Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs update from Al Viro:

 - big one - consolidation of descriptor-related logics; almost all of
   that is moved to fs/file.c

   (BTW, I'm seriously tempted to rename the result to fd.c.  As it is,
   we have a situation when file_table.c is about handling of struct
   file and file.c is about handling of descriptor tables; the reasons
   are historical - file_table.c used to be about a static array of
   struct file we used to have way back).

   A lot of stray ends got cleaned up and converted to saner primitives,
   disgusting mess in android/binder.c is still disgusting, but at least
   doesn't poke so much in descriptor table guts anymore.  A bunch of
   relatively minor races got fixed in process, plus an ext4 struct file
   leak.

 - related thing - fget_light() partially unuglified; see fdget() in
   there (and yes, it generates the code as good as we used to have).

 - also related - bits of Cyrill's procfs stuff that got entangled into
   that work; _not_ all of it, just the initial move to fs/proc/fd.c and
   switch of fdinfo to seq_file.

 - Alex's fs/coredump.c spiltoff - the same story, had been easier to
   take that commit than mess with conflicts.  The rest is a separate
   pile, this was just a mechanical code movement.

 - a few misc patches all over the place.  Not all for this cycle,
   there'll be more (and quite a few currently sit in akpm's tree)."

Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
  MAX_LFS_FILESIZE should be a loff_t
  compat: fs: Generic compat_sys_sendfile implementation
  fs: push rcu_barrier() from deactivate_locked_super() to filesystems
  btrfs: reada_extent doesn't need kref for refcount
  coredump: move core dump functionality into its own file
  coredump: prevent double-free on an error path in core dumper
  usb/gadget: fix misannotations
  fcntl: fix misannotations
  ceph: don't abuse d_delete() on failure exits
  hypfs: ->d_parent is never NULL or negative
  vfs: delete surplus inode NULL check
  switch simple cases of fget_light to fdget
  new helpers: fdget()/fdput()
  switch o2hb_region_dev_write() to fget_light()
  proc_map_files_readdir(): don't bother with grabbing files
  make get_file() return its argument
  vhost_set_vring(): turn pollstart/pollstop into bool
  switch prctl_set_mm_exe_file() to fget_light()
  switch xfs_find_handle() to fget_light()
  switch xfs_swapext() to fget_light()
  ...

arch/alpha/kernel/osf_sys.c

@@ -145,27 +145,24 @@ SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd,
 		long __user *, basep)
 {
 	int error;
-	struct file *file;
+	struct fd arg = fdget(fd);
 	struct osf_dirent_callback buf;
 
-	error = -EBADF;
+	if (!arg.file)
-	file = fget(fd);
+		return -EBADF;
-	if (!file)
-		goto out;
 
 	buf.dirent = dirent;
 	buf.basep = basep;
 	buf.count = count;
 	buf.error = 0;
 
-	error = vfs_readdir(file, osf_filldir, &buf);
+	error = vfs_readdir(arg.file, osf_filldir, &buf);
 	if (error >= 0)
 		error = buf.error;
 	if (count != buf.count)
 		error = count - buf.count;
 
-	fput(file);
+	fdput(arg);
- out:
 	return error;
 }
 

arch/ia64/kernel/perfmon.c

@@ -2306,7 +2306,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	 * partially initialize the vma for the sampling buffer
 	 */
 	vma->vm_mm	     = mm;
-	vma->vm_file	     = filp;
+	vma->vm_file	     = get_file(filp);
 	vma->vm_flags	     = VM_READ| VM_MAYREAD |VM_RESERVED;
 	vma->vm_page_prot    = PAGE_READONLY; /* XXX may need to change */
 
@@ -2345,8 +2345,6 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 		goto error;
 	}
 
-	get_file(filp);
-
 	/*
 	 * now insert the vma in the vm list for the process, must be
 	 * done with mmap lock held
@@ -4782,7 +4780,7 @@ recheck:
 asmlinkage long
 sys_perfmonctl (int fd, int cmd, void __user *arg, int count)
 {
-	struct file *file = NULL;
+	struct fd f = {NULL, 0};
 	pfm_context_t *ctx = NULL;
 	unsigned long flags = 0UL;
 	void *args_k = NULL;
@@ -4879,17 +4877,17 @@ restart_args:
 
 	ret = -EBADF;
 
-	file = fget(fd);
+	f = fdget(fd);
-	if (unlikely(file == NULL)) {
+	if (unlikely(f.file == NULL)) {
 		DPRINT(("invalid fd %d\n", fd));
 		goto error_args;
 	}
-	if (unlikely(PFM_IS_FILE(file) == 0)) {
+	if (unlikely(PFM_IS_FILE(f.file) == 0)) {
 		DPRINT(("fd %d not related to perfmon\n", fd));
 		goto error_args;
 	}
 
-	ctx = file->private_data;
+	ctx = f.file->private_data;
 	if (unlikely(ctx == NULL)) {
 		DPRINT(("no context for fd %d\n", fd));
 		goto error_args;
@@ -4919,8 +4917,8 @@ abort_locked:
 	if (call_made && PFM_CMD_RW_ARG(cmd) && copy_to_user(arg, args_k, base_sz*count)) ret = -EFAULT;
 
 error_args:
-	if (file)
+	if (f.file)
-		fput(file);
+		fdput(f);
 
 	kfree(args_k);
 

arch/parisc/hpux/fs.c

@@ -109,33 +109,32 @@ Efault:
 
 int hpux_getdents(unsigned int fd, struct hpux_dirent __user *dirent, unsigned int count)
 {
-	struct file * file;
+	struct fd arg;
 	struct hpux_dirent __user * lastdirent;
 	struct getdents_callback buf;
-	int error = -EBADF;
+	int error;
 
-	file = fget(fd);
+	arg = fdget(fd);
-	if (!file)
+	if (!arg.file)
-		goto out;
+		return -EBADF;
 
 	buf.current_dir = dirent;
 	buf.previous = NULL;
 	buf.count = count;
 	buf.error = 0;
 
-	error = vfs_readdir(file, filldir, &buf);
+	error = vfs_readdir(arg.file, filldir, &buf);
 	if (error >= 0)
 		error = buf.error;
 	lastdirent = buf.previous;
 	if (lastdirent) {
-		if (put_user(file->f_pos, &lastdirent->d_off))
+		if (put_user(arg.file->f_pos, &lastdirent->d_off))
 			error = -EFAULT;
 		else
 			error = count - buf.count;
 	}
 
-	fput(file);
+	fdput(arg);
-out:
 	return error;
 }
 

arch/powerpc/include/asm/systbl.h

@@ -189,7 +189,7 @@ SYSCALL_SPU(getcwd)
 SYSCALL_SPU(capget)
 SYSCALL_SPU(capset)
 COMPAT_SYS(sigaltstack)
-SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
+SYSX_SPU(sys_sendfile,compat_sys_sendfile_wrapper,sys_sendfile)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 PPC_SYS(vfork)
@@ -229,7 +229,7 @@ COMPAT_SYS_SPU(sched_setaffinity)
 COMPAT_SYS_SPU(sched_getaffinity)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
-SYS32ONLY(sendfile64)
+SYSX(sys_ni_syscall,compat_sys_sendfile64_wrapper,sys_sendfile64)
 COMPAT_SYS_SPU(io_setup)
 SYSCALL_SPU(io_destroy)
 COMPAT_SYS_SPU(io_getevents)

arch/powerpc/include/asm/unistd.h

@@ -419,6 +419,7 @@
 #define __ARCH_WANT_COMPAT_SYS_TIME
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_SYS_NEWFSTATAT
+#define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #endif
 
 /*

arch/powerpc/kernel/sys_ppc32.c

@@ -143,48 +143,17 @@ long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t pt
  * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode)
  * and the register representation of a signed int (msr in 64-bit mode) is performed.
  */
-asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count)
+asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd,
+					    compat_off_t __user *offset, u32 count)
 {
-	mm_segment_t old_fs = get_fs();
+	return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count);
-	int ret;
-	off_t of;
-	off_t __user *up;
-
-	if (offset && get_user(of, offset))
-		return -EFAULT;
-
-	/* The __user pointer cast is valid because of the set_fs() */		
-	set_fs(KERNEL_DS);
-	up = offset ? (off_t __user *) &of : NULL;
-	ret = sys_sendfile((int)out_fd, (int)in_fd, up, count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(of, offset))
-		return -EFAULT;
-		
-	return ret;
 }
 
-asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count)
+asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd,
+					      compat_loff_t __user *offset, u32 count)
 {
-	mm_segment_t old_fs = get_fs();
+	return sys_sendfile((int)out_fd, (int)in_fd,
-	int ret;
+			    (off_t __user *)offset, count);
-	loff_t lof;
-	loff_t __user *up;
-	
-	if (offset && get_user(lof, offset))
-		return -EFAULT;
-		
-	/* The __user pointer cast is valid because of the set_fs() */		
-	set_fs(KERNEL_DS);
-	up = offset ? (loff_t __user *) &lof : NULL;
-	ret = sys_sendfile64(out_fd, in_fd, up, count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(lof, offset))
-		return -EFAULT;
-		
-	return ret;
 }
 
 long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2,

arch/powerpc/platforms/cell/spu_syscalls.c

@@ -69,8 +69,6 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags,
 	umode_t, mode, int, neighbor_fd)
 {
 	long ret;
-	struct file *neighbor;
-	int fput_needed;
 	struct spufs_calls *calls;
 
 	calls = spufs_calls_get();
@@ -78,11 +76,11 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags,
 		return -ENOSYS;
 
 	if (flags & SPU_CREATE_AFFINITY_SPU) {
+		struct fd neighbor = fdget(neighbor_fd);
 		ret = -EBADF;
-		neighbor = fget_light(neighbor_fd, &fput_needed);
+		if (neighbor.file) {
-		if (neighbor) {
+			ret = calls->create_thread(name, flags, mode, neighbor.file);
-			ret = calls->create_thread(name, flags, mode, neighbor);
+			fdput(neighbor);
-			fput_light(neighbor, fput_needed);
 		}
 	} else
 		ret = calls->create_thread(name, flags, mode, NULL);
@@ -94,8 +92,7 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags,
 asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus)
 {
 	long ret;
-	struct file *filp;
+	struct fd arg;
-	int fput_needed;
 	struct spufs_calls *calls;
 
 	calls = spufs_calls_get();
@@ -103,10 +100,10 @@ asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus)
 		return -ENOSYS;
 
 	ret = -EBADF;
-	filp = fget_light(fd, &fput_needed);
+	arg = fdget(fd);
-	if (filp) {
+	if (arg.file) {
-		ret = calls->spu_run(filp, unpc, ustatus);
+		ret = calls->spu_run(arg.file, unpc, ustatus);
-		fput_light(filp, fput_needed);
+		fdput(arg);
 	}
 
 	spufs_calls_put(calls);

arch/powerpc/platforms/cell/spufs/coredump.c

@@ -106,6 +106,17 @@ static int spufs_ctx_note_size(struct spu_context *ctx, int dfd)
 	return total;
 }
 
+static int match_context(const void *v, struct file *file, unsigned fd)
+{
+	struct spu_context *ctx;
+	if (file->f_op != &spufs_context_fops)
+		return 0;
+	ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx;
+	if (ctx->flags & SPU_CREATE_NOSCHED)
+		return 0;
+	return fd + 1;
+}
+
 /*
  * The additional architecture-specific notes for Cell are various
  * context files in the spu context.
@@ -115,29 +126,18 @@ static int spufs_ctx_note_size(struct spu_context *ctx, int dfd)
  * internal functionality to dump them without needing to actually
  * open the files.
  */
+/*
+ * descriptor table is not shared, so files can't change or go away.
+ */
 static struct spu_context *coredump_next_context(int *fd)
 {
-	struct fdtable *fdt = files_fdtable(current->files);
 	struct file *file;
-	struct spu_context *ctx = NULL;
+	int n = iterate_fd(current->files, *fd, match_context, NULL);
-
+	if (!n)
-	for (; *fd < fdt->max_fds; (*fd)++) {
+		return NULL;
-		if (!fd_is_open(*fd, fdt))
+	*fd = n - 1;
-			continue;
+	file = fcheck(*fd);
-
+	return SPUFS_I(file->f_dentry->d_inode)->i_ctx;
-		file = fcheck(*fd);
-
-		if (!file || file->f_op != &spufs_context_fops)
-			continue;
-
-		ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx;
-		if (ctx->flags & SPU_CREATE_NOSCHED)
-			continue;
-
-		break;
-	}
-
-	return ctx;
 }
 
 int spufs_coredump_extra_notes_size(void)

arch/s390/hypfs/inode.c

@@ -72,8 +72,6 @@ static void hypfs_remove(struct dentry *dentry)
 	struct dentry *parent;
 
 	parent = dentry->d_parent;
-	if (!parent || !parent->d_inode)
-		return;
 	mutex_lock(&parent->d_inode->i_mutex);
 	if (hypfs_positive(dentry)) {
 		if (S_ISDIR(dentry->d_inode->i_mode))

arch/sparc/include/asm/unistd.h

@@ -447,6 +447,7 @@
 #else
 #define __ARCH_WANT_COMPAT_SYS_TIME
 #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #endif
 
 /*

arch/sparc/kernel/sys32.S

@@ -90,7 +90,7 @@ SIGN1(sys32_mkdir, sys_mkdir, %o1)
 SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
 SIGN1(sys32_sysfs, compat_sys_sysfs, %o0)
 SIGN2(sys32_sendfile, compat_sys_sendfile, %o0, %o1)
-SIGN2(sys32_sendfile64, compat_sys_sendfile64, %o0, %o1)
+SIGN2(sys32_sendfile64, sys_sendfile, %o0, %o1)
 SIGN1(sys32_prctl, sys_prctl, %o0)
 SIGN1(sys32_sched_rr_get_interval, compat_sys_sched_rr_get_interval, %o0)
 SIGN2(sys32_waitpid, sys_waitpid, %o0, %o2)

arch/sparc/kernel/sys_sparc32.c

@@ -506,52 +506,6 @@ long compat_sys_fadvise64_64(int fd,
 				advice);
 }
 
-asmlinkage long compat_sys_sendfile(int out_fd, int in_fd,
-				    compat_off_t __user *offset,
-				    compat_size_t count)
-{
-	mm_segment_t old_fs = get_fs();
-	int ret;
-	off_t of;
-	
-	if (offset && get_user(of, offset))
-		return -EFAULT;
-		
-	set_fs(KERNEL_DS);
-	ret = sys_sendfile(out_fd, in_fd,
-			   offset ? (off_t __user *) &of : NULL,
-			   count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(of, offset))
-		return -EFAULT;
-		
-	return ret;
-}
-
-asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd,
-				      compat_loff_t __user *offset,
-				      compat_size_t count)
-{
-	mm_segment_t old_fs = get_fs();
-	int ret;
-	loff_t lof;
-	
-	if (offset && get_user(lof, offset))
-		return -EFAULT;
-		
-	set_fs(KERNEL_DS);
-	ret = sys_sendfile64(out_fd, in_fd,
-			     offset ? (loff_t __user *) &lof : NULL,
-			     count);
-	set_fs(old_fs);
-	
-	if (offset && put_user(lof, offset))
-		return -EFAULT;
-		
-	return ret;
-}
-
 /* This is just a version for 32-bit applications which does
  * not force O_LARGEFILE on.
  */

arch/um/drivers/mconsole_kern.c

@@ -21,6 +21,9 @@
 #include <linux/un.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/file.h>
 #include <asm/uaccess.h>
 #include <asm/switch_to.h>
 
@@ -118,18 +121,14 @@ void mconsole_log(struct mc_request *req)
 	mconsole_reply(req, "", 0, 0);
 }
 
-/* This is a more convoluted version of mconsole_proc, which has some stability
- * problems; however, we need it fixed, because it is expected that UML users
- * mount HPPFS instead of procfs on /proc. And we want mconsole_proc to still
- * show the real procfs content, not the ones from hppfs.*/
-#if 0
 void mconsole_proc(struct mc_request *req)
 {
 	struct vfsmount *mnt = current->nsproxy->pid_ns->proc_mnt;
+	char *buf;
+	int len;
 	struct file *file;
-	int n;
+	int first_chunk = 1;
-	char *ptr = req->request.data, *buf;
+	char *ptr = req->request.data;
-	mm_segment_t old_fs = get_fs();
 
 	ptr += strlen("proc");
 	ptr = skip_spaces(ptr);
@@ -137,6 +136,7 @@ void mconsole_proc(struct mc_request *req)
 	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY);
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
+		printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file));
 		goto out;
 	}
 
@@ -146,62 +146,13 @@ void mconsole_proc(struct mc_request *req)
 		goto out_fput;
 	}
 
-	if (file->f_op->read) {
+	do {
-		do {
+		loff_t pos;
-			loff_t pos;
+		mm_segment_t old_fs = get_fs();
-			set_fs(KERNEL_DS);
+		set_fs(KERNEL_DS);
-			n = vfs_read(file, buf, PAGE_SIZE - 1, &pos);
+		len = vfs_read(file, buf, PAGE_SIZE - 1, &pos);
-			file_pos_write(file, pos);
+		set_fs(old_fs);
-			set_fs(old_fs);
+		file->f_pos = pos;
-			if (n >= 0) {
-				buf[n] = '\0';
-				mconsole_reply(req, buf, 0, (n > 0));
-			}
-			else {
-				mconsole_reply(req, "Read of file failed",
-					       1, 0);
-				goto out_free;
-			}
-		} while (n > 0);
-	}
-	else mconsole_reply(req, "", 0, 0);
-
- out_free:
-	kfree(buf);
- out_fput:
-	fput(file);
- out: ;
-}
-#endif
-
-void mconsole_proc(struct mc_request *req)
-{
-	char path[64];
-	char *buf;
-	int len;
-	int fd;
-	int first_chunk = 1;
-	char *ptr = req->request.data;
-
-	ptr += strlen("proc");
-	ptr = skip_spaces(ptr);
-	snprintf(path, sizeof(path), "/proc/%s", ptr);
-
-	fd = sys_open(path, 0, 0);
-	if (fd < 0) {
-		mconsole_reply(req, "Failed to open file", 1, 0);
-		printk(KERN_ERR "open %s: %d\n",path,fd);
-		goto out;
-	}
-
-	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (buf == NULL) {
-		mconsole_reply(req, "Failed to allocate buffer", 1, 0);
-		goto out_close;
-	}
-
-	for (;;) {
-		len = sys_read(fd, buf, PAGE_SIZE-1);
 		if (len < 0) {
 			mconsole_reply(req, "Read of file failed", 1, 0);
 			goto out_free;
@@ -211,22 +162,14 @@ void mconsole_proc(struct mc_request *req)
 			mconsole_reply(req, "\n", 0, 1);
 			first_chunk = 0;
 		}
-		if (len == PAGE_SIZE-1) {
+		buf[len] = '\0';
-			buf[len] = '\0';
+		mconsole_reply(req, buf, 0, (len > 0));
-			mconsole_reply(req, buf, 0, 1);
+	} while (len > 0);
-		} else {
-			buf[len] = '\0';
-			mconsole_reply(req, buf, 0, 0);
-			break;
-		}
-	}
-
  out_free:
 	kfree(buf);
- out_close:
+ out_fput:
-	sys_close(fd);
+	fput(file);
- out:
+ out: ;
-	/* nothing */;
 }
 
 #define UML_MCONSOLE_HELPTEXT \

drivers/base/dma-buf.c

@@ -460,8 +460,7 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
 	if (vma->vm_file)
 		fput(vma->vm_file);
 
-	vma->vm_file = dmabuf->file;
+	vma->vm_file = get_file(dmabuf->file);
-	get_file(vma->vm_file);
 
 	vma->vm_pgoff = pgoff;
 

drivers/infiniband/core/ucma.c

@@ -1183,7 +1183,7 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file,
 	struct rdma_ucm_migrate_id cmd;
 	struct rdma_ucm_migrate_resp resp;
 	struct ucma_context *ctx;
-	struct file *filp;
+	struct fd f;
 	struct ucma_file *cur_file;
 	int ret = 0;
 
@@ -1191,12 +1191,12 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file,
 		return -EFAULT;
 
 	/* Get current fd to protect against it being closed */
-	filp = fget(cmd.fd);
+	f = fdget(cmd.fd);
-	if (!filp)
+	if (!f.file)
 		return -ENOENT;
 
 	/* Validate current fd and prevent destruction of id. */
-	ctx = ucma_get_ctx(filp->private_data, cmd.id);
+	ctx = ucma_get_ctx(f.file->private_data, cmd.id);
 	if (IS_ERR(ctx)) {
 		ret = PTR_ERR(ctx);
 		goto file_put;
@@ -1230,7 +1230,7 @@ response:
 
 	ucma_put_ctx(ctx);
 file_put:
-	fput(filp);
+	fdput(f);
 	return ret;
 }
 

drivers/infiniband/core/uverbs_cmd.c

@@ -705,7 +705,7 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 	struct ib_udata			udata;
 	struct ib_uxrcd_object         *obj;
 	struct ib_xrcd                 *xrcd = NULL;
-	struct file                    *f = NULL;
+	struct fd			f = {NULL, 0};
 	struct inode                   *inode = NULL;
 	int				ret = 0;
 	int				new_xrcd = 0;
@@ -724,18 +724,13 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 
 	if (cmd.fd != -1) {
 		/* search for file descriptor */
-		f = fget(cmd.fd);
+		f = fdget(cmd.fd);
-		if (!f) {
+		if (!f.file) {
-			ret = -EBADF;
-			goto err_tree_mutex_unlock;
-		}
-
-		inode = f->f_dentry->d_inode;
-		if (!inode) {
 			ret = -EBADF;
 			goto err_tree_mutex_unlock;
 		}
 
+		inode = f.file->f_path.dentry->d_inode;
 		xrcd = find_xrcd(file->device, inode);
 		if (!xrcd && !(cmd.oflags & O_CREAT)) {
 			/* no file descriptor. Need CREATE flag */
@@ -800,8 +795,8 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 		goto err_copy;
 	}
 
-	if (f)
+	if (f.file)
-		fput(f);
+		fdput(f);
 
 	mutex_lock(&file->mutex);
 	list_add_tail(&obj->uobject.list, &file->ucontext->xrcd_list);
@@ -830,8 +825,8 @@ err:
 	put_uobj_write(&obj->uobject);
 
 err_tree_mutex_unlock:
-	if (f)
+	if (f.file)
-		fput(f);
+		fdput(f);
 
 	mutex_unlock(&file->device->xrcd_tree_mutex);
 

drivers/infiniband/core/uverbs_main.c

@@ -541,16 +541,15 @@ struct file *ib_uverbs_alloc_event_file(struct ib_uverbs_file *uverbs_file,
 struct ib_uverbs_event_file *ib_uverbs_lookup_comp_file(int fd)
 {
 	struct ib_uverbs_event_file *ev_file = NULL;
-	struct file *filp;
+	struct fd f = fdget(fd);
 
-	filp = fget(fd);
+	if (!f.file)
-	if (!filp)
 		return NULL;
 
-	if (filp->f_op != &uverbs_event_fops)
+	if (f.file->f_op != &uverbs_event_fops)
 		goto out;
 
-	ev_file = filp->private_data;
+	ev_file = f.file->private_data;
 	if (ev_file->is_async) {
 		ev_file = NULL;
 		goto out;
@@ -559,7 +558,7 @@ struct ib_uverbs_event_file *ib_uverbs_lookup_comp_file(int fd)
 	kref_get(&ev_file->ref);
 
 out:
-	fput(filp);
+	fdput(f);
 	return ev_file;
 }
 

drivers/staging/android/binder.c

@@ -362,71 +362,22 @@ struct binder_transaction {
 static void
 binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer);
 
-/*
- * copied from get_unused_fd_flags
- */
 static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
 {
 	struct files_struct *files = proc->files;
-	int fd, error;
-	struct fdtable *fdt;
 	unsigned long rlim_cur;
 	unsigned long irqs;
 
 	if (files == NULL)
 		return -ESRCH;
 
-	error = -EMFILE;
+	if (!lock_task_sighand(proc->tsk, &irqs))
-	spin_lock(&files->file_lock);
+		return -EMFILE;
 
-repeat:
+	rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
-	fdt = files_fdtable(files);
+	unlock_task_sighand(proc->tsk, &irqs);
-	fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, files->next_fd);
 
-	/*
+	return __alloc_fd(files, 0, rlim_cur, flags);
-	 * N.B. For clone tasks sharing a files structure, this test
-	 * will limit the total number of files that can be opened.
-	 */
-	rlim_cur = 0;
-	if (lock_task_sighand(proc->tsk, &irqs)) {
-		rlim_cur = proc->tsk->signal->rlim[RLIMIT_NOFILE].rlim_cur;
-		unlock_task_sighand(proc->tsk, &irqs);
-	}
-	if (fd >= rlim_cur)
-		goto out;
-
-	/* Do we need to expand the fd array or fd set?  */
-	error = expand_files(files, fd);
-	if (error < 0)
-		goto out;
-
-	if (error) {
-		/*
-		 * If we needed to expand the fs array we
-		 * might have blocked - try again.
-		 */
-		error = -EMFILE;
-		goto repeat;
-	}
-
-	__set_open_fd(fd, fdt);
-	if (flags & O_CLOEXEC)
-		__set_close_on_exec(fd, fdt);
-	else
-		__clear_close_on_exec(fd, fdt);
-	files->next_fd = fd + 1;
-
-	/* Sanity check */
-	if (fdt->fd[fd] != NULL) {
-		pr_warn("get_unused_fd: slot %d not NULL!\n", fd);
-		fdt->fd[fd] = NULL;
-	}
-
-	error = fd;
-
-out:
-	spin_unlock(&files->file_lock);
-	return error;
 }
 
 /*
@@ -435,28 +386,8 @@ out:
 static void task_fd_install(
 	struct binder_proc *proc, unsigned int fd, struct file *file)
 {
-	struct files_struct *files = proc->files;
+	if (proc->files)
-	struct fdtable *fdt;
+		__fd_install(proc->files, fd, file);
-
-	if (files == NULL)
-		return;
-
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	BUG_ON(fdt->fd[fd] != NULL);
-	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
-}
-
-/*
- * copied from __put_unused_fd in open.c
- */
-static void __put_unused_fd(struct files_struct *files, unsigned int fd)
-{
-	struct fdtable *fdt = files_fdtable(files);
-	__clear_open_fd(fd, fdt);
-	if (fd < files->next_fd)
-		files->next_fd = fd;
 }
 
 /*
@@ -464,27 +395,12 @@ static void __put_unused_fd(struct files_struct *files, unsigned int fd)
  */
 static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 {
-	struct file *filp;
-	struct files_struct *files = proc->files;
-	struct fdtable *fdt;
 	int retval;
 
-	if (files == NULL)
+	if (proc->files == NULL)
 		return -ESRCH;
 
-	spin_lock(&files->file_lock);
+	retval = __close_fd(proc->files, fd);
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds)
-		goto out_unlock;
-	filp = fdt->fd[fd];
-	if (!filp)
-		goto out_unlock;
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__clear_close_on_exec(fd, fdt);
-	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
-	retval = filp_close(filp, files);
-
 	/* can't restart close syscall because file table entry was cleared */
 	if (unlikely(retval == -ERESTARTSYS ||
 		     retval == -ERESTARTNOINTR ||
@@ -493,10 +409,6 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 		retval = -EINTR;
 
 	return retval;
-
-out_unlock:
-	spin_unlock(&files->file_lock);
-	return -EBADF;
 }
 
 static void binder_set_nice(long nice)
@@ -2793,6 +2705,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	const char *failure_string;
 	struct binder_buffer *buffer;
 
+	if (proc->tsk != current)
+		return -EINVAL;
+
 	if ((vma->vm_end - vma->vm_start) > SZ_4M)
 		vma->vm_end = vma->vm_start + SZ_4M;
 
@@ -2857,7 +2772,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	binder_insert_free_buffer(proc, buffer);
 	proc->free_async_space = proc->buffer_size / 2;
 	barrier();
-	proc->files = get_files_struct(proc->tsk);
+	proc->files = get_files_struct(current);
 	proc->vma = vma;
 	proc->vma_vm_mm = vma->vm_mm;
 

drivers/staging/omapdrm/omap_gem.c

@@ -592,9 +592,8 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
 		fput(vma->vm_file);
-		get_file(obj->filp);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = obj->filp;
+		vma->vm_file  = get_file(obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}

drivers/tty/tty_io.c

@@ -1166,10 +1166,8 @@ ssize_t redirected_tty_write(struct file *file, const char __user *buf,
 	struct file *p = NULL;
 
 	spin_lock(&redirect_lock);
-	if (redirect) {
+	if (redirect)
-		get_file(redirect);
+		p = get_file(redirect);
-		p = redirect;
-	}
 	spin_unlock(&redirect_lock);
 
 	if (p) {
@@ -2264,8 +2262,7 @@ static int tioccons(struct file *file)
 		spin_unlock(&redirect_lock);
 		return -EBUSY;
 	}
-	get_file(file);
+	redirect = get_file(file);
-	redirect = file;
 	spin_unlock(&redirect_lock);
 	return 0;
 }
@@ -2809,6 +2806,13 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd,
 }
 #endif
 
+static int this_tty(const void *t, struct file *file, unsigned fd)
+{
+	if (likely(file->f_op->read != tty_read))
+		return 0;
+	return file_tty(file) != t ? 0 : fd + 1;
+}
+	
 /*
  * This implements the "Secure Attention Key" ---  the idea is to
  * prevent trojan horses by killing all processes associated with this
@@ -2836,8 +2840,6 @@ void __do_SAK(struct tty_struct *tty)
 	struct task_struct *g, *p;
 	struct pid *session;
 	int		i;
-	struct file	*filp;
-	struct fdtable *fdt;
 
 	if (!tty)
 		return;
@@ -2867,27 +2869,12 @@ void __do_SAK(struct tty_struct *tty)
 			continue;
 		}
 		task_lock(p);
-		if (p->files) {
+		i = iterate_fd(p->files, 0, this_tty, tty);
-			/*
+		if (i != 0) {
-			 * We don't take a ref to the file, so we must
+			printk(KERN_NOTICE "SAK: killed process %d"
-			 * hold ->file_lock instead.
+			    " (%s): fd#%d opened to the tty\n",
-			 */
+				    task_pid_nr(p), p->comm, i - 1);
-			spin_lock(&p->files->file_lock);
+			force_sig(SIGKILL, p);
-			fdt = files_fdtable(p->files);
-			for (i = 0; i < fdt->max_fds; i++) {
-				filp = fcheck_files(p->files, i);
-				if (!filp)
-					continue;
-				if (filp->f_op->read == tty_read &&
-				    file_tty(filp) == tty) {
-					printk(KERN_NOTICE "SAK: killed process %d"
-					    " (%s): fd#%d opened to the tty\n",
-					    task_pid_nr(p), p->comm, i);
-					force_sig(SIGKILL, p);
-					break;
-				}
-			}
-			spin_unlock(&p->files->file_lock);
 		}
 		task_unlock(p);
 	} while_each_thread(g, p);

drivers/usb/gadget/f_fs.c

@@ -340,7 +340,7 @@ ffs_sb_create_file(struct super_block *sb, const char *name, void *data,
 
 static int ffs_mutex_lock(struct mutex *mutex, unsigned nonblock)
 	__attribute__((warn_unused_result, nonnull));
-static char *ffs_prepare_buffer(const char * __user buf, size_t len)
+static char *ffs_prepare_buffer(const char __user *buf, size_t len)
 	__attribute__((warn_unused_result, nonnull));
 
 
@@ -2445,7 +2445,7 @@ static int ffs_mutex_lock(struct mutex *mutex, unsigned nonblock)
 		: mutex_lock_interruptible(mutex);
 }
 
-static char *ffs_prepare_buffer(const char * __user buf, size_t len)
+static char *ffs_prepare_buffer(const char __user *buf, size_t len)
 {
 	char *data;
 

drivers/vfio/vfio.c

@@ -1014,7 +1014,7 @@ static void vfio_group_try_dissolve_container(struct vfio_group *group)
 
 static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 {
-	struct file *filep;
+	struct fd f;
 	struct vfio_container *container;
 	struct vfio_iommu_driver *driver;
 	int ret = 0;
@@ -1022,17 +1022,17 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 	if (atomic_read(&group->container_users))
 		return -EINVAL;
 
-	filep = fget(container_fd);
+	f = fdget(container_fd);
-	if (!filep)
+	if (!f.file)
 		return -EBADF;
 
 	/* Sanity check, is this really our fd? */
-	if (filep->f_op != &vfio_fops) {
+	if (f.file->f_op != &vfio_fops) {
-		fput(filep);
+		fdput(f);
 		return -EINVAL;
 	}
 
-	container = filep->private_data;
+	container = f.file->private_data;
 	WARN_ON(!container); /* fget ensures we don't race vfio_release */
 
 	mutex_lock(&container->group_lock);
@@ -1054,8 +1054,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 
 unlock_out:
 	mutex_unlock(&container->group_lock);
-	fput(filep);
+	fdput(f);
-
 	return ret;
 }
 

drivers/vhost/vhost.c

@@ -636,8 +636,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 
 static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 {
-	struct file *eventfp, *filep = NULL,
+	struct file *eventfp, *filep = NULL;
-		    *pollstart = NULL, *pollstop = NULL;
+	bool pollstart = false, pollstop = false;
 	struct eventfd_ctx *ctx = NULL;
 	u32 __user *idxp = argp;
 	struct vhost_virtqueue *vq;
@@ -763,8 +763,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			break;
 		}
 		if (eventfp != vq->kick) {
-			pollstop = filep = vq->kick;
+			pollstop = (filep = vq->kick) != NULL;
-			pollstart = vq->kick = eventfp;
+			pollstart = (vq->kick = eventfp) != NULL;
 		} else
 			filep = eventfp;
 		break;

drivers/video/msm/mdp.c

@@ -257,19 +257,17 @@ int get_img(struct mdp_img *img, struct fb_info *info,
 	    unsigned long *start, unsigned long *len,
 	    struct file **filep)
 {
-	int put_needed, ret = 0;
+	int ret = 0;
-	struct file *file;
+	struct fd f = fdget(img->memory_id);
-
+	if (f.file == NULL)
-	file = fget_light(img->memory_id, &put_needed);
-	if (file == NULL)
 		return -1;
 
-	if (MAJOR(file->f_dentry->d_inode->i_rdev) == FB_MAJOR) {
+	if (MAJOR(f.file->f_dentry->d_inode->i_rdev) == FB_MAJOR) {
 		*start = info->fix.smem_start;
 		*len = info->fix.smem_len;
 	} else
 		ret = -1;
-	fput_light(file, put_needed);
+	fdput(f);
 
 	return ret;
 }

fs/9p/v9fs.c

@@ -560,6 +560,11 @@ static int v9fs_init_inode_cache(void)
  */
 static void v9fs_destroy_inode_cache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(v9fs_inode_cache);
 }
 

fs/Makefile

@@ -11,7 +11,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o drop_caches.o splice.o sync.o utimes.o \
-		stack.o fs_struct.o statfs.o
+		stack.o fs_struct.o statfs.o coredump.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o

fs/adfs/super.c

@@ -280,6 +280,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(adfs_inode_cachep);
 }
 

fs/affs/super.c

@@ -147,6 +147,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(affs_inode_cachep);
 }
 

fs/afs/super.c

@@ -123,6 +123,11 @@ void __exit afs_fs_exit(void)
 		BUG();
 	}
 
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(afs_inode_cachep);
 	_leave("");
 }

fs/autofs4/dev-ioctl.c

@@ -221,20 +221,6 @@ static int test_by_type(struct path *path, void *p)
 	return ino && ino->sbi->type & *(unsigned *)p;
 }
 
-static void autofs_dev_ioctl_fd_install(unsigned int fd, struct file *file)
-{
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	BUG_ON(fdt->fd[fd] != NULL);
-	rcu_assign_pointer(fdt->fd[fd], file);
-	__set_close_on_exec(fd, fdt);
-	spin_unlock(&files->file_lock);
-}
-
-
 /*
  * Open a file descriptor on the autofs mount point corresponding
  * to the given path and device number (aka. new_encode_dev(sb->s_dev)).
@@ -243,7 +229,7 @@ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid)
 {
 	int err, fd;
 
-	fd = get_unused_fd();
+	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (likely(fd >= 0)) {
 		struct file *filp;
 		struct path path;
@@ -264,7 +250,7 @@ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid)
 			goto out;
 		}
 
-		autofs_dev_ioctl_fd_install(fd, filp);
+		fd_install(fd, filp);
 	}
 
 	return fd;

fs/autofs4/waitq.c

@@ -175,8 +175,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
 		return;
 	}
 
-	pipe = sbi->pipe;
+	pipe = get_file(sbi->pipe);
-	get_file(pipe);
 
 	mutex_unlock(&sbi->wq_mutex);
 

fs/befs/linuxvfs.c

@@ -457,6 +457,11 @@ befs_init_inodecache(void)
 static void
 befs_destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(befs_inode_cachep);
 }
 

fs/bfs/inode.c

@@ -280,6 +280,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(bfs_inode_cachep);
 }
 

fs/binfmt_elf.c

@@ -1696,30 +1696,19 @@ static int elf_note_info_init(struct elf_note_info *info)
 		return 0;
 	info->psinfo = kmalloc(sizeof(*info->psinfo), GFP_KERNEL);
 	if (!info->psinfo)
-		goto notes_free;
+		return 0;
 	info->prstatus = kmalloc(sizeof(*info->prstatus), GFP_KERNEL);
 	if (!info->prstatus)
-		goto psinfo_free;
+		return 0;
 	info->fpu = kmalloc(sizeof(*info->fpu), GFP_KERNEL);
 	if (!info->fpu)
-		goto prstatus_free;
+		return 0;
 #ifdef ELF_CORE_COPY_XFPREGS
 	info->xfpu = kmalloc(sizeof(*info->xfpu), GFP_KERNEL);
 	if (!info->xfpu)
-		goto fpu_free;
+		return 0;
 #endif
 	return 1;
-#ifdef ELF_CORE_COPY_XFPREGS
- fpu_free:
-	kfree(info->fpu);
-#endif
- prstatus_free:
-	kfree(info->prstatus);
- psinfo_free:
-	kfree(info->psinfo);
- notes_free:
-	kfree(info->notes);
-	return 0;
 }
 
 static int fill_note_info(struct elfhdr *elf, int phdrs,

fs/btrfs/extent_io.c

@@ -107,6 +107,12 @@ void extent_io_exit(void)
 		list_del(&eb->leak_list);
 		kmem_cache_free(extent_buffer_cache, eb);
 	}
+
+	/*
+	 * Make sure all delayed rcu free are flushed before we
+	 * destroy caches.
+	 */
+	rcu_barrier();
 	if (extent_state_cache)
 		kmem_cache_destroy(extent_state_cache);
 	if (extent_buffer_cache)

fs/btrfs/inode.c

@@ -7076,6 +7076,11 @@ static void init_once(void *foo)
 
 void btrfs_destroy_cachep(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	if (btrfs_inode_cachep)
 		kmem_cache_destroy(btrfs_inode_cachep);
 	if (btrfs_trans_handle_cachep)

fs/btrfs/ioctl.c

@@ -1397,7 +1397,6 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 				u64 *transid, bool readonly,
 				struct btrfs_qgroup_inherit **inherit)
 {
-	struct file *src_file;
 	int namelen;
 	int ret = 0;
 
@@ -1421,25 +1420,24 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 		ret = btrfs_mksubvol(&file->f_path, name, namelen,
 				     NULL, transid, readonly, inherit);
 	} else {
+		struct fd src = fdget(fd);
 		struct inode *src_inode;
-		src_file = fget(fd);
+		if (!src.file) {
-		if (!src_file) {
 			ret = -EINVAL;
 			goto out_drop_write;
 		}
 
-		src_inode = src_file->f_path.dentry->d_inode;
+		src_inode = src.file->f_path.dentry->d_inode;
 		if (src_inode->i_sb != file->f_path.dentry->d_inode->i_sb) {
 			printk(KERN_INFO "btrfs: Snapshot src from "
 			       "another FS\n");
 			ret = -EINVAL;
-			fput(src_file);
+		} else {
-			goto out_drop_write;
+			ret = btrfs_mksubvol(&file->f_path, name, namelen,
+					     BTRFS_I(src_inode)->root,
+					     transid, readonly, inherit);
 		}
-		ret = btrfs_mksubvol(&file->f_path, name, namelen,
+		fdput(src);
-				     BTRFS_I(src_inode)->root,
-				     transid, readonly, inherit);
-		fput(src_file);
 	}
 out_drop_write:
 	mnt_drop_write_file(file);
@@ -2341,7 +2339,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 {
 	struct inode *inode = fdentry(file)->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct file *src_file;
+	struct fd src_file;
 	struct inode *src;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_path *path;
@@ -2376,24 +2374,24 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 	if (ret)
 		return ret;
 
-	src_file = fget(srcfd);
+	src_file = fdget(srcfd);
-	if (!src_file) {
+	if (!src_file.file) {
 		ret = -EBADF;
 		goto out_drop_write;
 	}
 
 	ret = -EXDEV;
-	if (src_file->f_path.mnt != file->f_path.mnt)
+	if (src_file.file->f_path.mnt != file->f_path.mnt)
 		goto out_fput;
 
-	src = src_file->f_dentry->d_inode;
+	src = src_file.file->f_dentry->d_inode;
 
 	ret = -EINVAL;
 	if (src == inode)
 		goto out_fput;
 
 	/* the src must be open for reading */
-	if (!(src_file->f_mode & FMODE_READ))
+	if (!(src_file.file->f_mode & FMODE_READ))
 		goto out_fput;
 
 	/* don't make the dst file partly checksummed */
@@ -2724,7 +2722,7 @@ out_unlock:
 	vfree(buf);
 	btrfs_free_path(path);
 out_fput:
-	fput(src_file);
+	fdput(src_file);
 out_drop_write:
 	mnt_drop_write_file(file);
 	return ret;

fs/btrfs/reada.c

@@ -68,7 +68,7 @@ struct reada_extent {
 	u32			blocksize;
 	int			err;
 	struct list_head	extctl;
-	struct kref		refcnt;
+	int 			refcnt;
 	spinlock_t		lock;
 	struct reada_zone	*zones[BTRFS_MAX_MIRRORS];
 	int			nzones;
@@ -126,7 +126,7 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree, index);
 	if (re)
-		kref_get(&re->refcnt);
+		re->refcnt++;
 	spin_unlock(&fs_info->reada_lock);
 
 	if (!re)
@@ -336,7 +336,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree, index);
 	if (re)
-		kref_get(&re->refcnt);
+		re->refcnt++;
 	spin_unlock(&fs_info->reada_lock);
 
 	if (re)
@@ -352,7 +352,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	re->top = *top;
 	INIT_LIST_HEAD(&re->extctl);
 	spin_lock_init(&re->lock);
-	kref_init(&re->refcnt);
+	re->refcnt = 1;
 
 	/*
 	 * map block
@@ -398,7 +398,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	if (ret == -EEXIST) {
 		re_exist = radix_tree_lookup(&fs_info->reada_tree, index);
 		BUG_ON(!re_exist);
-		kref_get(&re_exist->refcnt);
+		re_exist->refcnt++;
 		spin_unlock(&fs_info->reada_lock);
 		goto error;
 	}
@@ -465,10 +465,6 @@ error:
 	return re_exist;
 }
 
-static void reada_kref_dummy(struct kref *kr)
-{
-}
-
 static void reada_extent_put(struct btrfs_fs_info *fs_info,
 			     struct reada_extent *re)
 {
@@ -476,7 +472,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info,
 	unsigned long index = re->logical >> PAGE_CACHE_SHIFT;
 
 	spin_lock(&fs_info->reada_lock);
-	if (!kref_put(&re->refcnt, reada_kref_dummy)) {
+	if (--re->refcnt) {
 		spin_unlock(&fs_info->reada_lock);
 		return;
 	}
@@ -671,7 +667,7 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 		return 0;
 	}
 	dev->reada_next = re->logical + re->blocksize;
-	kref_get(&re->refcnt);
+	re->refcnt++;
 
 	spin_unlock(&fs_info->reada_lock);
 

fs/ceph/inode.c

@@ -1104,7 +1104,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 				pr_err("fill_trace bad get_inode "
 				       "%llx.%llx\n", vino.ino, vino.snap);
 				err = PTR_ERR(in);
-				d_delete(dn);
+				d_drop(dn);
 				goto done;
 			}
 			dn = splice_dentry(dn, in, &have_lease, true);
@@ -1277,7 +1277,7 @@ retry_lookup:
 			in = ceph_get_inode(parent->d_sb, vino);
 			if (IS_ERR(in)) {
 				dout("new_inode badness\n");
-				d_delete(dn);
+				d_drop(dn);
 				dput(dn);
 				err = PTR_ERR(in);
 				goto out;

fs/ceph/super.c

@@ -603,6 +603,11 @@ bad_cap:
 
 static void destroy_caches(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ceph_inode_cachep);
 	kmem_cache_destroy(ceph_cap_cachep);
 	kmem_cache_destroy(ceph_dentry_cachep);

fs/cifs/cifsfs.c

@@ -968,6 +968,11 @@ cifs_init_inodecache(void)
 static void
 cifs_destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(cifs_inode_cachep);
 }
 

fs/coda/inode.c

@@ -85,6 +85,11 @@ int coda_init_inodecache(void)
 
 void coda_destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(coda_inode_cachep);
 }
 
@@ -107,43 +112,41 @@ static const struct super_operations coda_super_operations =
 
 static int get_device_index(struct coda_mount_data *data)
 {
-	struct file *file;
+	struct fd f;
 	struct inode *inode;
 	int idx;
 
-	if(data == NULL) {
+	if (data == NULL) {
 		printk("coda_read_super: Bad mount data\n");
 		return -1;
 	}
 
-	if(data->version != CODA_MOUNT_VERSION) {
+	if (data->version != CODA_MOUNT_VERSION) {
 		printk("coda_read_super: Bad mount version\n");
 		return -1;
 	}
 
-	file = fget(data->fd);
+	f = fdget(data->fd);
-	inode = NULL;
+	if (!f.file)
-	if(file)
+		goto Ebadf;
-		inode = file->f_path.dentry->d_inode;
+	inode = f.file->f_path.dentry->d_inode;
-	
+	if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) {
-	if(!inode || !S_ISCHR(inode->i_mode) ||
+		fdput(f);
-	   imajor(inode) != CODA_PSDEV_MAJOR) {
+		goto Ebadf;
-		if(file)
-			fput(file);
-
-		printk("coda_read_super: Bad file\n");
-		return -1;
 	}
 
 	idx = iminor(inode);
-	fput(file);
+	fdput(f);
 
-	if(idx < 0 || idx >= MAX_CODADEVS) {
+	if (idx < 0 || idx >= MAX_CODADEVS) {
 		printk("coda_read_super: Bad minor number\n");
 		return -1;
 	}
 
 	return idx;
+Ebadf:
+	printk("coda_read_super: Bad file\n");
+	return -1;
 }
 
 static int coda_fill_super(struct super_block *sb, void *data, int silent)

fs/compat.c

@@ -870,22 +870,20 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd,
 	struct compat_old_linux_dirent __user *dirent, unsigned int count)
 {
 	int error;
-	struct file *file;
+	struct fd f = fdget(fd);
-	int fput_needed;
 	struct compat_readdir_callback buf;
 
-	file = fget_light(fd, &fput_needed);
+	if (!f.file)
-	if (!file)
 		return -EBADF;
 
 	buf.result = 0;
 	buf.dirent = dirent;
 
-	error = vfs_readdir(file, compat_fillonedir, &buf);
+	error = vfs_readdir(f.file, compat_fillonedir, &buf);
 	if (buf.result)
 		error = buf.result;
 
-	fput_light(file, fput_needed);
+	fdput(f);
 	return error;
 }
 
@@ -949,17 +947,16 @@ efault:
 asmlinkage long compat_sys_getdents(unsigned int fd,
 		struct compat_linux_dirent __user *dirent, unsigned int count)
 {
-	struct file * file;
+	struct fd f;
 	struct compat_linux_dirent __user * lastdirent;
 	struct compat_getdents_callback buf;
-	int fput_needed;
 	int error;
 
 	if (!access_ok(VERIFY_WRITE, dirent, count))
 		return -EFAULT;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
 	buf.current_dir = dirent;
@@ -967,17 +964,17 @@ asmlinkage long compat_sys_getdents(unsigned int fd,
 	buf.count = count;
 	buf.error = 0;
 
-	error = vfs_readdir(file, compat_filldir, &buf);
+	error = vfs_readdir(f.file, compat_filldir, &buf);
 	if (error >= 0)
 		error = buf.error;
 	lastdirent = buf.previous;
 	if (lastdirent) {
-		if (put_user(file->f_pos, &lastdirent->d_off))
+		if (put_user(f.file->f_pos, &lastdirent->d_off))
 			error = -EFAULT;
 		else
 			error = count - buf.count;
 	}
-	fput_light(file, fput_needed);
+	fdput(f);
 	return error;
 }
 
@@ -1035,17 +1032,16 @@ efault:
 asmlinkage long compat_sys_getdents64(unsigned int fd,
 		struct linux_dirent64 __user * dirent, unsigned int count)
 {
-	struct file * file;
+	struct fd f;
 	struct linux_dirent64 __user * lastdirent;
 	struct compat_getdents_callback64 buf;
-	int fput_needed;
 	int error;
 
 	if (!access_ok(VERIFY_WRITE, dirent, count))
 		return -EFAULT;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
 	buf.current_dir = dirent;
@@ -1053,18 +1049,18 @@ asmlinkage long compat_sys_getdents64(unsigned int fd,
 	buf.count = count;
 	buf.error = 0;
 
-	error = vfs_readdir(file, compat_filldir64, &buf);
+	error = vfs_readdir(f.file, compat_filldir64, &buf);
 	if (error >= 0)
 		error = buf.error;
 	lastdirent = buf.previous;
 	if (lastdirent) {
-		typeof(lastdirent->d_off) d_off = file->f_pos;
+		typeof(lastdirent->d_off) d_off = f.file->f_pos;
 		if (__put_user_unaligned(d_off, &lastdirent->d_off))
 			error = -EFAULT;
 		else
 			error = count - buf.count;
 	}
-	fput_light(file, fput_needed);
+	fdput(f);
 	return error;
 }
 #endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */
@@ -1152,18 +1148,16 @@ asmlinkage ssize_t
 compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec,
 		 unsigned long vlen)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
-	int fput_needed;
 	ssize_t ret;
 	loff_t pos;
 
-	file = fget_light(fd, &fput_needed);
+	if (!f.file)
-	if (!file)
 		return -EBADF;
-	pos = file->f_pos;
+	pos = f.file->f_pos;
-	ret = compat_readv(file, vec, vlen, &pos);
+	ret = compat_readv(f.file, vec, vlen, &pos);
-	file->f_pos = pos;
+	f.file->f_pos = pos;
-	fput_light(file, fput_needed);
+	fdput(f);
 	return ret;
 }
 
@@ -1171,19 +1165,18 @@ asmlinkage ssize_t
 compat_sys_preadv64(unsigned long fd, const struct compat_iovec __user *vec,
 		    unsigned long vlen, loff_t pos)
 {
-	struct file *file;
+	struct fd f;
-	int fput_needed;
 	ssize_t ret;
 
 	if (pos < 0)
 		return -EINVAL;
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 	ret = -ESPIPE;
-	if (file->f_mode & FMODE_PREAD)
+	if (f.file->f_mode & FMODE_PREAD)
-		ret = compat_readv(file, vec, vlen, &pos);
+		ret = compat_readv(f.file, vec, vlen, &pos);
-	fput_light(file, fput_needed);
+	fdput(f);
 	return ret;
 }
 
@@ -1221,18 +1214,16 @@ asmlinkage ssize_t
 compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec,
 		  unsigned long vlen)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
-	int fput_needed;
 	ssize_t ret;
 	loff_t pos;
 
-	file = fget_light(fd, &fput_needed);
+	if (!f.file)
-	if (!file)
 		return -EBADF;
-	pos = file->f_pos;
+	pos = f.file->f_pos;
-	ret = compat_writev(file, vec, vlen, &pos);
+	ret = compat_writev(f.file, vec, vlen, &pos);
-	file->f_pos = pos;
+	f.file->f_pos = pos;
-	fput_light(file, fput_needed);
+	fdput(f);
 	return ret;
 }
 
@@ -1240,19 +1231,18 @@ asmlinkage ssize_t
 compat_sys_pwritev64(unsigned long fd, const struct compat_iovec __user *vec,
 		     unsigned long vlen, loff_t pos)
 {
-	struct file *file;
+	struct fd f;
-	int fput_needed;
 	ssize_t ret;
 
 	if (pos < 0)
 		return -EINVAL;
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 	ret = -ESPIPE;
-	if (file->f_mode & FMODE_PWRITE)
+	if (f.file->f_mode & FMODE_PWRITE)
-		ret = compat_writev(file, vec, vlen, &pos);
+		ret = compat_writev(f.file, vec, vlen, &pos);
-	fput_light(file, fput_needed);
+	fdput(f);
 	return ret;
 }
 
@@ -1802,3 +1792,25 @@ compat_sys_open_by_handle_at(int mountdirfd,
 	return do_handle_open(mountdirfd, handle, flags);
 }
 #endif
+
+#ifdef __ARCH_WANT_COMPAT_SYS_SENDFILE
+asmlinkage long compat_sys_sendfile(int out_fd, int in_fd,
+				    compat_off_t __user *offset, compat_size_t count)
+{
+	loff_t pos;
+	off_t off;
+	ssize_t ret;
+
+	if (offset) {
+		if (unlikely(get_user(off, offset)))
+			return -EFAULT;
+		pos = off;
+		ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS);
+		if (unlikely(put_user(pos, offset)))
+			return -EFAULT;
+		return ret;
+	}
+
+	return do_sendfile(out_fd, in_fd, NULL, count, 0);
+}
+#endif /* __ARCH_WANT_COMPAT_SYS_SENDFILE */

fs/compat_ioctl.c

@@ -1539,16 +1539,13 @@ static int compat_ioctl_check_table(unsigned int xcmd)
 asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 				unsigned long arg)
 {
-	struct file *filp;
+	struct fd f = fdget(fd);
 	int error = -EBADF;
-	int fput_needed;
+	if (!f.file)
-
-	filp = fget_light(fd, &fput_needed);
-	if (!filp)
 		goto out;
 
 	/* RED-PEN how should LSM module know it's handling 32bit? */
-	error = security_file_ioctl(filp, cmd, arg);
+	error = security_file_ioctl(f.file, cmd, arg);
 	if (error)
 		goto out_fput;
 
@@ -1568,30 +1565,30 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 #if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
 	case FS_IOC_RESVSP_32:
 	case FS_IOC_RESVSP64_32:
-		error = compat_ioctl_preallocate(filp, compat_ptr(arg));
+		error = compat_ioctl_preallocate(f.file, compat_ptr(arg));
 		goto out_fput;
 #else
 	case FS_IOC_RESVSP:
 	case FS_IOC_RESVSP64:
-		error = ioctl_preallocate(filp, compat_ptr(arg));
+		error = ioctl_preallocate(f.file, compat_ptr(arg));
 		goto out_fput;
 #endif
 
 	case FIBMAP:
 	case FIGETBSZ:
 	case FIONREAD:
-		if (S_ISREG(filp->f_path.dentry->d_inode->i_mode))
+		if (S_ISREG(f.file->f_path.dentry->d_inode->i_mode))
 			break;
 		/*FALL THROUGH*/
 
 	default:
-		if (filp->f_op && filp->f_op->compat_ioctl) {
+		if (f.file->f_op && f.file->f_op->compat_ioctl) {
-			error = filp->f_op->compat_ioctl(filp, cmd, arg);
+			error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
 			if (error != -ENOIOCTLCMD)
 				goto out_fput;
 		}
 
-		if (!filp->f_op || !filp->f_op->unlocked_ioctl)
+		if (!f.file->f_op || !f.file->f_op->unlocked_ioctl)
 			goto do_ioctl;
 		break;
 	}
@@ -1599,7 +1596,7 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 	if (compat_ioctl_check_table(XFORM(cmd)))
 		goto found_handler;
 
-	error = do_ioctl_trans(fd, cmd, arg, filp);
+	error = do_ioctl_trans(fd, cmd, arg, f.file);
 	if (error == -ENOIOCTLCMD)
 		error = -ENOTTY;
 
@@ -1608,9 +1605,9 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
  found_handler:
 	arg = (unsigned long)compat_ptr(arg);
  do_ioctl:
-	error = do_vfs_ioctl(filp, fd, cmd, arg);
+	error = do_vfs_ioctl(f.file, fd, cmd, arg);
  out_fput:
-	fput_light(filp, fput_needed);
+	fdput(f);
  out:
 	return error;
 }

fs/coredump.c

@@ -0,0 +1,686 @@
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/stat.h>
+#include <linux/fcntl.h>
+#include <linux/swap.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/perf_event.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+#include <linux/key.h>
+#include <linux/personality.h>
+#include <linux/binfmts.h>
+#include <linux/utsname.h>
+#include <linux/pid_namespace.h>
+#include <linux/module.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/tsacct_kern.h>
+#include <linux/cn_proc.h>
+#include <linux/audit.h>
+#include <linux/tracehook.h>
+#include <linux/kmod.h>
+#include <linux/fsnotify.h>
+#include <linux/fs_struct.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/oom.h>
+#include <linux/compat.h>
+
+#include <asm/uaccess.h>
+#include <asm/mmu_context.h>
+#include <asm/tlb.h>
+#include <asm/exec.h>
+
+#include <trace/events/task.h>
+#include "internal.h"
+
+#include <trace/events/sched.h>
+
+int core_uses_pid;
+char core_pattern[CORENAME_MAX_SIZE] = "core";
+unsigned int core_pipe_limit;
+
+struct core_name {
+	char *corename;
+	int used, size;
+};
+static atomic_t call_count = ATOMIC_INIT(1);
+
+/* The maximal length of core_pattern is also specified in sysctl.c */
+
+static int expand_corename(struct core_name *cn)
+{
+	char *old_corename = cn->corename;
+
+	cn->size = CORENAME_MAX_SIZE * atomic_inc_return(&call_count);
+	cn->corename = krealloc(old_corename, cn->size, GFP_KERNEL);
+
+	if (!cn->corename) {
+		kfree(old_corename);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int cn_printf(struct core_name *cn, const char *fmt, ...)
+{
+	char *cur;
+	int need;
+	int ret;
+	va_list arg;
+
+	va_start(arg, fmt);
+	need = vsnprintf(NULL, 0, fmt, arg);
+	va_end(arg);
+
+	if (likely(need < cn->size - cn->used - 1))
+		goto out_printf;
+
+	ret = expand_corename(cn);
+	if (ret)
+		goto expand_fail;
+
+out_printf:
+	cur = cn->corename + cn->used;
+	va_start(arg, fmt);
+	vsnprintf(cur, need + 1, fmt, arg);
+	va_end(arg);
+	cn->used += need;
+	return 0;
+
+expand_fail:
+	return ret;
+}
+
+static void cn_escape(char *str)
+{
+	for (; *str; str++)
+		if (*str == '/')
+			*str = '!';
+}
+
+static int cn_print_exe_file(struct core_name *cn)
+{
+	struct file *exe_file;
+	char *pathbuf, *path;
+	int ret;
+
+	exe_file = get_mm_exe_file(current->mm);
+	if (!exe_file) {
+		char *commstart = cn->corename + cn->used;
+		ret = cn_printf(cn, "%s (path unknown)", current->comm);
+		cn_escape(commstart);
+		return ret;
+	}
+
+	pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
+	if (!pathbuf) {
+		ret = -ENOMEM;
+		goto put_exe_file;
+	}
+
+	path = d_path(&exe_file->f_path, pathbuf, PATH_MAX);
+	if (IS_ERR(path)) {
+		ret = PTR_ERR(path);
+		goto free_buf;
+	}
+
+	cn_escape(path);
+
+	ret = cn_printf(cn, "%s", path);
+
+free_buf:
+	kfree(pathbuf);
+put_exe_file:
+	fput(exe_file);
+	return ret;
+}
+
+/* format_corename will inspect the pattern parameter, and output a
+ * name into corename, which must have space for at least
+ * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
+ */
+static int format_corename(struct core_name *cn, long signr)
+{
+	const struct cred *cred = current_cred();
+	const char *pat_ptr = core_pattern;
+	int ispipe = (*pat_ptr == '|');
+	int pid_in_pattern = 0;
+	int err = 0;
+
+	cn->size = CORENAME_MAX_SIZE * atomic_read(&call_count);
+	cn->corename = kmalloc(cn->size, GFP_KERNEL);
+	cn->used = 0;
+
+	if (!cn->corename)
+		return -ENOMEM;
+
+	/* Repeat as long as we have more pattern to process and more output
+	   space */
+	while (*pat_ptr) {
+		if (*pat_ptr != '%') {
+			if (*pat_ptr == 0)
+				goto out;
+			err = cn_printf(cn, "%c", *pat_ptr++);
+		} else {
+			switch (*++pat_ptr) {
+			/* single % at the end, drop that */
+			case 0:
+				goto out;
+			/* Double percent, output one percent */
+			case '%':
+				err = cn_printf(cn, "%c", '%');
+				break;
+			/* pid */
+			case 'p':
+				pid_in_pattern = 1;
+				err = cn_printf(cn, "%d",
+					      task_tgid_vnr(current));
+				break;
+			/* uid */
+			case 'u':
+				err = cn_printf(cn, "%d", cred->uid);
+				break;
+			/* gid */
+			case 'g':
+				err = cn_printf(cn, "%d", cred->gid);
+				break;
+			/* signal that caused the coredump */
+			case 's':
+				err = cn_printf(cn, "%ld", signr);
+				break;
+			/* UNIX time of coredump */
+			case 't': {
+				struct timeval tv;
+				do_gettimeofday(&tv);
+				err = cn_printf(cn, "%lu", tv.tv_sec);
+				break;
+			}
+			/* hostname */
+			case 'h': {
+				char *namestart = cn->corename + cn->used;
+				down_read(&uts_sem);
+				err = cn_printf(cn, "%s",
+					      utsname()->nodename);
+				up_read(&uts_sem);
+				cn_escape(namestart);
+				break;
+			}
+			/* executable */
+			case 'e': {
+				char *commstart = cn->corename + cn->used;
+				err = cn_printf(cn, "%s", current->comm);
+				cn_escape(commstart);
+				break;
+			}
+			case 'E':
+				err = cn_print_exe_file(cn);
+				break;
+			/* core limit size */
+			case 'c':
+				err = cn_printf(cn, "%lu",
+					      rlimit(RLIMIT_CORE));
+				break;
+			default:
+				break;
+			}
+			++pat_ptr;
+		}
+
+		if (err)
+			return err;
+	}
+
+	/* Backward compatibility with core_uses_pid:
+	 *
+	 * If core_pattern does not include a %p (as is the default)
+	 * and core_uses_pid is set, then .%pid will be appended to
+	 * the filename. Do not do this for piped commands. */
+	if (!ispipe && !pid_in_pattern && core_uses_pid) {
+		err = cn_printf(cn, ".%d", task_tgid_vnr(current));
+		if (err)
+			return err;
+	}
+out:
+	return ispipe;
+}
+
+static int zap_process(struct task_struct *start, int exit_code)
+{
+	struct task_struct *t;
+	int nr = 0;
+
+	start->signal->flags = SIGNAL_GROUP_EXIT;
+	start->signal->group_exit_code = exit_code;
+	start->signal->group_stop_count = 0;
+
+	t = start;
+	do {
+		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
+		if (t != current && t->mm) {
+			sigaddset(&t->pending.signal, SIGKILL);
+			signal_wake_up(t, 1);
+			nr++;
+		}
+	} while_each_thread(start, t);
+
+	return nr;
+}
+
+static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
+				struct core_state *core_state, int exit_code)
+{
+	struct task_struct *g, *p;
+	unsigned long flags;
+	int nr = -EAGAIN;
+
+	spin_lock_irq(&tsk->sighand->siglock);
+	if (!signal_group_exit(tsk->signal)) {
+		mm->core_state = core_state;
+		nr = zap_process(tsk, exit_code);
+	}
+	spin_unlock_irq(&tsk->sighand->siglock);
+	if (unlikely(nr < 0))
+		return nr;
+
+	if (atomic_read(&mm->mm_users) == nr + 1)
+		goto done;
+	/*
+	 * We should find and kill all tasks which use this mm, and we should
+	 * count them correctly into ->nr_threads. We don't take tasklist
+	 * lock, but this is safe wrt:
+	 *
+	 * fork:
+	 *	None of sub-threads can fork after zap_process(leader). All
+	 *	processes which were created before this point should be
+	 *	visible to zap_threads() because copy_process() adds the new
+	 *	process to the tail of init_task.tasks list, and lock/unlock
+	 *	of ->siglock provides a memory barrier.
+	 *
+	 * do_exit:
+	 *	The caller holds mm->mmap_sem. This means that the task which
+	 *	uses this mm can't pass exit_mm(), so it can't exit or clear
+	 *	its ->mm.
+	 *
+	 * de_thread:
+	 *	It does list_replace_rcu(&leader->tasks, &current->tasks),
+	 *	we must see either old or new leader, this does not matter.
+	 *	However, it can change p->sighand, so lock_task_sighand(p)
+	 *	must be used. Since p->mm != NULL and we hold ->mmap_sem
+	 *	it can't fail.
+	 *
+	 *	Note also that "g" can be the old leader with ->mm == NULL
+	 *	and already unhashed and thus removed from ->thread_group.
+	 *	This is OK, __unhash_process()->list_del_rcu() does not
+	 *	clear the ->next pointer, we will find the new leader via
+	 *	next_thread().
+	 */
+	rcu_read_lock();
+	for_each_process(g) {
+		if (g == tsk->group_leader)
+			continue;
+		if (g->flags & PF_KTHREAD)
+			continue;
+		p = g;
+		do {
+			if (p->mm) {
+				if (unlikely(p->mm == mm)) {
+					lock_task_sighand(p, &flags);
+					nr += zap_process(p, exit_code);
+					unlock_task_sighand(p, &flags);
+				}
+				break;
+			}
+		} while_each_thread(g, p);
+	}
+	rcu_read_unlock();
+done:
+	atomic_set(&core_state->nr_threads, nr);
+	return nr;
+}
+
+static int coredump_wait(int exit_code, struct core_state *core_state)
+{
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+	int core_waiters = -EBUSY;
+
+	init_completion(&core_state->startup);
+	core_state->dumper.task = tsk;
+	core_state->dumper.next = NULL;
+
+	down_write(&mm->mmap_sem);
+	if (!mm->core_state)
+		core_waiters = zap_threads(tsk, mm, core_state, exit_code);
+	up_write(&mm->mmap_sem);
+
+	if (core_waiters > 0) {
+		struct core_thread *ptr;
+
+		wait_for_completion(&core_state->startup);
+		/*
+		 * Wait for all the threads to become inactive, so that
+		 * all the thread context (extended register state, like
+		 * fpu etc) gets copied to the memory.
+		 */
+		ptr = core_state->dumper.next;
+		while (ptr != NULL) {
+			wait_task_inactive(ptr->task, 0);
+			ptr = ptr->next;
+		}
+	}
+
+	return core_waiters;
+}
+
+static void coredump_finish(struct mm_struct *mm)
+{
+	struct core_thread *curr, *next;
+	struct task_struct *task;
+
+	next = mm->core_state->dumper.next;
+	while ((curr = next) != NULL) {
+		next = curr->next;
+		task = curr->task;
+		/*
+		 * see exit_mm(), curr->task must not see
+		 * ->task == NULL before we read ->next.
+		 */
+		smp_mb();
+		curr->task = NULL;
+		wake_up_process(task);
+	}
+
+	mm->core_state = NULL;
+}
+
+static void wait_for_dump_helpers(struct file *file)
+{
+	struct pipe_inode_info *pipe;
+
+	pipe = file->f_path.dentry->d_inode->i_pipe;
+
+	pipe_lock(pipe);
+	pipe->readers++;
+	pipe->writers--;
+
+	while ((pipe->readers > 1) && (!signal_pending(current))) {
+		wake_up_interruptible_sync(&pipe->wait);
+		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+		pipe_wait(pipe);
+	}
+
+	pipe->readers--;
+	pipe->writers++;
+	pipe_unlock(pipe);
+
+}
+
+/*
+ * umh_pipe_setup
+ * helper function to customize the process used
+ * to collect the core in userspace.  Specifically
+ * it sets up a pipe and installs it as fd 0 (stdin)
+ * for the process.  Returns 0 on success, or
+ * PTR_ERR on failure.
+ * Note that it also sets the core limit to 1.  This
+ * is a special value that we use to trap recursive
+ * core dumps
+ */
+static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
+{
+	struct file *files[2];
+	struct coredump_params *cp = (struct coredump_params *)info->data;
+	int err = create_pipe_files(files, 0);
+	if (err)
+		return err;
+
+	cp->file = files[1];
+
+	replace_fd(0, files[0], 0);
+	/* and disallow core files too */
+	current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
+
+	return 0;
+}
+
+void do_coredump(long signr, int exit_code, struct pt_regs *regs)
+{
+	struct core_state core_state;
+	struct core_name cn;
+	struct mm_struct *mm = current->mm;
+	struct linux_binfmt * binfmt;
+	const struct cred *old_cred;
+	struct cred *cred;
+	int retval = 0;
+	int flag = 0;
+	int ispipe;
+	struct files_struct *displaced;
+	bool need_nonrelative = false;
+	static atomic_t core_dump_count = ATOMIC_INIT(0);
+	struct coredump_params cprm = {
+		.signr = signr,
+		.regs = regs,
+		.limit = rlimit(RLIMIT_CORE),
+		/*
+		 * We must use the same mm->flags while dumping core to avoid
+		 * inconsistency of bit flags, since this flag is not protected
+		 * by any locks.
+		 */
+		.mm_flags = mm->flags,
+	};
+
+	audit_core_dumps(signr);
+
+	binfmt = mm->binfmt;
+	if (!binfmt || !binfmt->core_dump)
+		goto fail;
+	if (!__get_dumpable(cprm.mm_flags))
+		goto fail;
+
+	cred = prepare_creds();
+	if (!cred)
+		goto fail;
+	/*
+	 * We cannot trust fsuid as being the "true" uid of the process
+	 * nor do we know its entire history. We only know it was tainted
+	 * so we dump it as root in mode 2, and only into a controlled
+	 * environment (pipe handler or fully qualified path).
+	 */
+	if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
+		/* Setuid core dump mode */
+		flag = O_EXCL;		/* Stop rewrite attacks */
+		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
+		need_nonrelative = true;
+	}
+
+	retval = coredump_wait(exit_code, &core_state);
+	if (retval < 0)
+		goto fail_creds;
+
+	old_cred = override_creds(cred);
+
+	/*
+	 * Clear any false indication of pending signals that might
+	 * be seen by the filesystem code called to write the core file.
+	 */
+	clear_thread_flag(TIF_SIGPENDING);
+
+	ispipe = format_corename(&cn, signr);
+
+ 	if (ispipe) {
+		int dump_count;
+		char **helper_argv;
+
+		if (ispipe < 0) {
+			printk(KERN_WARNING "format_corename failed\n");
+			printk(KERN_WARNING "Aborting core\n");
+			goto fail_corename;
+		}
+
+		if (cprm.limit == 1) {
+			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
+			 *
+			 * Normally core limits are irrelevant to pipes, since
+			 * we're not writing to the file system, but we use
+			 * cprm.limit of 1 here as a speacial value, this is a
+			 * consistent way to catch recursive crashes.
+			 * We can still crash if the core_pattern binary sets
+			 * RLIM_CORE = !1, but it runs as root, and can do
+			 * lots of stupid things.
+			 *
+			 * Note that we use task_tgid_vnr here to grab the pid
+			 * of the process group leader.  That way we get the
+			 * right pid if a thread in a multi-threaded
+			 * core_pattern process dies.
+			 */
+			printk(KERN_WARNING
+				"Process %d(%s) has RLIMIT_CORE set to 1\n",
+				task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Aborting core\n");
+			goto fail_unlock;
+		}
+		cprm.limit = RLIM_INFINITY;
+
+		dump_count = atomic_inc_return(&core_dump_count);
+		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
+			printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
+			       task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Skipping core dump\n");
+			goto fail_dropcount;
+		}
+
+		helper_argv = argv_split(GFP_KERNEL, cn.corename+1, NULL);
+		if (!helper_argv) {
+			printk(KERN_WARNING "%s failed to allocate memory\n",
+			       __func__);
+			goto fail_dropcount;
+		}
+
+		retval = call_usermodehelper_fns(helper_argv[0], helper_argv,
+					NULL, UMH_WAIT_EXEC, umh_pipe_setup,
+					NULL, &cprm);
+		argv_free(helper_argv);
+		if (retval) {
+ 			printk(KERN_INFO "Core dump to %s pipe failed\n",
+			       cn.corename);
+			goto close_fail;
+ 		}
+	} else {
+		struct inode *inode;
+
+		if (cprm.limit < binfmt->min_coredump)
+			goto fail_unlock;
+
+		if (need_nonrelative && cn.corename[0] != '/') {
+			printk(KERN_WARNING "Pid %d(%s) can only dump core "\
+				"to fully qualified path!\n",
+				task_tgid_vnr(current), current->comm);
+			printk(KERN_WARNING "Skipping core dump\n");
+			goto fail_unlock;
+		}
+
+		cprm.file = filp_open(cn.corename,
+				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
+				 0600);
+		if (IS_ERR(cprm.file))
+			goto fail_unlock;
+
+		inode = cprm.file->f_path.dentry->d_inode;
+		if (inode->i_nlink > 1)
+			goto close_fail;
+		if (d_unhashed(cprm.file->f_path.dentry))
+			goto close_fail;
+		/*
+		 * AK: actually i see no reason to not allow this for named
+		 * pipes etc, but keep the previous behaviour for now.
+		 */
+		if (!S_ISREG(inode->i_mode))
+			goto close_fail;
+		/*
+		 * Dont allow local users get cute and trick others to coredump
+		 * into their pre-created files.
+		 */
+		if (!uid_eq(inode->i_uid, current_fsuid()))
+			goto close_fail;
+		if (!cprm.file->f_op || !cprm.file->f_op->write)
+			goto close_fail;
+		if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
+			goto close_fail;
+	}
+
+	/* get us an unshared descriptor table; almost always a no-op */
+	retval = unshare_files(&displaced);
+	if (retval)
+		goto close_fail;
+	if (displaced)
+		put_files_struct(displaced);
+	retval = binfmt->core_dump(&cprm);
+	if (retval)
+		current->signal->group_exit_code |= 0x80;
+
+	if (ispipe && core_pipe_limit)
+		wait_for_dump_helpers(cprm.file);
+close_fail:
+	if (cprm.file)
+		filp_close(cprm.file, NULL);
+fail_dropcount:
+	if (ispipe)
+		atomic_dec(&core_dump_count);
+fail_unlock:
+	kfree(cn.corename);
+fail_corename:
+	coredump_finish(mm);
+	revert_creds(old_cred);
+fail_creds:
+	put_cred(cred);
+fail:
+	return;
+}
+
+/*
+ * Core dumping helper functions.  These are the only things you should
+ * do on a core-file: use only these functions to write out all the
+ * necessary info.
+ */
+int dump_write(struct file *file, const void *addr, int nr)
+{
+	return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr;
+}
+EXPORT_SYMBOL(dump_write);
+
+int dump_seek(struct file *file, loff_t off)
+{
+	int ret = 1;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
+			return 0;
+	} else {
+		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
+
+		if (!buf)
+			return 0;
+		while (off > 0) {
+			unsigned long n = off;
+
+			if (n > PAGE_SIZE)
+				n = PAGE_SIZE;
+			if (!dump_write(file, buf, n)) {
+				ret = 0;
+				break;
+			}
+			off -= n;
+		}
+		free_page((unsigned long)buf);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(dump_seek);

fs/dcache.c

@@ -2113,7 +2113,7 @@ again:
 	inode = dentry->d_inode;
 	isdir = S_ISDIR(inode->i_mode);
 	if (dentry->d_count == 1) {
-		if (inode && !spin_trylock(&inode->i_lock)) {
+		if (!spin_trylock(&inode->i_lock)) {
 			spin_unlock(&dentry->d_lock);
 			cpu_relax();
 			goto again;

fs/ecryptfs/main.c

@@ -711,6 +711,12 @@ static void ecryptfs_free_kmem_caches(void)
 {
 	int i;
 
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+
 	for (i = 0; i < ARRAY_SIZE(ecryptfs_cache_infos); i++) {
 		struct ecryptfs_cache_info *info;
 

fs/efs/super.c

@@ -96,6 +96,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(efs_inode_cachep);
 }
 

fs/eventpoll.c

@@ -1810,7 +1810,7 @@ SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
 		int, maxevents, int, timeout)
 {
 	int error;
-	struct file *file;
+	struct fd f;
 	struct eventpoll *ep;
 
 	/* The maximum number of event must be greater than zero */
@@ -1818,38 +1818,33 @@ SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
 		return -EINVAL;
 
 	/* Verify that the area passed by the user is writeable */
-	if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
+	if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event)))
-		error = -EFAULT;
+		return -EFAULT;
-		goto error_return;
-	}
 
 	/* Get the "struct file *" for the eventpoll file */
-	error = -EBADF;
+	f = fdget(epfd);
-	file = fget(epfd);
+	if (!f.file)
-	if (!file)
+		return -EBADF;
-		goto error_return;
 
 	/*
 	 * We have to check that the file structure underneath the fd
 	 * the user passed to us _is_ an eventpoll file.
 	 */
 	error = -EINVAL;
-	if (!is_file_epoll(file))
+	if (!is_file_epoll(f.file))
 		goto error_fput;
 
 	/*
 	 * At this point it is safe to assume that the "private_data" contains
 	 * our own data structure.
 	 */
-	ep = file->private_data;
+	ep = f.file->private_data;
 
 	/* Time to fish for events ... */
 	error = ep_poll(ep, events, maxevents, timeout);
 
 error_fput:
-	fput(file);
+	fdput(f);
-error_return:
-
 	return error;
 }
 

fs/exec.c

@@ -66,19 +66,8 @@
 
 #include <trace/events/sched.h>
 
-int core_uses_pid;
-char core_pattern[CORENAME_MAX_SIZE] = "core";
-unsigned int core_pipe_limit;
 int suid_dumpable = 0;
 
-struct core_name {
-	char *corename;
-	int used, size;
-};
-static atomic_t call_count = ATOMIC_INIT(1);
-
-/* The maximal length of core_pattern is also specified in sysctl.c */
-
 static LIST_HEAD(formats);
 static DEFINE_RWLOCK(binfmt_lock);
 
@@ -1006,40 +995,6 @@ no_thread_group:
 	return 0;
 }
 
-/*
- * These functions flushes out all traces of the currently running executable
- * so that a new one can be started
- */
-static void flush_old_files(struct files_struct * files)
-{
-	long j = -1;
-	struct fdtable *fdt;
-
-	spin_lock(&files->file_lock);
-	for (;;) {
-		unsigned long set, i;
-
-		j++;
-		i = j * BITS_PER_LONG;
-		fdt = files_fdtable(files);
-		if (i >= fdt->max_fds)
-			break;
-		set = fdt->close_on_exec[j];
-		if (!set)
-			continue;
-		fdt->close_on_exec[j] = 0;
-		spin_unlock(&files->file_lock);
-		for ( ; set ; i++,set >>= 1) {
-			if (set & 1) {
-				sys_close(i);
-			}
-		}
-		spin_lock(&files->file_lock);
-
-	}
-	spin_unlock(&files->file_lock);
-}
-
 char *get_task_comm(char *buf, struct task_struct *tsk)
 {
 	/* buf must be at least sizeof(tsk->comm) in size */
@@ -1050,6 +1005,11 @@ char *get_task_comm(char *buf, struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(get_task_comm);
 
+/*
+ * These functions flushes out all traces of the currently running executable
+ * so that a new one can be started
+ */
+
 void set_task_comm(struct task_struct *tsk, char *buf)
 {
 	task_lock(tsk);
@@ -1171,7 +1131,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	current->self_exec_id++;
 			
 	flush_signal_handlers(current, 0);
-	flush_old_files(current->files);
+	do_close_on_exec(current->files);
 }
 EXPORT_SYMBOL(setup_new_exec);
 
@@ -1632,353 +1592,6 @@ void set_binfmt(struct linux_binfmt *new)
 
 EXPORT_SYMBOL(set_binfmt);
 
-static int expand_corename(struct core_name *cn)
-{
-	char *old_corename = cn->corename;
-
-	cn->size = CORENAME_MAX_SIZE * atomic_inc_return(&call_count);
-	cn->corename = krealloc(old_corename, cn->size, GFP_KERNEL);
-
-	if (!cn->corename) {
-		kfree(old_corename);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static int cn_printf(struct core_name *cn, const char *fmt, ...)
-{
-	char *cur;
-	int need;
-	int ret;
-	va_list arg;
-
-	va_start(arg, fmt);
-	need = vsnprintf(NULL, 0, fmt, arg);
-	va_end(arg);
-
-	if (likely(need < cn->size - cn->used - 1))
-		goto out_printf;
-
-	ret = expand_corename(cn);
-	if (ret)
-		goto expand_fail;
-
-out_printf:
-	cur = cn->corename + cn->used;
-	va_start(arg, fmt);
-	vsnprintf(cur, need + 1, fmt, arg);
-	va_end(arg);
-	cn->used += need;
-	return 0;
-
-expand_fail:
-	return ret;
-}
-
-static void cn_escape(char *str)
-{
-	for (; *str; str++)
-		if (*str == '/')
-			*str = '!';
-}
-
-static int cn_print_exe_file(struct core_name *cn)
-{
-	struct file *exe_file;
-	char *pathbuf, *path;
-	int ret;
-
-	exe_file = get_mm_exe_file(current->mm);
-	if (!exe_file) {
-		char *commstart = cn->corename + cn->used;
-		ret = cn_printf(cn, "%s (path unknown)", current->comm);
-		cn_escape(commstart);
-		return ret;
-	}
-
-	pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY);
-	if (!pathbuf) {
-		ret = -ENOMEM;
-		goto put_exe_file;
-	}
-
-	path = d_path(&exe_file->f_path, pathbuf, PATH_MAX);
-	if (IS_ERR(path)) {
-		ret = PTR_ERR(path);
-		goto free_buf;
-	}
-
-	cn_escape(path);
-
-	ret = cn_printf(cn, "%s", path);
-
-free_buf:
-	kfree(pathbuf);
-put_exe_file:
-	fput(exe_file);
-	return ret;
-}
-
-/* format_corename will inspect the pattern parameter, and output a
- * name into corename, which must have space for at least
- * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
- */
-static int format_corename(struct core_name *cn, long signr)
-{
-	const struct cred *cred = current_cred();
-	const char *pat_ptr = core_pattern;
-	int ispipe = (*pat_ptr == '|');
-	int pid_in_pattern = 0;
-	int err = 0;
-
-	cn->size = CORENAME_MAX_SIZE * atomic_read(&call_count);
-	cn->corename = kmalloc(cn->size, GFP_KERNEL);
-	cn->used = 0;
-
-	if (!cn->corename)
-		return -ENOMEM;
-
-	/* Repeat as long as we have more pattern to process and more output
-	   space */
-	while (*pat_ptr) {
-		if (*pat_ptr != '%') {
-			if (*pat_ptr == 0)
-				goto out;
-			err = cn_printf(cn, "%c", *pat_ptr++);
-		} else {
-			switch (*++pat_ptr) {
-			/* single % at the end, drop that */
-			case 0:
-				goto out;
-			/* Double percent, output one percent */
-			case '%':
-				err = cn_printf(cn, "%c", '%');
-				break;
-			/* pid */
-			case 'p':
-				pid_in_pattern = 1;
-				err = cn_printf(cn, "%d",
-					      task_tgid_vnr(current));
-				break;
-			/* uid */
-			case 'u':
-				err = cn_printf(cn, "%d", cred->uid);
-				break;
-			/* gid */
-			case 'g':
-				err = cn_printf(cn, "%d", cred->gid);
-				break;
-			/* signal that caused the coredump */
-			case 's':
-				err = cn_printf(cn, "%ld", signr);
-				break;
-			/* UNIX time of coredump */
-			case 't': {
-				struct timeval tv;
-				do_gettimeofday(&tv);
-				err = cn_printf(cn, "%lu", tv.tv_sec);
-				break;
-			}
-			/* hostname */
-			case 'h': {
-				char *namestart = cn->corename + cn->used;
-				down_read(&uts_sem);
-				err = cn_printf(cn, "%s",
-					      utsname()->nodename);
-				up_read(&uts_sem);
-				cn_escape(namestart);
-				break;
-			}
-			/* executable */
-			case 'e': {
-				char *commstart = cn->corename + cn->used;
-				err = cn_printf(cn, "%s", current->comm);
-				cn_escape(commstart);
-				break;
-			}
-			case 'E':
-				err = cn_print_exe_file(cn);
-				break;
-			/* core limit size */
-			case 'c':
-				err = cn_printf(cn, "%lu",
-					      rlimit(RLIMIT_CORE));
-				break;
-			default:
-				break;
-			}
-			++pat_ptr;
-		}
-
-		if (err)
-			return err;
-	}
-
-	/* Backward compatibility with core_uses_pid:
-	 *
-	 * If core_pattern does not include a %p (as is the default)
-	 * and core_uses_pid is set, then .%pid will be appended to
-	 * the filename. Do not do this for piped commands. */
-	if (!ispipe && !pid_in_pattern && core_uses_pid) {
-		err = cn_printf(cn, ".%d", task_tgid_vnr(current));
-		if (err)
-			return err;
-	}
-out:
-	return ispipe;
-}
-
-static int zap_process(struct task_struct *start, int exit_code)
-{
-	struct task_struct *t;
-	int nr = 0;
-
-	start->signal->flags = SIGNAL_GROUP_EXIT;
-	start->signal->group_exit_code = exit_code;
-	start->signal->group_stop_count = 0;
-
-	t = start;
-	do {
-		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
-		if (t != current && t->mm) {
-			sigaddset(&t->pending.signal, SIGKILL);
-			signal_wake_up(t, 1);
-			nr++;
-		}
-	} while_each_thread(start, t);
-
-	return nr;
-}
-
-static inline int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
-				struct core_state *core_state, int exit_code)
-{
-	struct task_struct *g, *p;
-	unsigned long flags;
-	int nr = -EAGAIN;
-
-	spin_lock_irq(&tsk->sighand->siglock);
-	if (!signal_group_exit(tsk->signal)) {
-		mm->core_state = core_state;
-		nr = zap_process(tsk, exit_code);
-	}
-	spin_unlock_irq(&tsk->sighand->siglock);
-	if (unlikely(nr < 0))
-		return nr;
-
-	if (atomic_read(&mm->mm_users) == nr + 1)
-		goto done;
-	/*
-	 * We should find and kill all tasks which use this mm, and we should
-	 * count them correctly into ->nr_threads. We don't take tasklist
-	 * lock, but this is safe wrt:
-	 *
-	 * fork:
-	 *	None of sub-threads can fork after zap_process(leader). All
-	 *	processes which were created before this point should be
-	 *	visible to zap_threads() because copy_process() adds the new
-	 *	process to the tail of init_task.tasks list, and lock/unlock
-	 *	of ->siglock provides a memory barrier.
-	 *
-	 * do_exit:
-	 *	The caller holds mm->mmap_sem. This means that the task which
-	 *	uses this mm can't pass exit_mm(), so it can't exit or clear
-	 *	its ->mm.
-	 *
-	 * de_thread:
-	 *	It does list_replace_rcu(&leader->tasks, &current->tasks),
-	 *	we must see either old or new leader, this does not matter.
-	 *	However, it can change p->sighand, so lock_task_sighand(p)
-	 *	must be used. Since p->mm != NULL and we hold ->mmap_sem
-	 *	it can't fail.
-	 *
-	 *	Note also that "g" can be the old leader with ->mm == NULL
-	 *	and already unhashed and thus removed from ->thread_group.
-	 *	This is OK, __unhash_process()->list_del_rcu() does not
-	 *	clear the ->next pointer, we will find the new leader via
-	 *	next_thread().
-	 */
-	rcu_read_lock();
-	for_each_process(g) {
-		if (g == tsk->group_leader)
-			continue;
-		if (g->flags & PF_KTHREAD)
-			continue;
-		p = g;
-		do {
-			if (p->mm) {
-				if (unlikely(p->mm == mm)) {
-					lock_task_sighand(p, &flags);
-					nr += zap_process(p, exit_code);
-					unlock_task_sighand(p, &flags);
-				}
-				break;
-			}
-		} while_each_thread(g, p);
-	}
-	rcu_read_unlock();
-done:
-	atomic_set(&core_state->nr_threads, nr);
-	return nr;
-}
-
-static int coredump_wait(int exit_code, struct core_state *core_state)
-{
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
-	int core_waiters = -EBUSY;
-
-	init_completion(&core_state->startup);
-	core_state->dumper.task = tsk;
-	core_state->dumper.next = NULL;
-
-	down_write(&mm->mmap_sem);
-	if (!mm->core_state)
-		core_waiters = zap_threads(tsk, mm, core_state, exit_code);
-	up_write(&mm->mmap_sem);
-
-	if (core_waiters > 0) {
-		struct core_thread *ptr;
-
-		wait_for_completion(&core_state->startup);
-		/*
-		 * Wait for all the threads to become inactive, so that
-		 * all the thread context (extended register state, like
-		 * fpu etc) gets copied to the memory.
-		 */
-		ptr = core_state->dumper.next;
-		while (ptr != NULL) {
-			wait_task_inactive(ptr->task, 0);
-			ptr = ptr->next;
-		}
-	}
-
-	return core_waiters;
-}
-
-static void coredump_finish(struct mm_struct *mm)
-{
-	struct core_thread *curr, *next;
-	struct task_struct *task;
-
-	next = mm->core_state->dumper.next;
-	while ((curr = next) != NULL) {
-		next = curr->next;
-		task = curr->task;
-		/*
-		 * see exit_mm(), curr->task must not see
-		 * ->task == NULL before we read ->next.
-		 */
-		smp_mb();
-		curr->task = NULL;
-		wake_up_process(task);
-	}
-
-	mm->core_state = NULL;
-}
-
 /*
  * set_dumpable converts traditional three-value dumpable to two flags and
  * stores them into mm->flags.  It modifies lower two bits of mm->flags, but
@@ -2020,7 +1633,7 @@ void set_dumpable(struct mm_struct *mm, int value)
 	}
 }
 
-static int __get_dumpable(unsigned long mm_flags)
+int __get_dumpable(unsigned long mm_flags)
 {
 	int ret;
 
@@ -2032,290 +1645,3 @@ int get_dumpable(struct mm_struct *mm)
 {
 	return __get_dumpable(mm->flags);
 }
-
-static void wait_for_dump_helpers(struct file *file)
-{
-	struct pipe_inode_info *pipe;
-
-	pipe = file->f_path.dentry->d_inode->i_pipe;
-
-	pipe_lock(pipe);
-	pipe->readers++;
-	pipe->writers--;
-
-	while ((pipe->readers > 1) && (!signal_pending(current))) {
-		wake_up_interruptible_sync(&pipe->wait);
-		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
-		pipe_wait(pipe);
-	}
-
-	pipe->readers--;
-	pipe->writers++;
-	pipe_unlock(pipe);
-
-}
-
-
-/*
- * umh_pipe_setup
- * helper function to customize the process used
- * to collect the core in userspace.  Specifically
- * it sets up a pipe and installs it as fd 0 (stdin)
- * for the process.  Returns 0 on success, or
- * PTR_ERR on failure.
- * Note that it also sets the core limit to 1.  This
- * is a special value that we use to trap recursive
- * core dumps
- */
-static int umh_pipe_setup(struct subprocess_info *info, struct cred *new)
-{
-	struct file *files[2];
-	struct fdtable *fdt;
-	struct coredump_params *cp = (struct coredump_params *)info->data;
-	struct files_struct *cf = current->files;
-	int err = create_pipe_files(files, 0);
-	if (err)
-		return err;
-
-	cp->file = files[1];
-
-	sys_close(0);
-	fd_install(0, files[0]);
-	spin_lock(&cf->file_lock);
-	fdt = files_fdtable(cf);
-	__set_open_fd(0, fdt);
-	__clear_close_on_exec(0, fdt);
-	spin_unlock(&cf->file_lock);
-
-	/* and disallow core files too */
-	current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1};
-
-	return 0;
-}
-
-void do_coredump(long signr, int exit_code, struct pt_regs *regs)
-{
-	struct core_state core_state;
-	struct core_name cn;
-	struct mm_struct *mm = current->mm;
-	struct linux_binfmt * binfmt;
-	const struct cred *old_cred;
-	struct cred *cred;
-	int retval = 0;
-	int flag = 0;
-	int ispipe;
-	bool need_nonrelative = false;
-	static atomic_t core_dump_count = ATOMIC_INIT(0);
-	struct coredump_params cprm = {
-		.signr = signr,
-		.regs = regs,
-		.limit = rlimit(RLIMIT_CORE),
-		/*
-		 * We must use the same mm->flags while dumping core to avoid
-		 * inconsistency of bit flags, since this flag is not protected
-		 * by any locks.
-		 */
-		.mm_flags = mm->flags,
-	};
-
-	audit_core_dumps(signr);
-
-	binfmt = mm->binfmt;
-	if (!binfmt || !binfmt->core_dump)
-		goto fail;
-	if (!__get_dumpable(cprm.mm_flags))
-		goto fail;
-
-	cred = prepare_creds();
-	if (!cred)
-		goto fail;
-	/*
-	 * We cannot trust fsuid as being the "true" uid of the process
-	 * nor do we know its entire history. We only know it was tainted
-	 * so we dump it as root in mode 2, and only into a controlled
-	 * environment (pipe handler or fully qualified path).
-	 */
-	if (__get_dumpable(cprm.mm_flags) == SUID_DUMPABLE_SAFE) {
-		/* Setuid core dump mode */
-		flag = O_EXCL;		/* Stop rewrite attacks */
-		cred->fsuid = GLOBAL_ROOT_UID;	/* Dump root private */
-		need_nonrelative = true;
-	}
-
-	retval = coredump_wait(exit_code, &core_state);
-	if (retval < 0)
-		goto fail_creds;
-
-	old_cred = override_creds(cred);
-
-	/*
-	 * Clear any false indication of pending signals that might
-	 * be seen by the filesystem code called to write the core file.
-	 */
-	clear_thread_flag(TIF_SIGPENDING);
-
-	ispipe = format_corename(&cn, signr);
-
- 	if (ispipe) {
-		int dump_count;
-		char **helper_argv;
-
-		if (ispipe < 0) {
-			printk(KERN_WARNING "format_corename failed\n");
-			printk(KERN_WARNING "Aborting core\n");
-			goto fail_corename;
-		}
-
-		if (cprm.limit == 1) {
-			/* See umh_pipe_setup() which sets RLIMIT_CORE = 1.
-			 *
-			 * Normally core limits are irrelevant to pipes, since
-			 * we're not writing to the file system, but we use
-			 * cprm.limit of 1 here as a speacial value, this is a
-			 * consistent way to catch recursive crashes.
-			 * We can still crash if the core_pattern binary sets
-			 * RLIM_CORE = !1, but it runs as root, and can do
-			 * lots of stupid things.
-			 *
-			 * Note that we use task_tgid_vnr here to grab the pid
-			 * of the process group leader.  That way we get the
-			 * right pid if a thread in a multi-threaded
-			 * core_pattern process dies.
-			 */
-			printk(KERN_WARNING
-				"Process %d(%s) has RLIMIT_CORE set to 1\n",
-				task_tgid_vnr(current), current->comm);
-			printk(KERN_WARNING "Aborting core\n");
-			goto fail_unlock;
-		}
-		cprm.limit = RLIM_INFINITY;
-
-		dump_count = atomic_inc_return(&core_dump_count);
-		if (core_pipe_limit && (core_pipe_limit < dump_count)) {
-			printk(KERN_WARNING "Pid %d(%s) over core_pipe_limit\n",
-			       task_tgid_vnr(current), current->comm);
-			printk(KERN_WARNING "Skipping core dump\n");
-			goto fail_dropcount;
-		}
-
-		helper_argv = argv_split(GFP_KERNEL, cn.corename+1, NULL);
-		if (!helper_argv) {
-			printk(KERN_WARNING "%s failed to allocate memory\n",
-			       __func__);
-			goto fail_dropcount;
-		}
-
-		retval = call_usermodehelper_fns(helper_argv[0], helper_argv,
-					NULL, UMH_WAIT_EXEC, umh_pipe_setup,
-					NULL, &cprm);
-		argv_free(helper_argv);
-		if (retval) {
- 			printk(KERN_INFO "Core dump to %s pipe failed\n",
-			       cn.corename);
-			goto close_fail;
- 		}
-	} else {
-		struct inode *inode;
-
-		if (cprm.limit < binfmt->min_coredump)
-			goto fail_unlock;
-
-		if (need_nonrelative && cn.corename[0] != '/') {
-			printk(KERN_WARNING "Pid %d(%s) can only dump core "\
-				"to fully qualified path!\n",
-				task_tgid_vnr(current), current->comm);
-			printk(KERN_WARNING "Skipping core dump\n");
-			goto fail_unlock;
-		}
-
-		cprm.file = filp_open(cn.corename,
-				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
-				 0600);
-		if (IS_ERR(cprm.file))
-			goto fail_unlock;
-
-		inode = cprm.file->f_path.dentry->d_inode;
-		if (inode->i_nlink > 1)
-			goto close_fail;
-		if (d_unhashed(cprm.file->f_path.dentry))
-			goto close_fail;
-		/*
-		 * AK: actually i see no reason to not allow this for named
-		 * pipes etc, but keep the previous behaviour for now.
-		 */
-		if (!S_ISREG(inode->i_mode))
-			goto close_fail;
-		/*
-		 * Dont allow local users get cute and trick others to coredump
-		 * into their pre-created files.
-		 */
-		if (!uid_eq(inode->i_uid, current_fsuid()))
-			goto close_fail;
-		if (!cprm.file->f_op || !cprm.file->f_op->write)
-			goto close_fail;
-		if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file))
-			goto close_fail;
-	}
-
-	retval = binfmt->core_dump(&cprm);
-	if (retval)
-		current->signal->group_exit_code |= 0x80;
-
-	if (ispipe && core_pipe_limit)
-		wait_for_dump_helpers(cprm.file);
-close_fail:
-	if (cprm.file)
-		filp_close(cprm.file, NULL);
-fail_dropcount:
-	if (ispipe)
-		atomic_dec(&core_dump_count);
-fail_unlock:
-	kfree(cn.corename);
-fail_corename:
-	coredump_finish(mm);
-	revert_creds(old_cred);
-fail_creds:
-	put_cred(cred);
-fail:
-	return;
-}
-
-/*
- * Core dumping helper functions.  These are the only things you should
- * do on a core-file: use only these functions to write out all the
- * necessary info.
- */
-int dump_write(struct file *file, const void *addr, int nr)
-{
-	return access_ok(VERIFY_READ, addr, nr) && file->f_op->write(file, addr, nr, &file->f_pos) == nr;
-}
-EXPORT_SYMBOL(dump_write);
-
-int dump_seek(struct file *file, loff_t off)
-{
-	int ret = 1;
-
-	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
-		if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
-			return 0;
-	} else {
-		char *buf = (char *)get_zeroed_page(GFP_KERNEL);
-
-		if (!buf)
-			return 0;
-		while (off > 0) {
-			unsigned long n = off;
-
-			if (n > PAGE_SIZE)
-				n = PAGE_SIZE;
-			if (!dump_write(file, buf, n)) {
-				ret = 0;
-				break;
-			}
-			off -= n;
-		}
-		free_page((unsigned long)buf);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(dump_seek);

fs/exofs/super.c

@@ -206,6 +206,11 @@ static int init_inodecache(void)
  */
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(exofs_inode_cachep);
 }
 

fs/ext2/super.c

@@ -206,6 +206,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ext2_inode_cachep);
 }
 

fs/ext3/super.c

@@ -532,6 +532,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ext3_inode_cachep);
 }
 

fs/ext4/ioctl.c

@@ -233,7 +233,7 @@ group_extend_out:
 
 	case EXT4_IOC_MOVE_EXT: {
 		struct move_extent me;
-		struct file *donor_filp;
+		struct fd donor;
 		int err;
 
 		if (!(filp->f_mode & FMODE_READ) ||
@@ -245,11 +245,11 @@ group_extend_out:
 			return -EFAULT;
 		me.moved_len = 0;
 
-		donor_filp = fget(me.donor_fd);
+		donor = fdget(me.donor_fd);
-		if (!donor_filp)
+		if (!donor.file)
 			return -EBADF;
 
-		if (!(donor_filp->f_mode & FMODE_WRITE)) {
+		if (!(donor.file->f_mode & FMODE_WRITE)) {
 			err = -EBADF;
 			goto mext_out;
 		}
@@ -258,14 +258,15 @@ group_extend_out:
 			       EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
 			ext4_msg(sb, KERN_ERR,
 				 "Online defrag not supported with bigalloc");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto mext_out;
 		}
 
 		err = mnt_want_write_file(filp);
 		if (err)
 			goto mext_out;
 
-		err = ext4_move_extents(filp, donor_filp, me.orig_start,
+		err = ext4_move_extents(filp, donor.file, me.orig_start,
 					me.donor_start, me.len, &me.moved_len);
 		mnt_drop_write_file(filp);
 
@@ -273,7 +274,7 @@ group_extend_out:
 				 &me, sizeof(me)))
 			err = -EFAULT;
 mext_out:
-		fput(donor_filp);
+		fdput(donor);
 		return err;
 	}
 

fs/ext4/super.c

@@ -1019,6 +1019,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ext4_inode_cachep);
 }
 

fs/fat/inode.c

@@ -521,6 +521,11 @@ static int __init fat_init_inodecache(void)
 
 static void __exit fat_destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(fat_inode_cachep);
 }
 

fs/fcntl.c

@@ -26,124 +26,6 @@
 #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)
-		__set_close_on_exec(fd, fdt);
-	else
-		__clear_close_on_exec(fd, fdt);
-	spin_unlock(&files->file_lock);
-}
-
-static bool get_close_on_exec(unsigned int fd)
-{
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	bool res;
-	rcu_read_lock();
-	fdt = files_fdtable(files);
-	res = close_on_exec(fd, fdt);
-	rcu_read_unlock();
-	return res;
-}
-
-SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
-{
-	int err = -EBADF;
-	struct file * file, *tofree;
-	struct files_struct * files = current->files;
-	struct fdtable *fdt;
-
-	if ((flags & ~O_CLOEXEC) != 0)
-		return -EINVAL;
-
-	if (unlikely(oldfd == newfd))
-		return -EINVAL;
-
-	spin_lock(&files->file_lock);
-	err = expand_files(files, newfd);
-	file = fcheck(oldfd);
-	if (unlikely(!file))
-		goto Ebadf;
-	if (unlikely(err < 0)) {
-		if (err == -EMFILE)
-			goto Ebadf;
-		goto out_unlock;
-	}
-	/*
-	 * We need to detect attempts to do dup2() over allocated but still
-	 * not finished descriptor.  NB: OpenBSD avoids that at the price of
-	 * extra work in their equivalent of fget() - they insert struct
-	 * file immediately after grabbing descriptor, mark it larval if
-	 * more work (e.g. actual opening) is needed and make sure that
-	 * fget() treats larval files as absent.  Potentially interesting,
-	 * but while extra work in fget() is trivial, locking implications
-	 * and amount of surgery on open()-related paths in VFS are not.
-	 * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
-	 * deadlocks in rather amusing ways, AFAICS.  All of that is out of
-	 * scope of POSIX or SUS, since neither considers shared descriptor
-	 * tables and this condition does not arise without those.
-	 */
-	err = -EBUSY;
-	fdt = files_fdtable(files);
-	tofree = fdt->fd[newfd];
-	if (!tofree && fd_is_open(newfd, fdt))
-		goto out_unlock;
-	get_file(file);
-	rcu_assign_pointer(fdt->fd[newfd], file);
-	__set_open_fd(newfd, fdt);
-	if (flags & O_CLOEXEC)
-		__set_close_on_exec(newfd, fdt);
-	else
-		__clear_close_on_exec(newfd, fdt);
-	spin_unlock(&files->file_lock);
-
-	if (tofree)
-		filp_close(tofree, files);
-
-	return newfd;
-
-Ebadf:
-	err = -EBADF;
-out_unlock:
-	spin_unlock(&files->file_lock);
-	return err;
-}
-
-SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
-{
-	if (unlikely(newfd == oldfd)) { /* corner case */
-		struct files_struct *files = current->files;
-		int retval = oldfd;
-
-		rcu_read_lock();
-		if (!fcheck_files(files, oldfd))
-			retval = -EBADF;
-		rcu_read_unlock();
-		return retval;
-	}
-	return sys_dup3(oldfd, newfd, 0);
-}
-
-SYSCALL_DEFINE1(dup, unsigned int, fildes)
-{
-	int ret = -EBADF;
-	struct file *file = fget_raw(fildes);
-
-	if (file) {
-		ret = get_unused_fd();
-		if (ret >= 0)
-			fd_install(ret, file);
-		else
-			fput(file);
-	}
-	return ret;
-}
-
 #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
 static int setfl(int fd, struct file * filp, unsigned long arg)
@@ -267,7 +149,7 @@ pid_t f_getown(struct file *filp)
 
 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 __user *owner_p = (void __user *)arg;
 	struct f_owner_ex owner;
 	struct pid *pid;
 	int type;
@@ -307,7 +189,7 @@ static int f_setown_ex(struct file *filp, unsigned long arg)
 
 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 __user *owner_p = (void __user *)arg;
 	struct f_owner_ex owner;
 	int ret = 0;
 
@@ -345,7 +227,7 @@ static int f_getown_ex(struct file *filp, unsigned long arg)
 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 __user *dst = (void __user *)arg;
 	uid_t src[2];
 	int err;
 
@@ -373,14 +255,10 @@ 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:
-		if (arg >= rlimit(RLIMIT_NOFILE))
+		err = f_dupfd(arg, filp, FD_CLOEXEC);
-			break;
-		err = alloc_fd(arg, cmd == F_DUPFD_CLOEXEC ? O_CLOEXEC : 0);
-		if (err >= 0) {
-			get_file(filp);
-			fd_install(err, filp);
-		}
 		break;
 	case F_GETFD:
 		err = get_close_on_exec(fd) ? FD_CLOEXEC : 0;
@@ -470,25 +348,23 @@ static int check_fcntl_cmd(unsigned cmd)
 
 SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {	
-	struct file *filp;
+	struct fd f = fdget_raw(fd);
-	int fput_needed;
 	long err = -EBADF;
 
-	filp = fget_raw_light(fd, &fput_needed);
+	if (!f.file)
-	if (!filp)
 		goto out;
 
-	if (unlikely(filp->f_mode & FMODE_PATH)) {
+	if (unlikely(f.file->f_mode & FMODE_PATH)) {
 		if (!check_fcntl_cmd(cmd))
 			goto out1;
 	}
 
-	err = security_file_fcntl(filp, cmd, arg);
+	err = security_file_fcntl(f.file, cmd, arg);
 	if (!err)
-		err = do_fcntl(fd, cmd, arg, filp);
+		err = do_fcntl(fd, cmd, arg, f.file);
 
 out1:
- 	fput_light(filp, fput_needed);
+ 	fdput(f);
 out:
 	return err;
 }
@@ -497,38 +373,36 @@ out:
 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 		unsigned long, arg)
 {	
-	struct file * filp;
+	struct fd f = fdget_raw(fd);
 	long err = -EBADF;
-	int fput_needed;
 
-	filp = fget_raw_light(fd, &fput_needed);
+	if (!f.file)
-	if (!filp)
 		goto out;
 
-	if (unlikely(filp->f_mode & FMODE_PATH)) {
+	if (unlikely(f.file->f_mode & FMODE_PATH)) {
 		if (!check_fcntl_cmd(cmd))
 			goto out1;
 	}
 
-	err = security_file_fcntl(filp, cmd, arg);
+	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);
+			err = fcntl_getlk64(f.file, (struct flock64 __user *) arg);
 			break;
 		case F_SETLK64:
 		case F_SETLKW64:
-			err = fcntl_setlk64(fd, filp, cmd,
+			err = fcntl_setlk64(fd, f.file, cmd,
 					(struct flock64 __user *) arg);
 			break;
 		default:
-			err = do_fcntl(fd, cmd, arg, filp);
+			err = do_fcntl(fd, cmd, arg, f.file);
 			break;
 	}
 out1:
-	fput_light(filp, fput_needed);
+	fdput(f);
 out:
 	return err;
 }

fs/fhandle.c

@@ -113,24 +113,21 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 
 static struct vfsmount *get_vfsmount_from_fd(int fd)
 {
-	struct path path;
+	struct vfsmount *mnt;
 
 	if (fd == AT_FDCWD) {
 		struct fs_struct *fs = current->fs;
 		spin_lock(&fs->lock);
-		path = fs->pwd;
+		mnt = mntget(fs->pwd.mnt);
-		mntget(path.mnt);
 		spin_unlock(&fs->lock);
 	} else {
-		int fput_needed;
+		struct fd f = fdget(fd);
-		struct file *file = fget_light(fd, &fput_needed);
+		if (!f.file)
-		if (!file)
 			return ERR_PTR(-EBADF);
-		path = file->f_path;
+		mnt = mntget(f.file->f_path.mnt);
-		mntget(path.mnt);
+		fdput(f);
-		fput_light(file, fput_needed);
 	}
-	return path.mnt;
+	return mnt;
 }
 
 static int vfs_dentry_acceptable(void *context, struct dentry *dentry)

fs/file.c

@@ -6,6 +6,7 @@
  *  Manage the dynamic fd arrays in the process files_struct.
  */
 
+#include <linux/syscalls.h>
 #include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
@@ -84,22 +85,14 @@ static void free_fdtable_work(struct work_struct *work)
 	}
 }
 
-void free_fdtable_rcu(struct rcu_head *rcu)
+static void free_fdtable_rcu(struct rcu_head *rcu)
 {
 	struct fdtable *fdt = container_of(rcu, struct fdtable, rcu);
 	struct fdtable_defer *fddef;
 
 	BUG_ON(!fdt);
+	BUG_ON(fdt->max_fds <= NR_OPEN_DEFAULT);
 
-	if (fdt->max_fds <= NR_OPEN_DEFAULT) {
-		/*
-		 * This fdtable is embedded in the files structure and that
-		 * structure itself is getting destroyed.
-		 */
-		kmem_cache_free(files_cachep,
-				container_of(fdt, struct files_struct, fdtab));
-		return;
-	}
 	if (!is_vmalloc_addr(fdt->fd) && !is_vmalloc_addr(fdt->open_fds)) {
 		kfree(fdt->fd);
 		kfree(fdt->open_fds);
@@ -229,7 +222,7 @@ static int expand_fdtable(struct files_struct *files, int nr)
 		copy_fdtable(new_fdt, cur_fdt);
 		rcu_assign_pointer(files->fdt, new_fdt);
 		if (cur_fdt->max_fds > NR_OPEN_DEFAULT)
-			free_fdtable(cur_fdt);
+			call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
 	} else {
 		/* Somebody else expanded, so undo our attempt */
 		__free_fdtable(new_fdt);
@@ -245,19 +238,12 @@ static int expand_fdtable(struct files_struct *files, int nr)
  * expanded and execution may have blocked.
  * The files->file_lock should be held on entry, and will be held on exit.
  */
-int expand_files(struct files_struct *files, int nr)
+static int expand_files(struct files_struct *files, int nr)
 {
 	struct fdtable *fdt;
 
 	fdt = files_fdtable(files);
 
-	/*
-	 * N.B. For clone tasks sharing a files structure, this test
-	 * will limit the total number of files that can be opened.
-	 */
-	if (nr >= rlimit(RLIMIT_NOFILE))
-		return -EMFILE;
-
 	/* Do we need to expand? */
 	if (nr < fdt->max_fds)
 		return 0;
@@ -270,6 +256,26 @@ int expand_files(struct files_struct *files, int nr)
 	return expand_fdtable(files, nr);
 }
 
+static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
+{
+	__set_bit(fd, fdt->close_on_exec);
+}
+
+static inline void __clear_close_on_exec(int fd, struct fdtable *fdt)
+{
+	__clear_bit(fd, fdt->close_on_exec);
+}
+
+static inline void __set_open_fd(int fd, struct fdtable *fdt)
+{
+	__set_bit(fd, fdt->open_fds);
+}
+
+static inline void __clear_open_fd(int fd, struct fdtable *fdt)
+{
+	__clear_bit(fd, fdt->open_fds);
+}
+
 static int count_open_files(struct fdtable *fdt)
 {
 	int size = fdt->max_fds;
@@ -395,6 +401,95 @@ out:
 	return NULL;
 }
 
+static void close_files(struct files_struct * files)
+{
+	int i, j;
+	struct fdtable *fdt;
+
+	j = 0;
+
+	/*
+	 * It is safe to dereference the fd table without RCU or
+	 * ->file_lock because this is the last reference to the
+	 * files structure.  But use RCU to shut RCU-lockdep up.
+	 */
+	rcu_read_lock();
+	fdt = files_fdtable(files);
+	rcu_read_unlock();
+	for (;;) {
+		unsigned long set;
+		i = j * BITS_PER_LONG;
+		if (i >= fdt->max_fds)
+			break;
+		set = fdt->open_fds[j++];
+		while (set) {
+			if (set & 1) {
+				struct file * file = xchg(&fdt->fd[i], NULL);
+				if (file) {
+					filp_close(file, files);
+					cond_resched();
+				}
+			}
+			i++;
+			set >>= 1;
+		}
+	}
+}
+
+struct files_struct *get_files_struct(struct task_struct *task)
+{
+	struct files_struct *files;
+
+	task_lock(task);
+	files = task->files;
+	if (files)
+		atomic_inc(&files->count);
+	task_unlock(task);
+
+	return files;
+}
+
+void put_files_struct(struct files_struct *files)
+{
+	struct fdtable *fdt;
+
+	if (atomic_dec_and_test(&files->count)) {
+		close_files(files);
+		/* not really needed, since nobody can see us */
+		rcu_read_lock();
+		fdt = files_fdtable(files);
+		rcu_read_unlock();
+		/* free the arrays if they are not embedded */
+		if (fdt != &files->fdtab)
+			__free_fdtable(fdt);
+		kmem_cache_free(files_cachep, files);
+	}
+}
+
+void reset_files_struct(struct files_struct *files)
+{
+	struct task_struct *tsk = current;
+	struct files_struct *old;
+
+	old = tsk->files;
+	task_lock(tsk);
+	tsk->files = files;
+	task_unlock(tsk);
+	put_files_struct(old);
+}
+
+void exit_files(struct task_struct *tsk)
+{
+	struct files_struct * files = tsk->files;
+
+	if (files) {
+		task_lock(tsk);
+		tsk->files = NULL;
+		task_unlock(tsk);
+		put_files_struct(files);
+	}
+}
+
 static void __devinit fdtable_defer_list_init(int cpu)
 {
 	struct fdtable_defer *fddef = &per_cpu(fdtable_defer_list, cpu);
@@ -424,12 +519,18 @@ struct files_struct init_files = {
 	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
 };
 
+void daemonize_descriptors(void)
+{
+	atomic_inc(&init_files.count);
+	reset_files_struct(&init_files);
+}
+
 /*
  * allocate a file descriptor, mark it busy.
  */
-int alloc_fd(unsigned start, unsigned flags)
+int __alloc_fd(struct files_struct *files,
+	       unsigned start, unsigned end, unsigned flags)
 {
-	struct files_struct *files = current->files;
 	unsigned int fd;
 	int error;
 	struct fdtable *fdt;
@@ -444,6 +545,14 @@ repeat:
 	if (fd < fdt->max_fds)
 		fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
 
+	/*
+	 * N.B. For clone tasks sharing a files structure, this test
+	 * will limit the total number of files that can be opened.
+	 */
+	error = -EMFILE;
+	if (fd >= end)
+		goto out;
+
 	error = expand_files(files, fd);
 	if (error < 0)
 		goto out;
@@ -477,8 +586,424 @@ out:
 	return error;
 }
 
-int get_unused_fd(void)
+static int alloc_fd(unsigned start, unsigned flags)
 {
-	return alloc_fd(0, 0);
+	return __alloc_fd(current->files, start, rlimit(RLIMIT_NOFILE), flags);
 }
-EXPORT_SYMBOL(get_unused_fd);
+
+int get_unused_fd_flags(unsigned flags)
+{
+	return __alloc_fd(current->files, 0, rlimit(RLIMIT_NOFILE), flags);
+}
+EXPORT_SYMBOL(get_unused_fd_flags);
+
+static void __put_unused_fd(struct files_struct *files, unsigned int fd)
+{
+	struct fdtable *fdt = files_fdtable(files);
+	__clear_open_fd(fd, fdt);
+	if (fd < files->next_fd)
+		files->next_fd = fd;
+}
+
+void put_unused_fd(unsigned int fd)
+{
+	struct files_struct *files = current->files;
+	spin_lock(&files->file_lock);
+	__put_unused_fd(files, fd);
+	spin_unlock(&files->file_lock);
+}
+
+EXPORT_SYMBOL(put_unused_fd);
+
+/*
+ * Install a file pointer in the fd array.
+ *
+ * The VFS is full of places where we drop the files lock between
+ * setting the open_fds bitmap and installing the file in the file
+ * array.  At any such point, we are vulnerable to a dup2() race
+ * installing a file in the array before us.  We need to detect this and
+ * fput() the struct file we are about to overwrite in this case.
+ *
+ * It should never happen - if we allow dup2() do it, _really_ bad things
+ * will follow.
+ *
+ * NOTE: __fd_install() variant is really, really low-level; don't
+ * use it unless you are forced to by truly lousy API shoved down
+ * your throat.  'files' *MUST* be either current->files or obtained
+ * by get_files_struct(current) done by whoever had given it to you,
+ * or really bad things will happen.  Normally you want to use
+ * fd_install() instead.
+ */
+
+void __fd_install(struct files_struct *files, unsigned int fd,
+		struct file *file)
+{
+	struct fdtable *fdt;
+	spin_lock(&files->file_lock);
+	fdt = files_fdtable(files);
+	BUG_ON(fdt->fd[fd] != NULL);
+	rcu_assign_pointer(fdt->fd[fd], file);
+	spin_unlock(&files->file_lock);
+}
+
+void fd_install(unsigned int fd, struct file *file)
+{
+	__fd_install(current->files, fd, file);
+}
+
+EXPORT_SYMBOL(fd_install);
+
+/*
+ * The same warnings as for __alloc_fd()/__fd_install() apply here...
+ */
+int __close_fd(struct files_struct *files, unsigned fd)
+{
+	struct file *file;
+	struct fdtable *fdt;
+
+	spin_lock(&files->file_lock);
+	fdt = files_fdtable(files);
+	if (fd >= fdt->max_fds)
+		goto out_unlock;
+	file = fdt->fd[fd];
+	if (!file)
+		goto out_unlock;
+	rcu_assign_pointer(fdt->fd[fd], NULL);
+	__clear_close_on_exec(fd, fdt);
+	__put_unused_fd(files, fd);
+	spin_unlock(&files->file_lock);
+	return filp_close(file, files);
+
+out_unlock:
+	spin_unlock(&files->file_lock);
+	return -EBADF;
+}
+
+void do_close_on_exec(struct files_struct *files)
+{
+	unsigned i;
+	struct fdtable *fdt;
+
+	/* exec unshares first */
+	BUG_ON(atomic_read(&files->count) != 1);
+	spin_lock(&files->file_lock);
+	for (i = 0; ; i++) {
+		unsigned long set;
+		unsigned fd = i * BITS_PER_LONG;
+		fdt = files_fdtable(files);
+		if (fd >= fdt->max_fds)
+			break;
+		set = fdt->close_on_exec[i];
+		if (!set)
+			continue;
+		fdt->close_on_exec[i] = 0;
+		for ( ; set ; fd++, set >>= 1) {
+			struct file *file;
+			if (!(set & 1))
+				continue;
+			file = fdt->fd[fd];
+			if (!file)
+				continue;
+			rcu_assign_pointer(fdt->fd[fd], NULL);
+			__put_unused_fd(files, fd);
+			spin_unlock(&files->file_lock);
+			filp_close(file, files);
+			cond_resched();
+			spin_lock(&files->file_lock);
+		}
+
+	}
+	spin_unlock(&files->file_lock);
+}
+
+struct file *fget(unsigned int fd)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file) {
+		/* File object ref couldn't be taken */
+		if (file->f_mode & FMODE_PATH ||
+		    !atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
+	}
+	rcu_read_unlock();
+
+	return file;
+}
+
+EXPORT_SYMBOL(fget);
+
+struct file *fget_raw(unsigned int fd)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	rcu_read_lock();
+	file = fcheck_files(files, fd);
+	if (file) {
+		/* File object ref couldn't be taken */
+		if (!atomic_long_inc_not_zero(&file->f_count))
+			file = NULL;
+	}
+	rcu_read_unlock();
+
+	return file;
+}
+
+EXPORT_SYMBOL(fget_raw);
+
+/*
+ * Lightweight file lookup - no refcnt increment if fd table isn't shared.
+ *
+ * You can use this instead of fget if you satisfy all of the following
+ * conditions:
+ * 1) You must call fput_light before exiting the syscall and returning control
+ *    to userspace (i.e. you cannot remember the returned struct file * after
+ *    returning to userspace).
+ * 2) You must not call filp_close on the returned struct file * in between
+ *    calls to fget_light and fput_light.
+ * 3) You must not clone the current task in between the calls to fget_light
+ *    and fput_light.
+ *
+ * The fput_needed flag returned by fget_light should be passed to the
+ * corresponding fput_light.
+ */
+struct file *fget_light(unsigned int fd, int *fput_needed)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	*fput_needed = 0;
+	if (atomic_read(&files->count) == 1) {
+		file = fcheck_files(files, fd);
+		if (file && (file->f_mode & FMODE_PATH))
+			file = NULL;
+	} else {
+		rcu_read_lock();
+		file = fcheck_files(files, fd);
+		if (file) {
+			if (!(file->f_mode & FMODE_PATH) &&
+			    atomic_long_inc_not_zero(&file->f_count))
+				*fput_needed = 1;
+			else
+				/* Didn't get the reference, someone's freed */
+				file = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return file;
+}
+EXPORT_SYMBOL(fget_light);
+
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	*fput_needed = 0;
+	if (atomic_read(&files->count) == 1) {
+		file = fcheck_files(files, fd);
+	} else {
+		rcu_read_lock();
+		file = fcheck_files(files, fd);
+		if (file) {
+			if (atomic_long_inc_not_zero(&file->f_count))
+				*fput_needed = 1;
+			else
+				/* Didn't get the reference, someone's freed */
+				file = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return file;
+}
+
+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)
+		__set_close_on_exec(fd, fdt);
+	else
+		__clear_close_on_exec(fd, fdt);
+	spin_unlock(&files->file_lock);
+}
+
+bool get_close_on_exec(unsigned int fd)
+{
+	struct files_struct *files = current->files;
+	struct fdtable *fdt;
+	bool res;
+	rcu_read_lock();
+	fdt = files_fdtable(files);
+	res = close_on_exec(fd, fdt);
+	rcu_read_unlock();
+	return res;
+}
+
+static int do_dup2(struct files_struct *files,
+	struct file *file, unsigned fd, unsigned flags)
+{
+	struct file *tofree;
+	struct fdtable *fdt;
+
+	/*
+	 * We need to detect attempts to do dup2() over allocated but still
+	 * not finished descriptor.  NB: OpenBSD avoids that at the price of
+	 * extra work in their equivalent of fget() - they insert struct
+	 * file immediately after grabbing descriptor, mark it larval if
+	 * more work (e.g. actual opening) is needed and make sure that
+	 * fget() treats larval files as absent.  Potentially interesting,
+	 * but while extra work in fget() is trivial, locking implications
+	 * and amount of surgery on open()-related paths in VFS are not.
+	 * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
+	 * deadlocks in rather amusing ways, AFAICS.  All of that is out of
+	 * scope of POSIX or SUS, since neither considers shared descriptor
+	 * tables and this condition does not arise without those.
+	 */
+	fdt = files_fdtable(files);
+	tofree = fdt->fd[fd];
+	if (!tofree && fd_is_open(fd, fdt))
+		goto Ebusy;
+	get_file(file);
+	rcu_assign_pointer(fdt->fd[fd], file);
+	__set_open_fd(fd, fdt);
+	if (flags & O_CLOEXEC)
+		__set_close_on_exec(fd, fdt);
+	else
+		__clear_close_on_exec(fd, fdt);
+	spin_unlock(&files->file_lock);
+
+	if (tofree)
+		filp_close(tofree, files);
+
+	return fd;
+
+Ebusy:
+	spin_unlock(&files->file_lock);
+	return -EBUSY;
+}
+
+int replace_fd(unsigned fd, struct file *file, unsigned flags)
+{
+	int err;
+	struct files_struct *files = current->files;
+
+	if (!file)
+		return __close_fd(files, fd);
+
+	if (fd >= rlimit(RLIMIT_NOFILE))
+		return -EMFILE;
+
+	spin_lock(&files->file_lock);
+	err = expand_files(files, fd);
+	if (unlikely(err < 0))
+		goto out_unlock;
+	return do_dup2(files, file, fd, flags);
+
+out_unlock:
+	spin_unlock(&files->file_lock);
+	return err;
+}
+
+SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
+{
+	int err = -EBADF;
+	struct file *file;
+	struct files_struct *files = current->files;
+
+	if ((flags & ~O_CLOEXEC) != 0)
+		return -EINVAL;
+
+	if (newfd >= rlimit(RLIMIT_NOFILE))
+		return -EMFILE;
+
+	spin_lock(&files->file_lock);
+	err = expand_files(files, newfd);
+	file = fcheck(oldfd);
+	if (unlikely(!file))
+		goto Ebadf;
+	if (unlikely(err < 0)) {
+		if (err == -EMFILE)
+			goto Ebadf;
+		goto out_unlock;
+	}
+	return do_dup2(files, file, newfd, flags);
+
+Ebadf:
+	err = -EBADF;
+out_unlock:
+	spin_unlock(&files->file_lock);
+	return err;
+}
+
+SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
+{
+	if (unlikely(newfd == oldfd)) { /* corner case */
+		struct files_struct *files = current->files;
+		int retval = oldfd;
+
+		rcu_read_lock();
+		if (!fcheck_files(files, oldfd))
+			retval = -EBADF;
+		rcu_read_unlock();
+		return retval;
+	}
+	return sys_dup3(oldfd, newfd, 0);
+}
+
+SYSCALL_DEFINE1(dup, unsigned int, fildes)
+{
+	int ret = -EBADF;
+	struct file *file = fget_raw(fildes);
+
+	if (file) {
+		ret = get_unused_fd();
+		if (ret >= 0)
+			fd_install(ret, file);
+		else
+			fput(file);
+	}
+	return ret;
+}
+
+int f_dupfd(unsigned int from, struct file *file, unsigned flags)
+{
+	int err;
+	if (from >= rlimit(RLIMIT_NOFILE))
+		return -EINVAL;
+	err = alloc_fd(from, flags);
+	if (err >= 0) {
+		get_file(file);
+		fd_install(err, file);
+	}
+	return err;
+}
+
+int iterate_fd(struct files_struct *files, unsigned n,
+		int (*f)(const void *, struct file *, unsigned),
+		const void *p)
+{
+	struct fdtable *fdt;
+	struct file *file;
+	int res = 0;
+	if (!files)
+		return 0;
+	spin_lock(&files->file_lock);
+	fdt = files_fdtable(files);
+	while (!res && n < fdt->max_fds) {
+		file = rcu_dereference_check_fdtable(files, fdt->fd[n++]);
+		if (file)
+			res = f(p, file, n);
+	}
+	spin_unlock(&files->file_lock);
+	return res;
+}
+EXPORT_SYMBOL(iterate_fd);

fs/file_table.c

@@ -339,112 +339,6 @@ void __fput_sync(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
-struct file *fget(unsigned int fd)
-{
-	struct file *file;
-	struct files_struct *files = current->files;
-
-	rcu_read_lock();
-	file = fcheck_files(files, fd);
-	if (file) {
-		/* File object ref couldn't be taken */
-		if (file->f_mode & FMODE_PATH ||
-		    !atomic_long_inc_not_zero(&file->f_count))
-			file = NULL;
-	}
-	rcu_read_unlock();
-
-	return file;
-}
-
-EXPORT_SYMBOL(fget);
-
-struct file *fget_raw(unsigned int fd)
-{
-	struct file *file;
-	struct files_struct *files = current->files;
-
-	rcu_read_lock();
-	file = fcheck_files(files, fd);
-	if (file) {
-		/* File object ref couldn't be taken */
-		if (!atomic_long_inc_not_zero(&file->f_count))
-			file = NULL;
-	}
-	rcu_read_unlock();
-
-	return file;
-}
-
-EXPORT_SYMBOL(fget_raw);
-
-/*
- * Lightweight file lookup - no refcnt increment if fd table isn't shared.
- *
- * You can use this instead of fget if you satisfy all of the following
- * conditions:
- * 1) You must call fput_light before exiting the syscall and returning control
- *    to userspace (i.e. you cannot remember the returned struct file * after
- *    returning to userspace).
- * 2) You must not call filp_close on the returned struct file * in between
- *    calls to fget_light and fput_light.
- * 3) You must not clone the current task in between the calls to fget_light
- *    and fput_light.
- *
- * The fput_needed flag returned by fget_light should be passed to the
- * corresponding fput_light.
- */
-struct file *fget_light(unsigned int fd, int *fput_needed)
-{
-	struct file *file;
-	struct files_struct *files = current->files;
-
-	*fput_needed = 0;
-	if (atomic_read(&files->count) == 1) {
-		file = fcheck_files(files, fd);
-		if (file && (file->f_mode & FMODE_PATH))
-			file = NULL;
-	} else {
-		rcu_read_lock();
-		file = fcheck_files(files, fd);
-		if (file) {
-			if (!(file->f_mode & FMODE_PATH) &&
-			    atomic_long_inc_not_zero(&file->f_count))
-				*fput_needed = 1;
-			else
-				/* Didn't get the reference, someone's freed */
-				file = NULL;
-		}
-		rcu_read_unlock();
-	}
-
-	return file;
-}
-
-struct file *fget_raw_light(unsigned int fd, int *fput_needed)
-{
-	struct file *file;
-	struct files_struct *files = current->files;
-
-	*fput_needed = 0;
-	if (atomic_read(&files->count) == 1) {
-		file = fcheck_files(files, fd);
-	} else {
-		rcu_read_lock();
-		file = fcheck_files(files, fd);
-		if (file) {
-			if (atomic_long_inc_not_zero(&file->f_count))
-				*fput_needed = 1;
-			else
-				/* Didn't get the reference, someone's freed */
-				file = NULL;
-		}
-		rcu_read_unlock();
-	}
-
-	return file;
-}
-
 void put_filp(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {

fs/freevxfs/vxfs_super.c

@@ -279,6 +279,11 @@ static void __exit
 vxfs_cleanup(void)
 {
 	unregister_filesystem(&vxfs_fs_type);
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(vxfs_inode_cachep);
 }
 

fs/fuse/dev.c

@@ -148,8 +148,7 @@ static struct fuse_req *get_reserved_req(struct fuse_conn *fc,
 		if (ff->reserved_req) {
 			req = ff->reserved_req;
 			ff->reserved_req = NULL;
-			get_file(file);
+			req->stolen_file = get_file(file);
-			req->stolen_file = file;
 		}
 		spin_unlock(&fc->lock);
 	} while (!req);

fs/fuse/inode.c

@@ -1197,6 +1197,12 @@ static void fuse_fs_cleanup(void)
 {
 	unregister_filesystem(&fuse_fs_type);
 	unregister_fuseblk();
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(fuse_inode_cachep);
 }
 

fs/hfs/super.c

@@ -492,6 +492,12 @@ static int __init init_hfs_fs(void)
 static void __exit exit_hfs_fs(void)
 {
 	unregister_filesystem(&hfs_fs_type);
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(hfs_inode_cachep);
 }
 

fs/hfsplus/super.c

@@ -635,6 +635,12 @@ static int __init init_hfsplus_fs(void)
 static void __exit exit_hfsplus_fs(void)
 {
 	unregister_filesystem(&hfsplus_fs_type);
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(hfsplus_inode_cachep);
 }
 

fs/hpfs/super.c

@@ -210,6 +210,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(hpfs_inode_cachep);
 }
 

fs/hugetlbfs/inode.c

@@ -1048,6 +1048,11 @@ static int __init init_hugetlbfs_fs(void)
 
 static void __exit exit_hugetlbfs_fs(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(hugetlbfs_inode_cachep);
 	kern_unmount(hugetlbfs_vfsmount);
 	unregister_filesystem(&hugetlbfs_fs_type);

fs/ioctl.c

@@ -603,21 +603,14 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 
 SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
 {
-	struct file *filp;
+	int error;
-	int error = -EBADF;
+	struct fd f = fdget(fd);
-	int fput_needed;
 
-	filp = fget_light(fd, &fput_needed);
+	if (!f.file)
-	if (!filp)
+		return -EBADF;
-		goto out;
+	error = security_file_ioctl(f.file, cmd, arg);
-
+	if (!error)
-	error = security_file_ioctl(filp, cmd, arg);
+		error = do_vfs_ioctl(f.file, fd, cmd, arg);
-	if (error)
+	fdput(f);
-		goto out_fput;
-
-	error = do_vfs_ioctl(filp, fd, cmd, arg);
- out_fput:
-	fput_light(filp, fput_needed);
- out:
 	return error;
 }

fs/isofs/inode.c

@@ -115,6 +115,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(isofs_inode_cachep);
 }
 

fs/jffs2/super.c

@@ -418,6 +418,12 @@ static void __exit exit_jffs2_fs(void)
 	unregister_filesystem(&jffs2_fs_type);
 	jffs2_destroy_slab_caches();
 	jffs2_compressors_exit();
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(jffs2_inode_cachep);
 }
 

fs/jfs/super.c

@@ -911,6 +911,12 @@ static void __exit exit_jfs_fs(void)
 	jfs_proc_clean();
 #endif
 	unregister_filesystem(&jfs_fs_type);
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(jfs_inode_cachep);
 }
 

fs/locks.c

@@ -1625,15 +1625,13 @@ EXPORT_SYMBOL(flock_lock_file_wait);
  */
 SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 {
-	struct file *filp;
+	struct fd f = fdget(fd);
-	int fput_needed;
 	struct file_lock *lock;
 	int can_sleep, unlock;
 	int error;
 
 	error = -EBADF;
-	filp = fget_light(fd, &fput_needed);
+	if (!f.file)
-	if (!filp)
 		goto out;
 
 	can_sleep = !(cmd & LOCK_NB);
@@ -1641,31 +1639,31 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
 	unlock = (cmd == LOCK_UN);
 
 	if (!unlock && !(cmd & LOCK_MAND) &&
-	    !(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
+	    !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
 		goto out_putf;
 
-	error = flock_make_lock(filp, &lock, cmd);
+	error = flock_make_lock(f.file, &lock, cmd);
 	if (error)
 		goto out_putf;
 	if (can_sleep)
 		lock->fl_flags |= FL_SLEEP;
 
-	error = security_file_lock(filp, lock->fl_type);
+	error = security_file_lock(f.file, lock->fl_type);
 	if (error)
 		goto out_free;
 
-	if (filp->f_op && filp->f_op->flock)
+	if (f.file->f_op && f.file->f_op->flock)
-		error = filp->f_op->flock(filp,
+		error = f.file->f_op->flock(f.file,
 					  (can_sleep) ? F_SETLKW : F_SETLK,
 					  lock);
 	else
-		error = flock_lock_file_wait(filp, lock);
+		error = flock_lock_file_wait(f.file, lock);
 
  out_free:
 	locks_free_lock(lock);
 
  out_putf:
-	fput_light(filp, fput_needed);
+	fdput(f);
  out:
 	return error;
 }

fs/logfs/inode.c

@@ -417,5 +417,10 @@ int logfs_init_inode_cache(void)
 
 void logfs_destroy_inode_cache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(logfs_inode_cache);
 }

fs/minix/inode.c

@@ -100,6 +100,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(minix_inode_cachep);
 }
 

fs/namei.c

@@ -1797,8 +1797,6 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		     struct nameidata *nd, struct file **fp)
 {
 	int retval = 0;
-	int fput_needed;
-	struct file *file;
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED;
@@ -1850,44 +1848,41 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 			get_fs_pwd(current->fs, &nd->path);
 		}
 	} else {
+		struct fd f = fdget_raw(dfd);
 		struct dentry *dentry;
 
-		file = fget_raw_light(dfd, &fput_needed);
+		if (!f.file)
-		retval = -EBADF;
+			return -EBADF;
-		if (!file)
-			goto out_fail;
 
-		dentry = file->f_path.dentry;
+		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			retval = -ENOTDIR;
+			if (!S_ISDIR(dentry->d_inode->i_mode)) {
-			if (!S_ISDIR(dentry->d_inode->i_mode))
+				fdput(f);
-				goto fput_fail;
+				return -ENOTDIR;
+			}
 
 			retval = inode_permission(dentry->d_inode, MAY_EXEC);
-			if (retval)
+			if (retval) {
-				goto fput_fail;
+				fdput(f);
+				return retval;
+			}
 		}
 
-		nd->path = file->f_path;
+		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			if (fput_needed)
+			if (f.need_put)
-				*fp = file;
+				*fp = f.file;
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			lock_rcu_walk();
 		} else {
-			path_get(&file->f_path);
+			path_get(&nd->path);
-			fput_light(file, fput_needed);
+			fdput(f);
 		}
 	}
 
 	nd->inode = nd->path.dentry->d_inode;
 	return 0;
-
-fput_fail:
-	fput_light(file, fput_needed);
-out_fail:
-	return retval;
 }
 
 static inline int lookup_last(struct nameidata *nd, struct path *path)
@@ -3971,7 +3966,7 @@ EXPORT_SYMBOL(user_path_at);
 EXPORT_SYMBOL(follow_down_one);
 EXPORT_SYMBOL(follow_down);
 EXPORT_SYMBOL(follow_up);
-EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
+EXPORT_SYMBOL(get_write_access); /* nfsd */
 EXPORT_SYMBOL(getname);
 EXPORT_SYMBOL(lock_rename);
 EXPORT_SYMBOL(lookup_one_len);

fs/ncpfs/inode.c

@@ -89,6 +89,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ncp_inode_cachep);
 }
 

fs/nfs/inode.c

@@ -1571,6 +1571,11 @@ static int __init nfs_init_inodecache(void)
 
 static void nfs_destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(nfs_inode_cachep);
 }
 

fs/nfsd/nfs4state.c

@@ -2837,8 +2837,7 @@ static int nfs4_setlease(struct nfs4_delegation *dp, int flag)
 		return -ENOMEM;
 	}
 	fp->fi_lease = fl;
-	fp->fi_deleg_file = fl->fl_file;
+	fp->fi_deleg_file = get_file(fl->fl_file);
-	get_file(fp->fi_deleg_file);
 	atomic_set(&fp->fi_delegees, 1);
 	list_add(&dp->dl_perfile, &fp->fi_delegations);
 	return 0;

fs/nilfs2/super.c

@@ -1382,6 +1382,12 @@ static void nilfs_segbuf_init_once(void *obj)
 
 static void nilfs_destroy_cachep(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+
 	if (nilfs_inode_cachep)
 		kmem_cache_destroy(nilfs_inode_cachep);
 	if (nilfs_transaction_cachep)

fs/notify/fanotify/fanotify_user.c

@@ -58,7 +58,9 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 	return fsnotify_remove_notify_event(group);
 }
 
-static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
+static int create_fd(struct fsnotify_group *group,
+			struct fsnotify_event *event,
+			struct file **file)
 {
 	int client_fd;
 	struct file *new_file;
@@ -98,7 +100,7 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
 		put_unused_fd(client_fd);
 		client_fd = PTR_ERR(new_file);
 	} else {
-		fd_install(client_fd, new_file);
+		*file = new_file;
 	}
 
 	return client_fd;
@@ -106,13 +108,15 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
 
 static int fill_event_metadata(struct fsnotify_group *group,
 				   struct fanotify_event_metadata *metadata,
-				   struct fsnotify_event *event)
+				   struct fsnotify_event *event,
+				   struct file **file)
 {
 	int ret = 0;
 
 	pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
 		 group, metadata, event);
 
+	*file = NULL;
 	metadata->event_len = FAN_EVENT_METADATA_LEN;
 	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata->vers = FANOTIFY_METADATA_VERSION;
@@ -121,7 +125,7 @@ static int fill_event_metadata(struct fsnotify_group *group,
 	if (unlikely(event->mask & FAN_Q_OVERFLOW))
 		metadata->fd = FAN_NOFD;
 	else {
-		metadata->fd = create_fd(group, event);
+		metadata->fd = create_fd(group, event, file);
 		if (metadata->fd < 0)
 			ret = metadata->fd;
 	}
@@ -220,25 +224,6 @@ static int prepare_for_access_response(struct fsnotify_group *group,
 	return 0;
 }
 
-static void remove_access_response(struct fsnotify_group *group,
-				   struct fsnotify_event *event,
-				   __s32 fd)
-{
-	struct fanotify_response_event *re;
-
-	if (!(event->mask & FAN_ALL_PERM_EVENTS))
-		return;
-
-	re = dequeue_re(group, fd);
-	if (!re)
-		return;
-
-	BUG_ON(re->event != event);
-
-	kmem_cache_free(fanotify_response_event_cache, re);
-
-	return;
-}
 #else
 static int prepare_for_access_response(struct fsnotify_group *group,
 				       struct fsnotify_event *event,
@@ -247,12 +232,6 @@ static int prepare_for_access_response(struct fsnotify_group *group,
 	return 0;
 }
 
-static void remove_access_response(struct fsnotify_group *group,
-				   struct fsnotify_event *event,
-				   __s32 fd)
-{
-	return;
-}
 #endif
 
 static ssize_t copy_event_to_user(struct fsnotify_group *group,
@@ -260,31 +239,33 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 				  char __user *buf)
 {
 	struct fanotify_event_metadata fanotify_event_metadata;
+	struct file *f;
 	int fd, ret;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	ret = fill_event_metadata(group, &fanotify_event_metadata, event);
+	ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
 	if (ret < 0)
 		goto out;
 
 	fd = fanotify_event_metadata.fd;
+	ret = -EFAULT;
+	if (copy_to_user(buf, &fanotify_event_metadata,
+			 fanotify_event_metadata.event_len))
+		goto out_close_fd;
+
 	ret = prepare_for_access_response(group, event, fd);
 	if (ret)
 		goto out_close_fd;
 
-	ret = -EFAULT;
+	fd_install(fd, f);
-	if (copy_to_user(buf, &fanotify_event_metadata,
-			 fanotify_event_metadata.event_len))
-		goto out_kill_access_response;
-
 	return fanotify_event_metadata.event_len;
 
-out_kill_access_response:
-	remove_access_response(group, event, fd);
 out_close_fd:
-	if (fd != FAN_NOFD)
+	if (fd != FAN_NOFD) {
-		sys_close(fd);
+		put_unused_fd(fd);
+		fput(f);
+	}
 out:
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	if (event->mask & FAN_ALL_PERM_EVENTS) {
@@ -470,24 +451,22 @@ static int fanotify_find_path(int dfd, const char __user *filename,
 		 dfd, filename, flags);
 
 	if (filename == NULL) {
-		struct file *file;
+		struct fd f = fdget(dfd);
-		int fput_needed;
 
 		ret = -EBADF;
-		file = fget_light(dfd, &fput_needed);
+		if (!f.file)
-		if (!file)
 			goto out;
 
 		ret = -ENOTDIR;
 		if ((flags & FAN_MARK_ONLYDIR) &&
-		    !(S_ISDIR(file->f_path.dentry->d_inode->i_mode))) {
+		    !(S_ISDIR(f.file->f_path.dentry->d_inode->i_mode))) {
-			fput_light(file, fput_needed);
+			fdput(f);
 			goto out;
 		}
 
-		*path = file->f_path;
+		*path = f.file->f_path;
 		path_get(path);
-		fput_light(file, fput_needed);
+		fdput(f);
 	} else {
 		unsigned int lookup_flags = 0;
 
@@ -767,9 +746,9 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
 	struct inode *inode = NULL;
 	struct vfsmount *mnt = NULL;
 	struct fsnotify_group *group;
-	struct file *filp;
+	struct fd f;
 	struct path path;
-	int ret, fput_needed;
+	int ret;
 
 	pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
 		 __func__, fanotify_fd, flags, dfd, pathname, mask);
@@ -803,15 +782,15 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
 #endif
 		return -EINVAL;
 
-	filp = fget_light(fanotify_fd, &fput_needed);
+	f = fdget(fanotify_fd);
-	if (unlikely(!filp))
+	if (unlikely(!f.file))
 		return -EBADF;
 
 	/* verify that this is indeed an fanotify instance */
 	ret = -EINVAL;
-	if (unlikely(filp->f_op != &fanotify_fops))
+	if (unlikely(f.file->f_op != &fanotify_fops))
 		goto fput_and_out;
-	group = filp->private_data;
+	group = f.file->private_data;
 
 	/*
 	 * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF.  These are not
@@ -858,7 +837,7 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
 
 	path_put(&path);
 fput_and_out:
-	fput_light(filp, fput_needed);
+	fdput(f);
 	return ret;
 }
 

fs/notify/inotify/inotify_user.c

@@ -757,16 +757,16 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	struct fsnotify_group *group;
 	struct inode *inode;
 	struct path path;
-	struct file *filp;
+	struct fd f;
-	int ret, fput_needed;
+	int ret;
 	unsigned flags = 0;
 
-	filp = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (unlikely(!filp))
+	if (unlikely(!f.file))
 		return -EBADF;
 
 	/* verify that this is indeed an inotify instance */
-	if (unlikely(filp->f_op != &inotify_fops)) {
+	if (unlikely(f.file->f_op != &inotify_fops)) {
 		ret = -EINVAL;
 		goto fput_and_out;
 	}
@@ -782,13 +782,13 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 
 	/* inode held in place by reference to path; group by fget on fd */
 	inode = path.dentry->d_inode;
-	group = filp->private_data;
+	group = f.file->private_data;
 
 	/* create/update an inode mark */
 	ret = inotify_update_watch(group, inode, mask);
 	path_put(&path);
 fput_and_out:
-	fput_light(filp, fput_needed);
+	fdput(f);
 	return ret;
 }
 
@@ -796,19 +796,19 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
 {
 	struct fsnotify_group *group;
 	struct inotify_inode_mark *i_mark;
-	struct file *filp;
+	struct fd f;
-	int ret = 0, fput_needed;
+	int ret = 0;
 
-	filp = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (unlikely(!filp))
+	if (unlikely(!f.file))
 		return -EBADF;
 
 	/* verify that this is indeed an inotify instance */
 	ret = -EINVAL;
-	if (unlikely(filp->f_op != &inotify_fops))
+	if (unlikely(f.file->f_op != &inotify_fops))
 		goto out;
 
-	group = filp->private_data;
+	group = f.file->private_data;
 
 	ret = -EINVAL;
 	i_mark = inotify_idr_find(group, wd);
@@ -823,7 +823,7 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
 	fsnotify_put_mark(&i_mark->fsn_mark);
 
 out:
-	fput_light(filp, fput_needed);
+	fdput(f);
 	return ret;
 }
 

fs/ntfs/super.c

@@ -3193,6 +3193,12 @@ static void __exit exit_ntfs_fs(void)
 	ntfs_debug("Unregistering NTFS driver.");
 
 	unregister_filesystem(&ntfs_fs_type);
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(ntfs_big_inode_cache);
 	kmem_cache_destroy(ntfs_inode_cache);
 	kmem_cache_destroy(ntfs_name_cache);

fs/ocfs2/cluster/heartbeat.c

@@ -1746,8 +1746,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	long fd;
 	int sectsize;
 	char *p = (char *)page;
-	struct file *filp = NULL;
+	struct fd f;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	ssize_t ret = -EINVAL;
 	int live_threshold;
 
@@ -1766,26 +1766,26 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	if (fd < 0 || fd >= INT_MAX)
 		goto out;
 
-	filp = fget(fd);
+	f = fdget(fd);
-	if (filp == NULL)
+	if (f.file == NULL)
 		goto out;
 
 	if (reg->hr_blocks == 0 || reg->hr_start_block == 0 ||
 	    reg->hr_block_bytes == 0)
-		goto out;
+		goto out2;
 
-	inode = igrab(filp->f_mapping->host);
+	inode = igrab(f.file->f_mapping->host);
 	if (inode == NULL)
-		goto out;
+		goto out2;
 
 	if (!S_ISBLK(inode->i_mode))
-		goto out;
+		goto out3;
 
-	reg->hr_bdev = I_BDEV(filp->f_mapping->host);
+	reg->hr_bdev = I_BDEV(f.file->f_mapping->host);
 	ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ, NULL);
 	if (ret) {
 		reg->hr_bdev = NULL;
-		goto out;
+		goto out3;
 	}
 	inode = NULL;
 
@@ -1797,7 +1797,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		     "blocksize %u incorrect for device, expected %d",
 		     reg->hr_block_bytes, sectsize);
 		ret = -EINVAL;
-		goto out;
+		goto out3;
 	}
 
 	o2hb_init_region_params(reg);
@@ -1811,13 +1811,13 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	ret = o2hb_map_slot_data(reg);
 	if (ret) {
 		mlog_errno(ret);
-		goto out;
+		goto out3;
 	}
 
 	ret = o2hb_populate_slot_data(reg);
 	if (ret) {
 		mlog_errno(ret);
-		goto out;
+		goto out3;
 	}
 
 	INIT_DELAYED_WORK(&reg->hr_write_timeout_work, o2hb_write_timeout);
@@ -1847,7 +1847,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	if (IS_ERR(hb_task)) {
 		ret = PTR_ERR(hb_task);
 		mlog_errno(ret);
-		goto out;
+		goto out3;
 	}
 
 	spin_lock(&o2hb_live_lock);
@@ -1863,7 +1863,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 
 	if (reg->hr_aborted_start) {
 		ret = -EIO;
-		goto out;
+		goto out3;
 	}
 
 	/* Ok, we were woken.  Make sure it wasn't by drop_item() */
@@ -1882,11 +1882,11 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n",
 		       config_item_name(&reg->hr_item), reg->hr_dev_name);
 
+out3:
+	iput(inode);
+out2:
+	fdput(f);
 out:
-	if (filp)
-		fput(filp);
-	if (inode)
-		iput(inode);
 	if (ret < 0) {
 		if (reg->hr_bdev) {
 			blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);

fs/ocfs2/dlmfs/dlmfs.c

@@ -691,6 +691,11 @@ static void __exit exit_dlmfs_fs(void)
 	flush_workqueue(user_dlm_worker);
 	destroy_workqueue(user_dlm_worker);
 
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(dlmfs_inode_cache);
 
 	bdi_destroy(&dlmfs_backing_dev_info);

fs/ocfs2/super.c

@@ -1818,6 +1818,11 @@ static int ocfs2_initialize_mem_caches(void)
 
 static void ocfs2_free_mem_caches(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	if (ocfs2_inode_cachep)
 		kmem_cache_destroy(ocfs2_inode_cachep);
 	ocfs2_inode_cachep = NULL;

fs/open.c

@@ -132,27 +132,27 @@ SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
 
 static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 {
-	struct inode * inode;
+	struct inode *inode;
 	struct dentry *dentry;
-	struct file * file;
+	struct fd f;
 	int error;
 
 	error = -EINVAL;
 	if (length < 0)
 		goto out;
 	error = -EBADF;
-	file = fget(fd);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		goto out;
 
 	/* explicitly opened as large or we are on 64-bit box */
-	if (file->f_flags & O_LARGEFILE)
+	if (f.file->f_flags & O_LARGEFILE)
 		small = 0;
 
-	dentry = file->f_path.dentry;
+	dentry = f.file->f_path.dentry;
 	inode = dentry->d_inode;
 	error = -EINVAL;
-	if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE))
+	if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
 		goto out_putf;
 
 	error = -EINVAL;
@@ -165,14 +165,14 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 		goto out_putf;
 
 	sb_start_write(inode->i_sb);
-	error = locks_verify_truncate(inode, file, length);
+	error = locks_verify_truncate(inode, f.file, length);
 	if (!error)
-		error = security_path_truncate(&file->f_path);
+		error = security_path_truncate(&f.file->f_path);
 	if (!error)
-		error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
+		error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
 	sb_end_write(inode->i_sb);
 out_putf:
-	fput(file);
+	fdput(f);
 out:
 	return error;
 }
@@ -276,15 +276,13 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 
 SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	int error = -EBADF;
 
-	file = fget(fd);
+	if (f.file) {
-	if (file) {
+		error = do_fallocate(f.file, mode, offset, len);
-		error = do_fallocate(file, mode, offset, len);
+		fdput(f);
-		fput(file);
 	}
-
 	return error;
 }
 
@@ -400,16 +398,15 @@ out:
 
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
-	struct file *file;
+	struct fd f = fdget_raw(fd);
 	struct inode *inode;
-	int error, fput_needed;
+	int error = -EBADF;
 
 	error = -EBADF;
-	file = fget_raw_light(fd, &fput_needed);
+	if (!f.file)
-	if (!file)
 		goto out;
 
-	inode = file->f_path.dentry->d_inode;
+	inode = f.file->f_path.dentry->d_inode;
 
 	error = -ENOTDIR;
 	if (!S_ISDIR(inode->i_mode))
@@ -417,9 +414,9 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 
 	error = inode_permission(inode, MAY_EXEC | MAY_CHDIR);
 	if (!error)
-		set_fs_pwd(current->fs, &file->f_path);
+		set_fs_pwd(current->fs, &f.file->f_path);
 out_putf:
-	fput_light(file, fput_needed);
+	fdput(f);
 out:
 	return error;
 }
@@ -582,23 +579,20 @@ SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group
 
 SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 {
-	struct file * file;
+	struct fd f = fdget(fd);
 	int error = -EBADF;
-	struct dentry * dentry;
 
-	file = fget(fd);
+	if (!f.file)
-	if (!file)
 		goto out;
 
-	error = mnt_want_write_file(file);
+	error = mnt_want_write_file(f.file);
 	if (error)
 		goto out_fput;
-	dentry = file->f_path.dentry;
+	audit_inode(NULL, f.file->f_path.dentry);
-	audit_inode(NULL, dentry);
+	error = chown_common(&f.file->f_path, user, group);
-	error = chown_common(&file->f_path, user, group);
+	mnt_drop_write_file(f.file);
-	mnt_drop_write_file(file);
 out_fput:
-	fput(file);
+	fdput(f);
 out:
 	return error;
 }
@@ -803,50 +797,6 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
-static void __put_unused_fd(struct files_struct *files, unsigned int fd)
-{
-	struct fdtable *fdt = files_fdtable(files);
-	__clear_open_fd(fd, fdt);
-	if (fd < files->next_fd)
-		files->next_fd = fd;
-}
-
-void put_unused_fd(unsigned int fd)
-{
-	struct files_struct *files = current->files;
-	spin_lock(&files->file_lock);
-	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
-}
-
-EXPORT_SYMBOL(put_unused_fd);
-
-/*
- * Install a file pointer in the fd array.
- *
- * The VFS is full of places where we drop the files lock between
- * setting the open_fds bitmap and installing the file in the file
- * array.  At any such point, we are vulnerable to a dup2() race
- * installing a file in the array before us.  We need to detect this and
- * fput() the struct file we are about to overwrite in this case.
- *
- * It should never happen - if we allow dup2() do it, _really_ bad things
- * will follow.
- */
-
-void fd_install(unsigned int fd, struct file *file)
-{
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	BUG_ON(fdt->fd[fd] != NULL);
-	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
-}
-
-EXPORT_SYMBOL(fd_install);
-
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;
@@ -858,7 +808,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 		op->mode = 0;
 
 	/* Must never be set by userspace */
-	flags &= ~FMODE_NONOTIFY;
+	flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC;
 
 	/*
 	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
@@ -1038,23 +988,7 @@ EXPORT_SYMBOL(filp_close);
  */
 SYSCALL_DEFINE1(close, unsigned int, fd)
 {
-	struct file * filp;
+	int retval = __close_fd(current->files, fd);
-	struct files_struct *files = current->files;
-	struct fdtable *fdt;
-	int retval;
-
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds)
-		goto out_unlock;
-	filp = fdt->fd[fd];
-	if (!filp)
-		goto out_unlock;
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__clear_close_on_exec(fd, fdt);
-	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
-	retval = filp_close(filp, files);
 
 	/* can't restart close syscall because file table entry was cleared */
 	if (unlikely(retval == -ERESTARTSYS ||
@@ -1064,10 +998,6 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
 		retval = -EINTR;
 
 	return retval;
-
-out_unlock:
-	spin_unlock(&files->file_lock);
-	return -EBADF;
 }
 EXPORT_SYMBOL(sys_close);
 

fs/openpromfs/inode.c

@@ -463,6 +463,11 @@ static int __init init_openprom_fs(void)
 static void __exit exit_openprom_fs(void)
 {
 	unregister_filesystem(&openprom_fs_type);
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(op_inode_cachep);
 }
 

fs/pipe.c

@@ -1064,9 +1064,8 @@ err_inode:
 	return err;
 }
 
-int do_pipe_flags(int *fd, int flags)
+static int __do_pipe_flags(int *fd, struct file **files, int flags)
 {
-	struct file *files[2];
 	int error;
 	int fdw, fdr;
 
@@ -1088,11 +1087,8 @@ int do_pipe_flags(int *fd, int flags)
 	fdw = error;
 
 	audit_fd_pair(fdr, fdw);
-	fd_install(fdr, files[0]);
-	fd_install(fdw, files[1]);
 	fd[0] = fdr;
 	fd[1] = fdw;
-
 	return 0;
 
  err_fdr:
@@ -1103,21 +1099,38 @@ int do_pipe_flags(int *fd, int flags)
 	return error;
 }
 
+int do_pipe_flags(int *fd, int flags)
+{
+	struct file *files[2];
+	int error = __do_pipe_flags(fd, files, flags);
+	if (!error) {
+		fd_install(fd[0], files[0]);
+		fd_install(fd[1], files[1]);
+	}
+	return error;
+}
+
 /*
  * sys_pipe() is the normal C calling standard for creating
  * a pipe. It's not the way Unix traditionally does this, though.
  */
 SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags)
 {
+	struct file *files[2];
 	int fd[2];
 	int error;
 
-	error = do_pipe_flags(fd, flags);
+	error = __do_pipe_flags(fd, files, flags);
 	if (!error) {
-		if (copy_to_user(fildes, fd, sizeof(fd))) {
+		if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) {
-			sys_close(fd[0]);
+			fput(files[0]);
-			sys_close(fd[1]);
+			fput(files[1]);
+			put_unused_fd(fd[0]);
+			put_unused_fd(fd[1]);
 			error = -EFAULT;
+		} else {
+			fd_install(fd[0], files[0]);
+			fd_install(fd[1], files[1]);
 		}
 	}
 	return error;

fs/proc/Makefile

@@ -8,7 +8,7 @@ proc-y			:= nommu.o task_nommu.o
 proc-$(CONFIG_MMU)	:= mmu.o task_mmu.o
 
 proc-y       += inode.o root.o base.o generic.o array.o \
-		proc_tty.o
+		proc_tty.o fd.o
 proc-y	+= cmdline.o
 proc-y	+= consoles.o
 proc-y	+= cpuinfo.o

fs/proc/base.c

@@ -90,6 +90,7 @@
 #endif
 #include <trace/events/oom.h>
 #include "internal.h"
+#include "fd.h"
 
 /* NOTE:
  *	Implementing inode permission operations in /proc is almost
@@ -136,8 +137,6 @@ struct pid_entry {
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = show } )
 
-static int proc_fd_permission(struct inode *inode, int mask);
-
 /*
  * Count the number of hardlinks for the pid_entry table, excluding the .
  * and .. links.
@@ -1500,7 +1499,7 @@ out:
 	return error;
 }
 
-static const struct inode_operations proc_pid_link_inode_operations = {
+const struct inode_operations proc_pid_link_inode_operations = {
 	.readlink	= proc_pid_readlink,
 	.follow_link	= proc_pid_follow_link,
 	.setattr	= proc_setattr,
@@ -1509,21 +1508,6 @@ static const struct inode_operations proc_pid_link_inode_operations = {
 
 /* building an inode */
 
-static int task_dumpable(struct task_struct *task)
-{
-	int dumpable = 0;
-	struct mm_struct *mm;
-
-	task_lock(task);
-	mm = task->mm;
-	if (mm)
-		dumpable = get_dumpable(mm);
-	task_unlock(task);
-	if(dumpable == 1)
-		return 1;
-	return 0;
-}
-
 struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
 {
 	struct inode * inode;
@@ -1649,15 +1633,6 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
 	return 0;
 }
 
-static int pid_delete_dentry(const struct dentry * dentry)
-{
-	/* Is the task we represent dead?
-	 * If so, then don't put the dentry on the lru list,
-	 * kill it immediately.
-	 */
-	return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
-}
-
 const struct dentry_operations pid_dentry_operations =
 {
 	.d_revalidate	= pid_revalidate,
@@ -1720,289 +1695,6 @@ end_instantiate:
 	return filldir(dirent, name, len, filp->f_pos, ino, type);
 }
 
-static unsigned name_to_int(struct dentry *dentry)
-{
-	const char *name = dentry->d_name.name;
-	int len = dentry->d_name.len;
-	unsigned n = 0;
-
-	if (len > 1 && *name == '0')
-		goto out;
-	while (len-- > 0) {
-		unsigned c = *name++ - '0';
-		if (c > 9)
-			goto out;
-		if (n >= (~0U-9)/10)
-			goto out;
-		n *= 10;
-		n += c;
-	}
-	return n;
-out:
-	return ~0U;
-}
-
-#define PROC_FDINFO_MAX 64
-
-static int proc_fd_info(struct inode *inode, struct path *path, char *info)
-{
-	struct task_struct *task = get_proc_task(inode);
-	struct files_struct *files = NULL;
-	struct file *file;
-	int fd = proc_fd(inode);
-
-	if (task) {
-		files = get_files_struct(task);
-		put_task_struct(task);
-	}
-	if (files) {
-		/*
-		 * We are not taking a ref to the file structure, so we must
-		 * hold ->file_lock.
-		 */
-		spin_lock(&files->file_lock);
-		file = fcheck_files(files, fd);
-		if (file) {
-			unsigned int f_flags;
-			struct fdtable *fdt;
-
-			fdt = files_fdtable(files);
-			f_flags = file->f_flags & ~O_CLOEXEC;
-			if (close_on_exec(fd, fdt))
-				f_flags |= O_CLOEXEC;
-
-			if (path) {
-				*path = file->f_path;
-				path_get(&file->f_path);
-			}
-			if (info)
-				snprintf(info, PROC_FDINFO_MAX,
-					 "pos:\t%lli\n"
-					 "flags:\t0%o\n",
-					 (long long) file->f_pos,
-					 f_flags);
-			spin_unlock(&files->file_lock);
-			put_files_struct(files);
-			return 0;
-		}
-		spin_unlock(&files->file_lock);
-		put_files_struct(files);
-	}
-	return -ENOENT;
-}
-
-static int proc_fd_link(struct dentry *dentry, struct path *path)
-{
-	return proc_fd_info(dentry->d_inode, path, NULL);
-}
-
-static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	struct inode *inode;
-	struct task_struct *task;
-	int fd;
-	struct files_struct *files;
-	const struct cred *cred;
-
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	inode = dentry->d_inode;
-	task = get_proc_task(inode);
-	fd = proc_fd(inode);
-
-	if (task) {
-		files = get_files_struct(task);
-		if (files) {
-			struct file *file;
-			rcu_read_lock();
-			file = fcheck_files(files, fd);
-			if (file) {
-				unsigned f_mode = file->f_mode;
-
-				rcu_read_unlock();
-				put_files_struct(files);
-
-				if (task_dumpable(task)) {
-					rcu_read_lock();
-					cred = __task_cred(task);
-					inode->i_uid = cred->euid;
-					inode->i_gid = cred->egid;
-					rcu_read_unlock();
-				} else {
-					inode->i_uid = GLOBAL_ROOT_UID;
-					inode->i_gid = GLOBAL_ROOT_GID;
-				}
-
-				if (S_ISLNK(inode->i_mode)) {
-					unsigned i_mode = S_IFLNK;
-					if (f_mode & FMODE_READ)
-						i_mode |= S_IRUSR | S_IXUSR;
-					if (f_mode & FMODE_WRITE)
-						i_mode |= S_IWUSR | S_IXUSR;
-					inode->i_mode = i_mode;
-				}
-
-				security_task_to_inode(task, inode);
-				put_task_struct(task);
-				return 1;
-			}
-			rcu_read_unlock();
-			put_files_struct(files);
-		}
-		put_task_struct(task);
-	}
-	d_drop(dentry);
-	return 0;
-}
-
-static const struct dentry_operations tid_fd_dentry_operations =
-{
-	.d_revalidate	= tid_fd_revalidate,
-	.d_delete	= pid_delete_dentry,
-};
-
-static struct dentry *proc_fd_instantiate(struct inode *dir,
-	struct dentry *dentry, struct task_struct *task, const void *ptr)
-{
-	unsigned fd = (unsigned long)ptr;
- 	struct inode *inode;
- 	struct proc_inode *ei;
-	struct dentry *error = ERR_PTR(-ENOENT);
-
-	inode = proc_pid_make_inode(dir->i_sb, task);
-	if (!inode)
-		goto out;
-	ei = PROC_I(inode);
-	ei->fd = fd;
-
-	inode->i_mode = S_IFLNK;
-	inode->i_op = &proc_pid_link_inode_operations;
-	inode->i_size = 64;
-	ei->op.proc_get_link = proc_fd_link;
-	d_set_d_op(dentry, &tid_fd_dentry_operations);
-	d_add(dentry, inode);
-	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, 0))
-		error = NULL;
-
- out:
-	return error;
-}
-
-static struct dentry *proc_lookupfd_common(struct inode *dir,
-					   struct dentry *dentry,
-					   instantiate_t instantiate)
-{
-	struct task_struct *task = get_proc_task(dir);
-	unsigned fd = name_to_int(dentry);
-	struct dentry *result = ERR_PTR(-ENOENT);
-
-	if (!task)
-		goto out_no_task;
-	if (fd == ~0U)
-		goto out;
-
-	result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
-out:
-	put_task_struct(task);
-out_no_task:
-	return result;
-}
-
-static int proc_readfd_common(struct file * filp, void * dirent,
-			      filldir_t filldir, instantiate_t instantiate)
-{
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-	struct task_struct *p = get_proc_task(inode);
-	unsigned int fd, ino;
-	int retval;
-	struct files_struct * files;
-
-	retval = -ENOENT;
-	if (!p)
-		goto out_no_task;
-	retval = 0;
-
-	fd = filp->f_pos;
-	switch (fd) {
-		case 0:
-			if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
-				goto out;
-			filp->f_pos++;
-		case 1:
-			ino = parent_ino(dentry);
-			if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
-				goto out;
-			filp->f_pos++;
-		default:
-			files = get_files_struct(p);
-			if (!files)
-				goto out;
-			rcu_read_lock();
-			for (fd = filp->f_pos-2;
-			     fd < files_fdtable(files)->max_fds;
-			     fd++, filp->f_pos++) {
-				char name[PROC_NUMBUF];
-				int len;
-				int rv;
-
-				if (!fcheck_files(files, fd))
-					continue;
-				rcu_read_unlock();
-
-				len = snprintf(name, sizeof(name), "%d", fd);
-				rv = proc_fill_cache(filp, dirent, filldir,
-						     name, len, instantiate, p,
-						     (void *)(unsigned long)fd);
-				if (rv < 0)
-					goto out_fd_loop;
-				rcu_read_lock();
-			}
-			rcu_read_unlock();
-out_fd_loop:
-			put_files_struct(files);
-	}
-out:
-	put_task_struct(p);
-out_no_task:
-	return retval;
-}
-
-static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
-				    unsigned int flags)
-{
-	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
-}
-
-static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
-{
-	return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
-}
-
-static ssize_t proc_fdinfo_read(struct file *file, char __user *buf,
-				      size_t len, loff_t *ppos)
-{
-	char tmp[PROC_FDINFO_MAX];
-	int err = proc_fd_info(file->f_path.dentry->d_inode, NULL, tmp);
-	if (!err)
-		err = simple_read_from_buffer(buf, len, ppos, tmp, strlen(tmp));
-	return err;
-}
-
-static const struct file_operations proc_fdinfo_file_operations = {
-	.open           = nonseekable_open,
-	.read		= proc_fdinfo_read,
-	.llseek		= no_llseek,
-};
-
-static const struct file_operations proc_fd_operations = {
-	.read		= generic_read_dir,
-	.readdir	= proc_readfd,
-	.llseek		= default_llseek,
-};
-
 #ifdef CONFIG_CHECKPOINT_RESTORE
 
 /*
@@ -2121,7 +1813,7 @@ out:
 }
 
 struct map_files_info {
-	struct file	*file;
+	fmode_t		mode;
 	unsigned long	len;
 	unsigned char	name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
 };
@@ -2130,13 +1822,10 @@ static struct dentry *
 proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 			   struct task_struct *task, const void *ptr)
 {
-	const struct file *file = ptr;
+	fmode_t mode = (fmode_t)(unsigned long)ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	if (!file)
-		return ERR_PTR(-ENOENT);
-
 	inode = proc_pid_make_inode(dir->i_sb, task);
 	if (!inode)
 		return ERR_PTR(-ENOENT);
@@ -2148,9 +1837,9 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 	inode->i_size = 64;
 	inode->i_mode = S_IFLNK;
 
-	if (file->f_mode & FMODE_READ)
+	if (mode & FMODE_READ)
 		inode->i_mode |= S_IRUSR;
-	if (file->f_mode & FMODE_WRITE)
+	if (mode & FMODE_WRITE)
 		inode->i_mode |= S_IWUSR;
 
 	d_set_d_op(dentry, &tid_map_files_dentry_operations);
@@ -2194,7 +1883,8 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	if (!vma)
 		goto out_no_vma;
 
-	result = proc_map_files_instantiate(dir, dentry, task, vma->vm_file);
+	result = proc_map_files_instantiate(dir, dentry, task,
+			(void *)(unsigned long)vma->vm_file->f_mode);
 
 out_no_vma:
 	up_read(&mm->mmap_sem);
@@ -2295,8 +1985,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
 				if (++pos <= filp->f_pos)
 					continue;
 
-				get_file(vma->vm_file);
+				info.mode = vma->vm_file->f_mode;
-				info.file = vma->vm_file;
 				info.len = snprintf(info.name,
 						sizeof(info.name), "%lx-%lx",
 						vma->vm_start, vma->vm_end);
@@ -2311,19 +2000,11 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
 			ret = proc_fill_cache(filp, dirent, filldir,
 					      p->name, p->len,
 					      proc_map_files_instantiate,
-					      task, p->file);
+					      task,
+					      (void *)(unsigned long)p->mode);
 			if (ret)
 				break;
 			filp->f_pos++;
-			fput(p->file);
-		}
-		for (; i < nr_files; i++) {
-			/*
-			 * In case of error don't forget
-			 * to put rest of file refs.
-			 */
-			p = flex_array_get(fa, i);
-			fput(p->file);
 		}
 		if (fa)
 			flex_array_free(fa);
@@ -2345,82 +2026,6 @@ static const struct file_operations proc_map_files_operations = {
 
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 
-/*
- * /proc/pid/fd needs a special permission handler so that a process can still
- * access /proc/self/fd after it has executed a setuid().
- */
-static int proc_fd_permission(struct inode *inode, int mask)
-{
-	int rv = generic_permission(inode, mask);
-	if (rv == 0)
-		return 0;
-	if (task_pid(current) == proc_pid(inode))
-		rv = 0;
-	return rv;
-}
-
-/*
- * proc directories can do almost nothing..
- */
-static const struct inode_operations proc_fd_inode_operations = {
-	.lookup		= proc_lookupfd,
-	.permission	= proc_fd_permission,
-	.setattr	= proc_setattr,
-};
-
-static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
-	struct dentry *dentry, struct task_struct *task, const void *ptr)
-{
-	unsigned fd = (unsigned long)ptr;
- 	struct inode *inode;
- 	struct proc_inode *ei;
-	struct dentry *error = ERR_PTR(-ENOENT);
-
-	inode = proc_pid_make_inode(dir->i_sb, task);
-	if (!inode)
-		goto out;
-	ei = PROC_I(inode);
-	ei->fd = fd;
-	inode->i_mode = S_IFREG | S_IRUSR;
-	inode->i_fop = &proc_fdinfo_file_operations;
-	d_set_d_op(dentry, &tid_fd_dentry_operations);
-	d_add(dentry, inode);
-	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, 0))
-		error = NULL;
-
- out:
-	return error;
-}
-
-static struct dentry *proc_lookupfdinfo(struct inode *dir,
-					struct dentry *dentry,
-					unsigned int flags)
-{
-	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
-}
-
-static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
-{
-	return proc_readfd_common(filp, dirent, filldir,
-				  proc_fdinfo_instantiate);
-}
-
-static const struct file_operations proc_fdinfo_operations = {
-	.read		= generic_read_dir,
-	.readdir	= proc_readfdinfo,
-	.llseek		= default_llseek,
-};
-
-/*
- * proc directories can do almost nothing..
- */
-static const struct inode_operations proc_fdinfo_inode_operations = {
-	.lookup		= proc_lookupfdinfo,
-	.setattr	= proc_setattr,
-};
-
-
 static struct dentry *proc_pident_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {

fs/proc/fd.c

@@ -0,0 +1,367 @@
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/dcache.h>
+#include <linux/path.h>
+#include <linux/fdtable.h>
+#include <linux/namei.h>
+#include <linux/pid.h>
+#include <linux/security.h>
+#include <linux/file.h>
+#include <linux/seq_file.h>
+
+#include <linux/proc_fs.h>
+
+#include "internal.h"
+#include "fd.h"
+
+static int seq_show(struct seq_file *m, void *v)
+{
+	struct files_struct *files = NULL;
+	int f_flags = 0, ret = -ENOENT;
+	struct file *file = NULL;
+	struct task_struct *task;
+
+	task = get_proc_task(m->private);
+	if (!task)
+		return -ENOENT;
+
+	files = get_files_struct(task);
+	put_task_struct(task);
+
+	if (files) {
+		int fd = proc_fd(m->private);
+
+		spin_lock(&files->file_lock);
+		file = fcheck_files(files, fd);
+		if (file) {
+			struct fdtable *fdt = files_fdtable(files);
+
+			f_flags = file->f_flags;
+			if (close_on_exec(fd, fdt))
+				f_flags |= O_CLOEXEC;
+
+			get_file(file);
+			ret = 0;
+		}
+		spin_unlock(&files->file_lock);
+		put_files_struct(files);
+	}
+
+	if (!ret) {
+                seq_printf(m, "pos:\t%lli\nflags:\t0%o\n",
+			   (long long)file->f_pos, f_flags);
+		fput(file);
+	}
+
+	return ret;
+}
+
+static int seq_fdinfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, seq_show, inode);
+}
+
+static const struct file_operations proc_fdinfo_file_operations = {
+	.open		= seq_fdinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct files_struct *files;
+	struct task_struct *task;
+	const struct cred *cred;
+	struct inode *inode;
+	int fd;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = dentry->d_inode;
+	task = get_proc_task(inode);
+	fd = proc_fd(inode);
+
+	if (task) {
+		files = get_files_struct(task);
+		if (files) {
+			struct file *file;
+
+			rcu_read_lock();
+			file = fcheck_files(files, fd);
+			if (file) {
+				unsigned f_mode = file->f_mode;
+
+				rcu_read_unlock();
+				put_files_struct(files);
+
+				if (task_dumpable(task)) {
+					rcu_read_lock();
+					cred = __task_cred(task);
+					inode->i_uid = cred->euid;
+					inode->i_gid = cred->egid;
+					rcu_read_unlock();
+				} else {
+					inode->i_uid = GLOBAL_ROOT_UID;
+					inode->i_gid = GLOBAL_ROOT_GID;
+				}
+
+				if (S_ISLNK(inode->i_mode)) {
+					unsigned i_mode = S_IFLNK;
+					if (f_mode & FMODE_READ)
+						i_mode |= S_IRUSR | S_IXUSR;
+					if (f_mode & FMODE_WRITE)
+						i_mode |= S_IWUSR | S_IXUSR;
+					inode->i_mode = i_mode;
+				}
+
+				security_task_to_inode(task, inode);
+				put_task_struct(task);
+				return 1;
+			}
+			rcu_read_unlock();
+			put_files_struct(files);
+		}
+		put_task_struct(task);
+	}
+
+	d_drop(dentry);
+	return 0;
+}
+
+static const struct dentry_operations tid_fd_dentry_operations = {
+	.d_revalidate	= tid_fd_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+static int proc_fd_link(struct dentry *dentry, struct path *path)
+{
+	struct files_struct *files = NULL;
+	struct task_struct *task;
+	int ret = -ENOENT;
+
+	task = get_proc_task(dentry->d_inode);
+	if (task) {
+		files = get_files_struct(task);
+		put_task_struct(task);
+	}
+
+	if (files) {
+		int fd = proc_fd(dentry->d_inode);
+		struct file *fd_file;
+
+		spin_lock(&files->file_lock);
+		fd_file = fcheck_files(files, fd);
+		if (fd_file) {
+			*path = fd_file->f_path;
+			path_get(&fd_file->f_path);
+			ret = 0;
+		}
+		spin_unlock(&files->file_lock);
+		put_files_struct(files);
+	}
+
+	return ret;
+}
+
+static struct dentry *
+proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
+		    struct task_struct *task, const void *ptr)
+{
+	struct dentry *error = ERR_PTR(-ENOENT);
+	unsigned fd = (unsigned long)ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	ei->fd = fd;
+
+	inode->i_mode = S_IFLNK;
+	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_size = 64;
+
+	ei->op.proc_get_link = proc_fd_link;
+
+	d_set_d_op(dentry, &tid_fd_dentry_operations);
+	d_add(dentry, inode);
+
+	/* Close the race of the process dying before we return the dentry */
+	if (tid_fd_revalidate(dentry, 0))
+		error = NULL;
+ out:
+	return error;
+}
+
+static struct dentry *proc_lookupfd_common(struct inode *dir,
+					   struct dentry *dentry,
+					   instantiate_t instantiate)
+{
+	struct task_struct *task = get_proc_task(dir);
+	struct dentry *result = ERR_PTR(-ENOENT);
+	unsigned fd = name_to_int(dentry);
+
+	if (!task)
+		goto out_no_task;
+	if (fd == ~0U)
+		goto out;
+
+	result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
+out:
+	put_task_struct(task);
+out_no_task:
+	return result;
+}
+
+static int proc_readfd_common(struct file * filp, void * dirent,
+			      filldir_t filldir, instantiate_t instantiate)
+{
+	struct dentry *dentry = filp->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+	struct task_struct *p = get_proc_task(inode);
+	struct files_struct *files;
+	unsigned int fd, ino;
+	int retval;
+
+	retval = -ENOENT;
+	if (!p)
+		goto out_no_task;
+	retval = 0;
+
+	fd = filp->f_pos;
+	switch (fd) {
+		case 0:
+			if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
+				goto out;
+			filp->f_pos++;
+		case 1:
+			ino = parent_ino(dentry);
+			if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
+				goto out;
+			filp->f_pos++;
+		default:
+			files = get_files_struct(p);
+			if (!files)
+				goto out;
+			rcu_read_lock();
+			for (fd = filp->f_pos - 2;
+			     fd < files_fdtable(files)->max_fds;
+			     fd++, filp->f_pos++) {
+				char name[PROC_NUMBUF];
+				int len;
+				int rv;
+
+				if (!fcheck_files(files, fd))
+					continue;
+				rcu_read_unlock();
+
+				len = snprintf(name, sizeof(name), "%d", fd);
+				rv = proc_fill_cache(filp, dirent, filldir,
+						     name, len, instantiate, p,
+						     (void *)(unsigned long)fd);
+				if (rv < 0)
+					goto out_fd_loop;
+				rcu_read_lock();
+			}
+			rcu_read_unlock();
+out_fd_loop:
+			put_files_struct(files);
+	}
+out:
+	put_task_struct(p);
+out_no_task:
+	return retval;
+}
+
+static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
+{
+	return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
+}
+
+const struct file_operations proc_fd_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_readfd,
+	.llseek		= default_llseek,
+};
+
+static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
+				    unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
+}
+
+/*
+ * /proc/pid/fd needs a special permission handler so that a process can still
+ * access /proc/self/fd after it has executed a setuid().
+ */
+int proc_fd_permission(struct inode *inode, int mask)
+{
+	int rv = generic_permission(inode, mask);
+	if (rv == 0)
+		return 0;
+	if (task_pid(current) == proc_pid(inode))
+		rv = 0;
+	return rv;
+}
+
+const struct inode_operations proc_fd_inode_operations = {
+	.lookup		= proc_lookupfd,
+	.permission	= proc_fd_permission,
+	.setattr	= proc_setattr,
+};
+
+static struct dentry *
+proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
+			struct task_struct *task, const void *ptr)
+{
+	struct dentry *error = ERR_PTR(-ENOENT);
+	unsigned fd = (unsigned long)ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		goto out;
+
+	ei = PROC_I(inode);
+	ei->fd = fd;
+
+	inode->i_mode = S_IFREG | S_IRUSR;
+	inode->i_fop = &proc_fdinfo_file_operations;
+
+	d_set_d_op(dentry, &tid_fd_dentry_operations);
+	d_add(dentry, inode);
+
+	/* Close the race of the process dying before we return the dentry */
+	if (tid_fd_revalidate(dentry, 0))
+		error = NULL;
+ out:
+	return error;
+}
+
+static struct dentry *
+proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
+	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
+}
+
+static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
+{
+	return proc_readfd_common(filp, dirent, filldir,
+				  proc_fdinfo_instantiate);
+}
+
+const struct inode_operations proc_fdinfo_inode_operations = {
+	.lookup		= proc_lookupfdinfo,
+	.setattr	= proc_setattr,
+};
+
+const struct file_operations proc_fdinfo_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_readfdinfo,
+	.llseek		= default_llseek,
+};

fs/proc/fd.h

@@ -0,0 +1,14 @@
+#ifndef __PROCFS_FD_H__
+#define __PROCFS_FD_H__
+
+#include <linux/fs.h>
+
+extern const struct file_operations proc_fd_operations;
+extern const struct inode_operations proc_fd_inode_operations;
+
+extern const struct file_operations proc_fdinfo_operations;
+extern const struct inode_operations proc_fdinfo_inode_operations;
+
+extern int proc_fd_permission(struct inode *inode, int mask);
+
+#endif /* __PROCFS_FD_H__ */

fs/proc/internal.h

@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/sched.h>
 #include <linux/proc_fs.h>
 struct  ctl_table_header;
 
@@ -65,6 +66,7 @@ extern const struct file_operations proc_clear_refs_operations;
 extern const struct file_operations proc_pagemap_operations;
 extern const struct file_operations proc_net_operations;
 extern const struct inode_operations proc_net_inode_operations;
+extern const struct inode_operations proc_pid_link_inode_operations;
 
 struct proc_maps_private {
 	struct pid *pid;
@@ -91,6 +93,52 @@ static inline int proc_fd(struct inode *inode)
 	return PROC_I(inode)->fd;
 }
 
+static inline int task_dumpable(struct task_struct *task)
+{
+	int dumpable = 0;
+	struct mm_struct *mm;
+
+	task_lock(task);
+	mm = task->mm;
+	if (mm)
+		dumpable = get_dumpable(mm);
+	task_unlock(task);
+	if(dumpable == 1)
+		return 1;
+	return 0;
+}
+
+static inline int pid_delete_dentry(const struct dentry * dentry)
+{
+	/* Is the task we represent dead?
+	 * If so, then don't put the dentry on the lru list,
+	 * kill it immediately.
+	 */
+	return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
+}
+
+static inline unsigned name_to_int(struct dentry *dentry)
+{
+	const char *name = dentry->d_name.name;
+	int len = dentry->d_name.len;
+	unsigned n = 0;
+
+	if (len > 1 && *name == '0')
+		goto out;
+	while (len-- > 0) {
+		unsigned c = *name++ - '0';
+		if (c > 9)
+			goto out;
+		if (n >= (~0U-9)/10)
+			goto out;
+		n *= 10;
+		n += c;
+	}
+	return n;
+out:
+	return ~0U;
+}
+
 struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino,
 		struct dentry *dentry);
 int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,

fs/qnx4/inode.c

@@ -391,6 +391,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(qnx4_inode_cachep);
 }
 

fs/qnx6/inode.c

@@ -651,6 +651,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(qnx6_inode_cachep);
 }
 

fs/read_write.c

@@ -232,23 +232,18 @@ EXPORT_SYMBOL(vfs_llseek);
 SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
 {
 	off_t retval;
-	struct file * file;
+	struct fd f = fdget(fd);
-	int fput_needed;
+	if (!f.file)
-
+		return -EBADF;
-	retval = -EBADF;
-	file = fget_light(fd, &fput_needed);
-	if (!file)
-		goto bad;
 
 	retval = -EINVAL;
 	if (origin <= SEEK_MAX) {
-		loff_t res = vfs_llseek(file, offset, origin);
+		loff_t res = vfs_llseek(f.file, offset, origin);
 		retval = res;
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
 	}
-	fput_light(file, fput_needed);
+	fdput(f);
-bad:
 	return retval;
 }
 
@@ -258,20 +253,17 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 		unsigned int, origin)
 {
 	int retval;
-	struct file * file;
+	struct fd f = fdget(fd);
 	loff_t offset;
-	int fput_needed;
 
-	retval = -EBADF;
+	if (!f.file)
-	file = fget_light(fd, &fput_needed);
+		return -EBADF;
-	if (!file)
-		goto bad;
 
 	retval = -EINVAL;
 	if (origin > SEEK_MAX)
 		goto out_putf;
 
-	offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
+	offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
 			origin);
 
 	retval = (int)offset;
@@ -281,8 +273,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 			retval = 0;
 	}
 out_putf:
-	fput_light(file, fput_needed);
+	fdput(f);
-bad:
 	return retval;
 }
 #endif
@@ -461,34 +452,29 @@ static inline void file_pos_write(struct file *file, loff_t pos)
 
 SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
+	if (f.file) {
-	if (file) {
+		loff_t pos = file_pos_read(f.file);
-		loff_t pos = file_pos_read(file);
+		ret = vfs_read(f.file, buf, count, &pos);
-		ret = vfs_read(file, buf, count, &pos);
+		file_pos_write(f.file, pos);
-		file_pos_write(file, pos);
+		fdput(f);
-		fput_light(file, fput_needed);
 	}
-
 	return ret;
 }
 
 SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 		size_t, count)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
+	if (f.file) {
-	if (file) {
+		loff_t pos = file_pos_read(f.file);
-		loff_t pos = file_pos_read(file);
+		ret = vfs_write(f.file, buf, count, &pos);
-		ret = vfs_write(file, buf, count, &pos);
+		file_pos_write(f.file, pos);
-		file_pos_write(file, pos);
+		fdput(f);
-		fput_light(file, fput_needed);
 	}
 
 	return ret;
@@ -497,19 +483,18 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf,
 			size_t count, loff_t pos)
 {
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (file) {
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PREAD)
+		if (f.file->f_mode & FMODE_PREAD)
-			ret = vfs_read(file, buf, count, &pos);
+			ret = vfs_read(f.file, buf, count, &pos);
-		fput_light(file, fput_needed);
+		fdput(f);
 	}
 
 	return ret;
@@ -526,19 +511,18 @@ SYSCALL_ALIAS(sys_pread64, SyS_pread64);
 SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf,
 			 size_t count, loff_t pos)
 {
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (file) {
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PWRITE)  
+		if (f.file->f_mode & FMODE_PWRITE)  
-			ret = vfs_write(file, buf, count, &pos);
+			ret = vfs_write(f.file, buf, count, &pos);
-		fput_light(file, fput_needed);
+		fdput(f);
 	}
 
 	return ret;
@@ -789,16 +773,14 @@ EXPORT_SYMBOL(vfs_writev);
 SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
+	if (f.file) {
-	if (file) {
+		loff_t pos = file_pos_read(f.file);
-		loff_t pos = file_pos_read(file);
+		ret = vfs_readv(f.file, vec, vlen, &pos);
-		ret = vfs_readv(file, vec, vlen, &pos);
+		file_pos_write(f.file, pos);
-		file_pos_write(file, pos);
+		fdput(f);
-		fput_light(file, fput_needed);
 	}
 
 	if (ret > 0)
@@ -810,16 +792,14 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
+	if (f.file) {
-	if (file) {
+		loff_t pos = file_pos_read(f.file);
-		loff_t pos = file_pos_read(file);
+		ret = vfs_writev(f.file, vec, vlen, &pos);
-		ret = vfs_writev(file, vec, vlen, &pos);
+		file_pos_write(f.file, pos);
-		file_pos_write(file, pos);
+		fdput(f);
-		fput_light(file, fput_needed);
 	}
 
 	if (ret > 0)
@@ -838,19 +818,18 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
 {
 	loff_t pos = pos_from_hilo(pos_h, pos_l);
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (file) {
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PREAD)
+		if (f.file->f_mode & FMODE_PREAD)
-			ret = vfs_readv(file, vec, vlen, &pos);
+			ret = vfs_readv(f.file, vec, vlen, &pos);
-		fput_light(file, fput_needed);
+		fdput(f);
 	}
 
 	if (ret > 0)
@@ -863,19 +842,18 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
 {
 	loff_t pos = pos_from_hilo(pos_h, pos_l);
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (file) {
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PWRITE)
+		if (f.file->f_mode & FMODE_PWRITE)
-			ret = vfs_writev(file, vec, vlen, &pos);
+			ret = vfs_writev(f.file, vec, vlen, &pos);
-		fput_light(file, fput_needed);
+		fdput(f);
 	}
 
 	if (ret > 0)
@@ -884,31 +862,31 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
-static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
+ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count,
-			   size_t count, loff_t max)
+		    loff_t max)
 {
-	struct file * in_file, * out_file;
+	struct fd in, out;
-	struct inode * in_inode, * out_inode;
+	struct inode *in_inode, *out_inode;
 	loff_t pos;
 	ssize_t retval;
-	int fput_needed_in, fput_needed_out, fl;
+	int fl;
 
 	/*
 	 * Get input file, and verify that it is ok..
 	 */
 	retval = -EBADF;
-	in_file = fget_light(in_fd, &fput_needed_in);
+	in = fdget(in_fd);
-	if (!in_file)
+	if (!in.file)
 		goto out;
-	if (!(in_file->f_mode & FMODE_READ))
+	if (!(in.file->f_mode & FMODE_READ))
 		goto fput_in;
 	retval = -ESPIPE;
 	if (!ppos)
-		ppos = &in_file->f_pos;
+		ppos = &in.file->f_pos;
 	else
-		if (!(in_file->f_mode & FMODE_PREAD))
+		if (!(in.file->f_mode & FMODE_PREAD))
 			goto fput_in;
-	retval = rw_verify_area(READ, in_file, ppos, count);
+	retval = rw_verify_area(READ, in.file, ppos, count);
 	if (retval < 0)
 		goto fput_in;
 	count = retval;
@@ -917,15 +895,15 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	 * Get output file, and verify that it is ok..
 	 */
 	retval = -EBADF;
-	out_file = fget_light(out_fd, &fput_needed_out);
+	out = fdget(out_fd);
-	if (!out_file)
+	if (!out.file)
 		goto fput_in;
-	if (!(out_file->f_mode & FMODE_WRITE))
+	if (!(out.file->f_mode & FMODE_WRITE))
 		goto fput_out;
 	retval = -EINVAL;
-	in_inode = in_file->f_path.dentry->d_inode;
+	in_inode = in.file->f_path.dentry->d_inode;
-	out_inode = out_file->f_path.dentry->d_inode;
+	out_inode = out.file->f_path.dentry->d_inode;
-	retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
+	retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count);
 	if (retval < 0)
 		goto fput_out;
 	count = retval;
@@ -949,10 +927,10 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	 * and the application is arguably buggy if it doesn't expect
 	 * EAGAIN on a non-blocking file descriptor.
 	 */
-	if (in_file->f_flags & O_NONBLOCK)
+	if (in.file->f_flags & O_NONBLOCK)
 		fl = SPLICE_F_NONBLOCK;
 #endif
-	retval = do_splice_direct(in_file, ppos, out_file, count, fl);
+	retval = do_splice_direct(in.file, ppos, out.file, count, fl);
 
 	if (retval > 0) {
 		add_rchar(current, retval);
@@ -965,9 +943,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		retval = -EOVERFLOW;
 
 fput_out:
-	fput_light(out_file, fput_needed_out);
+	fdput(out);
 fput_in:
-	fput_light(in_file, fput_needed_in);
+	fdput(in);
 out:
 	return retval;
 }

fs/read_write.h

@@ -12,3 +12,5 @@ ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 		unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn);
 ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
 		unsigned long nr_segs, loff_t *ppos, io_fn_t fn);
+ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count,
+		    loff_t max);

fs/readdir.c

@@ -106,22 +106,20 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
 		struct old_linux_dirent __user *, dirent, unsigned int, count)
 {
 	int error;
-	struct file * file;
+	struct fd f = fdget(fd);
 	struct readdir_callback buf;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
+	if (!f.file)
-	if (!file)
 		return -EBADF;
 
 	buf.result = 0;
 	buf.dirent = dirent;
 
-	error = vfs_readdir(file, fillonedir, &buf);
+	error = vfs_readdir(f.file, fillonedir, &buf);
 	if (buf.result)
 		error = buf.result;
 
-	fput_light(file, fput_needed);
+	fdput(f);
 	return error;
 }
 
@@ -191,17 +189,16 @@ efault:
 SYSCALL_DEFINE3(getdents, unsigned int, fd,
 		struct linux_dirent __user *, dirent, unsigned int, count)
 {
-	struct file * file;
+	struct fd f;
 	struct linux_dirent __user * lastdirent;
 	struct getdents_callback buf;
-	int fput_needed;
 	int error;
 
 	if (!access_ok(VERIFY_WRITE, dirent, count))
 		return -EFAULT;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
 	buf.current_dir = dirent;
@@ -209,17 +206,17 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
 	buf.count = count;
 	buf.error = 0;
 
-	error = vfs_readdir(file, filldir, &buf);
+	error = vfs_readdir(f.file, filldir, &buf);
 	if (error >= 0)
 		error = buf.error;
 	lastdirent = buf.previous;
 	if (lastdirent) {
-		if (put_user(file->f_pos, &lastdirent->d_off))
+		if (put_user(f.file->f_pos, &lastdirent->d_off))
 			error = -EFAULT;
 		else
 			error = count - buf.count;
 	}
-	fput_light(file, fput_needed);
+	fdput(f);
 	return error;
 }
 
@@ -272,17 +269,16 @@ efault:
 SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 		struct linux_dirent64 __user *, dirent, unsigned int, count)
 {
-	struct file * file;
+	struct fd f;
 	struct linux_dirent64 __user * lastdirent;
 	struct getdents_callback64 buf;
-	int fput_needed;
 	int error;
 
 	if (!access_ok(VERIFY_WRITE, dirent, count))
 		return -EFAULT;
 
-	file = fget_light(fd, &fput_needed);
+	f = fdget(fd);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
 	buf.current_dir = dirent;
@@ -290,17 +286,17 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	buf.count = count;
 	buf.error = 0;
 
-	error = vfs_readdir(file, filldir64, &buf);
+	error = vfs_readdir(f.file, filldir64, &buf);
 	if (error >= 0)
 		error = buf.error;
 	lastdirent = buf.previous;
 	if (lastdirent) {
-		typeof(lastdirent->d_off) d_off = file->f_pos;
+		typeof(lastdirent->d_off) d_off = f.file->f_pos;
 		if (__put_user(d_off, &lastdirent->d_off))
 			error = -EFAULT;
 		else
 			error = count - buf.count;
 	}
-	fput_light(file, fput_needed);
+	fdput(f);
 	return error;
 }

fs/reiserfs/super.c

@@ -608,6 +608,11 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(reiserfs_inode_cachep);
 }
 

fs/romfs/super.c

@@ -648,6 +648,11 @@ error_register:
 static void __exit exit_romfs_fs(void)
 {
 	unregister_filesystem(&romfs_fs_type);
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(romfs_inode_cachep);
 }