux/proc_fs.h>
+#include <linux/binfmts.h>
struct ctl_table_header;
struct mempolicy;
@@ -108,7 +109,7 @@
if (mm)
dumpable = get_dumpable(mm);
task_unlock(task);
- if (dumpable == SUID_DUMPABLE_ENABLED)
+ if (dumpable == SUID_DUMP_USER)
return 1;
return 0;
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e96d4f1..eda6f01 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -17,6 +17,7 @@
#include <linux/elfcore.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
+#include <linux/printk.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/slab.h>
@@ -619,7 +620,7 @@
proc_root_kcore = proc_create("kcore", S_IRUSR, NULL,
&proc_kcore_operations);
if (!proc_root_kcore) {
- printk(KERN_ERR "couldn't create /proc/kcore\n");
+ pr_err("couldn't create /proc/kcore\n");
return 0; /* Always returns 0. */
}
/* Store text area if it's special */
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 80e4645..1efaaa1 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -40,7 +40,7 @@
* sysctl_overcommit_ratio / 100) + total_swap_pages;
cached = global_page_state(NR_FILE_PAGES) -
- total_swapcache_pages - i.bufferram;
+ total_swapcache_pages() - i.bufferram;
if (cached < 0)
cached = 0;
@@ -109,7 +109,7 @@
K(i.freeram),
K(i.bufferram),
K(cached),
- K(total_swapcache_pages),
+ K(total_swapcache_pages()),
K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]),
K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
K(pages[LRU_ACTIVE_ANON]),
@@ -158,7 +158,7 @@
vmi.used >> 10,
vmi.largest_chunk >> 10
#ifdef CONFIG_MEMORY_FAILURE
- ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
+ ,atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
,K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index b7a4719..66b51c0 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -118,7 +118,7 @@
struct super_block *sb = inode->i_sb;
struct proc_inode *ei = PROC_I(inode);
struct task_struct *task;
- struct dentry *ns_dentry;
+ struct path ns_path;
void *error = ERR_PTR(-EACCES);
task = get_proc_task(inode);
@@ -128,14 +128,14 @@
if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto out_put_task;
- ns_dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
- if (IS_ERR(ns_dentry)) {
- error = ERR_CAST(ns_dentry);
+ ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
+ if (IS_ERR(ns_path.dentry)) {
+ error = ERR_CAST(ns_path.dentry);
goto out_put_task;
}
- dput(nd->path.dentry);
- nd->path.dentry = ns_dentry;
+ ns_path.mnt = mntget(nd->path.mnt);
+ nd_jump_link(nd, &ns_path);
error = NULL;
out_put_task:
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index b1822dd..ccfd99b 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -45,7 +45,7 @@
file = region->vm_file;
if (file) {
- struct inode *inode = region->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(region->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
}
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index de20ec4..30b590f 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -8,6 +8,7 @@
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/printk.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/of.h>
@@ -110,8 +111,8 @@
if (ent->data == oldprop)
break;
if (ent == NULL) {
- printk(KERN_WARNING "device-tree: property \"%s\" "
- " does not exist\n", oldprop->name);
+ pr_warn("device-tree: property \"%s\" does not exist\n",
+ oldprop->name);
} else {
ent->data = newprop;
ent->size = newprop->length;
@@ -153,8 +154,8 @@
realloc:
fixed_name = kmalloc(fixup_len, GFP_KERNEL);
if (fixed_name == NULL) {
- printk(KERN_ERR "device-tree: Out of memory trying to fixup "
- "name \"%s\"\n", name);
+ pr_err("device-tree: Out of memory trying to fixup "
+ "name \"%s\"\n", name);
return name;
}
@@ -175,8 +176,8 @@
goto retry;
}
- printk(KERN_WARNING "device-tree: Duplicate name in %s, "
- "renamed to \"%s\"\n", np->full_name, fixed_name);
+ pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
+ np->full_name, fixed_name);
return fixed_name;
}
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index fe72cd0..b4ac657 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -163,7 +163,7 @@
struct net *net;
ret = -EINVAL;
- net = get_proc_task_net(filp->f_path.dentry->d_inode);
+ net = get_proc_task_net(file_inode(filp));
if (net != NULL) {
ret = proc_readdir_de(net->proc_net, filp, dirent, filldir);
put_net(net);
@@ -177,20 +177,6 @@
.readdir = proc_tgid_net_readdir,
};
-
-struct proc_dir_entry *proc_net_fops_create(struct net *net,
- const char *name, umode_t mode, const struct file_operations *fops)
-{
- return proc_create(name, mode, net->proc_net, fops);
-}
-EXPORT_SYMBOL_GPL(proc_net_fops_create);
-
-void proc_net_remove(struct net *net, const char *name)
-{
- remove_proc_entry(name, net->proc_net);
-}
-EXPORT_SYMBOL_GPL(proc_net_remove);
-
static __net_init int proc_net_ns_init(struct net *net)
{
struct proc_dir_entry *netd, *net_statd;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 1827d88..ac05f33 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -5,6 +5,7 @@
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/proc_fs.h>
+#include <linux/printk.h>
#include <linux/security.h>
#include <linux/sched.h>
#include <linux/namei.h>
@@ -57,7 +58,7 @@
{
if (dir->header.parent)
sysctl_print_dir(dir->header.parent);
- printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
+ pr_cont("%s/", dir->header.ctl_table[0].procname);
}
static int namecmp(const char *name1, int len1, const char *name2, int len2)
@@ -134,9 +135,9 @@
else if (cmp > 0)
p = &(*p)->rb_right;
else {
- printk(KERN_ERR "sysctl duplicate entry: ");
+ pr_err("sysctl duplicate entry: ");
sysctl_print_dir(head->parent);
- printk(KERN_CONT "/%s\n", entry->procname);
+ pr_cont("/%s\n", entry->procname);
return -EEXIST;
}
}
@@ -478,7 +479,7 @@
static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
size_t count, loff_t *ppos, int write)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ctl_table_header *head = grab_header(inode);
struct ctl_table *table = PROC_I(inode)->sysctl_entry;
ssize_t error;
@@ -542,7 +543,7 @@
static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ctl_table_header *head = grab_header(inode);
struct ctl_table *table = PROC_I(inode)->sysctl_entry;
unsigned int ret = DEFAULT_POLLMASK;
@@ -927,9 +928,9 @@
subdir->header.nreg++;
failed:
if (unlikely(IS_ERR(subdir))) {
- printk(KERN_ERR "sysctl could not get directory: ");
+ pr_err("sysctl could not get directory: ");
sysctl_print_dir(dir);
- printk(KERN_CONT "/%*.*s %ld\n",
+ pr_cont("/%*.*s %ld\n",
namelen, namelen, name, PTR_ERR(subdir));
}
drop_sysctl_table(&dir->header);
@@ -995,8 +996,8 @@
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n",
- path, table->procname, &vaf);
+ pr_err("sysctl table check failed: %s/%s %pV\n",
+ path, table->procname, &vaf);
va_end(args);
return -EINVAL;
@@ -1510,9 +1511,9 @@
drop_sysctl_table(link_head);
}
else {
- printk(KERN_ERR "sysctl link missing during unregister: ");
+ pr_err("sysctl link missing during unregister: ");
sysctl_print_dir(parent);
- printk(KERN_CONT "/%s\n", name);
+ pr_cont("/%s\n", name);
}
}
}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index c6e9fac..9c7fab1 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -16,6 +16,7 @@
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/bitops.h>
+#include <linux/user_namespace.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
#include <linux/parser.h>
@@ -108,6 +109,9 @@
} else {
ns = task_active_pid_ns(current);
options = data;
+
+ if (!current_user_ns()->may_mount_proc)
+ return ERR_PTR(-EPERM);
}
sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ca5ce7f..3e636d8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -271,7 +271,7 @@
const char *name = NULL;
if (file) {
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -743,7 +743,7 @@
return rv;
if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
return -EINVAL;
- task = get_proc_task(file->f_path.dentry->d_inode);
+ task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
mm = get_task_mm(task);
@@ -1015,7 +1015,7 @@
static ssize_t pagemap_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);
+ struct task_struct *task = get_proc_task(file_inode(file));
struct mm_struct *mm;
struct pagemapread pm;
int ret = -ESRCH;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 1ccfa53..56123a6 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -149,7 +149,7 @@
file = vma->vm_file;
if (file) {
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 0d5071d..b870f74 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -15,6 +15,7 @@
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/highmem.h>
+#include <linux/printk.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
@@ -175,15 +176,15 @@
start = map_offset_to_paddr(*fpos, &vmcore_list, &curr_m);
if (!curr_m)
return -EINVAL;
- if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
- tsz = buflen;
-
- /* Calculate left bytes in current memory segment. */
- nr_bytes = (curr_m->size - (start - curr_m->paddr));
- if (tsz > nr_bytes)
- tsz = nr_bytes;
while (buflen) {
+ tsz = min_t(size_t, buflen, PAGE_SIZE - (start & ~PAGE_MASK));
+
+ /* Calculate left bytes in current memory segment. */
+ nr_bytes = (curr_m->size - (start - curr_m->paddr));
+ if (tsz > nr_bytes)
+ tsz = nr_bytes;
+
tmp = read_from_oldmem(buffer, tsz, &start, 1);
if (tmp < 0)
return tmp;
@@ -198,12 +199,6 @@
struct vmcore, list);
start = curr_m->paddr;
}
- if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
- tsz = buflen;
- /* Calculate left bytes in current memory segment. */
- nr_bytes = (curr_m->size - (start - curr_m->paddr));
- if (tsz > nr_bytes)
- tsz = nr_bytes;
}
return acc;
}
@@ -553,8 +548,7 @@
ehdr.e_ehsize != sizeof(Elf64_Ehdr) ||
ehdr.e_phentsize != sizeof(Elf64_Phdr) ||
ehdr.e_phnum == 0) {
- printk(KERN_WARNING "Warning: Core image elf header is not"
- "sane\n");
+ pr_warn("Warning: Core image elf header is not sane\n");
return -EINVAL;
}
@@ -609,8 +603,7 @@
ehdr.e_ehsize != sizeof(Elf32_Ehdr) ||
ehdr.e_phentsize != sizeof(Elf32_Phdr) ||
ehdr.e_phnum == 0) {
- printk(KERN_WARNING "Warning: Core image elf header is not"
- "sane\n");
+ pr_warn("Warning: Core image elf header is not sane\n");
return -EINVAL;
}
@@ -653,8 +646,7 @@
if (rc < 0)
return rc;
if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
- printk(KERN_WARNING "Warning: Core image elf header"
- " not found\n");
+ pr_warn("Warning: Core image elf header not found\n");
return -EINVAL;
}
@@ -673,8 +665,7 @@
/* Determine vmcore size. */
vmcore_size = get_vmcore_size_elf32(elfcorebuf);
} else {
- printk(KERN_WARNING "Warning: Core image elf header is not"
- " sane\n");
+ pr_warn("Warning: Core image elf header is not sane\n");
return -EINVAL;
}
return 0;
@@ -690,7 +681,7 @@
return rc;
rc = parse_crash_elf_headers();
if (rc) {
- printk(KERN_WARNING "Kdump: vmcore not initialized\n");
+ pr_warn("Kdump: vmcore not initialized\n");
return rc;
}
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 67de74c..e4bcb2c 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -418,9 +418,25 @@
.kill_sb = pstore_kill_sb,
};
+static struct kobject *pstore_kobj;
+
static int __init init_pstore_fs(void)
{
- return register_filesystem(&pstore_fs_type);
+ int err = 0;
+
+ /* Create a convenient mount point for people to access pstore */
+ pstore_kobj = kobject_create_and_add("pstore", fs_kobj);
+ if (!pstore_kobj) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ err = register_filesystem(&pstore_fs_type);
+ if (err < 0)
+ kobject_put(pstore_kobj);
+
+out:
+ return err;
}
module_init(init_pstore_fs)
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 5ea2e77..86d1038 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -96,6 +96,27 @@
}
}
+bool pstore_cannot_block_path(enum kmsg_dump_reason reason)
+{
+ /*
+ * In case of NMI path, pstore shouldn't be blocked
+ * regardless of reason.
+ */
+ if (in_nmi())
+ return true;
+
+ switch (reason) {
+ /* In panic case, other cpus are stopped by smp_send_stop(). */
+ case KMSG_DUMP_PANIC:
+ /* Emergency restart shouldn't be blocked by spin lock. */
+ case KMSG_DUMP_EMERG:
+ return true;
+ default:
+ return false;
+ }
+}
+EXPORT_SYMBOL_GPL(pstore_cannot_block_path);
+
/*
* callback from kmsg_dump. (s2,l2) has the most recently
* written bytes, older bytes are in (s1,l1). Save as much
@@ -114,10 +135,12 @@
why = get_reason_str(reason);
- if (in_nmi()) {
- is_locked = spin_trylock(&psinfo->buf_lock);
- if (!is_locked)
- pr_err("pstore dump routine blocked in NMI, may corrupt error record\n");
+ if (pstore_cannot_block_path(reason)) {
+ is_locked = spin_trylock_irqsave(&psinfo->buf_lock, flags);
+ if (!is_locked) {
+ pr_err("pstore dump routine blocked in %s path, may corrupt error record\n"
+ , in_nmi() ? "NMI" : why);
+ }
} else
spin_lock_irqsave(&psinfo->buf_lock, flags);
oopscount++;
@@ -143,9 +166,9 @@
total += hsize + len;
part++;
}
- if (in_nmi()) {
+ if (pstore_cannot_block_path(reason)) {
if (is_locked)
- spin_unlock(&psinfo->buf_lock);
+ spin_unlock_irqrestore(&psinfo->buf_lock, flags);
} else
spin_unlock_irqrestore(&psinfo->buf_lock, flags);
}
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 7003e52..288f068 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -167,12 +167,16 @@
static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz)
{
char *hdr;
- struct timeval timestamp;
+ struct timespec timestamp;
size_t len;
- do_gettimeofday(×tamp);
+ /* Report zeroed timestamp if called before timekeeping has resumed. */
+ if (__getnstimeofday(×tamp)) {
+ timestamp.tv_sec = 0;
+ timestamp.tv_nsec = 0;
+ }
hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n",
- (long)timestamp.tv_sec, (long)timestamp.tv_usec);
+ (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000));
WARN_ON_ONCE(!hdr);
len = hdr ? strlen(hdr) : 0;
persistent_ram_write(prz, hdr, len);
diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c
index 7b03294..28ce014 100644
--- a/fs/qnx4/dir.c
+++ b/fs/qnx4/dir.c
@@ -16,7 +16,7 @@
static int qnx4_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
unsigned int offset;
struct buffer_head *bh;
struct qnx4_inode_entry *de;
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 43098bb..2e8caa6 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -412,6 +412,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("qnx4");
static int __init init_qnx4_fs(void)
{
diff --git a/fs/qnx6/dir.c b/fs/qnx6/dir.c
index dc59735..8798d06 100644
--- a/fs/qnx6/dir.c
+++ b/fs/qnx6/dir.c
@@ -117,7 +117,7 @@
static int qnx6_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *s = inode->i_sb;
struct qnx6_sb_info *sbi = QNX6_SB(s);
loff_t pos = filp->f_pos & (QNX6_DIR_ENTRY_SIZE - 1);
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index b6addf5..8d941ed 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -285,7 +285,7 @@
if (fs32_to_cpu(sbi, sb->sb_magic) == QNX6_SUPER_MAGIC) {
/* we got a big endian fs */
QNX6DEBUG((KERN_INFO "qnx6: fs got different"
- " endianess.\n"));
+ " endianness.\n"));
return bh;
} else
sbi->s_bytesex = BYTESEX_LE;
@@ -672,6 +672,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("qnx6");
static int __init init_qnx6_fs(void)
{
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 05ae3c9..3e64169 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1439,8 +1439,11 @@
* did a write before quota was turned on
*/
rsv = inode_get_rsv_space(inode);
- if (unlikely(rsv))
+ if (unlikely(rsv)) {
+ spin_lock(&dq_data_lock);
dquot_resv_space(inode->i_dquot[cnt], rsv);
+ spin_unlock(&dq_data_lock);
+ }
}
}
out_err:
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index d5378d0..8d5b438 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -202,7 +202,7 @@
unsigned long pgoff, unsigned long flags)
{
unsigned long maxpages, lpages, nr, loop, ret;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct page **pages = NULL, **ptr, *page;
loff_t isize;
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index eab8c09..c24f1e1 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -260,6 +260,7 @@
.name = "ramfs",
.mount = ramfs_mount,
.kill_sb = ramfs_kill_sb,
+ .fs_flags = FS_USERNS_MOUNT,
};
static struct file_system_type rootfs_fs_type = {
.name = "rootfs",
diff --git a/fs/read_write.c b/fs/read_write.c
index bb34af3..e6ddc8d 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -15,7 +15,9 @@
#include <linux/syscalls.h>
#include <linux/pagemap.h>
#include <linux/splice.h>
+#include <linux/compat.h>
#include "read_write.h"
+#include "internal.h"
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -163,7 +165,7 @@
loff_t default_llseek(struct file *file, loff_t offset, int whence)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
loff_t retval;
mutex_lock(&inode->i_mutex);
@@ -247,6 +249,13 @@
return retval;
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence)
+{
+ return sys_lseek(fd, offset, whence);
+}
+#endif
+
#ifdef __ARCH_WANT_SYS_LLSEEK
SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned long, offset_low, loff_t __user *, result,
@@ -278,7 +287,6 @@
}
#endif
-
/*
* rw_verify_area doesn't like huge counts. We limit
* them to something that fits in "int" so that others
@@ -290,7 +298,7 @@
loff_t pos;
int retval = -EINVAL;
- inode = file->f_path.dentry->d_inode;
+ inode = file_inode(file);
if (unlikely((ssize_t) count < 0))
return retval;
pos = *ppos;
@@ -410,6 +418,33 @@
EXPORT_SYMBOL(do_sync_write);
+ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
+{
+ mm_segment_t old_fs;
+ const char __user *p;
+ ssize_t ret;
+
+ if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
+ return -EINVAL;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ p = (__force const char __user *)buf;
+ if (count > MAX_RW_COUNT)
+ count = MAX_RW_COUNT;
+ if (file->f_op->write)
+ ret = file->f_op->write(file, p, count, pos);
+ else
+ ret = do_sync_write(file, p, count, pos);
+ set_fs(old_fs);
+ if (ret > 0) {
+ fsnotify_modify(file);
+ add_wchar(current, ret);
+ }
+ inc_syscw(current);
+ return ret;
+}
+
ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
{
ssize_t ret;
@@ -901,8 +936,8 @@
if (!(out.file->f_mode & FMODE_WRITE))
goto fput_out;
retval = -EINVAL;
- in_inode = in.file->f_path.dentry->d_inode;
- out_inode = out.file->f_path.dentry->d_inode;
+ in_inode = file_inode(in.file);
+ out_inode = file_inode(out.file);
retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count);
if (retval < 0)
goto fput_out;
diff --git a/fs/readdir.c b/fs/readdir.c
index 5e69ef5..fee38e0 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -22,7 +22,7 @@
int vfs_readdir(struct file *file, filldir_t filler, void *buf)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
int res = -ENOTDIR;
if (!file->f_op || !file->f_op->readdir)
goto out;
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 50302d6..6165bd4 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -268,7 +268,7 @@
* new current position before returning. */
)
{
- struct inode *inode = file->f_path.dentry->d_inode; // Inode of the file that we are writing to.
+ struct inode *inode = file_inode(file); // Inode of the file that we are writing to.
/* To simplify coding at this time, we store
locked pages in array for now */
struct reiserfs_transaction_handle th;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 95d7680..ea5061fd 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1603,10 +1603,10 @@
if (parent && (maxlen < 5)) {
*lenp = 5;
- return 255;
+ return FILEID_INVALID;
} else if (maxlen < 3) {
*lenp = 3;
- return 255;
+ return FILEID_INVALID;
}
data[0] = inode->i_ino;
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 0c21850..15cb5fe 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -21,7 +21,7 @@
*/
long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
unsigned int flags;
int err = 0;
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index e60e870..9cc0740a 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -281,7 +281,7 @@
}
#if defined( REISERFS_USE_OIDMAPF )
if (sb_info->oidmap.use_file && (sb_info->oidmap.mapf != NULL)) {
- loff_t size = sb_info->oidmap.mapf->f_path.dentry->d_inode->i_size;
+ loff_t size = file_inode(sb_info->oidmap.mapf)->i_size;
total_used += size / sizeof(reiserfs_oidinterval_d_t);
}
#endif
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 418bdc3..f8a23c3 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1147,8 +1147,7 @@
"on filesystem root.");
return 0;
}
- qf_names[qtype] =
- kmalloc(strlen(arg) + 1, GFP_KERNEL);
+ qf_names[qtype] = kstrdup(arg, GFP_KERNEL);
if (!qf_names[qtype]) {
reiserfs_warning(s, "reiserfs-2502",
"not enough memory "
@@ -1156,7 +1155,6 @@
"quotafile name.");
return 0;
}
- strcpy(qf_names[qtype], arg);
if (qtype == USRQUOTA)
*mount_options |= 1 << REISERFS_USRQUOTA;
else
@@ -2434,6 +2432,7 @@
.kill_sb = reiserfs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("reiserfs");
MODULE_DESCRIPTION("ReiserFS journaled filesystem");
MODULE_AUTHOR("Hans Reiser <reiser@namesys.com>");
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index fd7c5f6..15cbc41e 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -147,7 +147,7 @@
*/
static int romfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *i = filp->f_dentry->d_inode;
+ struct inode *i = file_inode(filp);
struct romfs_inode ri;
unsigned long offset, maxoff;
int j, ino, nextfh;
@@ -599,6 +599,7 @@
.kill_sb = romfs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("romfs");
/*
* inode storage initialiser
diff --git a/fs/select.c b/fs/select.c
index 2ef72d9..8c1c96c 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -26,6 +26,7 @@
#include <linux/fs.h>
#include <linux/rcupdate.h>
#include <linux/hrtimer.h>
+#include <linux/sched/rt.h>
#include <asm/uaccess.h>
diff --git a/fs/seq_file.c b/fs/seq_file.c
index f2bc3df..38bb59f 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -308,27 +308,27 @@
mutex_lock(&m->lock);
m->version = file->f_version;
switch (whence) {
- case 1:
- offset += file->f_pos;
- case 0:
- if (offset < 0)
- break;
- retval = offset;
- if (offset != m->read_pos) {
- while ((retval=traverse(m, offset)) == -EAGAIN)
- ;
- if (retval) {
- /* with extreme prejudice... */
- file->f_pos = 0;
- m->read_pos = 0;
- m->version = 0;
- m->index = 0;
- m->count = 0;
- } else {
- m->read_pos = offset;
- retval = file->f_pos = offset;
- }
+ case SEEK_CUR:
+ offset += file->f_pos;
+ case SEEK_SET:
+ if (offset < 0)
+ break;
+ retval = offset;
+ if (offset != m->read_pos) {
+ while ((retval = traverse(m, offset)) == -EAGAIN)
+ ;
+ if (retval) {
+ /* with extreme prejudice... */
+ file->f_pos = 0;
+ m->read_pos = 0;
+ m->version = 0;
+ m->index = 0;
+ m->count = 0;
+ } else {
+ m->read_pos = offset;
+ retval = file->f_pos = offset;
}
+ }
}
file->f_version = m->version;
mutex_unlock(&m->lock);
@@ -339,7 +339,7 @@
/**
* seq_release - free the structures associated with sequential file.
* @file: file in question
- * @inode: file->f_path.dentry->d_inode
+ * @inode: its inode
*
* Frees the structures associated with sequential file; can be used
* as ->f_op->release() if you don't have private data to destroy.
diff --git a/fs/splice.c b/fs/splice.c
index 6909d89d0..29e394e 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -31,6 +31,7 @@
#include <linux/security.h>
#include <linux/gfp.h>
#include <linux/socket.h>
+#include "internal.h"
/*
* Attempt to steal a page from a pipe buffer. This should perhaps go into
@@ -569,7 +570,7 @@
return res;
}
-static ssize_t kernel_write(struct file *file, const char *buf, size_t count,
+ssize_t kernel_write(struct file *file, const char *buf, size_t count,
loff_t pos)
{
mm_segment_t old_fs;
@@ -578,11 +579,12 @@
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
- res = vfs_write(file, (const char __user *)buf, count, &pos);
+ res = vfs_write(file, (__force const char __user *)buf, count, &pos);
set_fs(old_fs);
return res;
}
+EXPORT_SYMBOL(kernel_write);
ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
@@ -1047,9 +1049,10 @@
{
int ret;
void *data;
+ loff_t tmp = sd->pos;
data = buf->ops->map(pipe, buf, 0);
- ret = kernel_write(sd->u.file, data + buf->offset, sd->len, sd->pos);
+ ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
buf->ops->unmap(pipe, buf, data);
return ret;
@@ -1170,7 +1173,7 @@
* randomly drop data for eg socket -> socket splicing. Use the
* piped splicing for that!
*/
- i_mode = in->f_path.dentry->d_inode->i_mode;
+ i_mode = file_inode(in)->i_mode;
if (unlikely(!S_ISREG(i_mode) && !S_ISBLK(i_mode)))
return -EINVAL;
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index b381305..57dc70e 100644
--- a/fs/squashfs/dir.c
+++ b/fs/squashfs/dir.c
@@ -102,7 +102,7 @@
static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
u64 block = squashfs_i(inode)->start + msblk->directory_table;
int offset = squashfs_i(inode)->offset, length, dir_count, size,
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 260e392..60553a9 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -489,6 +489,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV
};
+MODULE_ALIAS_FS("squashfs");
static const struct super_operations squashfs_super_ops = {
.alloc_inode = squashfs_alloc_inode,
diff --git a/fs/stat.c b/fs/stat.c
index 14f4545..04ce1ac 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -37,17 +37,17 @@
EXPORT_SYMBOL(generic_fillattr);
-int vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int vfs_getattr(struct path *path, struct kstat *stat)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = path->dentry->d_inode;
int retval;
- retval = security_inode_getattr(mnt, dentry);
+ retval = security_inode_getattr(path->mnt, path->dentry);
if (retval)
return retval;
if (inode->i_op->getattr)
- return inode->i_op->getattr(mnt, dentry, stat);
+ return inode->i_op->getattr(path->mnt, path->dentry, stat);
generic_fillattr(inode, stat);
return 0;
@@ -61,8 +61,7 @@
int error = -EBADF;
if (f.file) {
- error = vfs_getattr(f.file->f_path.mnt, f.file->f_path.dentry,
- stat);
+ error = vfs_getattr(&f.file->f_path, stat);
fdput(f);
}
return error;
@@ -89,7 +88,7 @@
if (error)
goto out;
- error = vfs_getattr(path.mnt, path.dentry, stat);
+ error = vfs_getattr(&path, stat);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
diff --git a/fs/super.c b/fs/super.c
index 12f1237..7465d43 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -447,14 +447,13 @@
void *data)
{
struct super_block *s = NULL;
- struct hlist_node *node;
struct super_block *old;
int err;
retry:
spin_lock(&sb_lock);
if (test) {
- hlist_for_each_entry(old, node, &type->fs_supers, s_instances) {
+ hlist_for_each_entry(old, &type->fs_supers, s_instances) {
if (!test(old, data))
continue;
if (!grab_super(old))
@@ -554,10 +553,9 @@
void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
- struct hlist_node *node;
spin_lock(&sb_lock);
- hlist_for_each_entry(sb, node, &type->fs_supers, s_instances) {
+ hlist_for_each_entry(sb, &type->fs_supers, s_instances) {
sb->s_count++;
spin_unlock(&sb_lock);
@@ -842,7 +840,7 @@
else if (error)
return -EAGAIN;
- if ((dev & MAX_IDR_MASK) == (1 << MINORBITS)) {
+ if (dev == (1 << MINORBITS)) {
spin_lock(&unnamed_dev_lock);
ida_remove(&unnamed_dev_ida, dev);
if (unnamed_dev_start > dev)
diff --git a/fs/sync.c b/fs/sync.c
index 14eefeb..2c5d663 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -332,7 +332,7 @@
if (!f.file)
goto out;
- i_mode = f.file->f_path.dentry->d_inode->i_mode;
+ i_mode = file_inode(f.file)->i_mode;
ret = -ESPIPE;
if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
!S_ISLNK(i_mode))
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index 614b2b5..15c68f9 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -70,7 +70,7 @@
read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off)
{
struct bin_buffer *bb = file->private_data;
- int size = file->f_path.dentry->d_inode->i_size;
+ int size = file_inode(file)->i_size;
loff_t offs = *off;
int count = min_t(size_t, bytes, PAGE_SIZE);
char *temp;
@@ -140,7 +140,7 @@
size_t bytes, loff_t *off)
{
struct bin_buffer *bb = file->private_data;
- int size = file->f_path.dentry->d_inode->i_size;
+ int size = file_inode(file)->i_size;
loff_t offs = *off;
int count = min_t(size_t, bytes, PAGE_SIZE);
char *temp;
@@ -461,15 +461,14 @@
void unmap_bin_file(struct sysfs_dirent *attr_sd)
{
struct bin_buffer *bb;
- struct hlist_node *tmp;
if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR)
return;
mutex_lock(&sysfs_bin_lock);
- hlist_for_each_entry(bb, tmp, &attr_sd->s_bin_attr.buffers, list) {
- struct inode *inode = bb->file->f_path.dentry->d_inode;
+ hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) {
+ struct inode *inode = file_inode(bb->file);
unmap_mapping_range(inode->i_mapping, 0, 0, 1);
}
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 2fbdff6..e145126 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -1020,6 +1020,8 @@
ino = parent_sd->s_ino;
if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) == 0)
filp->f_pos++;
+ else
+ return 0;
}
if (filp->f_pos == 1) {
if (parent_sd->s_parent)
@@ -1028,6 +1030,8 @@
ino = parent_sd->s_ino;
if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
filp->f_pos++;
+ else
+ return 0;
}
mutex_lock(&sysfs_mutex);
for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
@@ -1058,10 +1062,21 @@
return 0;
}
+static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+ struct inode *inode = file_inode(file);
+ loff_t ret;
+
+ mutex_lock(&inode->i_mutex);
+ ret = generic_file_llseek(file, offset, whence);
+ mutex_unlock(&inode->i_mutex);
+
+ return ret;
+}
const struct file_operations sysfs_dir_operations = {
.read = generic_read_dir,
.readdir = sysfs_readdir,
.release = sysfs_dir_release,
- .llseek = generic_file_llseek,
+ .llseek = sysfs_dir_llseek,
};
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 2df555c..aec3d5c 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -205,6 +205,48 @@
}
EXPORT_SYMBOL_GPL(sysfs_unmerge_group);
+/**
+ * sysfs_add_link_to_group - add a symlink to an attribute group.
+ * @kobj: The kobject containing the group.
+ * @group_name: The name of the group.
+ * @target: The target kobject of the symlink to create.
+ * @link_name: The name of the symlink to create.
+ */
+int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
+ struct kobject *target, const char *link_name)
+{
+ struct sysfs_dirent *dir_sd;
+ int error = 0;
+
+ dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+ if (!dir_sd)
+ return -ENOENT;
+
+ error = sysfs_create_link_sd(dir_sd, target, link_name);
+ sysfs_put(dir_sd);
+
+ return error;
+}
+EXPORT_SYMBOL_GPL(sysfs_add_link_to_group);
+
+/**
+ * sysfs_remove_link_from_group - remove a symlink from an attribute group.
+ * @kobj: The kobject containing the group.
+ * @group_name: The name of the group.
+ * @link_name: The name of the symlink to remove.
+ */
+void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
+ const char *link_name)
+{
+ struct sysfs_dirent *dir_sd;
+
+ dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+ if (dir_sd) {
+ sysfs_hash_and_remove(dir_sd, NULL, link_name);
+ sysfs_put(dir_sd);
+ }
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group);
EXPORT_SYMBOL_GPL(sysfs_create_group);
EXPORT_SYMBOL_GPL(sysfs_update_group);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index db940a9..afd8327 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -10,7 +10,7 @@
* Please see Documentation/filesystems/sysfs.txt for more information.
*/
-#define DEBUG
+#define DEBUG
#include <linux/fs.h>
#include <linux/mount.h>
@@ -19,6 +19,7 @@
#include <linux/module.h>
#include <linux/magic.h>
#include <linux/slab.h>
+#include <linux/user_namespace.h>
#include "sysfs.h"
@@ -111,6 +112,9 @@
struct super_block *sb;
int error;
+ if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
+ return ERR_PTR(-EPERM);
+
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info)
return ERR_PTR(-ENOMEM);
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 3c9eb56..8c940df 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -21,26 +21,17 @@
#include "sysfs.h"
-static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
- const char *name, int warn)
+static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
+ struct kobject *target,
+ const char *name, int warn)
{
- struct sysfs_dirent *parent_sd = NULL;
struct sysfs_dirent *target_sd = NULL;
struct sysfs_dirent *sd = NULL;
struct sysfs_addrm_cxt acxt;
enum kobj_ns_type ns_type;
int error;
- BUG_ON(!name);
-
- if (!kobj)
- parent_sd = &sysfs_root;
- else
- parent_sd = kobj->sd;
-
- error = -EFAULT;
- if (!parent_sd)
- goto out_put;
+ BUG_ON(!name || !parent_sd);
/* target->sd can go away beneath us but is protected with
* sysfs_assoc_lock. Fetch target_sd from it.
@@ -96,6 +87,34 @@
}
/**
+ * sysfs_create_link_sd - create symlink to a given object.
+ * @sd: directory we're creating the link in.
+ * @target: object we're pointing to.
+ * @name: name of the symlink.
+ */
+int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target,
+ const char *name)
+{
+ return sysfs_do_create_link_sd(sd, target, name, 1);
+}
+
+static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
+ const char *name, int warn)
+{
+ struct sysfs_dirent *parent_sd = NULL;
+
+ if (!kobj)
+ parent_sd = &sysfs_root;
+ else
+ parent_sd = kobj->sd;
+
+ if (!parent_sd)
+ return -EFAULT;
+
+ return sysfs_do_create_link_sd(parent_sd, target, name, warn);
+}
+
+/**
* sysfs_create_link - create symlink between two objects.
* @kobj: object whose directory we're creating the link in.
* @target: object we're pointing to.
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index d73c093..d1e4043 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -240,3 +240,5 @@
* symlink.c
*/
extern const struct inode_operations sysfs_symlink_inode_operations;
+int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target,
+ const char *name);
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index a77c421..3799e8d 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -68,7 +68,7 @@
static int sysv_readdir(struct file * filp, void * dirent, filldir_t filldir)
{
unsigned long pos = filp->f_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
unsigned offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index a38e87b..d0c6a00 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -545,6 +545,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("sysv");
static struct file_system_type v7_fs_type = {
.owner = THIS_MODULE,
@@ -553,6 +554,8 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("v7");
+MODULE_ALIAS("v7");
static int __init init_sysv_fs(void)
{
@@ -586,5 +589,4 @@
module_init(init_sysv_fs)
module_exit(exit_sysv_fs)
-MODULE_ALIAS("v7");
MODULE_LICENSE("GPL");
diff --git a/fs/timerfd.c b/fs/timerfd.c
index d03822b..32b644f 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -22,6 +22,7 @@
#include <linux/anon_inodes.h>
#include <linux/timerfd.h>
#include <linux/syscalls.h>
+#include <linux/compat.h>
#include <linux/rcupdate.h>
struct timerfd_ctx {
@@ -278,21 +279,17 @@
return ufd;
}
-SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
- const struct itimerspec __user *, utmr,
- struct itimerspec __user *, otmr)
+static int do_timerfd_settime(int ufd, int flags,
+ const struct itimerspec *new,
+ struct itimerspec *old)
{
struct fd f;
struct timerfd_ctx *ctx;
- struct itimerspec ktmr, kotmr;
int ret;
- if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
- return -EFAULT;
-
if ((flags & ~TFD_SETTIME_FLAGS) ||
- !timespec_valid(&ktmr.it_value) ||
- !timespec_valid(&ktmr.it_interval))
+ !timespec_valid(&new->it_value) ||
+ !timespec_valid(&new->it_interval))
return -EINVAL;
ret = timerfd_fget(ufd, &f);
@@ -323,27 +320,23 @@
if (ctx->expired && ctx->tintv.tv64)
hrtimer_forward_now(&ctx->tmr, ctx->tintv);
- kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
- kotmr.it_interval = ktime_to_timespec(ctx->tintv);
+ old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
+ old->it_interval = ktime_to_timespec(ctx->tintv);
/*
* Re-program the timer to the new value ...
*/
- ret = timerfd_setup(ctx, flags, &ktmr);
+ ret = timerfd_setup(ctx, flags, new);
spin_unlock_irq(&ctx->wqh.lock);
fdput(f);
- if (otmr && copy_to_user(otmr, &kotmr, sizeof(kotmr)))
- return -EFAULT;
-
return ret;
}
-SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
+static int do_timerfd_gettime(int ufd, struct itimerspec *t)
{
struct fd f;
struct timerfd_ctx *ctx;
- struct itimerspec kotmr;
int ret = timerfd_fget(ufd, &f);
if (ret)
return ret;
@@ -356,11 +349,65 @@
hrtimer_forward_now(&ctx->tmr, ctx->tintv) - 1;
hrtimer_restart(&ctx->tmr);
}
- kotmr.it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
- kotmr.it_interval = ktime_to_timespec(ctx->tintv);
+ t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
+ t->it_interval = ktime_to_timespec(ctx->tintv);
spin_unlock_irq(&ctx->wqh.lock);
fdput(f);
+ return 0;
+}
+SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
+ const struct itimerspec __user *, utmr,
+ struct itimerspec __user *, otmr)
+{
+ struct itimerspec new, old;
+ int ret;
+
+ if (copy_from_user(&new, utmr, sizeof(new)))
+ return -EFAULT;
+ ret = do_timerfd_settime(ufd, flags, &new, &old);
+ if (ret)
+ return ret;
+ if (otmr && copy_to_user(otmr, &old, sizeof(old)))
+ return -EFAULT;
+
+ return ret;
+}
+
+SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
+{
+ struct itimerspec kotmr;
+ int ret = do_timerfd_gettime(ufd, &kotmr);
+ if (ret)
+ return ret;
return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0;
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
+ const struct compat_itimerspec __user *, utmr,
+ struct compat_itimerspec __user *, otmr)
+{
+ struct itimerspec new, old;
+ int ret;
+
+ if (get_compat_itimerspec(&new, utmr))
+ return -EFAULT;
+ ret = do_timerfd_settime(ufd, flags, &new, &old);
+ if (ret)
+ return ret;
+ if (otmr && put_compat_itimerspec(otmr, &old))
+ return -EFAULT;
+ return ret;
+}
+
+COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd,
+ struct compat_itimerspec __user *, otmr)
+{
+ struct itimerspec kotmr;
+ int ret = do_timerfd_gettime(ufd, &kotmr);
+ if (ret)
+ return ret;
+ return put_compat_itimerspec(otmr, &kotmr) ? -EFAULT: 0;
+}
+#endif
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 12817ff..7f60e90 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2459,7 +2459,7 @@
static inline int chance(unsigned int n, unsigned int out_of)
{
- return !!((random32() % out_of) + 1 <= n);
+ return !!((prandom_u32() % out_of) + 1 <= n);
}
@@ -2477,13 +2477,13 @@
if (chance(1, 2)) {
d->pc_delay = 1;
/* Fail withing 1 minute */
- delay = random32() % 60000;
+ delay = prandom_u32() % 60000;
d->pc_timeout = jiffies;
d->pc_timeout += msecs_to_jiffies(delay);
ubifs_warn("failing after %lums", delay);
} else {
d->pc_delay = 2;
- delay = random32() % 10000;
+ delay = prandom_u32() % 10000;
/* Fail within 10000 operations */
d->pc_cnt_max = delay;
ubifs_warn("failing after %lu calls", delay);
@@ -2563,7 +2563,7 @@
unsigned int from, to, ffs = chance(1, 2);
unsigned char *p = (void *)buf;
- from = random32() % (len + 1);
+ from = prandom_u32() % (len + 1);
/* Corruption may only span one max. write unit */
to = min(len, ALIGN(from, c->max_write_size));
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 8a57477..de08c92f 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -352,7 +352,7 @@
struct qstr nm;
union ubifs_key key;
struct ubifs_dent_node *dent;
- struct inode *dir = file->f_path.dentry->d_inode;
+ struct inode *dir = file_inode(file);
struct ubifs_info *c = dir->i_sb->s_fs_info;
dbg_gen("dir ino %lu, f_pos %#llx", dir->i_ino, file->f_pos);
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 5bc7781..f12189d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1444,7 +1444,7 @@
struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct ubifs_info *c = inode->i_sb->s_fs_info;
struct timespec now = ubifs_current_time(inode);
struct ubifs_budget_req req = { .new_page = 1 };
@@ -1522,6 +1522,7 @@
ubifs_release_dirty_inode_budget(c, ui);
}
+ wait_for_stable_page(page);
unlock_page(page);
return 0;
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 1a7e2d8..648b143 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -147,7 +147,7 @@
long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
int flags, err;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
switch (cmd) {
case FS_IOC_GETFLAGS:
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index 9daaeef..4b826ab 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -2007,28 +2007,28 @@
if (!dbg_is_chk_gen(c))
return 0;
- if (random32() & 3)
+ if (prandom_u32() & 3)
return 0;
for (i = 0; i < c->lsave_cnt; i++)
c->lsave[i] = c->main_first;
list_for_each_entry(lprops, &c->empty_list, list)
- c->lsave[random32() % c->lsave_cnt] = lprops->lnum;
+ c->lsave[prandom_u32() % c->lsave_cnt] = lprops->lnum;
list_for_each_entry(lprops, &c->freeable_list, list)
- c->lsave[random32() % c->lsave_cnt] = lprops->lnum;
+ c->lsave[prandom_u32() % c->lsave_cnt] = lprops->lnum;
list_for_each_entry(lprops, &c->frdi_idx_list, list)
- c->lsave[random32() % c->lsave_cnt] = lprops->lnum;
+ c->lsave[prandom_u32() % c->lsave_cnt] = lprops->lnum;
heap = &c->lpt_heap[LPROPS_DIRTY_IDX - 1];
for (i = 0; i < heap->cnt; i++)
- c->lsave[random32() % c->lsave_cnt] = heap->arr[i]->lnum;
+ c->lsave[prandom_u32() % c->lsave_cnt] = heap->arr[i]->lnum;
heap = &c->lpt_heap[LPROPS_DIRTY - 1];
for (i = 0; i < heap->cnt; i++)
- c->lsave[random32() % c->lsave_cnt] = heap->arr[i]->lnum;
+ c->lsave[prandom_u32() % c->lsave_cnt] = heap->arr[i]->lnum;
heap = &c->lpt_heap[LPROPS_FREE - 1];
for (i = 0; i < heap->cnt; i++)
- c->lsave[random32() % c->lsave_cnt] = heap->arr[i]->lnum;
+ c->lsave[prandom_u32() % c->lsave_cnt] = heap->arr[i]->lnum;
return 1;
}
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 769701c..ba32da3 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -126,13 +126,14 @@
else if (inum > o->inum)
p = p->rb_right;
else {
- if (o->dnext) {
+ if (o->del) {
spin_unlock(&c->orphan_lock);
dbg_gen("deleted twice ino %lu",
(unsigned long)inum);
return;
}
- if (o->cnext) {
+ if (o->cmt) {
+ o->del = 1;
o->dnext = c->orph_dnext;
c->orph_dnext = o;
spin_unlock(&c->orphan_lock);
@@ -172,7 +173,9 @@
last = &c->orph_cnext;
list_for_each_entry(orphan, &c->orph_new, new_list) {
ubifs_assert(orphan->new);
+ ubifs_assert(!orphan->cmt);
orphan->new = 0;
+ orphan->cmt = 1;
*last = orphan;
last = &orphan->cnext;
}
@@ -299,7 +302,9 @@
cnext = c->orph_cnext;
for (i = 0; i < cnt; i++) {
orphan = cnext;
+ ubifs_assert(orphan->cmt);
orph->inos[i] = cpu_to_le64(orphan->inum);
+ orphan->cmt = 0;
cnext = orphan->cnext;
orphan->cnext = NULL;
}
@@ -378,6 +383,7 @@
list_for_each_entry(orphan, &c->orph_list, list) {
if (orphan->new)
continue;
+ orphan->cmt = 1;
*last = orphan;
last = &orphan->cnext;
cnt += 1;
@@ -442,6 +448,7 @@
orphan = dnext;
dnext = orphan->dnext;
ubifs_assert(!orphan->new);
+ ubifs_assert(orphan->del);
rb_erase(&orphan->rb, &c->orph_tree);
list_del(&orphan->list);
c->tot_orphans -= 1;
@@ -531,6 +538,7 @@
rb_link_node(&orphan->rb, parent, p);
rb_insert_color(&orphan->rb, &c->orph_tree);
list_add_tail(&orphan->list, &c->orph_list);
+ orphan->del = 1;
orphan->dnext = c->orph_dnext;
c->orph_dnext = orphan;
dbg_mnt("ino %lu, new %d, tot %d", (unsigned long)inum,
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index ddc0f6a..ac838b8 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2174,6 +2174,7 @@
.mount = ubifs_mount,
.kill_sb = kill_ubifs_super,
};
+MODULE_ALIAS_FS("ubifs");
/*
* Inode slab cache constructor.
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index 523bbad..52a6559 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -683,7 +683,7 @@
c->ilebs[c->ileb_cnt++] = lnum;
dbg_cmt("LEB %d", lnum);
}
- if (dbg_is_chk_index(c) && !(random32() & 7))
+ if (dbg_is_chk_index(c) && !(prandom_u32() & 7))
return -ENOSPC;
return 0;
}
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index d133c27..b2babce 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -904,6 +904,8 @@
* @dnext: next orphan to delete
* @inum: inode number
* @new: %1 => added since the last commit, otherwise %0
+ * @cmt: %1 => commit pending, otherwise %0
+ * @del: %1 => delete pending, otherwise %0
*/
struct ubifs_orphan {
struct rb_node rb;
@@ -912,7 +914,9 @@
struct ubifs_orphan *cnext;
struct ubifs_orphan *dnext;
ino_t inum;
- int new;
+ unsigned new:1;
+ unsigned cmt:1;
+ unsigned del:1;
};
/**
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index eb8bfe2..b3e93f5 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -186,7 +186,7 @@
static int udf_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct inode *dir = filp->f_path.dentry->d_inode;
+ struct inode *dir = file_inode(filp);
int result;
if (filp->f_pos == 0) {
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 77b5953..29569dd 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -139,7 +139,7 @@
{
ssize_t retval;
struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
int err, pos;
size_t count = iocb->ki_left;
struct udf_inode_info *iinfo = UDF_I(inode);
@@ -178,7 +178,7 @@
long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
long old_block, new_block;
int result = -EINVAL;
@@ -204,7 +204,7 @@
goto out;
case UDF_RELOCATE_BLOCKS:
if (!capable(CAP_SYS_ADMIN)) {
- result = -EACCES;
+ result = -EPERM;
goto out;
}
if (get_user(old_block, (long __user *)arg)) {
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index cbae1ed..7a12e48 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -67,6 +67,74 @@
struct extent_position *);
static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int);
+static void __udf_clear_extent_cache(struct inode *inode)
+{
+ struct udf_inode_info *iinfo = UDF_I(inode);
+
+ if (iinfo->cached_extent.lstart != -1) {
+ brelse(iinfo->cached_extent.epos.bh);
+ iinfo->cached_extent.lstart = -1;
+ }
+}
+
+/* Invalidate extent cache */
+static void udf_clear_extent_cache(struct inode *inode)
+{
+ struct udf_inode_info *iinfo = UDF_I(inode);
+
+ spin_lock(&iinfo->i_extent_cache_lock);
+ __udf_clear_extent_cache(inode);
+ spin_unlock(&iinfo->i_extent_cache_lock);
+}
+
+/* Return contents of extent cache */
+static int udf_read_extent_cache(struct inode *inode, loff_t bcount,
+ loff_t *lbcount, struct extent_position *pos)
+{
+ struct udf_inode_info *iinfo = UDF_I(inode);
+ int ret = 0;
+
+ spin_lock(&iinfo->i_extent_cache_lock);
+ if ((iinfo->cached_extent.lstart <= bcount) &&
+ (iinfo->cached_extent.lstart != -1)) {
+ /* Cache hit */
+ *lbcount = iinfo->cached_extent.lstart;
+ memcpy(pos, &iinfo->cached_extent.epos,
+ sizeof(struct extent_position));
+ if (pos->bh)
+ get_bh(pos->bh);
+ ret = 1;
+ }
+ spin_unlock(&iinfo->i_extent_cache_lock);
+ return ret;
+}
+
+/* Add extent to extent cache */
+static void udf_update_extent_cache(struct inode *inode, loff_t estart,
+ struct extent_position *pos, int next_epos)
+{
+ struct udf_inode_info *iinfo = UDF_I(inode);
+
+ spin_lock(&iinfo->i_extent_cache_lock);
+ /* Invalidate previously cached extent */
+ __udf_clear_extent_cache(inode);
+ if (pos->bh)
+ get_bh(pos->bh);
+ memcpy(&iinfo->cached_extent.epos, pos,
+ sizeof(struct extent_position));
+ iinfo->cached_extent.lstart = estart;
+ if (next_epos)
+ switch (iinfo->i_alloc_type) {
+ case ICBTAG_FLAG_AD_SHORT:
+ iinfo->cached_extent.epos.offset -=
+ sizeof(struct short_ad);
+ break;
+ case ICBTAG_FLAG_AD_LONG:
+ iinfo->cached_extent.epos.offset -=
+ sizeof(struct long_ad);
+ }
+ spin_unlock(&iinfo->i_extent_cache_lock);
+}
void udf_evict_inode(struct inode *inode)
{
@@ -90,6 +158,7 @@
}
kfree(iinfo->i_ext.i_data);
iinfo->i_ext.i_data = NULL;
+ udf_clear_extent_cache(inode);
if (want_delete) {
udf_free_inode(inode);
}
@@ -105,6 +174,7 @@
truncate_pagecache(inode, to, isize);
if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
down_write(&iinfo->i_data_sem);
+ udf_clear_extent_cache(inode);
udf_truncate_extents(inode);
up_write(&iinfo->i_data_sem);
}
@@ -372,7 +442,7 @@
iinfo->i_next_alloc_goal++;
}
-
+ udf_clear_extent_cache(inode);
phys = inode_getblk(inode, block, &err, &new);
if (!phys)
goto abort;
@@ -1171,6 +1241,7 @@
} else {
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
down_write(&iinfo->i_data_sem);
+ udf_clear_extent_cache(inode);
memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr + newsize,
0x00, bsize - newsize -
udf_file_entry_alloc_offset(inode));
@@ -1184,6 +1255,7 @@
if (err)
return err;
down_write(&iinfo->i_data_sem);
+ udf_clear_extent_cache(inode);
truncate_setsize(inode, newsize);
udf_truncate_extents(inode);
up_write(&iinfo->i_data_sem);
@@ -2156,11 +2228,12 @@
struct udf_inode_info *iinfo;
iinfo = UDF_I(inode);
- pos->offset = 0;
- pos->block = iinfo->i_location;
- pos->bh = NULL;
+ if (!udf_read_extent_cache(inode, bcount, &lbcount, pos)) {
+ pos->offset = 0;
+ pos->block = iinfo->i_location;
+ pos->bh = NULL;
+ }
*elen = 0;
-
do {
etype = udf_next_aext(inode, pos, eloc, elen, 1);
if (etype == -1) {
@@ -2170,7 +2243,8 @@
}
lbcount += *elen;
} while (lbcount <= bcount);
-
+ /* update extent cache */
+ udf_update_extent_cache(inode, lbcount - *elen, pos, 1);
*offset = (bcount + *elen - lbcount) >> blocksize_bits;
return etype;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 95fee27..102c072 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -1270,10 +1270,10 @@
if (parent && (len < 5)) {
*lenp = 5;
- return 255;
+ return FILEID_INVALID;
} else if (len < 3) {
*lenp = 3;
- return 255;
+ return FILEID_INVALID;
}
*lenp = 3;
diff --git a/fs/udf/super.c b/fs/udf/super.c
index e9be396..9ac4057 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -118,6 +118,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("udf");
static struct kmem_cache *udf_inode_cachep;
@@ -134,6 +135,8 @@
ei->i_next_alloc_goal = 0;
ei->i_strat4096 = 0;
init_rwsem(&ei->i_data_sem);
+ ei->cached_extent.lstart = -1;
+ spin_lock_init(&ei->i_extent_cache_lock);
return &ei->vfs_inode;
}
@@ -1021,7 +1024,6 @@
if (bitmap == NULL)
return NULL;
- bitmap->s_block_bitmap = (struct buffer_head **)(bitmap + 1);
bitmap->s_nr_groups = nr_groups;
return bitmap;
}
@@ -1079,8 +1081,6 @@
if (!bitmap)
return 1;
map->s_uspace.s_bitmap = bitmap;
- bitmap->s_extLength = le32_to_cpu(
- phd->unallocSpaceBitmap.extLength);
bitmap->s_extPosition = le32_to_cpu(
phd->unallocSpaceBitmap.extPosition);
map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_BITMAP;
@@ -1115,8 +1115,6 @@
if (!bitmap)
return 1;
map->s_fspace.s_bitmap = bitmap;
- bitmap->s_extLength = le32_to_cpu(
- phd->freedSpaceBitmap.extLength);
bitmap->s_extPosition = le32_to_cpu(
phd->freedSpaceBitmap.extPosition);
map->s_partition_flags |= UDF_PART_FLAG_FREED_BITMAP;
@@ -1866,6 +1864,8 @@
mark_buffer_dirty(bh);
sbi->s_lvid_dirty = 0;
mutex_unlock(&sbi->s_alloc_mutex);
+ /* Make opening of filesystem visible on the media immediately */
+ sync_dirty_buffer(bh);
}
static void udf_close_lvid(struct super_block *sb)
@@ -1906,6 +1906,8 @@
mark_buffer_dirty(bh);
sbi->s_lvid_dirty = 0;
mutex_unlock(&sbi->s_alloc_mutex);
+ /* Make closing of filesystem visible on the media immediately */
+ sync_dirty_buffer(bh);
}
u64 lvid_get_unique_id(struct super_block *sb)
diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h
index bb8309d..b5cd8ed 100644
--- a/fs/udf/udf_i.h
+++ b/fs/udf/udf_i.h
@@ -1,6 +1,19 @@
#ifndef _UDF_I_H
#define _UDF_I_H
+struct extent_position {
+ struct buffer_head *bh;
+ uint32_t offset;
+ struct kernel_lb_addr block;
+};
+
+struct udf_ext_cache {
+ /* Extent position */
+ struct extent_position epos;
+ /* Start logical offset in bytes */
+ loff_t lstart;
+};
+
/*
* The i_data_sem and i_mutex serve for protection of allocation information
* of a regular files and symlinks. This includes all extents belonging to
@@ -35,6 +48,9 @@
__u8 *i_data;
} i_ext;
struct rw_semaphore i_data_sem;
+ struct udf_ext_cache cached_extent;
+ /* Spinlock for protecting extent cache */
+ spinlock_t i_extent_cache_lock;
struct inode vfs_inode;
};
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 5f02722..ed401e9 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -80,10 +80,9 @@
};
struct udf_bitmap {
- __u32 s_extLength;
__u32 s_extPosition;
- __u16 s_nr_groups;
- struct buffer_head **s_block_bitmap;
+ int s_nr_groups;
+ struct buffer_head *s_block_bitmap[0];
};
struct udf_part_map {
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index de038da..be7dabb 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -113,11 +113,6 @@
uint8_t u_len;
};
-struct extent_position {
- struct buffer_head *bh;
- uint32_t offset;
- struct kernel_lb_addr block;
-};
/* super.c */
diff --git a/fs/ufs/Kconfig b/fs/ufs/Kconfig
index e4f10a4..0bf6e16 100644
--- a/fs/ufs/Kconfig
+++ b/fs/ufs/Kconfig
@@ -29,7 +29,7 @@
config UFS_FS_WRITE
bool "UFS file system write support (DANGEROUS)"
- depends on UFS_FS && EXPERIMENTAL
+ depends on UFS_FS
help
Say Y here if you want to try writing to UFS partitions. This is
experimental, so you should back up your UFS partitions beforehand.
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index dbc9099..3a75ca0 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -433,7 +433,7 @@
ufs_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
loff_t pos = filp->f_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
unsigned int offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index dc8e3a8..329f2f5 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1500,6 +1500,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ufs");
static int __init init_ufs_fs(void)
{
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 5a7ffe5..cc33aaf 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -70,8 +70,8 @@
If unsure, say N.
config XFS_DEBUG
- bool "XFS Debugging support (EXPERIMENTAL)"
- depends on XFS_FS && EXPERIMENTAL
+ bool "XFS Debugging support"
+ depends on XFS_FS
help
Say Y here to get an XFS build with many debugging features,
including ASSERT checks, function wrappers around macros,
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 393055f..0ad2325 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -1925,8 +1925,6 @@
targs.mp = mp;
targs.agbp = agbp;
targs.agno = args->agno;
- targs.mod = targs.minleft = targs.wasdel = targs.userdata =
- targs.minalignslop = 0;
targs.alignment = targs.minlen = targs.prod = targs.isfl = 1;
targs.type = XFS_ALLOCTYPE_THIS_AG;
targs.pag = pag;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index aaf4725..8886838 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -300,9 +300,12 @@
if (rsvd)
args.trans->t_flags |= XFS_TRANS_RESERVE;
- if ((error = xfs_trans_reserve(args.trans, args.total,
- XFS_ATTRSET_LOG_RES(mp, args.total), 0,
- XFS_TRANS_PERM_LOG_RES, XFS_ATTRSET_LOG_COUNT))) {
+ error = xfs_trans_reserve(args.trans, args.total,
+ XFS_ATTRSETM_LOG_RES(mp) +
+ XFS_ATTRSETRT_LOG_RES(mp) * args.total,
+ 0, XFS_TRANS_PERM_LOG_RES,
+ XFS_ATTRSET_LOG_COUNT);
+ if (error) {
xfs_trans_cancel(args.trans, 0);
return(error);
}
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index cdb2d33..b44af92 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -147,7 +147,10 @@
xfs_fsblock_t *firstblock, /* first block allocated in xaction */
xfs_extlen_t total, /* total blocks needed by transaction */
int *logflagsp, /* inode logging flags */
- int whichfork); /* data or attr fork */
+ int whichfork, /* data or attr fork */
+ void (*init_fn)(struct xfs_buf *bp,
+ struct xfs_inode *ip,
+ struct xfs_ifork *ifp));
/*
* Search the extents list for the inode, for the extent containing bno.
@@ -357,7 +360,42 @@
}
/*
- * Called from xfs_bmap_add_attrfork to handle local format files.
+ * Block initialisation functions for local to extent format conversion.
+ * As these get more complex, they will be moved to the relevant files,
+ * but for now they are too simple to worry about.
+ */
+STATIC void
+xfs_bmap_local_to_extents_init_fn(
+ struct xfs_buf *bp,
+ struct xfs_inode *ip,
+ struct xfs_ifork *ifp)
+{
+ bp->b_ops = &xfs_bmbt_buf_ops;
+ memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+}
+
+STATIC void
+xfs_symlink_local_to_remote(
+ struct xfs_buf *bp,
+ struct xfs_inode *ip,
+ struct xfs_ifork *ifp)
+{
+ /* remote symlink blocks are not verifiable until CRCs come along */
+ bp->b_ops = NULL;
+ memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+}
+
+/*
+ * Called from xfs_bmap_add_attrfork to handle local format files. Each
+ * different data fork content type needs a different callout to do the
+ * conversion. Some are basic and only require special block initialisation
+ * callouts for the data formating, others (directories) are so specialised they
+ * handle everything themselves.
+ *
+ * XXX (dgc): investigate whether directory conversion can use the generic
+ * formatting callout. It should be possible - it's just a very complex
+ * formatter. it would also require passing the transaction through to the init
+ * function.
*/
STATIC int /* error */
xfs_bmap_add_attrfork_local(
@@ -368,25 +406,29 @@
int *flags) /* inode logging flags */
{
xfs_da_args_t dargs; /* args for dir/attr code */
- int error; /* error return value */
- xfs_mount_t *mp; /* mount structure pointer */
if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
return 0;
+
if (S_ISDIR(ip->i_d.di_mode)) {
- mp = ip->i_mount;
memset(&dargs, 0, sizeof(dargs));
dargs.dp = ip;
dargs.firstblock = firstblock;
dargs.flist = flist;
- dargs.total = mp->m_dirblkfsbs;
+ dargs.total = ip->i_mount->m_dirblkfsbs;
dargs.whichfork = XFS_DATA_FORK;
dargs.trans = tp;
- error = xfs_dir2_sf_to_block(&dargs);
- } else
- error = xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags,
- XFS_DATA_FORK);
- return error;
+ return xfs_dir2_sf_to_block(&dargs);
+ }
+
+ if (S_ISLNK(ip->i_d.di_mode))
+ return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
+ flags, XFS_DATA_FORK,
+ xfs_symlink_local_to_remote);
+
+ return xfs_bmap_local_to_extents(tp, ip, firstblock, 1, flags,
+ XFS_DATA_FORK,
+ xfs_bmap_local_to_extents_init_fn);
}
/*
@@ -3099,8 +3141,6 @@
args.fsbno = *firstblock;
}
args.minlen = args.maxlen = args.prod = 1;
- args.total = args.minleft = args.alignment = args.mod = args.isfl =
- args.minalignslop = 0;
args.wasdel = wasdel;
*logflagsp = 0;
if ((error = xfs_alloc_vextent(&args))) {
@@ -3221,7 +3261,10 @@
xfs_fsblock_t *firstblock, /* first block allocated in xaction */
xfs_extlen_t total, /* total blocks needed by transaction */
int *logflagsp, /* inode logging flags */
- int whichfork) /* data or attr fork */
+ int whichfork,
+ void (*init_fn)(struct xfs_buf *bp,
+ struct xfs_inode *ip,
+ struct xfs_ifork *ifp))
{
int error; /* error return value */
int flags; /* logging flags returned */
@@ -3241,12 +3284,12 @@
xfs_buf_t *bp; /* buffer for extent block */
xfs_bmbt_rec_host_t *ep;/* extent record pointer */
+ ASSERT((ifp->if_flags &
+ (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == XFS_IFINLINE);
memset(&args, 0, sizeof(args));
args.tp = tp;
args.mp = ip->i_mount;
args.firstblock = *firstblock;
- ASSERT((ifp->if_flags &
- (XFS_IFINLINE|XFS_IFEXTENTS|XFS_IFEXTIREC)) == XFS_IFINLINE);
/*
* Allocate a block. We know we need only one, since the
* file currently fits in an inode.
@@ -3259,20 +3302,21 @@
args.type = XFS_ALLOCTYPE_NEAR_BNO;
}
args.total = total;
- args.mod = args.minleft = args.alignment = args.wasdel =
- args.isfl = args.minalignslop = 0;
args.minlen = args.maxlen = args.prod = 1;
- if ((error = xfs_alloc_vextent(&args)))
+ error = xfs_alloc_vextent(&args);
+ if (error)
goto done;
- /*
- * Can't fail, the space was reserved.
- */
+
+ /* Can't fail, the space was reserved. */
ASSERT(args.fsbno != NULLFSBLOCK);
ASSERT(args.len == 1);
*firstblock = args.fsbno;
bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
- bp->b_ops = &xfs_bmbt_buf_ops;
- memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
+
+ /* initialise the block and copy the data */
+ init_fn(bp, ip, ifp);
+
+ /* account for the change in fork size and log everything */
xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
xfs_bmap_forkoff_reset(args.mp, ip, whichfork);
xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
@@ -4919,8 +4963,32 @@
XFS_STATS_INC(xs_blk_mapw);
if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
+ /*
+ * XXX (dgc): This assumes we are only called for inodes that
+ * contain content neutral data in local format. Anything that
+ * contains caller-specific data in local format that needs
+ * transformation to move to a block format needs to do the
+ * conversion to extent format itself.
+ *
+ * Directory data forks and attribute forks handle this
+ * themselves, but with the addition of metadata verifiers every
+ * data fork in local format now contains caller specific data
+ * and as such conversion through this function is likely to be
+ * broken.
+ *
+ * The only likely user of this branch is for remote symlinks,
+ * but we cannot overwrite the data fork contents of the symlink
+ * (EEXIST occurs higher up the stack) and so it will never go
+ * from local format to extent format here. Hence I don't think
+ * this branch is ever executed intentionally and we should
+ * consider removing it and asserting that xfs_bmapi_write()
+ * cannot be called directly on local format forks. i.e. callers
+ * are completely responsible for local to extent format
+ * conversion, not xfs_bmapi_write().
+ */
error = xfs_bmap_local_to_extents(tp, ip, firstblock, total,
- &bma.logflags, whichfork);
+ &bma.logflags, whichfork,
+ xfs_bmap_local_to_extents_init_fn);
if (error)
goto error0;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index fbbb9eb..8459b5d 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -951,8 +951,6 @@
locked = down_trylock(&bp->b_sema) == 0;
if (locked)
XB_SET_OWNER(bp);
- else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
- xfs_log_force(bp->b_target->bt_mount, 0);
trace_xfs_buf_trylock(bp, _RET_IP_);
return locked;
@@ -1336,6 +1334,12 @@
int size;
int i;
+ /*
+ * Make sure we capture only current IO errors rather than stale errors
+ * left over from previous use of the buffer (e.g. failed readahead).
+ */
+ bp->b_error = 0;
+
if (bp->b_flags & XBF_WRITE) {
if (bp->b_flags & XBF_SYNCIO)
rw = WRITE_SYNC;
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3f9949f..cf26347 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -37,109 +37,6 @@
return container_of(lip, struct xfs_buf_log_item, bli_item);
}
-
-#ifdef XFS_TRANS_DEBUG
-/*
- * This function uses an alternate strategy for tracking the bytes
- * that the user requests to be logged. This can then be used
- * in conjunction with the bli_orig array in the buf log item to
- * catch bugs in our callers' code.
- *
- * We also double check the bits set in xfs_buf_item_log using a
- * simple algorithm to check that every byte is accounted for.
- */
-STATIC void
-xfs_buf_item_log_debug(
- xfs_buf_log_item_t *bip,
- uint first,
- uint last)
-{
- uint x;
- uint byte;
- uint nbytes;
- uint chunk_num;
- uint word_num;
- uint bit_num;
- uint bit_set;
- uint *wordp;
-
- ASSERT(bip->bli_logged != NULL);
- byte = first;
- nbytes = last - first + 1;
- bfset(bip->bli_logged, first, nbytes);
- for (x = 0; x < nbytes; x++) {
- chunk_num = byte >> XFS_BLF_SHIFT;
- word_num = chunk_num >> BIT_TO_WORD_SHIFT;
- bit_num = chunk_num & (NBWORD - 1);
- wordp = &(bip->__bli_format.blf_data_map[word_num]);
- bit_set = *wordp & (1 << bit_num);
- ASSERT(bit_set);
- byte++;
- }
-}
-
-/*
- * This function is called when we flush something into a buffer without
- * logging it. This happens for things like inodes which are logged
- * separately from the buffer.
- */
-void
-xfs_buf_item_flush_log_debug(
- xfs_buf_t *bp,
- uint first,
- uint last)
-{
- xfs_buf_log_item_t *bip = bp->b_fspriv;
- uint nbytes;
-
- if (bip == NULL || (bip->bli_item.li_type != XFS_LI_BUF))
- return;
-
- ASSERT(bip->bli_logged != NULL);
- nbytes = last - first + 1;
- bfset(bip->bli_logged, first, nbytes);
-}
-
-/*
- * This function is called to verify that our callers have logged
- * all the bytes that they changed.
- *
- * It does this by comparing the original copy of the buffer stored in
- * the buf log item's bli_orig array to the current copy of the buffer
- * and ensuring that all bytes which mismatch are set in the bli_logged
- * array of the buf log item.
- */
-STATIC void
-xfs_buf_item_log_check(
- xfs_buf_log_item_t *bip)
-{
- char *orig;
- char *buffer;
- int x;
- xfs_buf_t *bp;
-
- ASSERT(bip->bli_orig != NULL);
- ASSERT(bip->bli_logged != NULL);
-
- bp = bip->bli_buf;
- ASSERT(bp->b_length > 0);
- ASSERT(bp->b_addr != NULL);
- orig = bip->bli_orig;
- buffer = bp->b_addr;
- for (x = 0; x < BBTOB(bp->b_length); x++) {
- if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) {
- xfs_emerg(bp->b_mount,
- "%s: bip %x buffer %x orig %x index %d",
- __func__, bip, bp, orig, x);
- ASSERT(0);
- }
- }
-}
-#else
-#define xfs_buf_item_log_debug(x,y,z)
-#define xfs_buf_item_log_check(x)
-#endif
-
STATIC void xfs_buf_do_callbacks(struct xfs_buf *bp);
/*
@@ -429,7 +326,6 @@
* Check to make sure everything is consistent.
*/
trace_xfs_buf_item_format(bip);
- xfs_buf_item_log_check(bip);
}
/*
@@ -573,8 +469,18 @@
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
- if (!xfs_buf_trylock(bp))
+ if (!xfs_buf_trylock(bp)) {
+ /*
+ * If we have just raced with a buffer being pinned and it has
+ * been marked stale, we could end up stalling until someone else
+ * issues a log force to unpin the stale buffer. Check for the
+ * race condition here so xfsaild recognizes the buffer is pinned
+ * and queues a log force to move it along.
+ */
+ if (xfs_buf_ispinned(bp))
+ return XFS_ITEM_PINNED;
return XFS_ITEM_LOCKED;
+ }
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
@@ -923,8 +829,6 @@
mask = (1 << end_bit) - 1;
*wordp |= mask;
}
-
- xfs_buf_item_log_debug(bip, first, last);
}
/*
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 16def43..ee36c88 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -98,10 +98,6 @@
unsigned int bli_flags; /* misc flags */
unsigned int bli_recur; /* lock recursion count */
atomic_t bli_refcount; /* cnt of tp refs */
-#ifdef XFS_TRANS_DEBUG
- char *bli_orig; /* original buffer copy */
- char *bli_logged; /* bytes logged (bitmap) */
-#endif
int bli_format_count; /* count of headers */
struct xfs_buf_log_format *bli_formats; /* array of in-log header ptrs */
struct xfs_buf_log_format __bli_format; /* embedded in-log header */
@@ -117,16 +113,6 @@
void xfs_buf_iodone_callbacks(struct xfs_buf *);
void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
-#ifdef XFS_TRANS_DEBUG
-void
-xfs_buf_item_flush_log_debug(
- struct xfs_buf *bp,
- uint first,
- uint last);
-#else
-#define xfs_buf_item_flush_log_debug(bp, first, last)
-#endif
-
#endif /* __KERNEL__ */
#endif /* __XFS_BUF_ITEM_H__ */
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index a8bd26b..f852b08 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -78,14 +78,14 @@
goto out_put_tmp_file;
}
- if (IS_SWAPFILE(f.file->f_path.dentry->d_inode) ||
- IS_SWAPFILE(tmp.file->f_path.dentry->d_inode)) {
+ if (IS_SWAPFILE(file_inode(f.file)) ||
+ IS_SWAPFILE(file_inode(tmp.file))) {
error = XFS_ERROR(EINVAL);
goto out_put_tmp_file;
}
- ip = XFS_I(f.file->f_path.dentry->d_inode);
- tip = XFS_I(tmp.file->f_path.dentry->d_inode);
+ ip = XFS_I(file_inode(f.file));
+ tip = XFS_I(file_inode(tmp.file));
if (ip->i_mount != tip->i_mount) {
error = XFS_ERROR(EINVAL);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 9e1bf52..8025eb2 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -612,15 +612,9 @@
if (flags & XFS_QMOPT_DQALLOC) {
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_DQALLOC);
error = xfs_trans_reserve(tp, XFS_QM_DQALLOC_SPACE_RES(mp),
- XFS_WRITE_LOG_RES(mp) +
- /*
- * Round the chunklen up to the next multiple
- * of 128 (buf log item chunk size)).
- */
- BBTOB(mp->m_quotainfo->qi_dqchunklen) - 1 + 128,
- 0,
- XFS_TRANS_PERM_LOG_RES,
- XFS_WRITE_LOG_COUNT);
+ XFS_QM_DQALLOC_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES,
+ XFS_WRITE_LOG_COUNT);
if (error)
goto error1;
cancelflags = XFS_TRANS_RELEASE_LOG_RES;
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index a836118..c585bc6 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -48,7 +48,7 @@
case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG:
return 6;
}
- return 255; /* invalid */
+ return FILEID_INVALID;
}
STATIC int
@@ -90,7 +90,7 @@
len = xfs_fileid_length(fileid_type);
if (*max_len < len) {
*max_len = len;
- return 255;
+ return FILEID_INVALID;
}
*max_len = len;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 67284ed..f03bf1a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -811,7 +811,7 @@
loff_t offset,
loff_t len)
{
- struct inode *inode = file->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
long error;
loff_t new_size = 0;
xfs_flock64_t bf;
@@ -912,7 +912,7 @@
void *dirent,
filldir_t filldir)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
xfs_inode_t *ip = XFS_I(inode);
int error;
size_t bufsize;
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 94eaeed..2866b8c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -709,8 +709,8 @@
int error;
tp = _xfs_trans_alloc(mp, XFS_TRANS_DUMMY1, KM_SLEEP);
- error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
- XFS_DEFAULT_LOG_COUNT);
+ error = xfs_trans_reserve(tp, 0, XFS_SB_LOG_RES(mp), 0, 0,
+ XFS_DEFAULT_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index a815412..515bf71 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -279,8 +279,6 @@
(args.agbno < be32_to_cpu(agi->agi_length)))) {
args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno);
args.type = XFS_ALLOCTYPE_THIS_BNO;
- args.mod = args.total = args.wasdel = args.isfl =
- args.userdata = args.minalignslop = 0;
args.prod = 1;
/*
@@ -333,8 +331,6 @@
* Allocate a fixed-size extent of inodes.
*/
args.type = XFS_ALLOCTYPE_NEAR_BNO;
- args.mod = args.total = args.wasdel = args.isfl =
- args.userdata = args.minalignslop = 0;
args.prod = 1;
/*
* Allow space for the inode btree to split.
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 66282dc..4f20165 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2379,9 +2379,6 @@
char *cp;
xfs_ifork_t *ifp;
xfs_mount_t *mp;
-#ifdef XFS_TRANS_DEBUG
- int first;
-#endif
static const short brootflag[2] =
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
static const short dataflag[2] =
@@ -2724,9 +2721,6 @@
xfs_inode_log_item_t *iip;
xfs_dinode_t *dip;
xfs_mount_t *mp;
-#ifdef XFS_TRANS_DEBUG
- int first;
-#endif
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 22baf6e..237e7f6 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -419,6 +419,7 @@
static inline void xfs_ifunlock(struct xfs_inode *ip)
{
xfs_iflags_clear(ip, XFS_IFLOCK);
+ smp_mb();
wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT);
}
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index d041d47..f034bd1 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -269,17 +269,6 @@
} else {
ASSERT(!(iip->ili_fields &
XFS_ILOG_DBROOT));
-#ifdef XFS_TRANS_DEBUG
- if (iip->ili_root_size > 0) {
- ASSERT(iip->ili_root_size ==
- ip->i_df.if_broot_bytes);
- ASSERT(memcmp(iip->ili_orig_root,
- ip->i_df.if_broot,
- iip->ili_root_size) == 0);
- } else {
- ASSERT(ip->i_df.if_broot_bytes == 0);
- }
-#endif
iip->ili_fields &= ~XFS_ILOG_DBROOT;
}
break;
@@ -678,11 +667,6 @@
xfs_inode_item_destroy(
xfs_inode_t *ip)
{
-#ifdef XFS_TRANS_DEBUG
- if (ip->i_itemp->ili_root_size != 0) {
- kmem_free(ip->i_itemp->ili_orig_root);
- }
-#endif
kmem_zone_free(xfs_ili_zone, ip->i_itemp);
}
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 376d4d0..779812f 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -148,10 +148,6 @@
data exts */
struct xfs_bmbt_rec *ili_aextents_buf; /* array of logged
attr exts */
-#ifdef XFS_TRANS_DEBUG
- int ili_root_size;
- char *ili_orig_root;
-#endif
xfs_inode_log_format_t ili_format; /* logged structure */
} xfs_inode_log_item_t;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index c1c3ef8..d681e34 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -80,7 +80,7 @@
f = fdget(hreq->fd);
if (!f.file)
return -EBADF;
- inode = f.file->f_path.dentry->d_inode;
+ inode = file_inode(f.file);
} else {
error = user_lpath((const char __user *)hreq->path, &path);
if (error)
@@ -168,7 +168,7 @@
/*
* Only allow handle opens under a directory.
*/
- if (!S_ISDIR(parfilp->f_path.dentry->d_inode->i_mode))
+ if (!S_ISDIR(file_inode(parfilp)->i_mode))
return ERR_PTR(-ENOTDIR);
if (hlen != sizeof(xfs_handle_t))
@@ -1334,7 +1334,7 @@
unsigned int cmd,
unsigned long p)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
void __user *arg = (void __user *)p;
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 1244274a..63b8fc4 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -530,7 +530,7 @@
unsigned cmd,
unsigned long p)
{
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
void __user *arg = (void __user *)p;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 364818e..5a30dd8 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -311,6 +311,62 @@
}
/*
+ * Determine the initial size of the preallocation. We are beyond the current
+ * EOF here, but we need to take into account whether this is a sparse write or
+ * an extending write when determining the preallocation size. Hence we need to
+ * look up the extent that ends at the current write offset and use the result
+ * to determine the preallocation size.
+ *
+ * If the extent is a hole, then preallocation is essentially disabled.
+ * Otherwise we take the size of the preceeding data extent as the basis for the
+ * preallocation size. If the size of the extent is greater than half the
+ * maximum extent length, then use the current offset as the basis. This ensures
+ * that for large files the preallocation size always extends to MAXEXTLEN
+ * rather than falling short due to things like stripe unit/width alignment of
+ * real extents.
+ */
+STATIC xfs_fsblock_t
+xfs_iomap_eof_prealloc_initial_size(
+ struct xfs_mount *mp,
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ xfs_bmbt_irec_t *imap,
+ int nimaps)
+{
+ xfs_fileoff_t start_fsb;
+ int imaps = 1;
+ int error;
+
+ ASSERT(nimaps >= imaps);
+
+ /* if we are using a specific prealloc size, return now */
+ if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
+ return 0;
+
+ /*
+ * As we write multiple pages, the offset will always align to the
+ * start of a page and hence point to a hole at EOF. i.e. if the size is
+ * 4096 bytes, we only have one block at FSB 0, but XFS_B_TO_FSB(4096)
+ * will return FSB 1. Hence if there are blocks in the file, we want to
+ * point to the block prior to the EOF block and not the hole that maps
+ * directly at @offset.
+ */
+ start_fsb = XFS_B_TO_FSB(mp, offset);
+ if (start_fsb)
+ start_fsb--;
+ error = xfs_bmapi_read(ip, start_fsb, 1, imap, &imaps, XFS_BMAPI_ENTIRE);
+ if (error)
+ return 0;
+
+ ASSERT(imaps == 1);
+ if (imap[0].br_startblock == HOLESTARTBLOCK)
+ return 0;
+ if (imap[0].br_blockcount <= (MAXEXTLEN >> 1))
+ return imap[0].br_blockcount;
+ return XFS_B_TO_FSB(mp, offset);
+}
+
+/*
* If we don't have a user specified preallocation size, dynamically increase
* the preallocation size as the size of the file grows. Cap the maximum size
* at a single extent or less if the filesystem is near full. The closer the
@@ -319,20 +375,19 @@
STATIC xfs_fsblock_t
xfs_iomap_prealloc_size(
struct xfs_mount *mp,
- struct xfs_inode *ip)
+ struct xfs_inode *ip,
+ xfs_off_t offset,
+ struct xfs_bmbt_irec *imap,
+ int nimaps)
{
xfs_fsblock_t alloc_blocks = 0;
- if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
+ alloc_blocks = xfs_iomap_eof_prealloc_initial_size(mp, ip, offset,
+ imap, nimaps);
+ if (alloc_blocks > 0) {
int shift = 0;
int64_t freesp;
- /*
- * rounddown_pow_of_two() returns an undefined result
- * if we pass in alloc_blocks = 0. Hence the "+ 1" to
- * ensure we always pass in a non-zero value.
- */
- alloc_blocks = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)) + 1;
alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
rounddown_pow_of_two(alloc_blocks));
@@ -358,7 +413,7 @@
* have a large file on a small filesystem and the above
* lowspace thresholds are smaller than MAXEXTLEN.
*/
- while (alloc_blocks >= freesp)
+ while (alloc_blocks && alloc_blocks >= freesp)
alloc_blocks >>= 4;
}
@@ -399,7 +454,6 @@
extsz = xfs_get_extsz_hint(ip);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
-
error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count,
imap, XFS_WRITE_IMAPS, &prealloc);
if (error)
@@ -407,7 +461,10 @@
retry:
if (prealloc) {
- xfs_fsblock_t alloc_blocks = xfs_iomap_prealloc_size(mp, ip);
+ xfs_fsblock_t alloc_blocks;
+
+ alloc_blocks = xfs_iomap_prealloc_size(mp, ip, offset, imap,
+ XFS_WRITE_IMAPS);
aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
ioalign = XFS_B_TO_FSBT(mp, aligned_offset);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 46bd9d5..eec226f 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -120,7 +120,7 @@
struct xlog *log,
struct xlog_in_core *iclog,
int count,
- boolean_t syncing);
+ bool syncing);
STATIC void
xlog_verify_tail_lsn(
struct xlog *log,
@@ -1737,7 +1737,7 @@
ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);
- xlog_verify_iclog(log, iclog, count, B_TRUE);
+ xlog_verify_iclog(log, iclog, count, true);
/* account for log which doesn't start at block #0 */
XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
@@ -3611,7 +3611,7 @@
struct xlog *log,
struct xlog_in_core *iclog,
int count,
- boolean_t syncing)
+ bool syncing)
{
xlog_op_header_t *ophead;
xlog_in_core_t *icptr;
@@ -3659,7 +3659,7 @@
/* clientid is only 1 byte */
field_offset = (__psint_t)
((xfs_caddr_t)&(ophead->oh_clientid) - base_ptr);
- if (syncing == B_FALSE || (field_offset & 0x1ff)) {
+ if (!syncing || (field_offset & 0x1ff)) {
clientid = ophead->oh_clientid;
} else {
idx = BTOBBT((xfs_caddr_t)&(ophead->oh_clientid) - iclog->ic_datap);
@@ -3682,7 +3682,7 @@
/* check length */
field_offset = (__psint_t)
((xfs_caddr_t)&(ophead->oh_len) - base_ptr);
- if (syncing == B_FALSE || (field_offset & 0x1ff)) {
+ if (!syncing || (field_offset & 0x1ff)) {
op_len = be32_to_cpu(ophead->oh_len);
} else {
idx = BTOBBT((__psint_t)&ophead->oh_len -
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 96fcbb8..d1dba7c 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1442,9 +1442,8 @@
xlog_tid_t tid)
{
xlog_recover_t *trans;
- struct hlist_node *n;
- hlist_for_each_entry(trans, n, head, r_list) {
+ hlist_for_each_entry(trans, head, r_list) {
if (trans->r_log_tid == tid)
return trans;
}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 7d6df7c..3806088 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1109,8 +1109,8 @@
return 0;
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
- error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
- XFS_DEFAULT_LOG_COUNT);
+ error = xfs_trans_reserve(tp, 0, XFS_QM_SBCHANGE_LOG_RES(mp),
+ 0, 0, XFS_DEFAULT_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
xfs_alert(mp, "%s: Superblock update failed!", __func__);
@@ -1583,8 +1583,8 @@
return 0;
tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
- error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
- XFS_DEFAULT_LOG_COUNT);
+ error = xfs_trans_reserve(tp, 0, XFS_SB_LOG_RES(mp), 0, 0,
+ XFS_DEFAULT_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
@@ -1945,8 +1945,8 @@
XFS_SB_VERSIONNUM));
tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
- error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
- XFS_DEFAULT_LOG_COUNT);
+ error = xfs_trans_reserve(tp, 0, XFS_SB_LOG_RES(mp), 0, 0,
+ XFS_DEFAULT_LOG_COUNT);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index bab8314..bc90706 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -34,12 +34,19 @@
uint tr_addafork; /* cvt inode to attributed trans */
uint tr_writeid; /* write setuid/setgid file */
uint tr_attrinval; /* attr fork buffer invalidation */
- uint tr_attrset; /* set/create an attribute */
+ uint tr_attrsetm; /* set/create an attribute at mount time */
+ uint tr_attrsetrt; /* set/create an attribute at runtime */
uint tr_attrrm; /* remove an attribute */
uint tr_clearagi; /* clear bad agi unlinked ino bucket */
uint tr_growrtalloc; /* grow realtime allocations */
uint tr_growrtzero; /* grow realtime zeroing */
uint tr_growrtfree; /* grow realtime freeing */
+ uint tr_qm_sbchange; /* change quota flags */
+ uint tr_qm_setqlim; /* adjust quota limits */
+ uint tr_qm_dqalloc; /* allocate quota on disk */
+ uint tr_qm_quotaoff; /* turn quota off */
+ uint tr_qm_equotaoff;/* end of turn quota off */
+ uint tr_sb; /* modify superblock */
} xfs_trans_reservations_t;
#ifndef __KERNEL__
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 60eff47..e5b5cf9 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1584,10 +1584,9 @@
int error;
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
- if ((error = xfs_trans_reserve(tp, 0,
- mp->m_sb.sb_sectsize + 128, 0,
- 0,
- XFS_DEFAULT_LOG_COUNT))) {
+ error = xfs_trans_reserve(tp, 0, XFS_QM_SBCHANGE_LOG_RES(mp),
+ 0, 0, XFS_DEFAULT_LOG_COUNT);
+ if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 6b39115..2d02eac1 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -146,7 +146,7 @@
* inode goes inactive and wants to free blocks,
* or via xfs_log_mount_finish.
*/
- *needquotamount = B_TRUE;
+ *needquotamount = true;
*quotaflags = mp->m_qflags;
mp->m_qflags = 0;
}
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 8a59f85..cf9a340 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -408,10 +408,10 @@
{
struct xfs_quotainfo *q = mp->m_quotainfo;
struct xfs_inode *uip, *gip;
- boolean_t tempuqip, tempgqip;
+ bool tempuqip, tempgqip;
uip = gip = NULL;
- tempuqip = tempgqip = B_FALSE;
+ tempuqip = tempgqip = false;
memset(out, 0, sizeof(fs_quota_stat_t));
out->qs_version = FS_QSTAT_VERSION;
@@ -434,12 +434,12 @@
if (!uip && mp->m_sb.sb_uquotino != NULLFSINO) {
if (xfs_iget(mp, NULL, mp->m_sb.sb_uquotino,
0, 0, &uip) == 0)
- tempuqip = B_TRUE;
+ tempuqip = true;
}
if (!gip && mp->m_sb.sb_gquotino != NULLFSINO) {
if (xfs_iget(mp, NULL, mp->m_sb.sb_gquotino,
0, 0, &gip) == 0)
- tempgqip = B_TRUE;
+ tempgqip = true;
}
if (uip) {
out->qs_uquota.qfs_nblks = uip->i_d.di_nblocks;
@@ -490,8 +490,9 @@
return 0;
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
- if ((error = xfs_trans_reserve(tp, 0, sizeof(xfs_disk_dquot_t) + 128,
- 0, 0, XFS_DEFAULT_LOG_COUNT))) {
+ error = xfs_trans_reserve(tp, 0, XFS_QM_SETQLIM_LOG_RES(mp),
+ 0, 0, XFS_DEFAULT_LOG_COUNT);
+ if (error) {
xfs_trans_cancel(tp, 0);
return (error);
}
@@ -638,8 +639,9 @@
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QUOTAOFF_END);
- if ((error = xfs_trans_reserve(tp, 0, sizeof(xfs_qoff_logitem_t) * 2,
- 0, 0, XFS_DEFAULT_LOG_COUNT))) {
+ error = xfs_trans_reserve(tp, 0, XFS_QM_QUOTAOFF_END_LOG_RES(mp),
+ 0, 0, XFS_DEFAULT_LOG_COUNT);
+ if (error) {
xfs_trans_cancel(tp, 0);
return (error);
}
@@ -671,14 +673,10 @@
uint oldsbqflag=0;
tp = xfs_trans_alloc(mp, XFS_TRANS_QM_QUOTAOFF);
- if ((error = xfs_trans_reserve(tp, 0,
- sizeof(xfs_qoff_logitem_t) * 2 +
- mp->m_sb.sb_sectsize + 128,
- 0,
- 0,
- XFS_DEFAULT_LOG_COUNT))) {
+ error = xfs_trans_reserve(tp, 0, XFS_QM_QUOTAOFF_LOG_RES(mp),
+ 0, 0, XFS_DEFAULT_LOG_COUNT);
+ if (error)
goto error0;
- }
qoffi = xfs_trans_get_qoff_item(tp, NULL, flags & XFS_ALL_QUOTA_ACCT);
xfs_trans_log_quotaoff_item(tp, qoffi);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index ab8839b..ea341ce 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -139,9 +139,9 @@
STATIC unsigned long
-suffix_strtoul(char *s, char **endp, unsigned int base)
+suffix_kstrtoint(char *s, unsigned int base, int *res)
{
- int last, shift_left_factor = 0;
+ int last, shift_left_factor = 0, _res;
char *value = s;
last = strlen(value) - 1;
@@ -158,7 +158,10 @@
value[last] = '\0';
}
- return simple_strtoul((const char *)s, endp, base) << shift_left_factor;
+ if (kstrtoint(s, base, &_res))
+ return -EINVAL;
+ *res = _res << shift_left_factor;
+ return 0;
}
/*
@@ -174,7 +177,7 @@
char *options)
{
struct super_block *sb = mp->m_super;
- char *this_char, *value, *eov;
+ char *this_char, *value;
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
@@ -230,14 +233,16 @@
this_char);
return EINVAL;
}
- mp->m_logbufs = simple_strtoul(value, &eov, 10);
+ if (kstrtoint(value, 10, &mp->m_logbufs))
+ return EINVAL;
} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
- mp->m_logbsize = suffix_strtoul(value, &eov, 10);
+ if (suffix_kstrtoint(value, 10, &mp->m_logbsize))
+ return EINVAL;
} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
@@ -266,7 +271,8 @@
this_char);
return EINVAL;
}
- iosize = simple_strtoul(value, &eov, 10);
+ if (kstrtoint(value, 10, &iosize))
+ return EINVAL;
iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE)) {
if (!value || !*value) {
@@ -274,7 +280,8 @@
this_char);
return EINVAL;
}
- iosize = suffix_strtoul(value, &eov, 10);
+ if (suffix_kstrtoint(value, 10, &iosize))
+ return EINVAL;
iosizelog = ffs(iosize) - 1;
} else if (!strcmp(this_char, MNTOPT_GRPID) ||
!strcmp(this_char, MNTOPT_BSDGROUPS)) {
@@ -296,14 +303,16 @@
this_char);
return EINVAL;
}
- dsunit = simple_strtoul(value, &eov, 10);
+ if (kstrtoint(value, 10, &dsunit))
+ return EINVAL;
} else if (!strcmp(this_char, MNTOPT_SWIDTH)) {
if (!value || !*value) {
xfs_warn(mp, "%s option requires an argument",
this_char);
return EINVAL;
}
- dswidth = simple_strtoul(value, &eov, 10);
+ if (kstrtoint(value, 10, &dswidth))
+ return EINVAL;
} else if (!strcmp(this_char, MNTOPT_32BITINODE)) {
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
@@ -1552,6 +1561,7 @@
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("xfs");
STATIC int __init
xfs_init_zones(void)
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 06ed520..2fd7c1f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -37,14 +37,45 @@
#include "xfs_extent_busy.h"
#include "xfs_bmap.h"
#include "xfs_quota.h"
+#include "xfs_qm.h"
#include "xfs_trans_priv.h"
#include "xfs_trans_space.h"
#include "xfs_inode_item.h"
+#include "xfs_log_priv.h"
+#include "xfs_buf_item.h"
#include "xfs_trace.h"
kmem_zone_t *xfs_trans_zone;
kmem_zone_t *xfs_log_item_desc_zone;
+/*
+ * A buffer has a format structure overhead in the log in addition
+ * to the data, so we need to take this into account when reserving
+ * space in a transaction for a buffer. Round the space required up
+ * to a multiple of 128 bytes so that we don't change the historical
+ * reservation that has been used for this overhead.
+ */
+STATIC uint
+xfs_buf_log_overhead(void)
+{
+ return round_up(sizeof(struct xlog_op_header) +
+ sizeof(struct xfs_buf_log_format), 128);
+}
+
+/*
+ * Calculate out transaction log reservation per item in bytes.
+ *
+ * The nbufs argument is used to indicate the number of items that
+ * will be changed in a transaction. size is used to tell how many
+ * bytes should be reserved per item.
+ */
+STATIC uint
+xfs_calc_buf_res(
+ uint nbufs,
+ uint size)
+{
+ return nbufs * (size + xfs_buf_log_overhead());
+}
/*
* Various log reservation values.
@@ -85,18 +116,15 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- XFS_FSB_TO_B(mp, XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK)) +
- 2 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 2) +
- 128 * (4 + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) +
- XFS_ALLOCFREE_LOG_COUNT(mp, 2))),
- (2 * mp->m_sb.sb_sectsize +
- 2 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 2) +
- 128 * (5 + XFS_ALLOCFREE_LOG_COUNT(mp, 2))));
+ MAX((xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -117,18 +145,17 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- XFS_FSB_TO_B(mp, XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1) +
- 128 * (2 + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK))),
- (4 * mp->m_sb.sb_sectsize +
- 4 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 4) +
- 128 * (9 + XFS_ALLOCFREE_LOG_COUNT(mp, 4)) +
- 128 * 5 +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (2 + XFS_IALLOC_BLOCKS(mp) + mp->m_in_maxlevels +
- XFS_ALLOCFREE_LOG_COUNT(mp, 1))));
+ MAX((xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1,
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 4),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(5, 0) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(2 + XFS_IALLOC_BLOCKS(mp) +
+ mp->m_in_maxlevels, 0)));
}
/*
@@ -148,14 +175,12 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((4 * mp->m_sb.sb_inodesize +
- 2 * XFS_DIROP_LOG_RES(mp) +
- 128 * (4 + 2 * XFS_DIROP_LOG_COUNT(mp))),
- (3 * mp->m_sb.sb_sectsize +
- 3 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 3) +
- 128 * (7 + XFS_ALLOCFREE_LOG_COUNT(mp, 3))));
+ MAX((xfs_calc_buf_res(4, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 3),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -175,15 +200,12 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- mp->m_sb.sb_inodesize +
- XFS_DIROP_LOG_RES(mp) +
- 128 * (2 + XFS_DIROP_LOG_COUNT(mp))),
- (mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (3 + XFS_ALLOCFREE_LOG_COUNT(mp, 1))));
+ MAX((xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -203,15 +225,12 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- mp->m_sb.sb_inodesize +
- XFS_DIROP_LOG_RES(mp) +
- 128 * (2 + XFS_DIROP_LOG_COUNT(mp))),
- (2 * mp->m_sb.sb_sectsize +
- 2 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 2) +
- 128 * (5 + XFS_ALLOCFREE_LOG_COUNT(mp, 2))));
+ MAX((xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -233,18 +252,18 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- mp->m_sb.sb_inodesize +
- XFS_FSB_TO_B(mp, 1) +
- XFS_DIROP_LOG_RES(mp) +
- 1024 +
- 128 * (4 + XFS_DIROP_LOG_COUNT(mp))),
- (2 * mp->m_sb.sb_sectsize +
- XFS_FSB_TO_B(mp, XFS_IALLOC_BLOCKS(mp)) +
- XFS_FSB_TO_B(mp, mp->m_in_maxlevels) +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (2 + XFS_IALLOC_BLOCKS(mp) + mp->m_in_maxlevels +
- XFS_ALLOCFREE_LOG_COUNT(mp, 1))));
+ MAX((xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(1, 1024)),
+ (xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_IALLOC_BLOCKS(mp),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(mp->m_in_maxlevels,
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -267,18 +286,19 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- mp->m_sb.sb_inodesize +
+ MAX((xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+ (uint)XFS_FSB_TO_B(mp, 1) +
+ xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
mp->m_sb.sb_sectsize +
- XFS_FSB_TO_B(mp, 1) +
- XFS_DIROP_LOG_RES(mp) +
- 128 * (3 + XFS_DIROP_LOG_COUNT(mp))),
- (3 * mp->m_sb.sb_sectsize +
- XFS_FSB_TO_B(mp, XFS_IALLOC_BLOCKS(mp)) +
- XFS_FSB_TO_B(mp, mp->m_in_maxlevels) +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (2 + XFS_IALLOC_BLOCKS(mp) + mp->m_in_maxlevels +
- XFS_ALLOCFREE_LOG_COUNT(mp, 1))));
+ xfs_calc_buf_res(XFS_IALLOC_BLOCKS(mp),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(mp->m_in_maxlevels,
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -306,16 +326,16 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- mp->m_sb.sb_inodesize +
- mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_FSB_TO_B(mp, 1) +
+ xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
MAX((__uint16_t)XFS_FSB_TO_B(mp, 1),
XFS_INODE_CLUSTER_SIZE(mp)) +
- 128 * 5 +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (2 + XFS_IALLOC_BLOCKS(mp) + mp->m_in_maxlevels +
- XFS_ALLOCFREE_LOG_COUNT(mp, 1));
+ xfs_calc_buf_res(1, 0) +
+ xfs_calc_buf_res(2 + XFS_IALLOC_BLOCKS(mp) +
+ mp->m_in_maxlevels, 0) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1));
}
/*
@@ -343,9 +363,9 @@
xfs_calc_growdata_reservation(
struct xfs_mount *mp)
{
- return mp->m_sb.sb_sectsize * 3 +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (3 + XFS_ALLOCFREE_LOG_COUNT(mp, 1));
+ return xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1));
}
/*
@@ -362,12 +382,12 @@
xfs_calc_growrtalloc_reservation(
struct xfs_mount *mp)
{
- return 2 * mp->m_sb.sb_sectsize +
- XFS_FSB_TO_B(mp, XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK)) +
- mp->m_sb.sb_inodesize +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (3 + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) +
- XFS_ALLOCFREE_LOG_COUNT(mp, 1));
+ return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1));
}
/*
@@ -379,7 +399,7 @@
xfs_calc_growrtzero_reservation(
struct xfs_mount *mp)
{
- return mp->m_sb.sb_blocksize + 128;
+ return xfs_calc_buf_res(1, mp->m_sb.sb_blocksize);
}
/*
@@ -396,11 +416,10 @@
xfs_calc_growrtfree_reservation(
struct xfs_mount *mp)
{
- return mp->m_sb.sb_sectsize +
- 2 * mp->m_sb.sb_inodesize +
- mp->m_sb.sb_blocksize +
- mp->m_rsumsize +
- 128 * 5;
+ return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(1, mp->m_sb.sb_blocksize) +
+ xfs_calc_buf_res(1, mp->m_rsumsize);
}
/*
@@ -411,7 +430,7 @@
xfs_calc_swrite_reservation(
struct xfs_mount *mp)
{
- return mp->m_sb.sb_inodesize + 128;
+ return xfs_calc_buf_res(1, mp->m_sb.sb_inodesize);
}
/*
@@ -421,7 +440,7 @@
STATIC uint
xfs_calc_writeid_reservation(xfs_mount_t *mp)
{
- return mp->m_sb.sb_inodesize + 128;
+ return xfs_calc_buf_res(1, mp->m_sb.sb_inodesize);
}
/*
@@ -437,13 +456,13 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- mp->m_sb.sb_inodesize +
- mp->m_sb.sb_sectsize * 2 +
- mp->m_dirblksize +
- XFS_FSB_TO_B(mp, XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1) +
- XFS_ALLOCFREE_LOG_RES(mp, 1) +
- 128 * (4 + XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1 +
- XFS_ALLOCFREE_LOG_COUNT(mp, 1));
+ xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(1, mp->m_dirblksize) +
+ xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
+ XFS_FSB_TO_B(mp, 1)) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+ XFS_FSB_TO_B(mp, 1));
}
/*
@@ -461,35 +480,51 @@
xfs_calc_attrinval_reservation(
struct xfs_mount *mp)
{
- return MAX((mp->m_sb.sb_inodesize +
- XFS_FSB_TO_B(mp, XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
- 128 * (1 + XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK))),
- (4 * mp->m_sb.sb_sectsize +
- 4 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 4) +
- 128 * (9 + XFS_ALLOCFREE_LOG_COUNT(mp, 4))));
+ return MAX((xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
+ XFS_FSB_TO_B(mp, 1))),
+ (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 4),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
- * Setting an attribute.
+ * Setting an attribute at mount time.
* the inode getting the attribute
* the superblock for allocations
* the agfs extents are allocated from
* the attribute btree * max depth
* the inode allocation btree
* Since attribute transaction space is dependent on the size of the attribute,
- * the calculation is done partially at mount time and partially at runtime.
+ * the calculation is done partially at mount time and partially at runtime(see
+ * below).
*/
STATIC uint
-xfs_calc_attrset_reservation(
+xfs_calc_attrsetm_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- mp->m_sb.sb_inodesize +
- mp->m_sb.sb_sectsize +
- XFS_FSB_TO_B(mp, XFS_DA_NODE_MAXDEPTH) +
- 128 * (2 + XFS_DA_NODE_MAXDEPTH);
+ xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1));
+}
+
+/*
+ * Setting an attribute at runtime, transaction space unit per block.
+ * the superblock for allocations: sector size
+ * the inode bmap btree could join or split: max depth * block size
+ * Since the runtime attribute transaction space is dependent on the total
+ * blocks needed for the 1st bmap, here we calculate out the space unit for
+ * one block so that the caller could figure out the total space according
+ * to the attibute extent length in blocks by: ext * XFS_ATTRSETRT_LOG_RES(mp).
+ */
+STATIC uint
+xfs_calc_attrsetrt_reservation(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
+ XFS_FSB_TO_B(mp, 1));
}
/*
@@ -508,16 +543,15 @@
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- MAX((mp->m_sb.sb_inodesize +
- XFS_FSB_TO_B(mp, XFS_DA_NODE_MAXDEPTH) +
- XFS_FSB_TO_B(mp, XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
- 128 * (1 + XFS_DA_NODE_MAXDEPTH +
- XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK))),
- (2 * mp->m_sb.sb_sectsize +
- 2 * mp->m_sb.sb_sectsize +
- mp->m_sb.sb_sectsize +
- XFS_ALLOCFREE_LOG_RES(mp, 2) +
- 128 * (5 + XFS_ALLOCFREE_LOG_COUNT(mp, 2))));
+ MAX((xfs_calc_buf_res(1, mp->m_sb.sb_inodesize) +
+ xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH,
+ XFS_FSB_TO_B(mp, 1)) +
+ (uint)XFS_FSB_TO_B(mp,
+ XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
+ xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), 0)),
+ (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 2),
+ XFS_FSB_TO_B(mp, 1))));
}
/*
@@ -527,7 +561,78 @@
xfs_calc_clear_agi_bucket_reservation(
struct xfs_mount *mp)
{
- return mp->m_sb.sb_sectsize + 128;
+ return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
+}
+
+/*
+ * Clearing the quotaflags in the superblock.
+ * the super block for changing quota flags: sector size
+ */
+STATIC uint
+xfs_calc_qm_sbchange_reservation(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
+}
+
+/*
+ * Adjusting quota limits.
+ * the xfs_disk_dquot_t: sizeof(struct xfs_disk_dquot)
+ */
+STATIC uint
+xfs_calc_qm_setqlim_reservation(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_buf_res(1, sizeof(struct xfs_disk_dquot));
+}
+
+/*
+ * Allocating quota on disk if needed.
+ * the write transaction log space: XFS_WRITE_LOG_RES(mp)
+ * the unit of quota allocation: one system block size
+ */
+STATIC uint
+xfs_calc_qm_dqalloc_reservation(
+ struct xfs_mount *mp)
+{
+ return XFS_WRITE_LOG_RES(mp) +
+ xfs_calc_buf_res(1,
+ XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1);
+}
+
+/*
+ * Turning off quotas.
+ * the xfs_qoff_logitem_t: sizeof(struct xfs_qoff_logitem) * 2
+ * the superblock for the quota flags: sector size
+ */
+STATIC uint
+xfs_calc_qm_quotaoff_reservation(
+ struct xfs_mount *mp)
+{
+ return sizeof(struct xfs_qoff_logitem) * 2 +
+ xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
+}
+
+/*
+ * End of turning off quotas.
+ * the xfs_qoff_logitem_t: sizeof(struct xfs_qoff_logitem) * 2
+ */
+STATIC uint
+xfs_calc_qm_quotaoff_end_reservation(
+ struct xfs_mount *mp)
+{
+ return sizeof(struct xfs_qoff_logitem) * 2;
+}
+
+/*
+ * Syncing the incore super block changes to disk.
+ * the super block to reflect the changes: sector size
+ */
+STATIC uint
+xfs_calc_sb_reservation(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}
/*
@@ -555,12 +660,19 @@
resp->tr_writeid = xfs_calc_writeid_reservation(mp);
resp->tr_addafork = xfs_calc_addafork_reservation(mp);
resp->tr_attrinval = xfs_calc_attrinval_reservation(mp);
- resp->tr_attrset = xfs_calc_attrset_reservation(mp);
+ resp->tr_attrsetm = xfs_calc_attrsetm_reservation(mp);
+ resp->tr_attrsetrt = xfs_calc_attrsetrt_reservation(mp);
resp->tr_attrrm = xfs_calc_attrrm_reservation(mp);
resp->tr_clearagi = xfs_calc_clear_agi_bucket_reservation(mp);
resp->tr_growrtalloc = xfs_calc_growrtalloc_reservation(mp);
resp->tr_growrtzero = xfs_calc_growrtzero_reservation(mp);
resp->tr_growrtfree = xfs_calc_growrtfree_reservation(mp);
+ resp->tr_qm_sbchange = xfs_calc_qm_sbchange_reservation(mp);
+ resp->tr_qm_setqlim = xfs_calc_qm_setqlim_reservation(mp);
+ resp->tr_qm_dqalloc = xfs_calc_qm_dqalloc_reservation(mp);
+ resp->tr_qm_quotaoff = xfs_calc_qm_quotaoff_reservation(mp);
+ resp->tr_qm_equotaoff = xfs_calc_qm_quotaoff_end_reservation(mp);
+ resp->tr_sb = xfs_calc_sb_reservation(mp);
}
/*
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index c6c0601..cd29f61 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -252,17 +252,19 @@
* as long as SWRITE logs the entire inode core
*/
#define XFS_FSYNC_TS_LOG_RES(mp) ((mp)->m_reservations.tr_swrite)
-#define XFS_WRITEID_LOG_RES(mp) ((mp)->m_reservations.tr_swrite)
+#define XFS_WRITEID_LOG_RES(mp) ((mp)->m_reservations.tr_swrite)
#define XFS_ADDAFORK_LOG_RES(mp) ((mp)->m_reservations.tr_addafork)
#define XFS_ATTRINVAL_LOG_RES(mp) ((mp)->m_reservations.tr_attrinval)
-#define XFS_ATTRSET_LOG_RES(mp, ext) \
- ((mp)->m_reservations.tr_attrset + \
- (ext * (mp)->m_sb.sb_sectsize) + \
- (ext * XFS_FSB_TO_B((mp), XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK))) + \
- (128 * (ext + (ext * XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)))))
-#define XFS_ATTRRM_LOG_RES(mp) ((mp)->m_reservations.tr_attrrm)
+#define XFS_ATTRSETM_LOG_RES(mp) ((mp)->m_reservations.tr_attrsetm)
+#define XFS_ATTRSETRT_LOG_RES(mp) ((mp)->m_reservations.tr_attrsetrt)
+#define XFS_ATTRRM_LOG_RES(mp) ((mp)->m_reservations.tr_attrrm)
#define XFS_CLEAR_AGI_BUCKET_LOG_RES(mp) ((mp)->m_reservations.tr_clearagi)
-
+#define XFS_QM_SBCHANGE_LOG_RES(mp) ((mp)->m_reservations.tr_qm_sbchange)
+#define XFS_QM_SETQLIM_LOG_RES(mp) ((mp)->m_reservations.tr_qm_setqlim)
+#define XFS_QM_DQALLOC_LOG_RES(mp) ((mp)->m_reservations.tr_qm_dqalloc)
+#define XFS_QM_QUOTAOFF_LOG_RES(mp) ((mp)->m_reservations.tr_qm_quotaoff)
+#define XFS_QM_QUOTAOFF_END_LOG_RES(mp) ((mp)->m_reservations.tr_qm_equotaoff)
+#define XFS_SB_LOG_RES(mp) ((mp)->m_reservations.tr_sb)
/*
* Various log count values.
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 6011ee6..0eda725 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -55,20 +55,6 @@
ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) >= 0);
-#ifdef XFS_TRANS_DEBUG
- /*
- * Walk the list checking lsn ordering, and that every entry has the
- * XFS_LI_IN_AIL flag set. This is really expensive, so only do it
- * when specifically debugging the transaction subsystem.
- */
- prev_lip = list_entry(&ailp->xa_ail, xfs_log_item_t, li_ail);
- list_for_each_entry(lip, &ailp->xa_ail, li_ail) {
- if (&prev_lip->li_ail != &ailp->xa_ail)
- ASSERT(XFS_LSN_CMP(prev_lip->li_lsn, lip->li_lsn) <= 0);
- ASSERT((lip->li_flags & XFS_LI_IN_AIL) != 0);
- prev_lip = lip;
- }
-#endif /* XFS_TRANS_DEBUG */
}
#else /* !DEBUG */
#define xfs_ail_check(a,l)
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 0c7fa54..642c2d6 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -516,7 +516,7 @@
int i, j;
xfs_dquot_t *dqp;
xfs_dqtrx_t *qtrx, *qa;
- boolean_t locked;
+ bool locked;
if (!tp->t_dqinfo || !(tp->t_flags & XFS_TRANS_DQ_DIRTY))
return;
@@ -537,17 +537,17 @@
* about the number of blocks used field, or deltas.
* Also we don't bother to zero the fields.
*/
- locked = B_FALSE;
+ locked = false;
if (qtrx->qt_blk_res) {
xfs_dqlock(dqp);
- locked = B_TRUE;
+ locked = true;
dqp->q_res_bcount -=
(xfs_qcnt_t)qtrx->qt_blk_res;
}
if (qtrx->qt_ino_res) {
if (!locked) {
xfs_dqlock(dqp);
- locked = B_TRUE;
+ locked = true;
}
dqp->q_res_icount -=
(xfs_qcnt_t)qtrx->qt_ino_res;
@@ -556,7 +556,7 @@
if (qtrx->qt_rtblk_res) {
if (!locked) {
xfs_dqlock(dqp);
- locked = B_TRUE;
+ locked = true;
}
dqp->q_res_rtbcount -=
(xfs_qcnt_t)qtrx->qt_rtblk_res;
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index d2eee20..ac6d567 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -33,14 +33,6 @@
#include "xfs_inode_item.h"
#include "xfs_trace.h"
-#ifdef XFS_TRANS_DEBUG
-STATIC void
-xfs_trans_inode_broot_debug(
- xfs_inode_t *ip);
-#else
-#define xfs_trans_inode_broot_debug(ip)
-#endif
-
/*
* Add a locked inode to the transaction.
*
@@ -67,8 +59,6 @@
* Get a log_item_desc to point at the new item.
*/
xfs_trans_add_item(tp, &iip->ili_item);
-
- xfs_trans_inode_broot_debug(ip);
}
/*
@@ -135,34 +125,3 @@
flags |= ip->i_itemp->ili_last_fields;
ip->i_itemp->ili_fields |= flags;
}
-
-#ifdef XFS_TRANS_DEBUG
-/*
- * Keep track of the state of the inode btree root to make sure we
- * log it properly.
- */
-STATIC void
-xfs_trans_inode_broot_debug(
- xfs_inode_t *ip)
-{
- xfs_inode_log_item_t *iip;
-
- ASSERT(ip->i_itemp != NULL);
- iip = ip->i_itemp;
- if (iip->ili_root_size != 0) {
- ASSERT(iip->ili_orig_root != NULL);
- kmem_free(iip->ili_orig_root);
- iip->ili_root_size = 0;
- iip->ili_orig_root = NULL;
- }
- if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
- ASSERT((ip->i_df.if_broot != NULL) &&
- (ip->i_df.if_broot_bytes > 0));
- iip->ili_root_size = ip->i_df.if_broot_bytes;
- iip->ili_orig_root =
- (char*)kmem_alloc(iip->ili_root_size, KM_SLEEP);
- memcpy(iip->ili_orig_root, (char*)(ip->i_df.if_broot),
- iip->ili_root_size);
- }
-}
-#endif
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index 7a41874..61ba1cf 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -32,7 +32,6 @@
typedef signed long long int __int64_t;
typedef unsigned long long int __uint64_t;
-typedef enum { B_FALSE,B_TRUE } boolean_t;
typedef __uint32_t prid_t; /* project ID */
typedef __uint32_t inst_t; /* an instruction */
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index d95f565..77ad748 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -725,7 +725,7 @@
int error;
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
- boolean_t unlock_dp_on_error = B_FALSE;
+ bool unlock_dp_on_error = false;
uint cancel_flags;
int committed;
prid_t prid;
@@ -794,7 +794,7 @@
}
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
- unlock_dp_on_error = B_TRUE;
+ unlock_dp_on_error = true;
xfs_bmap_init(&free_list, &first_block);
@@ -830,7 +830,7 @@
* error path.
*/
xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
- unlock_dp_on_error = B_FALSE;
+ unlock_dp_on_error = false;
error = xfs_dir_createname(tp, dp, name, ip->i_ino,
&first_block, &free_list, resblks ?
@@ -1367,7 +1367,7 @@
int pathlen;
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
- boolean_t unlock_dp_on_error = B_FALSE;
+ bool unlock_dp_on_error = false;
uint cancel_flags;
int committed;
xfs_fileoff_t first_fsb;
@@ -1438,7 +1438,7 @@
}
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
- unlock_dp_on_error = B_TRUE;
+ unlock_dp_on_error = true;
/*
* Check whether the directory allows new symlinks or not.
@@ -1484,7 +1484,7 @@
* error path.
*/
xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
- unlock_dp_on_error = B_FALSE;
+ unlock_dp_on_error = false;
/*
* Also attach the dquot(s) to it, if applicable.