aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/binfmt_flat.c6
-rw-r--r--fs/cifs/cifsfs.c16
-rw-r--r--fs/cifs/cifsproto.h1
-rw-r--r--fs/cifs/dir.c76
-rw-r--r--fs/cifs/file.c100
-rw-r--r--fs/cifs/inode.c4
-rw-r--r--fs/cifs/sess.c10
-rw-r--r--fs/dcache.c2
-rw-r--r--fs/ext2/acl.c1
-rw-r--r--fs/ext3/acl.c1
-rw-r--r--fs/fcntl.c6
-rw-r--r--fs/fs-writeback.c254
-rw-r--r--fs/nfs/client.c122
-rw-r--r--fs/nfs/getroot.c2
-rw-r--r--fs/nfs/nfs4xdr.c4
-rw-r--r--fs/nfs/super.c22
-rw-r--r--fs/ocfs2/reservations.c1
-rw-r--r--fs/proc/proc_devtree.c3
-rw-r--r--fs/proc/task_nommu.c20
-rw-r--r--fs/super.c6
-rw-r--r--fs/sysv/ialloc.c6
-rw-r--r--fs/ubifs/budget.c2
22 files changed, 317 insertions, 348 deletions
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index b6ab27ccf21..811384bec8d 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -68,11 +68,7 @@
* Here we can be a bit looser than the data sections since this
* needs to only meet arch ABI requirements.
*/
-#ifdef ARCH_SLAB_MINALIGN
-#define FLAT_STACK_ALIGN (ARCH_SLAB_MINALIGN)
-#else
-#define FLAT_STACK_ALIGN (sizeof(void *))
-#endif
+#define FLAT_STACK_ALIGN max_t(unsigned long, sizeof(void *), ARCH_SLAB_MINALIGN)
#define RELOC_FAILED 0xff00ff01 /* Relocation incorrect somewhere */
#define UNLOADED_LIB 0x7ff000ff /* Placeholder for unused library */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 78c02eb4cb1..484e52bb40b 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -473,14 +473,24 @@ static int cifs_remount(struct super_block *sb, int *flags, char *data)
return 0;
}
+void cifs_drop_inode(struct inode *inode)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
+ return generic_drop_inode(inode);
+
+ return generic_delete_inode(inode);
+}
+
static const struct super_operations cifs_super_ops = {
.put_super = cifs_put_super,
.statfs = cifs_statfs,
.alloc_inode = cifs_alloc_inode,
.destroy_inode = cifs_destroy_inode,
-/* .drop_inode = generic_delete_inode,
- .delete_inode = cifs_delete_inode, */ /* Do not need above two
- functions unless later we add lazy close of inodes or unless the
+ .drop_inode = cifs_drop_inode,
+/* .delete_inode = cifs_delete_inode, */ /* Do not need above
+ function unless later we add lazy close of inodes or unless the
kernel forgets to call us with the same number of releases (closes)
as opens */
.show_options = cifs_show_options,
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index fb1657e0fdb..fb6318b8150 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -106,7 +106,6 @@ extern struct cifsFileInfo *cifs_new_fileinfo(struct inode *newinode,
__u16 fileHandle, struct file *file,
struct vfsmount *mnt, unsigned int oflags);
extern int cifs_posix_open(char *full_path, struct inode **pinode,
- struct vfsmount *mnt,
struct super_block *sb,
int mode, int oflags,
__u32 *poplock, __u16 *pnetfid, int xid);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 391816b461c..e7ae78b66fa 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/mount.h>
+#include <linux/file.h>
#include "cifsfs.h"
#include "cifspdu.h"
#include "cifsglob.h"
@@ -184,12 +185,13 @@ cifs_new_fileinfo(struct inode *newinode, __u16 fileHandle,
}
write_unlock(&GlobalSMBSeslock);
+ file->private_data = pCifsFile;
+
return pCifsFile;
}
int cifs_posix_open(char *full_path, struct inode **pinode,
- struct vfsmount *mnt, struct super_block *sb,
- int mode, int oflags,
+ struct super_block *sb, int mode, int oflags,
__u32 *poplock, __u16 *pnetfid, int xid)
{
int rc;
@@ -258,19 +260,6 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
cifs_fattr_to_inode(*pinode, &fattr);
}
- /*
- * cifs_fill_filedata() takes care of setting cifsFileInfo pointer to
- * file->private_data.
- */
- if (mnt) {
- struct cifsFileInfo *pfile_info;
-
- pfile_info = cifs_new_fileinfo(*pinode, *pnetfid, NULL, mnt,
- oflags);
- if (pfile_info == NULL)
- rc = -ENOMEM;
- }
-
posix_open_ret:
kfree(presp_data);
return rc;
@@ -298,7 +287,6 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
int create_options = CREATE_NOT_DIR;
__u32 oplock = 0;
int oflags;
- bool posix_create = false;
/*
* BB below access is probably too much for mknod to request
* but we have to do query and setpathinfo so requesting
@@ -339,7 +327,6 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_open(full_path, &newinode,
- nd ? nd->path.mnt : NULL,
inode->i_sb, mode, oflags, &oplock, &fileHandle, xid);
/* EIO could indicate that (posix open) operation is not
supported, despite what server claimed in capability
@@ -347,7 +334,6 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
handled in posix open */
if (rc == 0) {
- posix_create = true;
if (newinode == NULL) /* query inode info */
goto cifs_create_get_file_info;
else /* success, no need to query */
@@ -478,21 +464,28 @@ cifs_create_set_dentry:
else
cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
- /* nfsd case - nfs srv does not set nd */
- if ((nd == NULL) || (!(nd->flags & LOOKUP_OPEN))) {
- /* mknod case - do not leave file open */
- CIFSSMBClose(xid, tcon, fileHandle);
- } else if (!(posix_create) && (newinode)) {
+ if (newinode && nd && (nd->flags & LOOKUP_OPEN)) {
struct cifsFileInfo *pfile_info;
- /*
- * cifs_fill_filedata() takes care of setting cifsFileInfo
- * pointer to file->private_data.
- */
- pfile_info = cifs_new_fileinfo(newinode, fileHandle, NULL,
+ struct file *filp;
+
+ filp = lookup_instantiate_filp(nd, direntry, generic_file_open);
+ if (IS_ERR(filp)) {
+ rc = PTR_ERR(filp);
+ CIFSSMBClose(xid, tcon, fileHandle);
+ goto cifs_create_out;
+ }
+
+ pfile_info = cifs_new_fileinfo(newinode, fileHandle, filp,
nd->path.mnt, oflags);
- if (pfile_info == NULL)
+ if (pfile_info == NULL) {
+ fput(filp);
+ CIFSSMBClose(xid, tcon, fileHandle);
rc = -ENOMEM;
+ }
+ } else {
+ CIFSSMBClose(xid, tcon, fileHandle);
}
+
cifs_create_out:
kfree(buf);
kfree(full_path);
@@ -636,6 +629,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
bool posix_open = false;
struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *pTcon;
+ struct cifsFileInfo *cfile;
struct inode *newInode = NULL;
char *full_path = NULL;
struct file *filp;
@@ -703,7 +697,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
if (nd && !(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY)) &&
(nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open &&
(nd->intent.open.flags & O_CREAT)) {
- rc = cifs_posix_open(full_path, &newInode, nd->path.mnt,
+ rc = cifs_posix_open(full_path, &newInode,
parent_dir_inode->i_sb,
nd->intent.open.create_mode,
nd->intent.open.flags, &oplock,
@@ -733,8 +727,25 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
else
direntry->d_op = &cifs_dentry_ops;
d_add(direntry, newInode);
- if (posix_open)
- filp = lookup_instantiate_filp(nd, direntry, NULL);
+ if (posix_open) {
+ filp = lookup_instantiate_filp(nd, direntry,
+ generic_file_open);
+ if (IS_ERR(filp)) {
+ rc = PTR_ERR(filp);
+ CIFSSMBClose(xid, pTcon, fileHandle);
+ goto lookup_out;
+ }
+
+ cfile = cifs_new_fileinfo(newInode, fileHandle, filp,
+ nd->path.mnt,
+ nd->intent.open.flags);
+ if (cfile == NULL) {
+ fput(filp);
+ CIFSSMBClose(xid, pTcon, fileHandle);
+ rc = -ENOMEM;
+ goto lookup_out;
+ }
+ }
/* since paths are not looked up by component - the parent
directories are presumed to be good here */
renew_parental_timestamps(direntry);
@@ -755,6 +766,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
is a common return code */
}
+lookup_out:
kfree(full_path);
FreeXid(xid);
return ERR_PTR(rc);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 75541af4b3d..409e4f523e6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -162,44 +162,12 @@ psx_client_can_cache:
return 0;
}
-static struct cifsFileInfo *
-cifs_fill_filedata(struct file *file)
-{
- struct list_head *tmp;
- struct cifsFileInfo *pCifsFile = NULL;
- struct cifsInodeInfo *pCifsInode = NULL;
-
- /* search inode for this file and fill in file->private_data */
- pCifsInode = CIFS_I(file->f_path.dentry->d_inode);
- read_lock(&GlobalSMBSeslock);
- list_for_each(tmp, &pCifsInode->openFileList) {
- pCifsFile = list_entry(tmp, struct cifsFileInfo, flist);
- if ((pCifsFile->pfile == NULL) &&
- (pCifsFile->pid == current->tgid)) {
- /* mode set in cifs_create */
-
- /* needed for writepage */
- pCifsFile->pfile = file;
- file->private_data = pCifsFile;
- break;
- }
- }
- read_unlock(&GlobalSMBSeslock);
-
- if (file->private_data != NULL) {
- return pCifsFile;
- } else if ((file->f_flags & O_CREAT) && (file->f_flags & O_EXCL))
- cERROR(1, "could not find file instance for "
- "new file %p", file);
- return NULL;
-}
-
/* all arguments to this function must be checked for validity in caller */
-static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
- struct cifsInodeInfo *pCifsInode, struct cifsFileInfo *pCifsFile,
+static inline int cifs_open_inode_helper(struct inode *inode,
struct cifsTconInfo *pTcon, int *oplock, FILE_ALL_INFO *buf,
char *full_path, int xid)
{
+ struct cifsInodeInfo *pCifsInode = CIFS_I(inode);
struct timespec temp;
int rc;
@@ -213,36 +181,35 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
/* if not oplocked, invalidate inode pages if mtime or file
size changed */
temp = cifs_NTtimeToUnix(buf->LastWriteTime);
- if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) &&
- (file->f_path.dentry->d_inode->i_size ==
+ if (timespec_equal(&inode->i_mtime, &temp) &&
+ (inode->i_size ==
(loff_t)le64_to_cpu(buf->EndOfFile))) {
cFYI(1, "inode unchanged on server");
} else {
- if (file->f_path.dentry->d_inode->i_mapping) {
+ if (inode->i_mapping) {
/* BB no need to lock inode until after invalidate
since namei code should already have it locked? */
- rc = filemap_write_and_wait(file->f_path.dentry->d_inode->i_mapping);
+ rc = filemap_write_and_wait(inode->i_mapping);
if (rc != 0)
- CIFS_I(file->f_path.dentry->d_inode)->write_behind_rc = rc;
+ pCifsInode->write_behind_rc = rc;
}
cFYI(1, "invalidating remote inode since open detected it "
"changed");
- invalidate_remote_inode(file->f_path.dentry->d_inode);
+ invalidate_remote_inode(inode);
}
client_can_cache:
if (pTcon->unix_ext)
- rc = cifs_get_inode_info_unix(&file->f_path.dentry->d_inode,
- full_path, inode->i_sb, xid);
+ rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb,
+ xid);
else
- rc = cifs_get_inode_info(&file->f_path.dentry->d_inode,
- full_path, buf, inode->i_sb, xid, NULL);
+ rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
+ xid, NULL);
if ((*oplock & 0xF) == OPLOCK_EXCLUSIVE) {
pCifsInode->clientCanCacheAll = true;
pCifsInode->clientCanCacheRead = true;
- cFYI(1, "Exclusive Oplock granted on inode %p",
- file->f_path.dentry->d_inode);
+ cFYI(1, "Exclusive Oplock granted on inode %p", inode);
} else if ((*oplock & 0xF) == OPLOCK_READ)
pCifsInode->clientCanCacheRead = true;
@@ -256,7 +223,7 @@ int cifs_open(struct inode *inode, struct file *file)
__u32 oplock;
struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *tcon;
- struct cifsFileInfo *pCifsFile;
+ struct cifsFileInfo *pCifsFile = NULL;
struct cifsInodeInfo *pCifsInode;
char *full_path = NULL;
int desiredAccess;
@@ -270,12 +237,6 @@ int cifs_open(struct inode *inode, struct file *file)
tcon = cifs_sb->tcon;
pCifsInode = CIFS_I(file->f_path.dentry->d_inode);
- pCifsFile = cifs_fill_filedata(file);
- if (pCifsFile) {
- rc = 0;
- FreeXid(xid);
- return rc;
- }
full_path = build_path_from_dentry(file->f_path.dentry);
if (full_path == NULL) {
@@ -299,8 +260,7 @@ int cifs_open(struct inode *inode, struct file *file)
int oflags = (int) cifs_posix_convert_flags(file->f_flags);
oflags |= SMB_O_CREAT;
/* can not refresh inode info since size could be stale */
- rc = cifs_posix_open(full_path, &inode, file->f_path.mnt,
- inode->i_sb,
+ rc = cifs_posix_open(full_path, &inode, inode->i_sb,
cifs_sb->mnt_file_mode /* ignored */,
oflags, &oplock, &netfid, xid);
if (rc == 0) {
@@ -308,9 +268,20 @@ int cifs_open(struct inode *inode, struct file *file)
/* no need for special case handling of setting mode
on read only files needed here */
- pCifsFile = cifs_fill_filedata(file);
- cifs_posix_open_inode_helper(inode, file, pCifsInode,
- oplock, netfid);
+ rc = cifs_posix_open_inode_helper(inode, file,
+ pCifsInode, oplock, netfid);
+ if (rc != 0) {
+ CIFSSMBClose(xid, tcon, netfid);
+ goto out;
+ }
+
+ pCifsFile = cifs_new_fileinfo(inode, netfid, file,
+ file->f_path.mnt,
+ oflags);
+ if (pCifsFile == NULL) {
+ CIFSSMBClose(xid, tcon, netfid);
+ rc = -ENOMEM;
+ }
goto out;
} else if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
if (tcon->ses->serverNOS)
@@ -391,17 +362,17 @@ int cifs_open(struct inode *inode, struct file *file)
goto out;
}
+ rc = cifs_open_inode_helper(inode, tcon, &oplock, buf, full_path, xid);
+ if (rc != 0)
+ goto out;
+
pCifsFile = cifs_new_fileinfo(inode, netfid, file, file->f_path.mnt,
file->f_flags);
- file->private_data = pCifsFile;
- if (file->private_data == NULL) {
+ if (pCifsFile == NULL) {
rc = -ENOMEM;
goto out;
}
- rc = cifs_open_inode_helper(inode, file, pCifsInode, pCifsFile, tcon,
- &oplock, buf, full_path, xid);
-
if (oplock & CIFS_CREATE_ACTION) {
/* time to set mode which we can not set earlier due to
problems creating new read-only files */
@@ -513,8 +484,7 @@ reopen_error_exit:
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
int oflags = (int) cifs_posix_convert_flags(file->f_flags);
/* can not refresh inode info since size could be stale */
- rc = cifs_posix_open(full_path, NULL, file->f_path.mnt,
- inode->i_sb,
+ rc = cifs_posix_open(full_path, NULL, inode->i_sb,
cifs_sb->mnt_file_mode /* ignored */,
oflags, &oplock, &netfid, xid);
if (rc == 0) {
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 62b324f26a5..6f0683c6895 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1401,6 +1401,10 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath,
if (rc == 0 || rc != -ETXTBSY)
return rc;
+ /* open-file renames don't work across directories */
+ if (to_dentry->d_parent != from_dentry->d_parent)
+ return rc;
+
/* open the file to be renamed -- we need DELETE perms */
rc = CIFSSMBOpen(xid, pTcon, fromPath, FILE_OPEN, DELETE,
CREATE_NOT_DIR, &srcfid, &oplock, NULL,
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 7707389bdf2..0a57cb7db5d 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -730,15 +730,7 @@ ssetup_ntlmssp_authenticate:
/* calculate session key */
setup_ntlmv2_rsp(ses, v2_sess_key, nls_cp);
- if (first_time) /* should this be moved into common code
- with similar ntlmv2 path? */
- /* cifs_calculate_ntlmv2_mac_key(ses->server->mac_signing_key,
- response BB FIXME, v2_sess_key); */
-
- /* copy session key */
-
- /* memcpy(bcc_ptr, (char *)ntlm_session_key,LM2_SESS_KEY_SIZE);
- bcc_ptr += LM2_SESS_KEY_SIZE; */
+ /* FIXME: calculate MAC key */
memcpy(bcc_ptr, (char *)v2_sess_key,
sizeof(struct ntlmv2_resp));
bcc_ptr += sizeof(struct ntlmv2_resp);
diff --git a/fs/dcache.c b/fs/dcache.c
index d96047b4a63..c8c78ba0782 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -590,6 +590,8 @@ static void prune_dcache(int count)
up_read(&sb->s_umount);
}
spin_lock(&sb_lock);
+ /* lock was dropped, must reset next */
+ list_safe_reset_next(sb, n, s_list);
count -= pruned;
__put_super(sb);
/* more work left to do? */
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index ca7e2a0ed98..2bcc0431bad 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -200,6 +200,7 @@ ext2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
return error;
else {
inode->i_mode = mode;
+ inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
if (error == 0)
acl = NULL;
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index 01552abbca3..8a11fe21218 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -205,6 +205,7 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type,
return error;
else {
inode->i_mode = mode;
+ inode->i_ctime = CURRENT_TIME_SEC;
ext3_mark_inode_dirty(handle, inode);
if (error == 0)
acl = NULL;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 51e11bf5708..9d175d623aa 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -733,12 +733,14 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
{
while (fa) {
struct fown_struct *fown;
+ unsigned long flags;
+
if (fa->magic != FASYNC_MAGIC) {
printk(KERN_ERR "kill_fasync: bad magic number in "
"fasync_struct!\n");
return;
}
- spin_lock(&fa->fa_lock);
+ spin_lock_irqsave(&fa->fa_lock, flags);
if (fa->fa_file) {
fown = &fa->fa_file->f_owner;
/* Don't send SIGURG to processes which have not set a
@@ -747,7 +749,7 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
if (!(sig == SIGURG && fown->signum == 0))
send_sigio(fown, fa->fa_fd, band);
}
- spin_unlock(&fa->fa_lock);
+ spin_unlock_irqrestore(&fa->fa_lock, flags);
fa = rcu_dereference(fa->fa_next);
}
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1d1088f48bc..0609607d395 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -63,24 +63,16 @@ struct bdi_work {
};
enum {
- WS_USED_B = 0,
- WS_ONSTACK_B,
+ WS_INPROGRESS = 0,
+ WS_ONSTACK,
};
-#define WS_USED (1 << WS_USED_B)
-#define WS_ONSTACK (1 << WS_ONSTACK_B)
-
-static inline bool bdi_work_on_stack(struct bdi_work *work)
-{
- return test_bit(WS_ONSTACK_B, &work->state);
-}
-
static inline void bdi_work_init(struct bdi_work *work,
struct wb_writeback_args *args)
{
INIT_RCU_HEAD(&work->rcu_head);
work->args = *args;
- work->state = WS_USED;
+ __set_bit(WS_INPROGRESS, &work->state);
}
/**
@@ -95,43 +87,16 @@ int writeback_in_progress(struct backing_dev_info *bdi)
return !list_empty(&bdi->work_list);
}
-static void bdi_work_clear(struct bdi_work *work)
-{
- clear_bit(WS_USED_B, &work->state);
- smp_mb__after_clear_bit();
- /*
- * work can have disappeared at this point. bit waitq functions
- * should be able to tolerate this, provided bdi_sched_wait does
- * not dereference it's pointer argument.
- */
- wake_up_bit(&work->state, WS_USED_B);
-}
-
static void bdi_work_free(struct rcu_head *head)
{
struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
- if (!bdi_work_on_stack(work))
- kfree(work);
- else
- bdi_work_clear(work);
-}
-
-static void wb_work_complete(struct bdi_work *work)
-{
- const enum writeback_sync_modes sync_mode = work->args.sync_mode;
- int onstack = bdi_work_on_stack(work);
+ clear_bit(WS_INPROGRESS, &work->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&work->state, WS_INPROGRESS);
- /*
- * For allocated work, we can clear the done/seen bit right here.
- * For on-stack work, we need to postpone both the clear and free
- * to after the RCU grace period, since the stack could be invalidated
- * as soon as bdi_work_clear() has done the wakeup.
- */
- if (!onstack)
- bdi_work_clear(work);
- if (sync_mode == WB_SYNC_NONE || onstack)
- call_rcu(&work->rcu_head, bdi_work_free);
+ if (!test_bit(WS_ONSTACK, &work->state))
+ kfree(work);
}
static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
@@ -147,7 +112,7 @@ static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
list_del_rcu(&work->list);
spin_unlock(&bdi->wb_lock);
- wb_work_complete(work);
+ call_rcu(&work->rcu_head, bdi_work_free);
}
}
@@ -185,9 +150,9 @@ static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
* Used for on-stack allocated work items. The caller needs to wait until
* the wb threads have acked the work before it's safe to continue.
*/
-static void bdi_wait_on_work_clear(struct bdi_work *work)
+static void bdi_wait_on_work_done(struct bdi_work *work)
{
- wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait,
+ wait_on_bit(&work->state, WS_INPROGRESS, bdi_sched_wait,
TASK_UNINTERRUPTIBLE);
}
@@ -213,37 +178,28 @@ static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
}
/**
- * bdi_sync_writeback - start and wait for writeback
- * @bdi: the backing device to write from
+ * bdi_queue_work_onstack - start and wait for writeback
* @sb: write inodes from this super_block
*
* Description:
- * This does WB_SYNC_ALL data integrity writeback and waits for the
- * IO to complete. Callers must hold the sb s_umount semaphore for
+ * This function initiates writeback and waits for the operation to
+ * complete. Callers must hold the sb s_umount semaphore for
* reading, to avoid having the super disappear before we are done.
*/
-static void bdi_sync_writeback(struct backing_dev_info *bdi,
- struct super_block *sb)
+static void bdi_queue_work_onstack(struct wb_writeback_args *args)
{
- struct wb_writeback_args args = {
- .sb = sb,
- .sync_mode = WB_SYNC_ALL,
- .nr_pages = LONG_MAX,
- .range_cyclic = 0,
- };
struct bdi_work work;
- bdi_work_init(&work, &args);
- work.state |= WS_ONSTACK;
+ bdi_work_init(&work, args);
+ __set_bit(WS_ONSTACK, &work.state);
- bdi_queue_work(bdi, &work);
- bdi_wait_on_work_clear(&work);
+ bdi_queue_work(args->sb->s_bdi, &work);
+ bdi_wait_on_work_done(&work);
}
/**
* bdi_start_writeback - start writeback
* @bdi: the backing device to write from
- * @sb: write inodes from this super_block
* @nr_pages: the number of pages to write
*
* Description:
@@ -252,25 +208,34 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi,
* completion. Caller need not hold sb s_umount semaphore.
*
*/
-void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
- long nr_pages)
+void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
{
struct wb_writeback_args args = {
- .sb = sb,
.sync_mode = WB_SYNC_NONE,
.nr_pages = nr_pages,
.range_cyclic = 1,
};
- /*
- * We treat @nr_pages=0 as the special case to do background writeback,
- * ie. to sync pages until the background dirty threshold is reached.
- */
- if (!nr_pages) {
- args.nr_pages = LONG_MAX;
- args.for_background = 1;
- }
+ bdi_alloc_queue_work(bdi, &args);
+}
+/**
+ * bdi_start_background_writeback - start background writeback
+ * @bdi: the backing device to write from
+ *
+ * Description:
+ * This does WB_SYNC_NONE background writeback. The IO is only
+ * started when this function returns, we make no guarentees on
+ * completion. Caller need not hold sb s_umount semaphore.
+ */
+void bdi_start_background_writeback(struct backing_dev_info *bdi)
+{
+ struct wb_writeback_args args = {
+ .sync_mode = WB_SYNC_NONE,
+ .nr_pages = LONG_MAX,
+ .for_background = 1,
+ .range_cyclic = 1,
+ };
bdi_alloc_queue_work(bdi, &args);
}
@@ -561,48 +526,30 @@ select_queue:
return ret;
}
-static void unpin_sb_for_writeback(struct super_block *sb)
-{
- up_read(&sb->s_umount);
- put_super(sb);
-}
-
-enum sb_pin_state {
- SB_PINNED,
- SB_NOT_PINNED,
- SB_PIN_FAILED
-};
-
/*
- * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
+ * For background writeback the caller does not have the sb pinned
* before calling writeback. So make sure that we do pin it, so it doesn't
* go away while we are writing inodes from it.
*/
-static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc,
- struct super_block *sb)
+static bool pin_sb_for_writeback(struct super_block *sb)
{
- /*
- * Caller must already hold the ref for this
- */
- if (wbc->sync_mode == WB_SYNC_ALL) {
- WARN_ON(!rwsem_is_locked(&sb->s_umount));
- return SB_NOT_PINNED;
- }
spin_lock(&sb_lock);
+ if (list_empty(&sb->s_instances)) {
+ spin_unlock(&sb_lock);
+ return false;
+ }
+
sb->s_count++;
+ spin_unlock(&sb_lock);
+
if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root) {
- spin_unlock(&sb_lock);
- return SB_PINNED;
- }
- /*
- * umounted, drop rwsem again and fall through to failure
- */
+ if (sb->s_root)
+ return true;
up_read(&sb->s_umount);
}
- sb->s_count--;
- spin_unlock(&sb_lock);
- return SB_PIN_FAILED;
+
+ put_super(sb);
+ return false;
}
/*
@@ -681,24 +628,31 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
struct inode *inode = list_entry(wb->b_io.prev,
struct inode, i_list);
struct super_block *sb = inode->i_sb;
- enum sb_pin_state state;
- if (wbc->sb && sb != wbc->sb) {
- /* super block given and doesn't
- match, skip this inode */
- redirty_tail(inode);
- continue;
- }
- state = pin_sb_for_writeback(wbc, sb);
+ if (wbc->sb) {
+ /*
+ * We are requested to write out inodes for a specific
+ * superblock. This means we already have s_umount
+ * taken by the caller which also waits for us to
+ * complete the writeout.
+ */
+ if (sb != wbc->sb) {
+ redirty_tail(inode);
+ continue;
+ }
- if (state == SB_PIN_FAILED) {
- requeue_io(inode);
- continue;
+ WARN_ON(!rwsem_is_locked(&sb->s_umount));
+
+ ret = writeback_sb_inodes(sb, wb, wbc);
+ } else {
+ if (!pin_sb_for_writeback(sb)) {
+ requeue_io(inode);
+ continue;
+ }
+ ret = writeback_sb_inodes(sb, wb, wbc);
+ drop_super(sb);
}
- ret = writeback_sb_inodes(sb, wb, wbc);
- if (state == SB_PINNED)
- unpin_sb_for_writeback(sb);
if (ret)
break;
}
@@ -911,7 +865,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
* If this isn't a data integrity operation, just notify
* that we have seen this work and we are now starting it.
*/
- if (args.sync_mode == WB_SYNC_NONE)
+ if (!test_bit(WS_ONSTACK, &work->state))
wb_clear_pending(wb, work);
wrote += wb_writeback(wb, &args);
@@ -920,7 +874,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
* This is a data integrity writeback, so only do the
* notification when we have completed the work.
*/
- if (args.sync_mode == WB_SYNC_ALL)
+ if (test_bit(WS_ONSTACK, &work->state))
wb_clear_pending(wb, work);
}
@@ -978,42 +932,32 @@ int bdi_writeback_task(struct bdi_writeback *wb)
}
/*
- * Schedule writeback for all backing devices. This does WB_SYNC_NONE
- * writeback, for integrity writeback see bdi_sync_writeback().
+ * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
+ * the whole world.
*/
-static void bdi_writeback_all(struct super_block *sb, long nr_pages)
+void wakeup_flusher_threads(long nr_pages)
{
+ struct backing_dev_info *bdi;
struct wb_writeback_args args = {
- .sb = sb,
- .nr_pages = nr_pages,
.sync_mode = WB_SYNC_NONE,
};
- struct backing_dev_info *bdi;
- rcu_read_lock();
+ if (nr_pages) {
+ args.nr_pages = nr_pages;
+ } else {
+ args.nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
+ }
+ rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
if (!bdi_has_dirty_io(bdi))
continue;
-
bdi_alloc_queue_work(bdi, &args);
}
-
rcu_read_unlock();
}
-/*
- * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
- * the whole world.
- */
-void wakeup_flusher_threads(long nr_pages)
-{
- if (nr_pages == 0)
- nr_pages = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- bdi_writeback_all(NULL, nr_pages);
-}
-
static noinline void block_dump___mark_inode_dirty(struct inode *inode)
{
if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
@@ -1218,12 +1162,17 @@ void writeback_inodes_sb(struct super_block *sb)
{
unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
- long nr_to_write;
+ struct wb_writeback_args args = {
+ .sb = sb,
+ .sync_mode = WB_SYNC_NONE,
+ };
+
+ WARN_ON(!rwsem_is_locked(&