aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/buffer.c10
-rw-r--r--fs/cifs/Kconfig1
-rw-r--r--fs/cifs/cifsfs.c93
-rw-r--r--fs/cifs/cifsglob.h21
-rw-r--r--fs/cifs/cifsproto.h11
-rw-r--r--fs/cifs/cifssmb.c1
-rw-r--r--fs/cifs/connect.c1
-rw-r--r--fs/cifs/dir.c64
-rw-r--r--fs/cifs/file.c137
-rw-r--r--fs/cifs/misc.c34
-rw-r--r--fs/cifs/readdir.c4
-rw-r--r--fs/cifs/transport.c50
-rw-r--r--fs/ecryptfs/Kconfig4
-rw-r--r--fs/ecryptfs/crypto.c39
-rw-r--r--fs/ecryptfs/inode.c2
-rw-r--r--fs/ecryptfs/keystore.c39
-rw-r--r--fs/ecryptfs/kthread.c24
-rw-r--r--fs/ecryptfs/main.c3
-rw-r--r--fs/ecryptfs/mmap.c4
-rw-r--r--fs/ecryptfs/read_write.c32
-rw-r--r--fs/ecryptfs/super.c2
-rw-r--r--fs/fs-writeback.c165
-rw-r--r--fs/nfs/super.c2
-rw-r--r--fs/proc/array.c7
24 files changed, 366 insertions, 384 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index 24afd7422ae..6fa530256bf 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -280,7 +280,7 @@ void invalidate_bdev(struct block_device *bdev)
EXPORT_SYMBOL(invalidate_bdev);
/*
- * Kick pdflush then try to free up some ZONE_NORMAL memory.
+ * Kick the writeback threads then try to free up some ZONE_NORMAL memory.
*/
static void free_more_memory(void)
{
@@ -1709,9 +1709,9 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
/*
* If it's a fully non-blocking write attempt and we cannot
* lock the buffer then redirty the page. Note that this can
- * potentially cause a busy-wait loop from pdflush and kswapd
- * activity, but those code paths have their own higher-level
- * throttling.
+ * potentially cause a busy-wait loop from writeback threads
+ * and kswapd activity, but those code paths have their own
+ * higher-level throttling.
*/
if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
lock_buffer(bh);
@@ -3208,7 +3208,7 @@ EXPORT_SYMBOL(block_sync_page);
* still running obsolete flush daemons, so we terminate them here.
*
* Use of bdflush() is deprecated and will be removed in a future kernel.
- * The `pdflush' kernel threads fully replace bdflush daemons and this call.
+ * The `flush-X' kernel threads fully replace bdflush daemons and this call.
*/
SYSCALL_DEFINE2(bdflush, int, func, long, data)
{
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 6994a0f54f0..80f35259680 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -2,6 +2,7 @@ config CIFS
tristate "CIFS support (advanced network filesystem, SMBFS successor)"
depends on INET
select NLS
+ select SLOW_WORK
help
This is the client VFS module for the Common Internet File System
(CIFS) protocol which is the successor to the Server Message Block
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 90c5b39f031..9a5e4f5f312 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -64,9 +64,6 @@ unsigned int multiuser_mount = 0;
unsigned int extended_security = CIFSSEC_DEF;
/* unsigned int ntlmv2_support = 0; */
unsigned int sign_CIFS_PDUs = 1;
-extern struct task_struct *oplockThread; /* remove sparse warning */
-struct task_struct *oplockThread = NULL;
-/* extern struct task_struct * dnotifyThread; remove sparse warning */
static const struct super_operations cifs_super_ops;
unsigned int CIFSMaxBufSize = CIFS_MAX_MSGSIZE;
module_param(CIFSMaxBufSize, int, 0);
@@ -972,89 +969,12 @@ cifs_destroy_mids(void)
kmem_cache_destroy(cifs_oplock_cachep);
}
-static int cifs_oplock_thread(void *dummyarg)
-{
- struct oplock_q_entry *oplock_item;
- struct cifsTconInfo *pTcon;
- struct inode *inode;
- __u16 netfid;
- int rc, waitrc = 0;
-
- set_freezable();
- do {
- if (try_to_freeze())
- continue;
-
- spin_lock(&cifs_oplock_lock);
- if (list_empty(&cifs_oplock_list)) {
- spin_unlock(&cifs_oplock_lock);
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(39*HZ);
- } else {
- oplock_item = list_entry(cifs_oplock_list.next,
- struct oplock_q_entry, qhead);
- cFYI(1, ("found oplock item to write out"));
- pTcon = oplock_item->tcon;
- inode = oplock_item->pinode;
- netfid = oplock_item->netfid;
- spin_unlock(&cifs_oplock_lock);
- DeleteOplockQEntry(oplock_item);
- /* can not grab inode sem here since it would
- deadlock when oplock received on delete
- since vfs_unlink holds the i_mutex across
- the call */
- /* mutex_lock(&inode->i_mutex);*/
- if (S_ISREG(inode->i_mode)) {
-#ifdef CONFIG_CIFS_EXPERIMENTAL
- if (CIFS_I(inode)->clientCanCacheAll == 0)
- break_lease(inode, FMODE_READ);
- else if (CIFS_I(inode)->clientCanCacheRead == 0)
- break_lease(inode, FMODE_WRITE);
-#endif
- rc = filemap_fdatawrite(inode->i_mapping);
- if (CIFS_I(inode)->clientCanCacheRead == 0) {
- waitrc = filemap_fdatawait(
- inode->i_mapping);
- invalidate_remote_inode(inode);
- }
- if (rc == 0)
- rc = waitrc;
- } else
- rc = 0;
- /* mutex_unlock(&inode->i_mutex);*/
- if (rc)
- CIFS_I(inode)->write_behind_rc = rc;
- cFYI(1, ("Oplock flush inode %p rc %d",
- inode, rc));
-
- /* releasing stale oplock after recent reconnect
- of smb session using a now incorrect file
- handle is not a data integrity issue but do
- not bother sending an oplock release if session
- to server still is disconnected since oplock
- already released by the server in that case */
- if (!pTcon->need_reconnect) {
- rc = CIFSSMBLock(0, pTcon, netfid,
- 0 /* len */ , 0 /* offset */, 0,
- 0, LOCKING_ANDX_OPLOCK_RELEASE,
- false /* wait flag */);
- cFYI(1, ("Oplock release rc = %d", rc));
- }
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(1); /* yield in case q were corrupt */
- }
- } while (!kthread_should_stop());
-
- return 0;
-}
-
static int __init
init_cifs(void)
{
int rc = 0;
cifs_proc_init();
INIT_LIST_HEAD(&cifs_tcp_ses_list);
- INIT_LIST_HEAD(&cifs_oplock_list);
#ifdef CONFIG_CIFS_EXPERIMENTAL
INIT_LIST_HEAD(&GlobalDnotifyReqList);
INIT_LIST_HEAD(&GlobalDnotifyRsp_Q);
@@ -1083,7 +1003,6 @@ init_cifs(void)
rwlock_init(&GlobalSMBSeslock);
rwlock_init(&cifs_tcp_ses_lock);
spin_lock_init(&GlobalMid_Lock);
- spin_lock_init(&cifs_oplock_lock);
if (cifs_max_pending < 2) {
cifs_max_pending = 2;
@@ -1118,16 +1037,13 @@ init_cifs(void)
if (rc)
goto out_unregister_key_type;
#endif
- oplockThread = kthread_run(cifs_oplock_thread, NULL, "cifsoplockd");
- if (IS_ERR(oplockThread)) {
- rc = PTR_ERR(oplockThread);
- cERROR(1, ("error %d create oplock thread", rc));
- goto out_unregister_dfs_key_type;
- }
+ rc = slow_work_register_user();
+ if (rc)
+ goto out_unregister_resolver_key;
return 0;
- out_unregister_dfs_key_type:
+ out_unregister_resolver_key:
#ifdef CONFIG_CIFS_DFS_UPCALL
unregister_key_type(&key_type_dns_resolver);
out_unregister_key_type:
@@ -1164,7 +1080,6 @@ exit_cifs(void)
cifs_destroy_inodecache();
cifs_destroy_mids();
cifs_destroy_request_bufs();
- kthread_stop(oplockThread);
}
MODULE_AUTHOR("Steve French <sfrench@us.ibm.com>");
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 6cfc81a3270..5d0fde18039 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -18,6 +18,7 @@
*/
#include <linux/in.h>
#include <linux/in6.h>
+#include <linux/slow-work.h>
#include "cifs_fs_sb.h"
#include "cifsacl.h"
/*
@@ -346,14 +347,16 @@ struct cifsFileInfo {
/* lock scope id (0 if none) */
struct file *pfile; /* needed for writepage */
struct inode *pInode; /* needed for oplock break */
+ struct vfsmount *mnt;
struct mutex lock_mutex;
struct list_head llist; /* list of byte range locks we have. */
bool closePend:1; /* file is marked to close */
bool invalidHandle:1; /* file closed via session abend */
- bool messageMode:1; /* for pipes: message vs byte mode */
+ bool oplock_break_cancelled:1;
atomic_t count; /* reference count */
struct mutex fh_mutex; /* prevents reopen race after dead ses*/
struct cifs_search_info srch_inf;
+ struct slow_work oplock_break; /* slow_work job for oplock breaks */
};
/* Take a reference on the file private data */
@@ -365,8 +368,10 @@ static inline void cifsFileInfo_get(struct cifsFileInfo *cifs_file)
/* Release a reference on the file private data */
static inline void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
{
- if (atomic_dec_and_test(&cifs_file->count))
+ if (atomic_dec_and_test(&cifs_file->count)) {
+ iput(cifs_file->pInode);
kfree(cifs_file);
+ }
}
/*
@@ -382,7 +387,6 @@ struct cifsInodeInfo {
unsigned long time; /* jiffies of last update/check of inode */
bool clientCanCacheRead:1; /* read oplock */
bool clientCanCacheAll:1; /* read and writebehind oplock */
- bool oplockPending:1;
bool delete_pending:1; /* DELETE_ON_CLOSE is set */
u64 server_eof; /* current file size on server */
u64 uniqueid; /* server inode number */
@@ -585,9 +589,9 @@ require use of the stronger protocol */
#define CIFSSEC_MUST_LANMAN 0x10010
#define CIFSSEC_MUST_PLNTXT 0x20020
#ifdef CONFIG_CIFS_UPCALL
-#define CIFSSEC_MASK 0xAF0AF /* allows weak security but also krb5 */
+#define CIFSSEC_MASK 0xBF0BF /* allows weak security but also krb5 */
#else
-#define CIFSSEC_MASK 0xA70A7 /* current flags supported if weak */
+#define CIFSSEC_MASK 0xB70B7 /* current flags supported if weak */
#endif /* UPCALL */
#else /* do not allow weak pw hash */
#ifdef CONFIG_CIFS_UPCALL
@@ -669,12 +673,6 @@ GLOBAL_EXTERN rwlock_t cifs_tcp_ses_lock;
*/
GLOBAL_EXTERN rwlock_t GlobalSMBSeslock;
-/* Global list of oplocks */
-GLOBAL_EXTERN struct list_head cifs_oplock_list;
-
-/* Protects the cifs_oplock_list */
-GLOBAL_EXTERN spinlock_t cifs_oplock_lock;
-
/* Outstanding dir notify requests */
GLOBAL_EXTERN struct list_head GlobalDnotifyReqList;
/* DirNotify response queue */
@@ -725,3 +723,4 @@ GLOBAL_EXTERN unsigned int cifs_min_rcv; /* min size of big ntwrk buf pool */
GLOBAL_EXTERN unsigned int cifs_min_small; /* min size of small buf pool */
GLOBAL_EXTERN unsigned int cifs_max_pending; /* MAX requests at once to server*/
+extern const struct slow_work_ops cifs_oplock_break_ops;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index da8fbf56599..6928c24d1d4 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -86,18 +86,17 @@ extern int CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses,
const int stage,
const struct nls_table *nls_cp);
extern __u16 GetNextMid(struct TCP_Server_Info *server);
-extern struct oplock_q_entry *AllocOplockQEntry(struct inode *, u16,
- struct cifsTconInfo *);
-extern void DeleteOplockQEntry(struct oplock_q_entry *);
-extern void DeleteTconOplockQEntries(struct cifsTconInfo *);
extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
extern u64 cifs_UnixTimeToNT(struct timespec);
extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
int offset);
+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 super_block *sb, int mode, int oflags,
- int *poplock, __u16 *pnetfid, int xid);
+ struct vfsmount *mnt, int mode, int oflags,
+ __u32 *poplock, __u16 *pnetfid, int xid);
extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr,
FILE_UNIX_BASIC_INFO *info,
struct cifs_sb_info *cifs_sb);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 301e307e127..941441d3e38 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -94,6 +94,7 @@ static void mark_open_files_invalid(struct cifsTconInfo *pTcon)
list_for_each_safe(tmp, tmp1, &pTcon->openFileList) {
open_file = list_entry(tmp, struct cifsFileInfo, tlist);
open_file->invalidHandle = true;
+ open_file->oplock_break_cancelled = true;
}
write_unlock(&GlobalSMBSeslock);
/* BB Add call to invalidate_inodes(sb) for all superblocks mounted
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d49682433c2..43003e0bef1 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1670,7 +1670,6 @@ cifs_put_tcon(struct cifsTconInfo *tcon)
CIFSSMBTDis(xid, tcon);
_FreeXid(xid);
- DeleteTconOplockQEntries(tcon);
tconInfoFree(tcon);
cifs_put_smb_ses(ses);
}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index a6424cfc012..627a60a6c1b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -24,6 +24,7 @@
#include <linux/stat.h>
#include <linux/slab.h>
#include <linux/namei.h>
+#include <linux/mount.h>
#include "cifsfs.h"
#include "cifspdu.h"
#include "cifsglob.h"
@@ -129,44 +130,45 @@ cifs_bp_rename_retry:
return full_path;
}
-static void
-cifs_fill_fileinfo(struct inode *newinode, __u16 fileHandle,
- struct cifsTconInfo *tcon, bool write_only)
+struct cifsFileInfo *
+cifs_new_fileinfo(struct inode *newinode, __u16 fileHandle,
+ struct file *file, struct vfsmount *mnt, unsigned int oflags)
{
int oplock = 0;
struct cifsFileInfo *pCifsFile;
struct cifsInodeInfo *pCifsInode;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(mnt->mnt_sb);
pCifsFile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL);
-
if (pCifsFile == NULL)
- return;
+ return pCifsFile;
if (oplockEnabled)
oplock = REQ_OPLOCK;
pCifsFile->netfid = fileHandle;
pCifsFile->pid = current->tgid;
- pCifsFile->pInode = newinode;
+ pCifsFile->pInode = igrab(newinode);
+ pCifsFile->mnt = mnt;
+ pCifsFile->pfile = file;
pCifsFile->invalidHandle = false;
pCifsFile->closePend = false;
mutex_init(&pCifsFile->fh_mutex);
mutex_init(&pCifsFile->lock_mutex);
INIT_LIST_HEAD(&pCifsFile->llist);
atomic_set(&pCifsFile->count, 1);
+ slow_work_init(&pCifsFile->oplock_break, &cifs_oplock_break_ops);
- /* set the following in open now
- pCifsFile->pfile = file; */
write_lock(&GlobalSMBSeslock);
- list_add(&pCifsFile->tlist, &tcon->openFileList);
+ list_add(&pCifsFile->tlist, &cifs_sb->tcon->openFileList);
pCifsInode = CIFS_I(newinode);
if (pCifsInode) {
/* if readable file instance put first in list*/
- if (write_only)
+ if (oflags & FMODE_READ)
+ list_add(&pCifsFile->flist, &pCifsInode->openFileList);
+ else
list_add_tail(&pCifsFile->flist,
&pCifsInode->openFileList);
- else
- list_add(&pCifsFile->flist, &pCifsInode->openFileList);
if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
pCifsInode->clientCanCacheAll = true;
@@ -176,18 +178,18 @@ cifs_fill_fileinfo(struct inode *newinode, __u16 fileHandle,
pCifsInode->clientCanCacheRead = true;
}
write_unlock(&GlobalSMBSeslock);
+
+ return pCifsFile;
}
int cifs_posix_open(char *full_path, struct inode **pinode,
- struct super_block *sb, int mode, int oflags,
- int *poplock, __u16 *pnetfid, int xid)
+ struct vfsmount *mnt, int mode, int oflags,
+ __u32 *poplock, __u16 *pnetfid, int xid)
{
int rc;
- __u32 oplock;
- bool write_only = false;
FILE_UNIX_BASIC_INFO *presp_data;
__u32 posix_flags = 0;
- struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(mnt->mnt_sb);
struct cifs_fattr fattr;
cFYI(1, ("posix open %s", full_path));
@@ -223,12 +225,9 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
if (oflags & O_DIRECT)
posix_flags |= SMB_O_DIRECT;
- if (!(oflags & FMODE_READ))
- write_only = true;
-
mode &= ~current_umask();
rc = CIFSPOSIXCreate(xid, cifs_sb->tcon, posix_flags, mode,
- pnetfid, presp_data, &oplock, full_path,
+ pnetfid, presp_data, poplock, full_path,
cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
if (rc)
@@ -244,7 +243,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
/* get new inode and set it up */
if (*pinode == NULL) {
- *pinode = cifs_iget(sb, &fattr);
+ *pinode = cifs_iget(mnt->mnt_sb, &fattr);
if (!*pinode) {
rc = -ENOMEM;
goto posix_open_ret;
@@ -253,7 +252,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
cifs_fattr_to_inode(*pinode, &fattr);
}
- cifs_fill_fileinfo(*pinode, *pnetfid, cifs_sb->tcon, write_only);
+ cifs_new_fileinfo(*pinode, *pnetfid, NULL, mnt, oflags);
posix_open_ret:
kfree(presp_data);
@@ -280,7 +279,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
int rc = -ENOENT;
int xid;
int create_options = CREATE_NOT_DIR;
- int oplock = 0;
+ __u32 oplock = 0;
int oflags;
bool posix_create = false;
/*
@@ -298,7 +297,6 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
int disposition = FILE_OVERWRITE_IF;
- bool write_only = false;
xid = GetXid();
@@ -323,7 +321,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
- rc = cifs_posix_open(full_path, &newinode, inode->i_sb,
+ rc = cifs_posix_open(full_path, &newinode, nd->path.mnt,
mode, oflags, &oplock, &fileHandle, xid);
/* EIO could indicate that (posix open) operation is not
supported, despite what server claimed in capability
@@ -351,11 +349,8 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
desiredAccess = 0;
if (oflags & FMODE_READ)
desiredAccess |= GENERIC_READ; /* is this too little? */
- if (oflags & FMODE_WRITE) {
+ if (oflags & FMODE_WRITE)
desiredAccess |= GENERIC_WRITE;
- if (!(oflags & FMODE_READ))
- write_only = true;
- }
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
disposition = FILE_CREATE;
@@ -470,8 +465,8 @@ cifs_create_set_dentry:
/* mknod case - do not leave file open */
CIFSSMBClose(xid, tcon, fileHandle);
} else if (!(posix_create) && (newinode)) {
- cifs_fill_fileinfo(newinode, fileHandle,
- cifs_sb->tcon, write_only);
+ cifs_new_fileinfo(newinode, fileHandle, NULL,
+ nd->path.mnt, oflags);
}
cifs_create_out:
kfree(buf);
@@ -611,7 +606,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
{
int xid;
int rc = 0; /* to get around spurious gcc warning, set to zero here */
- int oplock = 0;
+ __u32 oplock = 0;
__u16 fileHandle = 0;
bool posix_open = false;
struct cifs_sb_info *cifs_sb;
@@ -683,8 +678,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
if (!(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,
- parent_dir_inode->i_sb,
+ rc = cifs_posix_open(full_path, &newInode, nd->path.mnt,
nd->intent.open.create_mode,
nd->intent.open.flags, &oplock,
&fileHandle, xid);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index fa7beac8b80..429337eb7af 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -30,6 +30,7 @@
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/delay.h>
+#include <linux/mount.h>
#include <asm/div64.h>
#include "cifsfs.h"
#include "cifspdu.h"
@@ -39,27 +40,6 @@
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
-static inline struct cifsFileInfo *cifs_init_private(
- struct cifsFileInfo *private_data, struct inode *inode,
- struct file *file, __u16 netfid)
-{
- memset(private_data, 0, sizeof(struct cifsFileInfo));
- private_data->netfid = netfid;
- private_data->pid = current->tgid;
- mutex_init(&private_data->fh_mutex);
- mutex_init(&private_data->lock_mutex);
- INIT_LIST_HEAD(&private_data->llist);
- private_data->pfile = file; /* needed for writepage */
- private_data->pInode = inode;
- private_data->invalidHandle = false;
- private_data->closePend = false;
- /* Initialize reference count to one. The private data is
- freed on the release of the last reference */
- atomic_set(&private_data->count, 1);
-
- return private_data;
-}
-
static inline int cifs_convert_flags(unsigned int flags)
{
if ((flags & O_ACCMODE) == O_RDONLY)
@@ -123,9 +103,11 @@ static inline int cifs_get_disposition(unsigned int flags)
}
/* all arguments to this function must be checked for validity in caller */
-static inline int cifs_posix_open_inode_helper(struct inode *inode,
- struct file *file, struct cifsInodeInfo *pCifsInode,
- struct cifsFileInfo *pCifsFile, int oplock, u16 netfid)
+static inline int
+cifs_posix_open_inode_helper(struct inode *inode, struct file *file,
+ struct cifsInodeInfo *pCifsInode,
+ struct cifsFileInfo *pCifsFile, __u32 oplock,
+ u16 netfid)
{
write_lock(&GlobalSMBSeslock);
@@ -219,17 +201,6 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
struct timespec temp;
int rc;
- /* want handles we can use to read with first
- in the list so we do not have to walk the
- list to search for one in write_begin */
- if ((file->f_flags & O_ACCMODE) == O_WRONLY) {
- list_add_tail(&pCifsFile->flist,
- &pCifsInode->openFileList);
- } else {
- list_add(&pCifsFile->flist,
- &pCifsInode->openFileList);
- }
- write_unlock(&GlobalSMBSeslock);
if (pCifsInode->clientCanCacheRead) {
/* we have the inode open somewhere else
no need to discard cache data */
@@ -279,7 +250,8 @@ client_can_cache:
int cifs_open(struct inode *inode, struct file *file)
{
int rc = -EACCES;
- int xid, oplock;
+ int xid;
+ __u32 oplock;
struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *tcon;
struct cifsFileInfo *pCifsFile;
@@ -324,7 +296,7 @@ int cifs_open(struct inode *inode, struct file *file)
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, &inode, inode->i_sb,
+ rc = cifs_posix_open(full_path, &inode, file->f_path.mnt,
cifs_sb->mnt_file_mode /* ignored */,
oflags, &oplock, &netfid, xid);
if (rc == 0) {
@@ -414,24 +386,17 @@ int cifs_open(struct inode *inode, struct file *file)
cFYI(1, ("cifs_open returned 0x%x", rc));
goto out;
}
- file->private_data =
- kmalloc(sizeof(struct cifsFileInfo), GFP_KERNEL);
+
+ pCifsFile = cifs_new_fileinfo(inode, netfid, file, file->f_path.mnt,
+ file->f_flags);
+ file->private_data = pCifsFile;
if (file->private_data == NULL) {
rc = -ENOMEM;
goto out;
}
- pCifsFile = cifs_init_private(file->private_data, inode, file, netfid);
- write_lock(&GlobalSMBSeslock);
- list_add(&pCifsFile->tlist, &tcon->openFileList);
- pCifsInode = CIFS_I(file->f_path.dentry->d_inode);
- if (pCifsInode) {
- rc = cifs_open_inode_helper(inode, file, pCifsInode,
- pCifsFile, tcon,
- &oplock, buf, full_path, xid);
- } else {
- write_unlock(&GlobalSMBSeslock);
- }
+ 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
@@ -474,7 +439,8 @@ static int cifs_relock_file(struct cifsFileInfo *cifsFile)
static int cifs_reopen_file(struct file *file, bool can_flush)
{
int rc = -EACCES;
- int xid, oplock;
+ int xid;
+ __u32 oplock;
struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *tcon;
struct cifsFileInfo *pCifsFile;
@@ -543,7 +509,7 @@ 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, inode->i_sb,
+ rc = cifs_posix_open(full_path, NULL, file->f_path.mnt,
cifs_sb->mnt_file_mode /* ignored */,
oflags, &oplock, &netfid, xid);
if (rc == 0) {
@@ -2308,6 +2274,73 @@ out:
return rc;
}
+static void
+cifs_oplock_break(struct slow_work *work)
+{
+ struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
+ oplock_break);
+ struct inode *inode = cfile->pInode;
+ struct cifsInodeInfo *cinode = CIFS_I(inode);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->mnt->mnt_sb);
+ int rc, waitrc = 0;
+
+ if (inode && S_ISREG(inode->i_mode)) {
+#ifdef CONFIG_CIFS_EXPERIMENTAL
+ if (cinode->clientCanCacheAll == 0)
+ break_lease(inode, FMODE_READ);
+ else if (cinode->clientCanCacheRead == 0)
+ break_lease(inode, FMODE_WRITE);
+#endif
+ rc = filemap_fdatawrite(inode->i_mapping);
+ if (cinode->clientCanCacheRead == 0) {
+ waitrc = filemap_fdatawait(inode->i_mapping);
+ invalidate_remote_inode(inode);
+ }
+ if (!rc)
+ rc = waitrc;
+ if (rc)
+ cinode->write_behind_rc = rc;
+ cFYI(1, ("Oplock flush inode %p rc %d", inode, rc));
+ }
+
+ /*
+ * releasing stale oplock after recent reconnect of smb session using
+ * a now incorrect file handle is not a data integrity issue but do
+ * not bother sending an oplock release if session to server still is
+ * disconnected since oplock already released by the server
+ */
+ if (!cfile->closePend && !cfile->oplock_break_cancelled) {
+ rc = CIFSSMBLock(0, cifs_sb->tcon, cfile->netfid, 0, 0, 0, 0,
+ LOCKING_ANDX_OPLOCK_RELEASE, false);
+ cFYI(1, ("Oplock release rc = %d", rc));
+ }
+}
+
+static int
+cifs_oplock_break_get(struct slow_work *work)
+{
+ struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
+ oplock_break);
+ mntget(cfile->mnt);
+ cifsFileInfo_get(cfile);
+ return 0;
+}
+
+static void
+cifs_oplock_break_put(struct slow_work *work)
+{
+ struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
+ oplock_break);
+ mntput(cfile->mnt);
+ cifsFileInfo_put(cfile);
+}
+
+const struct slow_work_ops cifs_oplock_break_ops = {
+ .get_ref = cifs_oplock_break_get,
+ .put_ref = cifs_oplock_break_put,
+ .execute = cifs_oplock_break,
+};
+
const struct address_space_operations cifs_addr_ops = {
.readpage = cifs_readpage,
.readpages = cifs_readpages,
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index e079a9190ec..0241b25ac33 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -32,7 +32,6 @@
extern mempool_t *cifs_sm_req_poolp;
extern mempool_t *cifs_req_poolp;
-extern struct task_struct *oplockThread;
/* The xid serves as a useful identifier for each incoming vfs request,
in a similar way to the mid which is useful to track each sent smb,
@@ -500,6 +499,7 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
struct cifsTconInfo *tcon;
struct cifsInodeInfo *pCifsInode;
struct cifsFileInfo *netfile;
+ int rc;
cFYI(1, ("Checking for oplock break or dnotify response"));
if ((pSMB->hdr.Command == SMB_COM_NT_TRANSACT) &&
@@ -562,30 +562,40 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
continue;
cifs_stats_inc(&tcon->num_oplock_brks);
- write_lock(&GlobalSMBSeslock);
+ read_lock(&GlobalSMBSeslock);
list_for_each(tmp2, &tcon->openFileList) {
netfile = list_entry(tmp2, struct cifsFileInfo,
tlist);
if (pSMB->Fid != netfile->netfid)
continue;
- write_unlock(&GlobalSMBSeslock);
- read_unlock(&cifs_tcp_ses_lock);
+ /*
+ * don't do anything if file is about to be
+ * closed anyway.
+ */
+ if (netfile->closePend) {
+ read_unlock(&GlobalSMBSeslock);
+ read_unlock(&cifs_tcp_ses_lock);
+ return true;
+ }
+
cFYI(1, ("file id match, oplock break"));
pCifsInode = CIFS_I(netfile->pInode);
pCifsInode->clientCanCacheAll = false;
if (pSMB->OplockLevel == 0)
pCifsInode->clientCanCacheRead = false;
- pCifsInode->oplockPending = true;
- AllocOplockQEntry(netfile->pInode,
- netfile->netfid, tcon);
- cFYI(1, ("about to wake up oplock thread"));
- if (oplockThread)
- wake_up_process(oplockThread);
-
+ rc = slow_work_enqueue(&netfile->oplock_break);
+ if (rc) {
+ cERROR(1, ("failed to enqueue oplock "
+ "break: %d\n", rc));
+ } else {
+ netfile->oplock_break_cancelled = false;
+ }
+ read_unlock(&GlobalSMBSeslock);
+ read_unlock(&cifs_tcp_ses_lock);
return true;
}
- write_unlock(&GlobalSMBSeslock);
+ read_unlock(&GlobalSMBSeslock);
read_unlock(&cifs_tcp_ses_lock);
cFYI(1, ("No matching file for oplock break"));
return true;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index f823a4a208a..1f098ca7163 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -146,7 +146,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb)
}
}
-void
+static void
cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
struct cifs_sb_info *cifs_sb)
{
@@ -161,7 +161,7 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info,
cifs_fill_common_info(fattr, cifs_sb);
}
-void
+static void
cifs_std_info_to_fattr(struct cifs_fattr *fattr, FIND_FILE_STANDARD_INFO *info,
struct cifs_sb_info *cifs_sb)
{
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 1da4ab250ea..07b8e71544e 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -103,56 +103,6 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
mempool_free(midEntry, cifs_mid_poolp);
}
-struct oplock_q_entry *
-AllocOplockQEntry(struct inode *pinode, __u16 fid, struct cifsTconInfo *tcon)
-{
- struct oplock_q_entry *temp;
- if ((pinode == NULL) || (tcon == NULL)) {
- cERROR(1, ("Null parms passed to AllocOplockQEntry"));
- return NULL;
- }
- temp = (struct oplock_q_entry *) kmem_cache_alloc(cifs_oplock_cachep,
- GFP_KERNEL);
- if (temp == NULL)
- return temp;
- else {
- temp->pinode = pinode;
- temp->tcon = tcon;
- temp->netfid = fid;
- spin_lock(&cifs_oplock_lock);
- list_add_tail(&temp->qhead, &cifs_oplock_list);
- spin_unlock(&cifs_oplock_lock);
- }
- return temp;
-}
-
-void DeleteOplockQEntry(struct oplock_q_entry *oplockEntry)
-{
- spin_lock(&cifs_oplock_lock);
- /* should we check if list empty first? */
- list_del(&oplockEntry->qhead);
- spin_unlock(&cifs_oplock_lock);
- kmem_cache_free(cifs_oplock_cachep, oplockEntry);
-}
-
-
-void DeleteTconOplockQEntries(struct cifsTconInfo *tcon)
-{
- struct oplock_q_entry *temp;
-
- if (tcon == NULL)
- return;
-
- spin_lock(&cifs_oplock_lock);
- list_for_each_entry(temp, &cifs_oplock_list, qhead) {
- if ((temp->tcon) && (temp->tcon == tcon)) {
- list_del(&temp->qhead);
- kmem_cache_free(cifs_oplock_cachep, temp);
- }
- }
- spin_unlock(&cifs_oplock_lock);
-}
-
static int
smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
{
diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig
index 0c754e64232..8aadb99b763 100644
--- a/fs/ecryptfs/Kconfig
+++ b/fs/ecryptfs/Kconfig
@@ -1,6 +1,8 @@
config ECRYPT_FS
tristate "eCrypt filesystem layer support (EXPERIMENTAL)"
- depends on EXPERIMENTAL && KEYS && CRYPTO && NET
+ depends on EXPERIMENTAL && KEYS && NET
+ select CRYPTO_ECB
+ select CRYPTO_CBC
help
Encrypted filesystem that operates on the VFS layer. See
<file:Documentation/filesystems/ecryptfs.txt> to learn more about
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index b91851f1cda..fbb6e5eed69 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -245,13 +245,11 @@ void ecryptfs_destroy_crypt_stat(struct ecryptfs_crypt_stat *crypt_stat)
crypto_free_blkcipher(crypt_stat->tfm);
if (crypt_stat->hash_tfm)
crypto_free_hash(crypt_stat->hash_tfm);
- mutex_lock(&crypt_stat->keysig_list_mutex);
list_for_each_entry_safe(key_sig, key_sig_tmp,
&crypt_stat->keysig_list, crypt_stat_list) {
list_del(&key_sig->crypt_stat_list);
kmem_cache_free(ecryptfs_key_sig_cache, key_sig);
}
- mutex_unlock(&crypt_stat->keysig_list_mutex);
memset(crypt_stat, 0, sizeof(struct ecryptfs_crypt_stat));
}
@@ -511,13 +509,14 @@ int ecryptfs_encrypt_page(struct page *page)
+ extent_offset), crypt_stat);
rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt,
offset, crypt_stat->extent_size);
- if (rc) {
+ if (rc < 0) {
ecryptfs_printk(KERN_ERR, "Error attempting "
"to write lower page; rc = [%d]"
"\n", rc);
goto out;
}
}
+ rc = 0;
out:
if (enc_extent_page) {
kunmap(enc_extent_page);
@@ -633,7 +632,7 @@ int ecryptfs_decrypt_page(struct page *page)
rc = ecryptfs_read_lower(enc_extent_virt, offset,
crypt_stat->extent_size,
ecryptfs_inode);
- if (rc) {
+ if (rc < 0) {
ecryptfs_printk(KERN_ERR, "Error attempting "
"to read lower page; rc = [%d]"
"\n", rc);
@@ -797,6 +796,7 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat)
kfree(full_alg_name);
if (IS_ERR(crypt_stat->tfm)) {
rc = PTR_ERR(crypt_stat->tfm);
+ crypt_stat->tfm = NULL;
ecryptfs_printk(KERN_ERR, "cryptfs: init_crypt_ctx(): "
"Error initializing cipher [%s]\n",
crypt_stat->cipher);
@@ -925,7 +925,9 @@ static int ecryptfs_copy_mount_wide_sigs_to_inode_sigs(
struct ecryptfs_global_auth_tok *global_auth_tok;
int rc = 0;
+ mutex_lock(&crypt_stat->keysig_list_mutex);
mutex_lock(&mount_crypt_stat->global_auth_tok_list_mutex);
+
list_for_each_entry(global_auth_tok,
&mount_crypt_stat->global_auth_tok_list,
mount_crypt_stat_list) {
@@ -934,13 +936,13 @@ static int ecryptfs_copy_mount_wide_sigs_to_inode_sigs(
rc = ecryptfs_add_keysig(crypt_stat, global_auth_tok->sig);
if (rc) {
printk(KERN_ERR "Error adding keysig; rc = [%d]\n", rc);
- mutex_unlock(
- &mount_crypt_stat->global_auth_tok_list_mutex);
goto out;
}
}
- mutex_unlock(&mount_crypt_stat->global_auth_tok_list_mutex);
+
out:
+ mutex_unlock(&mount_crypt_stat->global_auth_tok_list_mutex);
+ mutex_unlock(&crypt_stat->keysig_list_mutex);
return rc;
}
@@ -1212,14 +1214,15 @@ int ecryptfs_read_and_validate_header_region(char *data,
crypt_stat->extent_size = ECRYPTFS_DEFAULT_EXTENT_SIZE;
rc = ecryptfs_read_lower(data, 0, crypt_stat->extent_size,
ecryptfs_inode);
- if (rc) {
+ if (rc < 0) {
printk(KERN_ERR "%s: Error reading header region; rc = [%d]\n",
__func__, rc);
goto out;
}
if (!contains_ecryptfs_marker(data + ECRYPTFS_FILE_SIZE_BYTES)) {
rc = -EINVAL;
- }
+ } else
+ rc = 0;
out:
return rc;
}
@@ -1314,10 +1317,11 @@ ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry,
rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt,
0, virt_len);
- if (rc)
+ if (rc < 0)
printk(KERN_ERR "%s: Error attempting to write header "
- "information to lower file; rc = [%d]\n", __func__,
- rc);
+ "information to lower file; rc = [%d]\n", __func__, rc);
+ else
+ rc = 0;
return rc;
}
@@ -1597,7 +1601,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
}
rc = ecryptfs_read_lower(page_virt, 0, crypt_stat->extent_size,
ecryptfs_inode);
- if (!rc)
+ if (rc >= 0)
rc = ecryptfs_read_headers_virt(page_virt, crypt_stat,
ecryptfs_dentry,
ECRYPTFS_VALIDATE_HEADER_SIZE);
@@ -1702,7 +1706,7 @@ ecryptfs_encrypt_filename(struct ecryptfs_filename *filename,
} else {
printk(KERN_ERR "%s: No support for requested filename "
"encryption method in this release\n", __func__);
- rc = -ENOTSUPP;
+ rc = -EOPNOTSUPP;
goto out;
}
out:
@@ -1763,7 +1767,7 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
if (IS_ERR(*key_tfm)) {
rc = PTR_ERR(*key_tfm);
printk(KERN_ERR "Unable to allocate crypto cipher with name "
- "[%s]; rc = [%d]\n", cipher_name, rc);
+ "[%s]; rc = [%d]\n", full_alg_name, rc);
goto out;
}
crypto_blkcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_WEAK_KEY);
@@ -1776,7 +1780,8 @@ ecryptfs_process_key_cipher(struct crypto_blkcipher **key_tfm,
rc = crypto_blkcipher_setkey(*key_tfm, dummy_key, *key_size);
if (rc) {
printk(KERN_ERR "Error attempting to set key of size [%zd] for "
- "cipher [%s]; rc = [%d]\n", *key_size, cipher_name, rc);
+ "cipher [%s]; rc = [%d]\n", *key_size, full_alg_name,
+ rc);
rc = -EINVAL;
goto out;
}
@@ -2166,7 +2171,7 @@ int ecryptfs_encrypt_and_encode_filename(
(*encoded_name)[(*encoded_name_size)] = '\0';
(*encoded_name_size)++;
} else {
- rc = -ENOTSUPP;
+ rc = -EOPNOTSUPP;
}
if (rc) {
printk(KERN_ERR "%s: Error attempting to encode "
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 2f0945d6329..056fed62d0d 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -476,6 +476,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
struct inode *lower_dir_inode = ecryptfs_inode_to_lower(dir);
struct dentry *lower_dir_dentry;
+ dget(lower_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
rc = vfs_unlink(lower_dir_inode, lower_dentry);
if (rc) {
@@ -489,6 +490,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
d_drop(dentry);
out_unlock:
unlock_dir(lower_dir_dentry);
+ dput(lower_dentry);
return rc;
}
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 259525c9abb..a0a7847567e 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -416,7 +416,9 @@ ecryptfs_find_global_auth_tok_for_sig(
&mount_crypt_stat->global_auth_tok_list,
mount_crypt_stat_list) {
if (memcmp(walker->sig, sig, ECRYPTFS_SIG_SIZE_HEX) == 0) {
- (*global_auth_tok) = walker;
+ rc = key_validate(walker->global_auth_tok_key);
+ if (!rc)
+ (*global_auth_tok) = walker;
goto out;
}
}
@@ -612,7 +614,12 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
}
/* TODO: Support other key modules than passphrase for
* filename encryption */
- BUG_ON(s->auth_tok->token_type != ECRYPTFS_PASSWORD);
+ if (s->auth_tok->token_type != ECRYPTFS_PASSWORD) {
+ rc = -EOPNOTSUPP;
+ printk(KERN_INFO "%s: Filename encryption only supports "
+ "password tokens\n", __func__);
+ goto out_free_unlock;
+ }
sg_init_one(
&s->hash_sg,
(u8 *)s->auth_tok->token.password.session_key_encryption_key,
@@ -910,7 +917,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size,
}
/* TODO: Support other key modules than passphrase for
* filename encryption */
- BUG_ON(s->auth_tok->token_type != ECRYPTFS_PASSWORD);
+ if (s->auth_tok->token_type != ECRYPTFS_PASSWORD) {
+ rc = -EOPNOTSUPP;
+ printk(KERN_INFO "%s: Filename encryption only supports "
+ "password tokens\n", __func__);
+ goto out_free_unlock;
+ }
rc = crypto_blkcipher_setkey(
s->desc.tfm,
s->auth_tok->token.password.session_key_encryption_key,
@@ -1316,8 +1328,10 @@ parse_tag_3_packet(struct ecryptfs_crypt_stat *crypt_stat,
rc = -EINVAL;
goto out_free;
}
- ecryptfs_cipher_code_to_string(crypt_stat->cipher,
- (u16)data[(*packet_size)]);
+ rc = ecryptfs_cipher_code_to_string(crypt_stat->cipher,
+ (u16)data[(*packet_size)]);
+ if (rc)
+ goto out_free;
/* A little extra work to differentiate among the AES key
* sizes; see RFC2440 */
switch(data[(*packet_size)++]) {
@@ -1328,7 +1342,9 @@ parse_tag_3_packet(struct ecryptfs_crypt_stat *crypt_stat,
crypt_stat->key_size =
(*new_auth_tok)->session_key.encrypted_key_size;
}
- ecryptfs_init_crypt_ctx(crypt_stat);
+ rc = ecryptfs_init_crypt_ctx(crypt_stat);
+ if (rc)
+ goto out_free;
if (unlikely(data[(*packet_size)++] != 0x03)) {
printk(KERN_WARNING "Only S2K ID 3 is currently supported\n");
rc = -ENOSYS;
@@ -2366,21 +2382,18 @@ struct kmem_cache *ecryptfs_key_sig_cache;
int ecryptfs_add_keysig(struct ecryptfs_crypt_stat *crypt_stat, char *sig)
{
struct ecryptfs_key_sig *new_key_sig;
- int rc = 0;
new_key_sig = kmem_cache_alloc(ecryptfs_key_sig_cache, GFP_KERNEL);
if (!new_key_sig) {
- rc = -ENOMEM;
printk(KERN_ERR
"Error allocating from ecryptfs_key_sig_cache\n");
- goto out;
+ return -ENOMEM;
}
memcpy(new_key_sig->keysig, sig, ECRYPTFS_SIG_SIZE_HEX);
- mutex_lock(&crypt_stat->keysig_list_mutex);
+ /* Caller must hold keysig_list_mutex */
list_add(&new_key_sig->crypt_stat_list, &crypt_stat->keysig_list);
- mutex_unlock(&crypt_stat->keysig_list_mutex);
-out:
- return rc;
+
+ return 0;
}
struct kmem_cache *ecryptfs_global_auth_tok_cache;
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index c6d7a4d748a..e14cf7e588d 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -136,6 +136,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
const struct cred *cred)
{
struct ecryptfs_open_req *req;
+ int flags = O_LARGEFILE;
int rc = 0;
/* Corresponding dput() and mntput() are done when the
@@ -143,10 +144,14 @@ int ecryptfs_privileged_open(struct file **lower_file,
* destroyed. */
dget(lower_dentry);
mntget(lower_mnt);
- (*lower_file) = dentry_open(lower_dentry, lower_mnt,
- (O_RDWR | O_LARGEFILE), cred);
+ flags |= IS_RDONLY(lower_dentry->d_inode) ? O_RDONLY : O_RDWR;
+ (*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred);
if (!IS_ERR(*lower_file))
goto out;
+ if (flags & O_RDONLY) {
+ rc = PTR_ERR((*lower_file));
+ goto out;
+ }
req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL);
if (!req) {
rc = -ENOMEM;
@@ -180,21 +185,8 @@ int ecryptfs_privileged_open(struct file **lower_file,
__func__);
goto out_unlock;
}
- if (IS_ERR(*req->lower_file)) {
+ if (IS_ERR(*req->lower_file))
rc = PTR_ERR(*req->lower_file);
- dget(lower_dentry);
- mntget(lower_mnt);
- (*lower_file) = dentry_open(lower_dentry, lower_mnt,
- (O_RDONLY | O_LARGEFILE), cred);
- if (IS_ERR(*lower_file)) {
- rc = PTR_ERR(*req->lower_file);
- (*lower_file) = NULL;
- printk(KERN_WARNING "%s: Error attempting privileged "
- "open of lower file with either RW or RO "
- "perms; rc = [%d]. Giving up.\n",
- __func__, rc);
- }
- }
out_unlock:
mutex_unlock(&req->mux);
out_free:
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 9f0aa9883c2..101fe4c7b1e 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -129,11 +129,10 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
rc = ecryptfs_privileged_open(&inode_info->lower_file,
lower_dentry, lower_mnt, cred);
- if (rc || IS_ERR(inode_info->lower_file)) {
+ if (rc) {
printk(KERN_ERR "Error opening lower persistent file "
"for lower_dentry [0x%p] and lower_mnt [0x%p]; "
"rc = [%d]\n", lower_dentry, lower_mnt, rc);
- rc = PTR_ERR(inode_info->lower_file);
inode_info->lower_file = NULL;
}
}
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 05772aeaa8f..df4ce99d059 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -396,9 +396,11 @@ static int ecryptfs_write_inode_size_to_header(struct inode *ecryptfs_inode)
rc = ecryptfs_write_lower(ecryptfs_inode, file_size_virt, 0,
sizeof(u64));
kfree(file_size_virt);
- if (rc)
+ if (rc < 0)
printk(KERN_ERR "%s: Error writing file size to header; "
"rc = [%d]\n", __func__, rc);
+ else
+ rc = 0;
out:
return rc;
}
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index a137c6ea2fe..0cc4fafd655 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -34,15 +34,14 @@
*
* Write data to the lower file.
*
- * Returns zero on success; non-zero on error
+ * Returns bytes written on success; less than zero on error
*/
int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
loff_t offset, size_t size)
{
struct ecryptfs_inode_info *inode_info;
- ssize_t octets_written;
mm_segment_t fs_save;
- int rc = 0;
+ ssize_t rc;
inode_info = ecryptfs_inode_to_private(ecryptfs_inode);
mutex_lock(&inode_info->lower_file_mutex);
@@ -50,14 +49,9 @@ int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
inode_info->lower_file->f_pos = offset;
fs_save = get_fs();
set_fs(get_ds());
- octets_written = vfs_write(inode_info->lower_file, data, size,
- &inode_info->lower_file->f_pos);
+ rc = vfs_write(inode_info->lower_file, data, size,
+ &inode_info->lower_file->f_pos);
set_fs(fs_save);
- if (octets_written < 0) {
- printk(KERN_ERR "%s: octets_written = [%td]; "
- "expected [%td]\n", __func__, octets_written, size);
- rc = -EINVAL;
- }
mutex_unlock(&inode_info->lower_file_mutex);
mark_inode_dirty_sync(ecryptfs_inode);
return rc;
@@ -91,6 +85,8 @@ int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
+ offset_in_page);
virt = kmap(page_for_lower);
rc = ecryptfs_write_lower(ecryptfs_inode, virt, offset, size);
+ if (rc > 0)
+ rc = 0;
kunmap(page_for_lower);
return rc;
}
@@ -229,30 +225,24 @@ out:
* Read @size bytes of data at byte offset @offset from the lower
* inode into memory location @data.
*
- * Returns zero on success; non-zero on error
+ * Returns bytes read on success; 0 on EOF; less than zero on error
*/
int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
struct inode *ecryptfs_inode)
{
struct ecryptfs_inode_info *inode_info =
ecryptfs_inode_to_private(ecryptfs_inode);
- ssize_t octets_read;
mm_segment_t fs_save;
- int rc = 0;
+ ssize_t rc;
mutex_lock(&inode_info->lower_file_mutex);
BUG_ON(!inode_info->lower_file);
inode_info->lower_file->f_pos = offset;
fs_save = get_fs();
set_fs(get_ds());
- octets_read = vfs_read(inode_info->lower_file, data, size,
- &inode_info->lower_file->f_pos);
+ rc = vfs_read(inode_info->lower_file, data, size,
+ &inode_info->lower_file->f_pos);
set_fs(fs_save);
- if (octets_read < 0) {
- printk(KERN_ERR "%s: octets_read = [%td]; "
- "expected [%td]\n", __func__, octets_read, size);
- rc = -EINVAL;
- }
mutex_unlock(&inode_info->lower_file_mutex);
return rc;
}
@@ -284,6 +274,8 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
offset = ((((loff_t)page_index) << PAGE_CACHE_SHIFT) + offset_in_page);
virt = kmap(page_for_ecryptfs);
rc = ecryptfs_read_lower(virt, offset, size, ecryptfs_inode);
+ if (rc > 0)
+ rc = 0;
kunmap(page_for_ecryptfs);
flush_dcache_page(page_for_ecryptfs);
return rc;
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 12d649602d3..b15a43a80ab 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -77,7 +77,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
struct ecryptfs_inode_info *inode_info;
inode_info = ecryptfs_inode_to_private(inode);
- mutex_lock(&inode_info->lower_file_mutex);
if (inode_info->lower_file) {
struct dentry *lower_dentry =
inode_info->lower_file->f_dentry;
@@ -89,7 +88,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
d_drop(lower_dentry);
}
}
- mutex_unlock(&inode_info->lower_file_mutex);
ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat);
kmem_cache_free(ecryptfs_inode_info_cache, inode_info);
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8e1e5e19d21..9d5360c4c2a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -41,8 +41,9 @@ struct wb_writeback_args {
long nr_pages;
struct super_block *sb;
enum writeback_sync_modes sync_mode;
- int for_kupdate;
- int range_cyclic;
+ int for_kupdate:1;
+ int range_cyclic:1;
+ int for_background:1;
};
/*
@@ -249,14 +250,25 @@ 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, long nr_pages)
+void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
+ 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);
}
@@ -310,7 +322,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
* For inodes being constantly redirtied, dirtied_when can get stuck.
* It _appears_ to be in the future, but is actually in distant past.
* This test is necessary to prevent such wrapped-around relative times
- * from permanently stopping the whole pdflush writeback.
+ * from permanently stopping the whole bdi writeback.
*/
ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
@@ -324,13 +336,38 @@ static void move_expired_inodes(struct list_head *delaying_queue,
struct list_head *dispatch_queue,
unsigned long *older_than_this)
{
+ LIST_HEAD(tmp);
+ struct list_head *pos, *node;
+ struct super_block *sb = NULL;
+ struct inode *inode;
+ int do_sb_sort = 0;
+
while (!list_empty(delaying_queue)) {
- struct inode *inode = list_entry(delaying_queue->prev,
- struct inode, i_list);
+ inode = list_entry(delaying_queue->prev, struct inode, i_list);
if (older_than_this &&
inode_dirtied_after(inode, *older_than_this))
break;
- list_move(&inode->i_list, dispatch_queue);
+ if (sb && sb != inode->i_sb)
+ do_sb_sort = 1;
+ sb = inode->i_sb;
+ list_move(&inode->i_list, &tmp);
+ }
+
+ /* just one sb in list, splice to dispatch_queue and we're done */
+ if (!do_sb_sort) {
+ list_splice(&tmp, dispatch_queue);
+ return;
+ }
+
+ /* Move inodes from one superblock together */
+ while (!list_empty(&tmp)) {
+ inode = list_entry(tmp.prev, struct inode, i_list);
+ sb = inode->i_sb;
+ list_for_each_prev_safe(pos, node, &tmp) {
+ inode = list_entry(pos, struct inode, i_list);
+ if (inode->i_sb == sb)
+ list_move(&inode->i_list, dispatch_queue);
+ }
}
}
@@ -439,8 +476,18 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
spin_lock(&inode_lock);
inode->i_state &= ~I_SYNC;
if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
- if (!(inode->i_state & I_DIRTY) &&
- mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
+ /*
+ * More pages get dirtied by a fast dirtier.
+ */
+ goto select_queue;
+ } else if (inode->i_state & I_DIRTY) {
+ /*
+ * At least XFS will redirty the inode during the
+ * writeback (delalloc) and on io completion (isize).
+ */
+ redirty_tail(inode);
+ } else if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything. Redirty
@@ -462,6 +509,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
+select_queue:
if (wbc->nr_to_write <= 0) {
/*
* slice used up: queue for next turn
@@ -484,12 +532,6 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
inode->i_state |= I_DIRTY_PAGES;
redirty_tail(inode);
}
- } else if (inode->i_state & I_DIRTY) {
- /*
- * Someone redirtied the inode while were writing back
- * the pages.
- */
- redirty_tail(inode);
} else if (atomic_read(&inode->i_count)) {
/*
* The inode is clean, inuse
@@ -506,6 +548,17 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return ret;
}
+static void unpin_sb_for_writeback(struct super_block **psb)
+{
+ struct super_block *sb = *psb;
+
+ if (sb) {
+ up_read(&sb->s_umount);
+ put_super(sb);
+ *psb = NULL;
+ }
+}
+
/*
* For WB_SYNC_NONE writeback, the caller does not have the sb pinned
* before calling writeback. So make sure that we do pin it, so it doesn't
@@ -515,11 +568,20 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
* 1 if we failed.
*/
static int pin_sb_for_writeback(struct writeback_control *wbc,
- struct inode *inode)
+ struct inode *inode, struct super_block **psb)
{
struct super_block *sb = inode->i_sb;
/*
+ * If this sb is already pinned, nothing more to do. If not and
+ * *psb is non-NULL, unpin the old one first
+ */
+ if (sb == *psb)
+ return 0;
+ else if (*psb)
+ unpin_sb_for_writeback(psb);
+
+ /*
* Caller must already hold the ref for this
*/
if (wbc->sync_mode == WB_SYNC_ALL) {
@@ -532,7 +594,7 @@ static int pin_sb_for_writeback(struct writeback_control *wbc,
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root) {
spin_unlock(&sb_lock);
- return 0;
+ goto pinned;
}
/*
* umounted, drop rwsem again and fall through to failure
@@ -543,24 +605,15 @@ static int pin_sb_for_writeback(struct writeback_control *wbc,
sb->s_count--;
spin_unlock(&sb_lock);
return 1;
-}
-
-static void unpin_sb_for_writeback(struct writeback_control *wbc,
- struct inode *inode)
-{
- struct super_block *sb = inode->i_sb;
-
- if (wbc->sync_mode == WB_SYNC_ALL)
- return;
-
- up_read(&sb->s_umount);
- put_super(sb);
+pinned:
+ *psb = sb;
+ return 0;
}
static void writeback_inodes_wb(struct bdi_writeback *wb,
struct writeback_control *wbc)
{
- struct super_block *sb = wbc->sb;
+ struct super_block *sb = wbc->sb, *pin_sb = NULL;
const int is_blkdev_sb = sb_is_blkdev_sb(sb);
const unsigned long start = jiffies; /* livelock avoidance */
@@ -619,7 +672,7 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
if (inode_dirtied_after(inode, start))
break;
- if (pin_sb_for_writeback(wbc, inode)) {
+ if (pin_sb_for_writeback(wbc, inode, &pin_sb)) {
requeue_io(inode);
continue;
}
@@ -628,7 +681,6 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
- unpin_sb_for_writeback(wbc, inode);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
@@ -648,6 +700,8 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
wbc->more_io = 1;
}
+ unpin_sb_for_writeback(&pin_sb);
+
spin_unlock(&inode_lock);
/* Leave any unwritten inodes on b_io */
}
@@ -706,6 +760,7 @@ static long wb_writeback(struct bdi_writeback *wb,
};
unsigned long oldest_jif;
long wrote = 0;
+ struct inode *inode;
if (wbc.for_kupdate) {
wbc.older_than_this = &oldest_jif;
@@ -719,20 +774,16 @@ static long wb_writeback(struct bdi_writeback *wb,
for (;;) {
/*
- * Don't flush anything for non-integrity writeback where
- * no nr_pages was given
+ * Stop writeback when nr_pages has been consumed
*/
- if (!args->for_kupdate && args->nr_pages <= 0 &&
- args->sync_mode == WB_SYNC_NONE)
+ if (args->nr_pages <= 0)
break;
/*
- * If no specific pages were given and this is just a
- * periodic background writeout and we are below the
- * background dirty threshold, don't do anything
+ * For background writeout, stop when we are below the
+ * background dirty threshold
*/
- if (args->for_kupdate && args->nr_pages <= 0 &&
- !over_bground_thresh())
+ if (args->for_background && !over_bground_thresh())
break;
wbc.more_io = 0;
@@ -744,13 +795,32 @@ static long wb_writeback(struct bdi_writeback *wb,
wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
/*
- * If we ran out of stuff to write, bail unless more_io got set
+ * If we consumed everything, see if we have more
*/
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- if (wbc.more_io && !wbc.for_kupdate)
- continue;
+ if (wbc.nr_to_write <= 0)
+ continue;
+ /*
+ * Didn't write everything and we don't have more IO, bail
+ */
+ if (!wbc.more_io)
break;
+ /*
+ * Did we write something? Try for more
+ */
+ if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
+ continue;
+ /*
+ * Nothing written. Wait for some inode to
+ * become available for writeback. Otherwise
+ * we'll just busyloop.
+ */
+ spin_lock(&inode_lock);
+ if (!list_empty(&wb->b_more_io)) {
+ inode = list_entry(wb->b_more_io.prev,
+ struct inode, i_list);
+ inode_wait_for_writeback(inode);
}
+ spin_unlock(&inode_lock);
}
return wrote;
@@ -1060,9 +1130,6 @@ EXPORT_SYMBOL(__mark_inode_dirty);
* If older_than_this is non-NULL, then only write out inodes which
* had their first dirtying at a time earlier than *older_than_this.
*
- * If we're a pdlfush thread, then implement pdflush collision avoidance
- * against the entire list.
- *
* If `bdi' is non-zero then we're being asked to writeback a specific queue.
* This function assumes that the blockdev superblock's inodes are backed by
* a variety of queues, so all inodes are searched. For other superblocks,
@@ -1141,7 +1208,7 @@ void writeback_inodes_sb(struct super_block *sb)
nr_to_write = nr_dirty + nr_unstable +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
- bdi_writeback_all(sb, nr_to_write);
+ bdi_start_writeback(sb->s_bdi, sb, nr_to_write);
}
EXPORT_SYMBOL(writeback_inodes_sb);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 810770f9681..29786d3b932 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1711,6 +1711,8 @@ static int nfs_validate_mount_data(void *options,
if (!(data->flags & NFS_MOUNT_TCP))
args->nfs_server.protocol = XPRT_TRANSPORT_UDP;
+ else
+ args->nfs_server.protocol = XPRT_TRANSPORT_TCP;
/* N.B. caller will free nfs_server.hostname in all cases */
args->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL);
args->namlen = data->namlen;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 0c6bc602e6c..07f77a7945c 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -322,6 +322,8 @@ static inline void task_context_switch_counts(struct seq_file *m,
p->nivcsw);
}
+#ifdef CONFIG_MMU
+
struct stack_stats {
struct vm_area_struct *vma;
unsigned long startpage;
@@ -402,6 +404,11 @@ static inline void task_show_stack_usage(struct seq_file *m,
mmput(mm);
}
}
+#else
+static void task_show_stack_usage(struct seq_file *m, struct task_struct *task)
+{
+}
+#endif /* CONFIG_MMU */
int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)