1 files changed, 410 insertions, 300 deletions

diff --git a/fs/fcntl.c b/fs/fcntl.c
index e632da761fc..72c82f69b01 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -9,205 +9,28 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/file.h>
+#include <linux/fdtable.h>
 #include <linux/capability.h>
 #include <linux/dnotify.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pipe_fs_i.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
 #include <asm/uaccess.h>
 
-void set_close_on_exec(unsigned int fd, int flag)
-{
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (flag)
-		FD_SET(fd, fdt->close_on_exec);
-	else
-		FD_CLR(fd, fdt->close_on_exec);
-	spin_unlock(&files->file_lock);
-}
-
-static int get_close_on_exec(unsigned int fd)
-{
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	int res;
-	rcu_read_lock();
-	fdt = files_fdtable(files);
-	res = FD_ISSET(fd, fdt->close_on_exec);
-	rcu_read_unlock();
-	return res;
-}
-
-/*
- * locate_fd finds a free file descriptor in the open_fds fdset,
- * expanding the fd arrays if necessary.  Must be called with the
- * file_lock held for write.
- */
-
-static int locate_fd(struct files_struct *files, 
-			    struct file *file, unsigned int orig_start)
-{
-	unsigned int newfd;
-	unsigned int start;
-	int error;
-	struct fdtable *fdt;
-
-	error = -EINVAL;
-	if (orig_start >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-		goto out;
-
-repeat:
-	fdt = files_fdtable(files);
-	/*
-	 * Someone might have closed fd's in the range
-	 * orig_start..fdt->next_fd
-	 */
-	start = orig_start;
-	if (start < files->next_fd)
-		start = files->next_fd;
-
-	newfd = start;
-	if (start < fdt->max_fds)
-		newfd = find_next_zero_bit(fdt->open_fds->fds_bits,
-					   fdt->max_fds, start);
-	
-	error = -EMFILE;
-	if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-		goto out;
-
-	error = expand_files(files, newfd);
-	if (error < 0)
-		goto out;
-
-	/*
-	 * If we needed to expand the fs array we
-	 * might have blocked - try again.
-	 */
-	if (error)
-		goto repeat;
-
-	/*
-	 * We reacquired files_lock, so we are safe as long as
-	 * we reacquire the fdtable pointer and use it while holding
-	 * the lock, no one can free it during that time.
-	 */
-	if (start <= files->next_fd)
-		files->next_fd = newfd + 1;
-
-	error = newfd;
-	
-out:
-	return error;
-}
-
-static int dupfd(struct file *file, unsigned int start, int cloexec)
-{
-	struct files_struct * files = current->files;
-	struct fdtable *fdt;
-	int fd;
-
-	spin_lock(&files->file_lock);
-	fd = locate_fd(files, file, start);
-	if (fd >= 0) {
-		/* locate_fd() may have expanded fdtable, load the ptr */
-		fdt = files_fdtable(files);
-		FD_SET(fd, fdt->open_fds);
-		if (cloexec)
-			FD_SET(fd, fdt->close_on_exec);
-		else
-			FD_CLR(fd, fdt->close_on_exec);
-		spin_unlock(&files->file_lock);
-		fd_install(fd, file);
-	} else {
-		spin_unlock(&files->file_lock);
-		fput(file);
-	}
-
-	return fd;
-}
-
-asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
-{
-	int err = -EBADF;
-	struct file * file, *tofree;
-	struct files_struct * files = current->files;
-	struct fdtable *fdt;
-
-	spin_lock(&files->file_lock);
-	if (!(file = fcheck(oldfd)))
-		goto out_unlock;
-	err = newfd;
-	if (newfd == oldfd)
-		goto out_unlock;
-	err = -EBADF;
-	if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
-		goto out_unlock;
-	get_file(file);			/* We are now finished with oldfd */
-
-	err = expand_files(files, newfd);
-	if (err < 0)
-		goto out_fput;
-
-	/* To avoid races with open() and dup(), we will mark the fd as
-	 * in-use in the open-file bitmap throughout the entire dup2()
-	 * process.  This is quite safe: do_close() uses the fd array
-	 * entry, not the bitmap, to decide what work needs to be
-	 * done.  --sct */
-	/* Doesn't work. open() might be there first. --AV */
-
-	/* Yes. It's a race. In user space. Nothing sane to do */
-	err = -EBUSY;
-	fdt = files_fdtable(files);
-	tofree = fdt->fd[newfd];
-	if (!tofree && FD_ISSET(newfd, fdt->open_fds))
-		goto out_fput;
-
-	rcu_assign_pointer(fdt->fd[newfd], file);
-	FD_SET(newfd, fdt->open_fds);
-	FD_CLR(newfd, fdt->close_on_exec);
-	spin_unlock(&files->file_lock);
-
-	if (tofree)
-		filp_close(tofree, files);
-	err = newfd;
-out:
-	return err;
-out_unlock:
-	spin_unlock(&files->file_lock);
-	goto out;
-
-out_fput:
-	spin_unlock(&files->file_lock);
-	fput(file);
-	goto out;
-}
-
-asmlinkage long sys_dup(unsigned int fildes)
-{
-	int ret = -EBADF;
-	struct file * file = fget(fildes);
-
-	if (file)
-		ret = dupfd(file, 0, 0);
-	return ret;
-}
-
-#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | FASYNC | O_DIRECT | O_NOATIME)
+#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
 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;
 
 	/*
@@ -219,7 +42,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 
 	/* O_NOATIME can only be set by the owner or superuser */
 	if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME))
-		if (!is_owner_or_cap(inode))
+		if (!inode_owner_or_capable(inode))
 			return -EPERM;
 
 	/* required for strict SunOS emulation */
@@ -233,36 +56,43 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 				return -EINVAL;
 	}
 
-	if (filp->f_op && filp->f_op->check_flags)
+	if (filp->f_op->check_flags)
 		error = filp->f_op->check_flags(arg);
 	if (error)
 		return error;
 
-	lock_kernel();
-	if ((arg ^ filp->f_flags) & FASYNC) {
-		if (filp->f_op && filp->f_op->fasync) {
-			error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
-			if (error < 0)
-				goto out;
-		}
+	/*
+	 * ->fasync() is responsible for setting the FASYNC bit.
+	 */
+	if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) {
+		error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
+		if (error < 0)
+			goto out;
+		if (error > 0)
+			error = 0;
 	}
-
+	spin_lock(&filp->f_lock);
 	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
+	spin_unlock(&filp->f_lock);
+
  out:
-	unlock_kernel();
 	return error;
 }
 
 static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
-                     uid_t uid, uid_t euid, int force)
+                     int force)
 {
 	write_lock_irq(&filp->f_owner.lock);
 	if (force || !filp->f_owner.pid) {
 		put_pid(filp->f_owner.pid);
 		filp->f_owner.pid = get_pid(pid);
 		filp->f_owner.pid_type = type;
-		filp->f_owner.uid = uid;
-		filp->f_owner.euid = euid;
+
+		if (pid) {
+			const struct cred *cred = current_cred();
+			filp->f_owner.uid = cred->uid;
+			filp->f_owner.euid = cred->euid;
+		}
 	}
 	write_unlock_irq(&filp->f_owner.lock);
 }
@@ -271,12 +101,12 @@ int __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 		int force)
 {
 	int err;
-	
+
 	err = security_file_set_fowner(filp);
 	if (err)
 		return err;
 
-	f_modown(filp, pid, type, current->uid, current->euid, force);
+	f_modown(filp, pid, type, force);
 	return 0;
 }
 EXPORT_SYMBOL(__f_setown);
@@ -302,7 +132,7 @@ EXPORT_SYMBOL(f_setown);
 
 void f_delown(struct file *filp)
 {
-	f_modown(filp, NULL, PIDTYPE_PID, 0, 0, 1);
+	f_modown(filp, NULL, PIDTYPE_PID, 1);
 }
 
 pid_t f_getown(struct file *filp)
@@ -316,6 +146,107 @@ pid_t f_getown(struct file *filp)
 	return pid;
 }
 
+static int f_setown_ex(struct file *filp, unsigned long arg)
+{
+	struct f_owner_ex __user *owner_p = (void __user *)arg;
+	struct f_owner_ex owner;
+	struct pid *pid;
+	int type;
+	int ret;
+
+	ret = copy_from_user(&owner, owner_p, sizeof(owner));
+	if (ret)
+		return -EFAULT;
+
+	switch (owner.type) {
+	case F_OWNER_TID:
+		type = PIDTYPE_MAX;
+		break;
+
+	case F_OWNER_PID:
+		type = PIDTYPE_PID;
+		break;
+
+	case F_OWNER_PGRP:
+		type = PIDTYPE_PGID;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+	pid = find_vpid(owner.pid);
+	if (owner.pid && !pid)
+		ret = -ESRCH;
+	else
+		ret = __f_setown(filp, pid, type, 1);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int f_getown_ex(struct file *filp, unsigned long arg)
+{
+	struct f_owner_ex __user *owner_p = (void __user *)arg;
+	struct f_owner_ex owner;
+	int ret = 0;
+
+	read_lock(&filp->f_owner.lock);
+	owner.pid = pid_vnr(filp->f_owner.pid);
+	switch (filp->f_owner.pid_type) {
+	case PIDTYPE_MAX:
+		owner.type = F_OWNER_TID;
+		break;
+
+	case PIDTYPE_PID:
+		owner.type = F_OWNER_PID;
+		break;
+
+	case PIDTYPE_PGID:
+		owner.type = F_OWNER_PGRP;
+		break;
+
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+		break;
+	}
+	read_unlock(&filp->f_owner.lock);
+
+	if (!ret) {
+		ret = copy_to_user(owner_p, &owner, sizeof(owner));
+		if (ret)
+			ret = -EFAULT;
+	}
+	return ret;
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static int f_getowner_uids(struct file *filp, unsigned long arg)
+{
+	struct user_namespace *user_ns = current_user_ns();
+	uid_t __user *dst = (void __user *)arg;
+	uid_t src[2];
+	int err;
+
+	read_lock(&filp->f_owner.lock);
+	src[0] = from_kuid(user_ns, filp->f_owner.uid);
+	src[1] = from_kuid(user_ns, filp->f_owner.euid);
+	read_unlock(&filp->f_owner.lock);
+
+	err  = put_user(src[0], &dst[0]);
+	err |= put_user(src[1], &dst[1]);
+
+	return err;
+}
+#else
+static int f_getowner_uids(struct file *filp, unsigned long arg)
+{
+	return -EINVAL;
+}
+#endif
+
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		struct file *filp)
 {
@@ -323,9 +254,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 
 	switch (cmd) {
 	case F_DUPFD:
+		err = f_dupfd(arg, filp, 0);
+		break;
 	case F_DUPFD_CLOEXEC:
-		get_file(filp);
-		err = dupfd(filp, arg, cmd == F_DUPFD_CLOEXEC);
+		err = f_dupfd(arg, filp, O_CLOEXEC);
 		break;
 	case F_GETFD:
 		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
@@ -340,9 +272,19 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_SETFL:
 		err = setfl(fd, filp, arg);
 		break;
+#if BITS_PER_LONG != 32
+	/* 32-bit arches must use fcntl64() */
+	case F_OFD_GETLK:
+#endif
 	case F_GETLK:
-		err = fcntl_getlk(filp, (struct flock __user *) arg);
+		err = fcntl_getlk(filp, cmd, (struct flock __user *) arg);
 		break;
+#if BITS_PER_LONG != 32
+	/* 32-bit arches must use fcntl64() */
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+#endif
+		/* Fallthrough */
 	case F_SETLK:
 	case F_SETLKW:
 		err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
@@ -361,6 +303,15 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_SETOWN:
 		err = f_setown(filp, arg, 1);
 		break;
+	case F_GETOWN_EX:
+		err = f_getown_ex(filp, arg);
+		break;
+	case F_SETOWN_EX:
+		err = f_setown_ex(filp, arg);
+		break;
+	case F_GETOWNER_UIDS:
+		err = f_getowner_uids(filp, arg);
+		break;
 	case F_GETSIG:
 		err = filp->f_owner.signum;
 		break;
@@ -381,66 +332,89 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_NOTIFY:
 		err = fcntl_dirnotify(fd, filp, arg);
 		break;
+	case F_SETPIPE_SZ:
+	case F_GETPIPE_SZ:
+		err = pipe_fcntl(filp, cmd, arg);
+		break;
 	default:
 		break;
 	}
 	return err;
 }
 
-asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg)
+static int check_fcntl_cmd(unsigned cmd)
+{
+	switch (cmd) {
+	case F_DUPFD:
+	case F_DUPFD_CLOEXEC:
+	case F_GETFD:
+	case F_SETFD:
+	case F_GETFL:
+		return 1;
+	}
+	return 0;
+}
+
+SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {	
-	struct file *filp;
+	struct fd f = fdget_raw(fd);
 	long err = -EBADF;
 
-	filp = fget(fd);
-	if (!filp)
+	if (!f.file)
 		goto out;
 
-	err = security_file_fcntl(filp, cmd, arg);
-	if (err) {
-		fput(filp);
-		return err;
+	if (unlikely(f.file->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd))
+			goto out1;
 	}
 
-	err = do_fcntl(fd, cmd, arg, filp);
+	err = security_file_fcntl(f.file, cmd, arg);
+	if (!err)
+		err = do_fcntl(fd, cmd, arg, f.file);
 
- 	fput(filp);
+out1:
+ 	fdput(f);
 out:
 	return err;
 }
 
 #if BITS_PER_LONG == 32
-asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg)
+SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
+		unsigned long, arg)
 {	
-	struct file * filp;
-	long err;
+	struct fd f = fdget_raw(fd);
+	long err = -EBADF;
 
-	err = -EBADF;
-	filp = fget(fd);
-	if (!filp)
+	if (!f.file)
 		goto out;
 
-	err = security_file_fcntl(filp, cmd, arg);
-	if (err) {
-		fput(filp);
-		return err;
+	if (unlikely(f.file->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd))
+			goto out1;
 	}
-	err = -EBADF;
+
+	err = security_file_fcntl(f.file, cmd, arg);
+	if (err)
+		goto out1;
 	
 	switch (cmd) {
-		case F_GETLK64:
-			err = fcntl_getlk64(filp, (struct flock64 __user *) arg);
-			break;
-		case F_SETLK64:
-		case F_SETLKW64:
-			err = fcntl_setlk64(fd, filp, cmd,
-					(struct flock64 __user *) arg);
-			break;
-		default:
-			err = do_fcntl(fd, cmd, arg, filp);
-			break;
+	case F_GETLK64:
+	case F_OFD_GETLK:
+		err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg);
+		break;
+	case F_SETLK64:
+	case F_SETLKW64:
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+		err = fcntl_setlk64(fd, f.file, cmd,
+				(struct flock64 __user *) arg);
+		break;
+	default:
+		err = do_fcntl(fd, cmd, arg, f.file);
+		break;
 	}
-	fput(filp);
+out1:
+	fdput(f);
 out:
 	return err;
 }
@@ -460,21 +434,33 @@ static const long band_table[NSIGPOLL] = {
 static inline int sigio_perm(struct task_struct *p,
                              struct fown_struct *fown, int sig)
 {
-	return (((fown->euid == 0) ||
-		 (fown->euid == p->suid) || (fown->euid == p->uid) ||
-		 (fown->uid == p->suid) || (fown->uid == p->uid)) &&
-		!security_file_send_sigiotask(p, fown, sig));
+	const struct cred *cred;
+	int ret;
+
+	rcu_read_lock();
+	cred = __task_cred(p);
+	ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) ||
+		uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) ||
+		uid_eq(fown->uid,  cred->suid) || uid_eq(fown->uid,  cred->uid)) &&
+	       !security_file_send_sigiotask(p, fown, sig));
+	rcu_read_unlock();
+	return ret;
 }
 
 static void send_sigio_to_task(struct task_struct *p,
-			       struct fown_struct *fown, 
-			       int fd,
-			       int reason)
+			       struct fown_struct *fown,
+			       int fd, int reason, int group)
 {
-	if (!sigio_perm(p, fown, fown->signum))
+	/*
+	 * F_SETSIG can change ->signum lockless in parallel, make
+	 * sure we read it once and use the same value throughout.
+	 */
+	int signum = ACCESS_ONCE(fown->signum);
+
+	if (!sigio_perm(p, fown, signum))
 		return;
 
-	switch (fown->signum) {
+	switch (signum) {
 		siginfo_t si;
 		default:
 			/* Queue a rt signal with the appropriate fd as its
@@ -483,7 +469,7 @@ static void send_sigio_to_task(struct task_struct *p,
 			   delivered even if we can't queue.  Failure to
 			   queue in this case _should_ be reported; we fall
 			   back to SIGIO in that case. --sct */
-			si.si_signo = fown->signum;
+			si.si_signo = signum;
 			si.si_errno = 0;
 		        si.si_code  = reason;
 			/* Make sure we are called with one of the POLL_*
@@ -495,11 +481,11 @@ static void send_sigio_to_task(struct task_struct *p,
 			else
 				si.si_band = band_table[reason - POLL_IN];
 			si.si_fd    = fd;
-			if (!group_send_sig_info(fown->signum, &si, p))
+			if (!do_send_sig_info(signum, &si, p, group))
 				break;
 		/* fall-through: fall back on the old plain SIGIO signal */
 		case 0:
-			group_send_sig_info(SIGIO, SEND_SIG_PRIV, p);
+			do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, group);
 	}
 }
 
@@ -508,16 +494,23 @@ void send_sigio(struct fown_struct *fown, int fd, int band)
 	struct task_struct *p;
 	enum pid_type type;
 	struct pid *pid;
+	int group = 1;
 	
 	read_lock(&fown->lock);
+
 	type = fown->pid_type;
+	if (type == PIDTYPE_MAX) {
+		group = 0;
+		type = PIDTYPE_PID;
+	}
+
 	pid = fown->pid;
 	if (!pid)
 		goto out_unlock_fown;
 	
 	read_lock(&tasklist_lock);
 	do_each_pid_task(pid, type, p) {
-		send_sigio_to_task(p, fown, fd, band);
+		send_sigio_to_task(p, fown, fd, band, group);
 	} while_each_pid_task(pid, type, p);
 	read_unlock(&tasklist_lock);
  out_unlock_fown:
@@ -525,10 +518,10 @@ void send_sigio(struct fown_struct *fown, int fd, int band)
 }
 
 static void send_sigurg_to_task(struct task_struct *p,
-                                struct fown_struct *fown)
+				struct fown_struct *fown, int group)
 {
 	if (sigio_perm(p, fown, SIGURG))
-		group_send_sig_info(SIGURG, SEND_SIG_PRIV, p);
+		do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, group);
 }
 
 int send_sigurg(struct fown_struct *fown)
@@ -536,10 +529,17 @@ int send_sigurg(struct fown_struct *fown)
 	struct task_struct *p;
 	enum pid_type type;
 	struct pid *pid;
+	int group = 1;
 	int ret = 0;
 	
 	read_lock(&fown->lock);
+
 	type = fown->pid_type;
+	if (type == PIDTYPE_MAX) {
+		group = 0;
+		type = PIDTYPE_PID;
+	}
+
 	pid = fown->pid;
 	if (!pid)
 		goto out_unlock_fown;
@@ -548,7 +548,7 @@ int send_sigurg(struct fown_struct *fown)
 	
 	read_lock(&tasklist_lock);
 	do_each_pid_task(pid, type, p) {
-		send_sigurg_to_task(p, fown);
+		send_sigurg_to_task(p, fown, group);
 	} while_each_pid_task(pid, type, p);
 	read_unlock(&tasklist_lock);
  out_unlock_fown:
@@ -556,95 +556,205 @@ int send_sigurg(struct fown_struct *fown)
 	return ret;
 }
 
-static DEFINE_RWLOCK(fasync_lock);
+static DEFINE_SPINLOCK(fasync_lock);
 static struct kmem_cache *fasync_cache __read_mostly;
 
+static void fasync_free_rcu(struct rcu_head *head)
+{
+	kmem_cache_free(fasync_cache,
+			container_of(head, struct fasync_struct, fa_rcu));
+}
+
 /*
- * fasync_helper() is used by some character device drivers (mainly mice)
- * to set up the fasync queue. It returns negative on error, 0 if it did
- * no changes and positive if it added/deleted the entry.
+ * Remove a fasync entry. If successfully removed, return
+ * positive and clear the FASYNC flag. If no entry exists,
+ * do nothing and return 0.
+ *
+ * NOTE! It is very important that the FASYNC flag always
+ * match the state "is the filp on a fasync list".
+ *
  */
-int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
+int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp)
 {
 	struct fasync_struct *fa, **fp;
-	struct fasync_struct *new = NULL;
 	int result = 0;
 
-	if (on) {
-		new = kmem_cache_alloc(fasync_cache, GFP_KERNEL);
-		if (!new)
-			return -ENOMEM;
-	}
-	write_lock_irq(&fasync_lock);
+	spin_lock(&filp->f_lock);
+	spin_lock(&fasync_lock);
 	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
-		if (fa->fa_file == filp) {
-			if(on) {
-				fa->fa_fd = fd;
-				kmem_cache_free(fasync_cache, new);
-			} else {
-				*fp = fa->fa_next;
-				kmem_cache_free(fasync_cache, fa);
-				result = 1;
-			}
-			goto out;
-		}
-	}
+		if (fa->fa_file != filp)
+			continue;
 
-	if (on) {
-		new->magic = FASYNC_MAGIC;
-		new->fa_file = filp;
-		new->fa_fd = fd;
-		new->fa_next = *fapp;
-		*fapp = new;
+		spin_lock_irq(&fa->fa_lock);
+		fa->fa_file = NULL;
+		spin_unlock_irq(&fa->fa_lock);
+
+		*fp = fa->fa_next;
+		call_rcu(&fa->fa_rcu, fasync_free_rcu);
+		filp->f_flags &= ~FASYNC;
 		result = 1;
+		break;
 	}
-out:
-	write_unlock_irq(&fasync_lock);
+	spin_unlock(&fasync_lock);
+	spin_unlock(&filp->f_lock);
 	return result;
 }
 
+struct fasync_struct *fasync_alloc(void)
+{
+	return kmem_cache_alloc(fasync_cache, GFP_KERNEL);
+}
+
+/*
+ * NOTE! This can be used only for unused fasync entries:
+ * entries that actually got inserted on the fasync list
+ * need to be released by rcu - see fasync_remove_entry.
+ */
+void fasync_free(struct fasync_struct *new)
+{
+	kmem_cache_free(fasync_cache, new);
+}
+
+/*
+ * Insert a new entry into the fasync list.  Return the pointer to the
+ * old one if we didn't use the new one.
+ *
+ * NOTE! It is very important that the FASYNC flag always
+ * match the state "is the filp on a fasync list".
+ */
+struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new)
+{
+        struct fasync_struct *fa, **fp;
+
+	spin_lock(&filp->f_lock);
+	spin_lock(&fasync_lock);
+	for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) {
+		if (fa->fa_file != filp)
+			continue;
+
+		spin_lock_irq(&fa->fa_lock);
+		fa->fa_fd = fd;
+		spin_unlock_irq(&fa->fa_lock);
+		goto out;
+	}
+
+	spin_lock_init(&new->fa_lock);
+	new->magic = FASYNC_MAGIC;
+	new->fa_file = filp;
+	new->fa_fd = fd;
+	new->fa_next = *fapp;
+	rcu_assign_pointer(*fapp, new);
+	filp->f_flags |= FASYNC;
+
+out:
+	spin_unlock(&fasync_lock);
+	spin_unlock(&filp->f_lock);
+	return fa;
+}
+
+/*
+ * Add a fasync entry. Return negative on error, positive if
+ * added, and zero if did nothing but change an existing one.
+ */
+static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp)
+{
+	struct fasync_struct *new;
+
+	new = fasync_alloc();
+	if (!new)
+		return -ENOMEM;
+
+	/*
+	 * fasync_insert_entry() returns the old (update) entry if
+	 * it existed.
+	 *
+	 * So free the (unused) new entry and return 0 to let the
+	 * caller know that we didn't add any new fasync entries.
+	 */
+	if (fasync_insert_entry(fd, filp, fapp, new)) {
+		fasync_free(new);
+		return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * fasync_helper() is used by almost all character device drivers
+ * to set up the fasync queue, and for regular files by the file
+ * lease code. It returns negative on error, 0 if it did no changes
+ * and positive if it added/deleted the entry.
+ */
+int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp)
+{
+	if (!on)
+		return fasync_remove_entry(filp, fapp);
+	return fasync_add_entry(fd, filp, fapp);
+}
+
 EXPORT_SYMBOL(fasync_helper);
 
-void __kill_fasync(struct fasync_struct *fa, int sig, int band)
+/*
+ * rcu_read_lock() is held
+ */
+static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 {
 	while (fa) {
-		struct fown_struct * fown;
+		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;
 		}
-		fown = &fa->fa_file->f_owner;
-		/* Don't send SIGURG to processes which have not set a
-		   queued signum: SIGURG has its own default signalling
-		   mechanism. */
-		if (!(sig == SIGURG && fown->signum == 0))
-			send_sigio(fown, fa->fa_fd, band);
-		fa = fa->fa_next;
+		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
+			   queued signum: SIGURG has its own default signalling
+			   mechanism. */
+			if (!(sig == SIGURG && fown->signum == 0))
+				send_sigio(fown, fa->fa_fd, band);
+		}
+		spin_unlock_irqrestore(&fa->fa_lock, flags);
+		fa = rcu_dereference(fa->fa_next);
 	}
 }
 
-EXPORT_SYMBOL(__kill_fasync);
-
 void kill_fasync(struct fasync_struct **fp, int sig, int band)
 {
 	/* First a quick test without locking: usually
 	 * the list is empty.
 	 */
 	if (*fp) {
-		read_lock(&fasync_lock);
-		/* reread *fp after obtaining the lock */
-		__kill_fasync(*fp, sig, band);
-		read_unlock(&fasync_lock);
+		rcu_read_lock();
+		kill_fasync_rcu(rcu_dereference(*fp), sig, band);
+		rcu_read_unlock();
 	}
 }
 EXPORT_SYMBOL(kill_fasync);
 
-static int __init fasync_init(void)
+static int __init fcntl_init(void)
 {
+	/*
+	 * Please add new bits here to ensure allocation uniqueness.
+	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
+	 * is defined as O_NONBLOCK on some platforms and not on others.
+	 */
+	BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+		O_RDONLY	| O_WRONLY	| O_RDWR	|
+		O_CREAT		| O_EXCL	| O_NOCTTY	|
+		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
+		__O_SYNC	| O_DSYNC	| FASYNC	|
+		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
+		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
+		__FMODE_EXEC	| O_PATH	| __O_TMPFILE
+		));
+
 	fasync_cache = kmem_cache_create("fasync_cache",
 		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
 	return 0;
 }
 
-module_init(fasync_init)
+module_init(fcntl_init)