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

Pull vfs updates from Al Viro:
 "The big thing in this pile is Eric's unmount-on-rmdir series; we
  finally have everything we need for that.  The final piece of prereqs
  is delayed mntput() - now filesystem shutdown always happens on
  shallow stack.

  Other than that, we have several new primitives for iov_iter (Matt
  Wilcox, culled from his XIP-related series) pushing the conversion to
  ->read_iter()/ ->write_iter() a bit more, a bunch of fs/dcache.c
  cleanups and fixes (including the external name refcounting, which
  gives consistent behaviour of d_move() wrt procfs symlinks for long
  and short names alike) and assorted cleanups and fixes all over the
  place.

  This is just the first pile; there's a lot of stuff from various
  people that ought to go in this window.  Starting with
  unionmount/overlayfs mess...  ;-/"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (60 commits)
  fs/file_table.c: Update alloc_file() comment
  vfs: Deduplicate code shared by xattr system calls operating on paths
  reiserfs: remove pointless forward declaration of struct nameidata
  don't need that forward declaration of struct nameidata in dcache.h anymore
  take dname_external() into fs/dcache.c
  let path_init() failures treated the same way as subsequent link_path_walk()
  fix misuses of f_count() in ppp and netlink
  ncpfs: use list_for_each_entry() for d_subdirs walk
  vfs: move getname() from callers to do_mount()
  gfs2_atomic_open(): skip lookups on hashed dentry
  [infiniband] remove pointless assignments
  gadgetfs: saner API for gadgetfs_create_file()
  f_fs: saner API for ffs_sb_create_file()
  jfs: don't hash direct inode
  [s390] remove pointless assignment of ->f_op in vmlogrdr ->open()
  ecryptfs: ->f_op is never NULL
  android: ->f_op is never NULL
  nouveau: __iomem misannotations
  missing annotation in fs/file.c
  fs: namespace: suppress 'may be used uninitialized' warnings
  ...

Documentation/filesystems/vfs.txt

@@ -237,7 +237,7 @@ noted. This means that most methods can block safely. All methods are
 only called from a process context (i.e. not from an interrupt handler
 or bottom half).
 
-  alloc_inode: this method is called by inode_alloc() to allocate memory
+  alloc_inode: this method is called by alloc_inode() to allocate memory
  	for struct inode and initialize it.  If this function is not
  	defined, a simple 'struct inode' is allocated.  Normally
  	alloc_inode will be used to allocate a larger structure which

arch/alpha/kernel/osf_sys.c

@@ -446,7 +446,8 @@ struct procfs_args {
  * unhappy with OSF UFS. [CHECKME]
  */
 static int
-osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
+osf_ufs_mount(const char __user *dirname,
+	      struct ufs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -466,7 +467,8 @@ osf_ufs_mount(const char *dirname, struct ufs_args __user *args, int flags)
 }
 
 static int
-osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
+osf_cdfs_mount(const char __user *dirname,
+	       struct cdfs_args __user *args, int flags)
 {
 	int retval;
 	struct cdfs_args tmp;
@@ -486,7 +488,8 @@ osf_cdfs_mount(const char *dirname, struct cdfs_args __user *args, int flags)
 }
 
 static int
-osf_procfs_mount(const char *dirname, struct procfs_args __user *args, int flags)
+osf_procfs_mount(const char __user *dirname,
+		 struct procfs_args __user *args, int flags)
 {
 	struct procfs_args tmp;
 
@@ -500,28 +503,22 @@ SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, const char __user *, path,
 		int, flag, void __user *, data)
 {
 	int retval;
-	struct filename *name;
 
-	name = getname(path);
-	retval = PTR_ERR(name);
-	if (IS_ERR(name))
-		goto out;
 	switch (typenr) {
 	case 1:
-		retval = osf_ufs_mount(name->name, data, flag);
+		retval = osf_ufs_mount(path, data, flag);
 		break;
 	case 6:
-		retval = osf_cdfs_mount(name->name, data, flag);
+		retval = osf_cdfs_mount(path, data, flag);
 		break;
 	case 9:
-		retval = osf_procfs_mount(name->name, data, flag);
+		retval = osf_procfs_mount(path, data, flag);
 		break;
 	default:
 		retval = -EINVAL;
 		printk("osf_mount(%ld, %x)\n", typenr, flag);
 	}
-	putname(name);
- out:
+
 	return retval;
 }
 

arch/x86/ia32/ia32_aout.c

@@ -308,11 +308,8 @@ static int load_aout_binary(struct linux_binprm *bprm)
 		(current->mm->start_brk = N_BSSADDR(ex));
 
 	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0) {
-		/* Someone check-me: is this error path enough? */
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		return retval;
-	}
 
 	install_exec_creds(bprm);
 
@@ -324,17 +321,13 @@ static int load_aout_binary(struct linux_binprm *bprm)
 
 		error = vm_brk(text_addr & PAGE_MASK, map_size);
 
-		if (error != (text_addr & PAGE_MASK)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != (text_addr & PAGE_MASK))
 			return error;
-		}
 
 		error = read_code(bprm->file, text_addr, 32,
 				  ex.a_text + ex.a_data);
-		if ((signed long)error < 0) {
-			send_sig(SIGKILL, current, 0);
+		if ((signed long)error < 0)
 			return error;
-		}
 	} else {
 #ifdef WARN_OLD
 		static unsigned long error_time, error_time2;
@@ -368,20 +361,16 @@ static int load_aout_binary(struct linux_binprm *bprm)
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset);
 
-		if (error != N_TXTADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_TXTADDR(ex))
 			return error;
-		}
 
 		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset + ex.a_text);
-		if (error != N_DATADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_DATADDR(ex))
 			return error;
-		}
 	}
 beyond_if:
 	set_binfmt(&aout_format);

drivers/block/rsxx/core.c

@@ -62,12 +62,6 @@ static DEFINE_SPINLOCK(rsxx_ida_lock);
 
 /* --------------------Debugfs Setup ------------------- */
 
-struct rsxx_cram {
-	u32 f_pos;
-	u32 offset;
-	void *i_private;
-};
-
 static int rsxx_attr_pci_regs_show(struct seq_file *m, void *p)
 {
 	struct rsxx_cardinfo *card = m->private;
@@ -184,93 +178,50 @@ static int rsxx_attr_pci_regs_open(struct inode *inode, struct file *file)
 static ssize_t rsxx_cram_read(struct file *fp, char __user *ubuf,
 			      size_t cnt, loff_t *ppos)
 {
-	struct rsxx_cram *info = fp->private_data;
-	struct rsxx_cardinfo *card = info->i_private;
+	struct rsxx_cardinfo *card = file_inode(fp)->i_private;
 	char *buf;
-	int st;
+	ssize_t st;
 
-	buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+	buf = kzalloc(cnt, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	info->f_pos = (u32)*ppos + info->offset;
-
-	st = rsxx_creg_read(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
-	if (st)
-		return st;
-
-	st = copy_to_user(ubuf, buf, cnt);
+	st = rsxx_creg_read(card, CREG_ADD_CRAM + (u32)*ppos, cnt, buf, 1);
+	if (!st)
+		st = copy_to_user(ubuf, buf, cnt);
+	kfree(buf);
 	if (st)
 		return st;
-
-	info->offset += cnt;
-
-	kfree(buf);
-
+	*ppos += cnt;
 	return cnt;
 }
 
 static ssize_t rsxx_cram_write(struct file *fp, const char __user *ubuf,
 			       size_t cnt, loff_t *ppos)
 {
-	struct rsxx_cram *info = fp->private_data;
-	struct rsxx_cardinfo *card = info->i_private;
+	struct rsxx_cardinfo *card = file_inode(fp)->i_private;
 	char *buf;
-	int st;
+	ssize_t st;
 
-	buf = kzalloc(sizeof(*buf) * cnt, GFP_KERNEL);
+	buf = kzalloc(cnt, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
 	st = copy_from_user(buf, ubuf, cnt);
+	if (!st)
+		st = rsxx_creg_write(card, CREG_ADD_CRAM + (u32)*ppos, cnt,
+				     buf, 1);
+	kfree(buf);
 	if (st)
 		return st;
-
-	info->f_pos = (u32)*ppos + info->offset;
-
-	st = rsxx_creg_write(card, CREG_ADD_CRAM + info->f_pos, cnt, buf, 1);
-	if (st)
-		return st;
-
-	info->offset += cnt;
-
-	kfree(buf);
-
+	*ppos += cnt;
 	return cnt;
 }
 
-static int rsxx_cram_open(struct inode *inode, struct file *file)
-{
-	struct rsxx_cram *info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->i_private = inode->i_private;
-	info->f_pos = file->f_pos;
-	file->private_data = info;
-
-	return 0;
-}
-
-static int rsxx_cram_release(struct inode *inode, struct file *file)
-{
-	struct rsxx_cram *info = file->private_data;
-
-	if (!info)
-		return 0;
-
-	kfree(info);
-	file->private_data = NULL;
-
-	return 0;
-}
-
 static const struct file_operations debugfs_cram_fops = {
 	.owner		= THIS_MODULE,
-	.open		= rsxx_cram_open,
 	.read		= rsxx_cram_read,
 	.write		= rsxx_cram_write,
-	.release	= rsxx_cram_release,
 };
 
 static const struct file_operations debugfs_stats_fops = {

drivers/bluetooth/hci_vhci.c

@@ -160,13 +160,11 @@ static int vhci_create_device(struct vhci_data *data, __u8 opcode)
 }
 
 static inline ssize_t vhci_get_user(struct vhci_data *data,
-				    const struct iovec *iov,
-				    unsigned long count)
+				    struct iov_iter *from)
 {
-	size_t len = iov_length(iov, count);
+	size_t len = iov_iter_count(from);
 	struct sk_buff *skb;
 	__u8 pkt_type, opcode;
-	unsigned long i;
 	int ret;
 
 	if (len < 2 || len > HCI_MAX_FRAME_SIZE)
@@ -176,12 +174,9 @@ static inline ssize_t vhci_get_user(struct vhci_data *data,
 	if (!skb)
 		return -ENOMEM;
 
-	for (i = 0; i < count; i++) {
-		if (copy_from_user(skb_put(skb, iov[i].iov_len),
-				   iov[i].iov_base, iov[i].iov_len)) {
-			kfree_skb(skb);
-			return -EFAULT;
-		}
+	if (copy_from_iter(skb_put(skb, len), len, from) != len) {
+		kfree_skb(skb);
+		return -EFAULT;
 	}
 
 	pkt_type = *((__u8 *) skb->data);
@@ -294,13 +289,12 @@ static ssize_t vhci_read(struct file *file,
 	return ret;
 }
 
-static ssize_t vhci_write(struct kiocb *iocb, const struct iovec *iov,
-			  unsigned long count, loff_t pos)
+static ssize_t vhci_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct vhci_data *data = file->private_data;
 
-	return vhci_get_user(data, iov, count);
+	return vhci_get_user(data, from);
 }
 
 static unsigned int vhci_poll(struct file *file, poll_table *wait)
@@ -365,7 +359,7 @@ static int vhci_release(struct inode *inode, struct file *file)
 static const struct file_operations vhci_fops = {
 	.owner		= THIS_MODULE,
 	.read		= vhci_read,
-	.aio_write	= vhci_write,
+	.write_iter	= vhci_write,
 	.poll		= vhci_poll,
 	.open		= vhci_open,
 	.release	= vhci_release,

drivers/char/mem.c

@@ -622,53 +622,23 @@ static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out,
 	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
 }
 
-static ssize_t read_zero(struct file *file, char __user *buf,
-			 size_t count, loff_t *ppos)
+static ssize_t read_iter_zero(struct kiocb *iocb, struct iov_iter *iter)
 {
-	size_t written;
-
-	if (!count)
-		return 0;
-
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		return -EFAULT;
-
-	written = 0;
-	while (count) {
-		unsigned long unwritten;
-		size_t chunk = count;
+	size_t written = 0;
 
+	while (iov_iter_count(iter)) {
+		size_t chunk = iov_iter_count(iter), n;
 		if (chunk > PAGE_SIZE)
 			chunk = PAGE_SIZE;	/* Just for latency reasons */
-		unwritten = __clear_user(buf, chunk);
-		written += chunk - unwritten;
-		if (unwritten)
-			break;
+		n = iov_iter_zero(chunk, iter);
+		if (!n && iov_iter_count(iter))
+			return written ? written : -EFAULT;
+		written += n;
 		if (signal_pending(current))
 			return written ? written : -ERESTARTSYS;
-		buf += chunk;
-		count -= chunk;
 		cond_resched();
 	}
-	return written ? written : -EFAULT;
-}
-
-static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov,
-			     unsigned long nr_segs, loff_t pos)
-{
-	size_t written = 0;
-	unsigned long i;
-	ssize_t ret;
-
-	for (i = 0; i < nr_segs; i++) {
-		ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len,
-				&pos);
-		if (ret < 0)
-			break;
-		written += ret;
-	}
-
-	return written ? written : -EFAULT;
+	return written;
 }
 
 static int mmap_zero(struct file *file, struct vm_area_struct *vma)
@@ -738,7 +708,6 @@ static int open_port(struct inode *inode, struct file *filp)
 #define zero_lseek	null_lseek
 #define full_lseek      null_lseek
 #define write_zero	write_null
-#define read_full       read_zero
 #define aio_write_zero	aio_write_null
 #define open_mem	open_port
 #define open_kmem	open_mem
@@ -783,9 +752,9 @@ static const struct file_operations port_fops = {
 
 static const struct file_operations zero_fops = {
 	.llseek		= zero_lseek,
-	.read		= read_zero,
+	.read		= new_sync_read,
 	.write		= write_zero,
-	.aio_read	= aio_read_zero,
+	.read_iter	= read_iter_zero,
 	.aio_write	= aio_write_zero,
 	.mmap		= mmap_zero,
 };
@@ -802,7 +771,8 @@ static struct backing_dev_info zero_bdi = {
 
 static const struct file_operations full_fops = {
 	.llseek		= full_lseek,
-	.read		= read_full,
+	.read		= new_sync_read,
+	.read_iter	= read_iter_zero,
 	.write		= write_full,
 };
 

drivers/dma-buf/dma-buf.c

@@ -799,7 +799,7 @@ static int dma_buf_describe(struct seq_file *s)
 		seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\n",
 				buf_obj->size,
 				buf_obj->file->f_flags, buf_obj->file->f_mode,
-				(long)(buf_obj->file->f_count.counter),
+				file_count(buf_obj->file),
 				buf_obj->exp_name);
 
 		seq_puts(s, "\tAttached Devices:\n");

drivers/gpu/drm/nouveau/nouveau_nvif.c

@@ -40,12 +40,12 @@
 #include "nouveau_usif.h"
 
 static void
-nvkm_client_unmap(void *priv, void *ptr, u32 size)
+nvkm_client_unmap(void *priv, void __iomem *ptr, u32 size)
 {
 	iounmap(ptr);
 }
 
-static void *
+static void __iomem *
 nvkm_client_map(void *priv, u64 handle, u32 size)
 {
 	return ioremap(handle, size);

drivers/gpu/drm/nouveau/nvif/driver.h

@@ -9,8 +9,8 @@ struct nvif_driver {
 	int (*suspend)(void *priv);
 	int (*resume)(void *priv);
 	int (*ioctl)(void *priv, bool super, void *data, u32 size, void **hack);
-	void *(*map)(void *priv, u64 handle, u32 size);
-	void (*unmap)(void *priv, void *ptr, u32 size);
+	void __iomem *(*map)(void *priv, u64 handle, u32 size);
+	void (*unmap)(void *priv, void __iomem *ptr, u32 size);
 	bool keep;
 };
 

drivers/gpu/drm/nouveau/nvif/object.h

@@ -14,7 +14,7 @@ struct nvif_object {
 	void *priv; /*XXX: hack */
 	void (*dtor)(struct nvif_object *);
 	struct {
-		void *ptr;
+		void __iomem *ptr;
 		u32 size;
 	} map;
 };
@@ -42,7 +42,7 @@ void nvif_object_unmap(struct nvif_object *);
 	struct nvif_object *_object = nvif_object(a);                          \
 	u32 _data;                                                             \
 	if (likely(_object->map.ptr))                                          \
-		_data = ioread##b##_native((u8 *)_object->map.ptr + (c));      \
+		_data = ioread##b##_native((u8 __iomem *)_object->map.ptr + (c));      \
 	else                                                                   \
 		_data = nvif_object_rd(_object, (b) / 8, (c));                 \
 	_data;                                                                 \
@@ -50,7 +50,7 @@ void nvif_object_unmap(struct nvif_object *);
 #define nvif_wr(a,b,c,d) ({                                                    \
 	struct nvif_object *_object = nvif_object(a);                          \
 	if (likely(_object->map.ptr))                                          \
-		iowrite##b##_native((d), (u8 *)_object->map.ptr + (c));        \
+		iowrite##b##_native((d), (u8 __iomem *)_object->map.ptr + (c));        \
 	else                                                                   \
 		nvif_object_wr(_object, (b) / 8, (c), (d));                    \
 })

drivers/infiniband/hw/ipath/ipath_fs.c

@@ -82,7 +82,6 @@ static int create_file(const char *name, umode_t mode,
 {
 	int error;
 
-	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(*dentry))

drivers/infiniband/hw/qib/qib_fs.c

@@ -89,7 +89,6 @@ static int create_file(const char *name, umode_t mode,
 {
 	int error;
 
-	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(*dentry))

drivers/misc/carma/carma-fpga-program.c

@@ -749,13 +749,8 @@ static ssize_t fpga_read(struct file *filp, char __user *buf, size_t count,
 			 loff_t *f_pos)
 {
 	struct fpga_dev *priv = filp->private_data;
-
-	count = min_t(size_t, priv->bytes - *f_pos, count);
-	if (copy_to_user(buf, priv->vb.vaddr + *f_pos, count))
-		return -EFAULT;
-
-	*f_pos += count;
-	return count;
+	return simple_read_from_buffer(buf, count, ppos,
+				       priv->vb.vaddr, priv->bytes);
 }
 
 static loff_t fpga_llseek(struct file *filp, loff_t offset, int origin)
@@ -767,26 +762,7 @@ static loff_t fpga_llseek(struct file *filp, loff_t offset, int origin)
 	if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
 		return -EINVAL;
 
-	switch (origin) {
-	case SEEK_SET: /* seek relative to the beginning of the file */
-		newpos = offset;
-		break;
-	case SEEK_CUR: /* seek relative to current position in the file */
-		newpos = filp->f_pos + offset;
-		break;
-	case SEEK_END: /* seek relative to the end of the file */
-		newpos = priv->fw_size - offset;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* check for sanity */
-	if (newpos > priv->fw_size)
-		return -EINVAL;
-
-	filp->f_pos = newpos;
-	return newpos;
+	return fixed_size_llseek(file, offset, origin, priv->fw_size);
 }
 
 static const struct file_operations fpga_fops = {

drivers/net/ppp/ppp_generic.c

@@ -594,7 +594,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			if (file == ppp->owner)
 				ppp_shutdown_interface(ppp);
 		}
-		if (atomic_long_read(&file->f_count) <= 2) {
+		if (atomic_long_read(&file->f_count) < 2) {
 			ppp_release(NULL, file);
 			err = 0;
 		} else

drivers/s390/char/vmlogrdr.c

@@ -338,7 +338,6 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp)
 
 	/* set the file options */
 	filp->private_data = logptr;
-	filp->f_op = &vmlogrdr_fops;
 
 	/* start recording for this service*/
 	if (logptr->autorecording) {

drivers/staging/android/ashmem.c

@@ -339,7 +339,7 @@ static loff_t ashmem_llseek(struct file *file, loff_t offset, int origin)
 		goto out;
 	}
 
-	ret = asma->file->f_op->llseek(asma->file, offset, origin);
+	ret = vfs_llseek(asma->file, offset, origin);
 	if (ret < 0)
 		goto out;
 

drivers/staging/android/ion/compat_ion.c

@@ -125,7 +125,7 @@ long compat_ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	long ret;
 
-	if (!filp->f_op || !filp->f_op->unlocked_ioctl)
+	if (!filp->f_op->unlocked_ioctl)
 		return -ENOTTY;
 
 	switch (cmd) {

drivers/staging/android/logger.c

@@ -411,69 +411,18 @@ static void fix_up_readers(struct logger_log *log, size_t len)
 }
 
 /*
- * do_write_log - writes 'len' bytes from 'buf' to 'log'
- *
- * The caller needs to hold log->mutex.
- */
-static void do_write_log(struct logger_log *log, const void *buf, size_t count)
-{
-	size_t len;
-
-	len = min(count, log->size - log->w_off);
-	memcpy(log->buffer + log->w_off, buf, len);
-
-	if (count != len)
-		memcpy(log->buffer, buf + len, count - len);
-
-	log->w_off = logger_offset(log, log->w_off + count);
-
-}
-
-/*
- * do_write_log_user - writes 'len' bytes from the user-space buffer 'buf' to
- * the log 'log'
- *
- * The caller needs to hold log->mutex.
- *
- * Returns 'count' on success, negative error code on failure.
- */
-static ssize_t do_write_log_from_user(struct logger_log *log,
-				      const void __user *buf, size_t count)
-{
-	size_t len;
-
-	len = min(count, log->size - log->w_off);
-	if (len && copy_from_user(log->buffer + log->w_off, buf, len))
-		return -EFAULT;
-
-	if (count != len)
-		if (copy_from_user(log->buffer, buf + len, count - len))
-			/*
-			 * Note that by not updating w_off, this abandons the
-			 * portion of the new entry that *was* successfully
-			 * copied, just above.  This is intentional to avoid
-			 * message corruption from missing fragments.
-			 */
-			return -EFAULT;
-
-	log->w_off = logger_offset(log, log->w_off + count);
-
-	return count;
-}
-
-/*
- * logger_aio_write - our write method, implementing support for write(),
+ * logger_write_iter - our write method, implementing support for write(),
  * writev(), and aio_write(). Writes are our fast path, and we try to optimize
  * them above all else.
  */
-static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t ppos)
+static ssize_t logger_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct logger_log *log = file_get_log(iocb->ki_filp);
-	size_t orig;
 	struct logger_entry header;
 	struct timespec now;
-	ssize_t ret = 0;
+	size_t len, count;
+
+	count = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
 
 	now = current_kernel_time();
 
@@ -482,7 +431,7 @@ static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	header.sec = now.tv_sec;
 	header.nsec = now.tv_nsec;
 	header.euid = current_euid();
-	header.len = min_t(size_t, iocb->ki_nbytes, LOGGER_ENTRY_MAX_PAYLOAD);
+	header.len = count;
 	header.hdr_size = sizeof(struct logger_entry);
 
 	/* null writes succeed, return zero */
@@ -491,8 +440,6 @@ static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	mutex_lock(&log->mutex);
 
-	orig = log->w_off;
-
 	/*
 	 * Fix up any readers, pulling them forward to the first readable
 	 * entry after (what will be) the new write offset. We do this now
@@ -501,33 +448,35 @@ static ssize_t logger_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	 */
 	fix_up_readers(log, sizeof(struct logger_entry) + header.len);
 
-	do_write_log(log, &header, sizeof(struct logger_entry));
-
-	while (nr_segs-- > 0) {
-		size_t len;
-		ssize_t nr;
+	len = min(sizeof(header), log->size - log->w_off);
+	memcpy(log->buffer + log->w_off, &header, len);
+	memcpy(log->buffer, (char *)&header + len, sizeof(header) - len);
 
-		/* figure out how much of this vector we can keep */
-		len = min_t(size_t, iov->iov_len, header.len - ret);
+	len = min(count, log->size - log->w_off);
 
-		/* write out this segment's payload */
-		nr = do_write_log_from_user(log, iov->iov_base, len);
-		if (unlikely(nr < 0)) {
-			log->w_off = orig;
-			mutex_unlock(&log->mutex);
-			return nr;
-		}
+	if (copy_from_iter(log->buffer + log->w_off, len, from) != len) {
+		/*
+		 * Note that by not updating w_off, this abandons the
+		 * portion of the new entry that *was* successfully
+		 * copied, just above.  This is intentional to avoid
+		 * message corruption from missing fragments.
+		 */
+		mutex_unlock(&log->mutex);
+		return -EFAULT;
+	}
 
-		iov++;
-		ret += nr;
+	if (copy_from_iter(log->buffer, count - len, from) != count - len) {
+		mutex_unlock(&log->mutex);
+		return -EFAULT;
 	}
 
+	log->w_off = logger_offset(log, log->w_off + count);
 	mutex_unlock(&log->mutex);
 
 	/* wake up any blocked readers */
 	wake_up_interruptible(&log->wq);
 
-	return ret;
+	return len;
 }
 
 static struct logger_log *get_log_from_minor(int minor)
@@ -736,7 +685,7 @@ static long logger_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 static const struct file_operations logger_fops = {
 	.owner = THIS_MODULE,
 	.read = logger_read,
-	.aio_write = logger_aio_write,
+	.write_iter = logger_write_iter,
 	.poll = logger_poll,
 	.unlocked_ioctl = logger_ioctl,
 	.compat_ioctl = logger_ioctl,

drivers/staging/vme/devices/vme_user.c

@@ -410,41 +410,19 @@ static ssize_t vme_user_write(struct file *file, const char __user *buf,
 
 static loff_t vme_user_llseek(struct file *file, loff_t off, int whence)
 {
-	loff_t absolute = -1;
 	unsigned int minor = MINOR(file_inode(file)->i_rdev);
 	size_t image_size;
+	loff_t res;
 
 	if (minor == CONTROL_MINOR)
 		return -EINVAL;
 
 	mutex_lock(&image[minor].mutex);
 	image_size = vme_get_size(image[minor].resource);
-
-	switch (whence) {
-	case SEEK_SET:
-		absolute = off;
-		break;
-	case SEEK_CUR:
-		absolute = file->f_pos + off;
-		break;
-	case SEEK_END:
-		absolute = image_size + off;
-		break;
-	default:
-		mutex_unlock(&image[minor].mutex);
-		return -EINVAL;
-	}
-
-	if ((absolute < 0) || (absolute >= image_size)) {
-		mutex_unlock(&image[minor].mutex);
-		return -EINVAL;
-	}
-
-	file->f_pos = absolute;
-
+	res = fixed_size_llseek(file, off, whence, image_size);
 	mutex_unlock(&image[minor].mutex);
 
-	return absolute;
+	return res;
 }
 
 /*

drivers/usb/gadget/function/f_fs.c

@@ -164,10 +164,9 @@ struct ffs_desc_helper {
 static int  __must_check ffs_epfiles_create(struct ffs_data *ffs);
 static void ffs_epfiles_destroy(struct ffs_epfile *epfiles, unsigned count);
 
-static struct inode *__must_check
+static struct dentry *
 ffs_sb_create_file(struct super_block *sb, const char *name, void *data,
-		   const struct file_operations *fops,
-		   struct dentry **dentry_p);
+		   const struct file_operations *fops);
 
 /* Devices management *******************************************************/
 
@@ -1119,10 +1118,9 @@ ffs_sb_make_inode(struct super_block *sb, void *data,
 }
 
 /* Create "regular" file */
-static struct inode *ffs_sb_create_file(struct super_block *sb,
+static struct dentry *ffs_sb_create_file(struct super_block *sb,
 					const char *name, void *data,
-					const struct file_operations *fops,
-					struct dentry **dentry_p)
+					const struct file_operations *fops)
 {
 	struct ffs_data	*ffs = sb->s_fs_info;
 	struct dentry	*dentry;
@@ -1141,10 +1139,7 @@ static struct inode *ffs_sb_create_file(struct super_block *sb,
 	}
 
 	d_add(dentry, inode);
-	if (dentry_p)
-		*dentry_p = dentry;
-
-	return inode;
+	return dentry;
 }
 
 /* Super block */
@@ -1189,7 +1184,7 @@ static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
 
 	/* EP0 file */
 	if (unlikely(!ffs_sb_create_file(sb, "ep0", ffs,
-					 &ffs_ep0_operations, NULL)))
+					 &ffs_ep0_operations)))
 		return -ENOMEM;
 
 	return 0;
@@ -1561,9 +1556,10 @@ static int ffs_epfiles_create(struct ffs_data *ffs)
 			sprintf(epfiles->name, "ep%02x", ffs->eps_addrmap[i]);
 		else
 			sprintf(epfiles->name, "ep%u", i);
-		if (!unlikely(ffs_sb_create_file(ffs->sb, epfiles->name, epfile,
-						 &ffs_epfile_operations,
-						 &epfile->dentry))) {
+		epfile->dentry = ffs_sb_create_file(ffs->sb, epfiles->name,
+						 epfile,
+						 &ffs_epfile_operations);
+		if (unlikely(!epfile->dentry)) {
 			ffs_epfiles_destroy(epfiles, i - 1);
 			return -ENOMEM;
 		}

drivers/usb/gadget/legacy/inode.c

@@ -198,7 +198,6 @@ struct ep_data {
 	struct list_head		epfiles;
 	wait_queue_head_t		wait;
 	struct dentry			*dentry;
-	struct inode			*inode;
 };
 
 static inline void get_ep (struct ep_data *data)
@@ -1618,10 +1617,9 @@ static void destroy_ep_files (struct dev_data *dev)
 }
 
 
-static struct inode *
+static struct dentry *
 gadgetfs_create_file (struct super_block *sb, char const *name,
-		void *data, const struct file_operations *fops,
-		struct dentry **dentry_p);
+		void *data, const struct file_operations *fops);
 
 static int activate_ep_files (struct dev_data *dev)
 {
@@ -1649,10 +1647,9 @@ static int activate_ep_files (struct dev_data *dev)
 		if (!data->req)
 			goto enomem1;
 
-		data->inode = gadgetfs_create_file (dev->sb, data->name,
-				data, &ep_config_operations,
-				&data->dentry);
-		if (!data->inode)
+		data->dentry = gadgetfs_create_file (dev->sb, data->name,
+				data, &ep_config_operations);
+		if (!data->dentry)
 			goto enomem2;
 		list_add_tail (&data->epfiles, &dev->epfiles);
 	}
@@ -2012,10 +2009,9 @@ gadgetfs_make_inode (struct super_block *sb,
 /* creates in fs root directory, so non-renamable and non-linkable.
  * so inode and dentry are paired, until device reconfig.
  */
-static struct inode *
+static struct dentry *
 gadgetfs_create_file (struct super_block *sb, char const *name,
-		void *data, const struct file_operations *fops,
-		struct dentry **dentry_p)
+		void *data, const struct file_operations *fops)
 {
 	struct dentry	*dentry;
 	struct inode	*inode;
@@ -2031,8 +2027,7 @@ gadgetfs_create_file (struct super_block *sb, char const *name,
 		return NULL;
 	}
 	d_add (dentry, inode);
-	*dentry_p = dentry;
-	return inode;
+	return dentry;
 }
 
 static const struct super_operations gadget_fs_operations = {
@@ -2080,9 +2075,8 @@ gadgetfs_fill_super (struct super_block *sb, void *opts, int silent)
 		goto Enomem;
 
 	dev->sb = sb;
-	if (!gadgetfs_create_file (sb, CHIP,
-				dev, &dev_init_operations,
-				&dev->dentry)) {
+	dev->dentry = gadgetfs_create_file(sb, CHIP, dev, &dev_init_operations);
+	if (!dev->dentry) {
 		put_dev(dev);
 		goto Enomem;
 	}

fs/9p/fid.c

@@ -65,8 +65,8 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
 {
 	struct p9_fid *fid, *ret;
 
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p) uid %d any %d\n",
-		 dentry->d_name.name, dentry, from_kuid(&init_user_ns, uid),
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p) uid %d any %d\n",
+		 dentry, dentry, from_kuid(&init_user_ns, uid),
 		 any);
 	ret = NULL;
 	/* we'll recheck under lock if there's anything to look in */

fs/9p/vfs_addr.c

@@ -266,8 +266,8 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 	 * Now that we do caching with cache mode enabled, We need
 	 * to support direct IO
 	 */
-	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
-		 iocb->ki_filp->f_path.dentry->d_name.name,
+	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%pD) off/no(%lld/%lu) EINVAL\n",
+		 iocb->ki_filp,
 		 (long long)pos, iter->nr_segs);
 
 	return -EINVAL;

fs/9p/vfs_dentry.c

@@ -49,8 +49,8 @@
  */
 static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 {
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
-		 dentry->d_name.name, dentry);
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+		 dentry, dentry);
 
 	/* Don't cache negative dentries */
 	if (!dentry->d_inode)
@@ -67,8 +67,8 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 static void v9fs_dentry_release(struct dentry *dentry)
 {
 	struct hlist_node *p, *n;
-	p9_debug(P9_DEBUG_VFS, " dentry: %s (%p)\n",
-		 dentry->d_name.name, dentry);
+	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
+		 dentry, dentry);
 	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
 		p9_client_clunk(hlist_entry(p, struct p9_fid, dlist));
 	dentry->d_fsdata = NULL;

fs/9p/vfs_dir.c

@@ -116,7 +116,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 	int reclen = 0;
 	struct p9_rdir *rdir;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", file->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
 	fid = file->private_data;
 
 	buflen = fid->clnt->msize - P9_IOHDRSZ;
@@ -172,7 +172,7 @@ static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx)
 	struct p9_rdir *rdir;
 	struct p9_dirent curdirent;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", file->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pD\n", file);
 	fid = file->private_data;
 
 	buflen = fid->clnt->msize - P9_READDIRHDRSZ;

fs/9p/vfs_file.c

@@ -301,8 +301,8 @@ static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
 	struct inode *inode = file_inode(filp);
 	int ret = -ENOLCK;
 
-	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
-		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+		 filp, cmd, fl, filp);
 
 	/* No mandatory locks */
 	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
@@ -337,8 +337,8 @@ static int v9fs_file_flock_dotl(struct file *filp, int cmd,
 	struct inode *inode = file_inode(filp);
 	int ret = -ENOLCK;
 
-	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n",
-		 filp, cmd, fl, filp->f_path.dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n",
+		 filp, cmd, fl, filp);
 
 	/* No mandatory locks */
 	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)

fs/9p/vfs_inode.c

@@ -648,7 +648,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	struct p9_fid *dfid, *ofid, *fid;
 	struct inode *inode;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 
 	err = 0;
 	ofid = NULL;
@@ -755,7 +755,7 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	struct p9_fid *fid;
 	struct v9fs_session_info *v9ses;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 	err = 0;
 	v9ses = v9fs_inode2v9ses(dir);
 	perm = unixmode2p9mode(v9ses, mode | S_IFDIR);
@@ -791,8 +791,8 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	char *name;
 
-	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n",
-		 dir, dentry->d_name.name, dentry, flags);
+	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n",
+		 dir, dentry, dentry, flags);
 
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -1239,7 +1239,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	struct p9_fid *fid;
 	struct p9_wstat *st;
 
-	p9_debug(P9_DEBUG_VFS, " %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, " %pd\n", dentry);
 	retval = -EPERM;
 	v9ses = v9fs_dentry2v9ses(dentry);
 	fid = v9fs_fid_lookup(dentry);
@@ -1262,8 +1262,8 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	retval = min(strlen(st->extension)+1, (size_t)buflen);
 	memcpy(buffer, st->extension, retval);
 
-	p9_debug(P9_DEBUG_VFS, "%s -> %s (%.*s)\n",
-		 dentry->d_name.name, st->extension, buflen, buffer);
+	p9_debug(P9_DEBUG_VFS, "%pd -> %s (%.*s)\n",
+		 dentry, st->extension, buflen, buffer);
 
 done:
 	p9stat_free(st);
@@ -1283,7 +1283,7 @@ static void *v9fs_vfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 	int len = 0;
 	char *link = __getname();
 
-	p9_debug(P9_DEBUG_VFS, "%s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
 	if (!link)
 		link = ERR_PTR(-ENOMEM);
@@ -1314,8 +1314,8 @@ v9fs_vfs_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
 {
 	char *s = nd_get_link(nd);
 
-	p9_debug(P9_DEBUG_VFS, " %s %s\n",
-		 dentry->d_name.name, IS_ERR(s) ? "<error>" : s);
+	p9_debug(P9_DEBUG_VFS, " %pd %s\n",
+		 dentry, IS_ERR(s) ? "<error>" : s);
 	if (!IS_ERR(s))
 		__putname(s);
 }
@@ -1364,8 +1364,8 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry,
 static int
 v9fs_vfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 {
-	p9_debug(P9_DEBUG_VFS, " %lu,%s,%s\n",
-		 dir->i_ino, dentry->d_name.name, symname);
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n",
+		 dir->i_ino, dentry, symname);
 
 	return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname);
 }
@@ -1386,8 +1386,8 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
 	char *name;
 	struct p9_fid *oldfid;
 
-	p9_debug(P9_DEBUG_VFS, " %lu,%s,%s\n",
-		 dir->i_ino, dentry->d_name.name, old_dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n",
+		 dir->i_ino, dentry, old_dentry);
 
 	oldfid = v9fs_fid_clone(old_dentry);
 	if (IS_ERR(oldfid))
@@ -1428,8 +1428,8 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rde
 	char *name;
 	u32 perm;
 
-	p9_debug(P9_DEBUG_VFS, " %lu,%s mode: %hx MAJOR: %u MINOR: %u\n",
-		 dir->i_ino, dentry->d_name.name, mode,
+	p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
+		 dir->i_ino, dentry, mode,
 		 MAJOR(rdev), MINOR(rdev));
 
 	if (!new_valid_dev(rdev))

fs/9p/vfs_inode_dotl.c

@@ -393,7 +393,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 	struct dentry *dir_dentry;
 	struct posix_acl *dacl = NULL, *pacl = NULL;
 
-	p9_debug(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
 	err = 0;
 	v9ses = v9fs_inode2v9ses(dir);
 
@@ -767,8 +767,8 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 	struct p9_fid *dfid, *oldfid;
 	struct v9fs_session_info *v9ses;
 
-	p9_debug(P9_DEBUG_VFS, "dir ino: %lu, old_name: %s, new_name: %s\n",
-		 dir->i_ino, old_dentry->d_name.name, dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "dir ino: %lu, old_name: %pd, new_name: %pd\n",
+		 dir->i_ino, old_dentry, dentry);
 
 	v9ses = v9fs_inode2v9ses(dir);
 	dir_dentry = dentry->d_parent;
@@ -917,7 +917,7 @@ v9fs_vfs_follow_link_dotl(struct dentry *dentry, struct nameidata *nd)
 	char *link = __getname();
 	char *target;
 
-	p9_debug(P9_DEBUG_VFS, "%s\n", dentry->d_name.name);
+	p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
 
 	if (!link) {
 		link = ERR_PTR(-ENOMEM);

fs/afs/dir.c

@@ -669,7 +669,6 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
 
 out_valid:
 	dentry->d_fsdata = dir_version;
-out_skip:
 	dput(parent);
 	key_put(key);
 	_leave(" = 1 [valid]");
@@ -682,10 +681,6 @@ not_found:
 	spin_unlock(&dentry->d_lock);
 
 out_bad:
-	/* don't unhash if we have submounts */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_skip;
-
 	_debug("dropping dentry %s/%s",
 	       parent->d_name.name, dentry->d_name.name);
 	dput(parent);

fs/autofs4/expire.c

@@ -255,12 +255,6 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 			struct autofs_info *ino = autofs4_dentry_ino(p);
 			unsigned int ino_count = atomic_read(&ino->count);
 
-			/*
-			 * Clean stale dentries below that have not been
-			 * invalidated after a mount fail during lookup
-			 */
-			d_invalidate(p);
-
 			/* allow for dget above and top is already dgot */
 			if (p == top)
 				ino_count += 2;

fs/binfmt_aout.c

@@ -256,11 +256,8 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		(current->mm->start_brk = N_BSSADDR(ex));
 
 	retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0) {
-		/* Someone check-me: is this error path enough? */
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		return retval;
-	}
 
 	install_exec_creds(bprm);
 
@@ -278,17 +275,13 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		map_size = ex.a_text+ex.a_data;
 #endif
 		error = vm_brk(text_addr & PAGE_MASK, map_size);
-		if (error != (text_addr & PAGE_MASK)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != (text_addr & PAGE_MASK))
 			return error;
-		}
 
 		error = read_code(bprm->file, text_addr, pos,
 				  ex.a_text+ex.a_data);
-		if ((signed long)error < 0) {
-			send_sig(SIGKILL, current, 0);
+		if ((signed long)error < 0)
 			return error;
-		}
 	} else {
 		if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
 		    (N_MAGIC(ex) != NMAGIC) && printk_ratelimit())
@@ -315,28 +308,22 @@ static int load_aout_binary(struct linux_binprm * bprm)
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
 			fd_offset);
 
-		if (error != N_TXTADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_TXTADDR(ex))
 			return error;
-		}
 
 		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
 				fd_offset + ex.a_text);
-		if (error != N_DATADDR(ex)) {
-			send_sig(SIGKILL, current, 0);
+		if (error != N_DATADDR(ex))
 			return error;
-		}
 	}
 beyond_if:
 	set_binfmt(&aout_format);
 
 	retval = set_brk(current->mm->start_brk, current->mm->brk);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		return retval;
-	}
 
 	current->mm->start_stack =
 		(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);

fs/binfmt_elf.c

@@ -738,10 +738,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	   change some of these later */
 	retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
 				 executable_stack);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		goto out_free_dentry;
-	}
 	
 	current->mm->start_stack = bprm->p;
 
@@ -763,10 +761,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			   and clear the area.  */
 			retval = set_brk(elf_bss + load_bias,
 					 elf_brk + load_bias);
-			if (retval) {
-				send_sig(SIGKILL, current, 0);
+			if (retval)
 				goto out_free_dentry;
-			}
 			nbyte = ELF_PAGEOFFSET(elf_bss);
 			if (nbyte) {
 				nbyte = ELF_MIN_ALIGN - nbyte;
@@ -820,7 +816,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
 				elf_prot, elf_flags, 0);
 		if (BAD_ADDR(error)) {
-			send_sig(SIGKILL, current, 0);
 			retval = IS_ERR((void *)error) ?
 				PTR_ERR((void*)error) : -EINVAL;
 			goto out_free_dentry;
@@ -851,7 +846,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		    elf_ppnt->p_memsz > TASK_SIZE ||
 		    TASK_SIZE - elf_ppnt->p_memsz < k) {
 			/* set_brk can never work. Avoid overflows. */
-			send_sig(SIGKILL, current, 0);
 			retval = -EINVAL;
 			goto out_free_dentry;
 		}
@@ -883,12 +877,9 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	 * up getting placed where the bss needs to go.
 	 */
 	retval = set_brk(elf_bss, elf_brk);
-	if (retval) {
-		send_sig(SIGKILL, current, 0);
+	if (retval)
 		goto out_free_dentry;
-	}
 	if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
-		send_sig(SIGSEGV, current, 0);
 		retval = -EFAULT; /* Nobody gets to see this, but.. */
 		goto out_free_dentry;
 	}
@@ -909,7 +900,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			elf_entry += loc->interp_elf_ex.e_entry;
 		}
 		if (BAD_ADDR(elf_entry)) {
-			force_sig(SIGSEGV, current);
 			retval = IS_ERR((void *)elf_entry) ?
 					(int)elf_entry : -EINVAL;
 			goto out_free_dentry;
@@ -922,7 +912,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	} else {
 		elf_entry = loc->elf_ex.e_entry;
 		if (BAD_ADDR(elf_entry)) {
-			force_sig(SIGSEGV, current);
 			retval = -EINVAL;
 			goto out_free_dentry;
 		}
@@ -934,19 +923,15 @@ static int load_elf_binary(struct linux_binprm *bprm)
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
 	retval = arch_setup_additional_pages(bprm, !!elf_interpreter);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		goto out;
-	}
 #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
 
 	install_exec_creds(bprm);
 	retval = create_elf_tables(bprm, &loc->elf_ex,
 			  load_addr, interp_load_addr);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
+	if (retval < 0)
 		goto out;
-	}
 	/* N.B. passed_fileno might not be initialized? */
 	current->mm->end_code = end_code;
 	current->mm->start_code = start_code;

fs/binfmt_elf_fdpic.c

@@ -317,8 +317,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 		goto error;
 
 	/* there's now no turning back... the old userspace image is dead,
-	 * defunct, deceased, etc. after this point we have to exit via
-	 * error_kill */
+	 * defunct, deceased, etc.
+	 */
 	set_personality(PER_LINUX_FDPIC);
 	if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
@@ -343,24 +343,22 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 
 	retval = setup_arg_pages(bprm, current->mm->start_stack,
 				 executable_stack);
-	if (retval < 0) {
-		send_sig(SIGKILL, current, 0);
-		goto error_kill;
-	}
+	if (retval < 0)
+		goto error;
 #endif
 
 	/* load the executable and interpreter into memory */
 	retval = elf_fdpic_map_file(&exec_params, bprm->file, current->mm,
 				    "executable");
 	if (retval < 0)
-		goto error_kill;
+		goto error;
 
 	if (interpreter_name) {
 		retval = elf_fdpic_map_file(&interp_params, interpreter,
 					    current->mm, "interpreter");
 		if (retval < 0) {
 			printk(KERN_ERR "Unable to load interpreter\n");
-			goto error_kill;
+			goto error;
 		}
 
 		allow_write_access(interpreter);
@@ -397,7 +395,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	if (IS_ERR_VALUE(current->mm->start_brk)) {
 		retval = current->mm->start_brk;
 		current->mm->start_brk = 0;
-		goto error_kill;
+		goto error;
 	}
 
 	current->mm->brk = current->mm->start_brk;
@@ -410,7 +408,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	install_exec_creds(bprm);
 	if (create_elf_fdpic_tables(bprm, current->mm,
 				    &exec_params, &interp_params) < 0)
-		goto error_kill;
+		goto error;
 
 	kdebug("- start_code  %lx", current->mm->start_code);
 	kdebug("- end_code    %lx", current->mm->end_code);
@@ -449,12 +447,6 @@ error:
 	kfree(interp_params.phdrs);
 	kfree(interp_params.loadmap);
 	return retval;
-
-	/* unrecoverable error - kill the process */
-error_kill:
-	send_sig(SIGSEGV, current, 0);
-	goto error;
-
 }
 
 /*****************************************************************************/

fs/btrfs/ioctl.c

@@ -2419,9 +2419,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		goto out_dput;
 	}
 
-	err = d_invalidate(dentry);
-	if (err)
-		goto out_unlock;
+	d_invalidate(dentry);
 
 	down_write(&root->fs_info->subvol_sem);
 
@@ -2506,7 +2504,6 @@ out_release:
 	btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
 out_up_write:
 	up_write(&root->fs_info->subvol_sem);
-out_unlock:
 	if (err) {
 		spin_lock(&dest->root_item_lock);
 		root_flags = btrfs_root_flags(&dest->root_item);

fs/buffer.c

@@ -2318,6 +2318,11 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		err = 0;
 
 		balance_dirty_pages_ratelimited(mapping);
+
+		if (unlikely(fatal_signal_pending(current))) {
+			err = -EINTR;
+			goto out;
+		}
 	}
 
 	/* page covers the boundary, find the boundary offset */

fs/cachefiles/rdwr.c

@@ -880,7 +880,6 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
-	mm_segment_t old_fs;
 	struct file *file;
 	struct path path;
 	loff_t pos, eof;
@@ -914,36 +913,27 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	if (IS_ERR(file)) {
 		ret = PTR_ERR(file);
 	} else {
-		ret = -EIO;
-		if (file->f_op->write) {
-			pos = (loff_t) page->index << PAGE_SHIFT;
-
-			/* we mustn't write more data than we have, so we have
-			 * to beware of a partial page at EOF */
-			eof = object->fscache.store_limit_l;
-			len = PAGE_SIZE;
-			if (eof & ~PAGE_MASK) {
-				ASSERTCMP(pos, <, eof);
-				if (eof - pos < PAGE_SIZE) {
-					_debug("cut short %llx to %llx",
-					       pos, eof);
-					len = eof - pos;
-					ASSERTCMP(pos + len, ==, eof);
-				}
+		pos = (loff_t) page->index << PAGE_SHIFT;
+
+		/* we mustn't write more data than we have, so we have
+		 * to beware of a partial page at EOF */
+		eof = object->fscache.store_limit_l;
+		len = PAGE_SIZE;
+		if (eof & ~PAGE_MASK) {
+			ASSERTCMP(pos, <, eof);
+			if (eof - pos < PAGE_SIZE) {
+				_debug("cut short %llx to %llx",
+				       pos, eof);
+				len = eof - pos;
+				ASSERTCMP(pos + len, ==, eof);
 			}
-
-			data = kmap(page);
-			file_start_write(file);
-			old_fs = get_fs();
-			set_fs(KERNEL_DS);
-			ret = file->f_op->write(
-				file, (const void __user *) data, len, &pos);
-			set_fs(old_fs);
-			kunmap(page);
-			file_end_write(file);
-			if (ret != len)
-				ret = -EIO;
 		}
+
+		data = kmap(page);
+		ret = __kernel_write(file, data, len, &pos);
+		kunmap(page);
+		if (ret != len)
+			ret = -EIO;
 		fput(file);
 	}
 

fs/ceph/dir.c

@@ -1069,7 +1069,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		ceph_dentry_lru_touch(dentry);
 	} else {
 		ceph_dir_clear_complete(dir);
-		d_drop(dentry);
 	}
 	iput(dir);
 	return valid;

fs/cifs/dir.c

@@ -461,8 +461,8 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "parent inode = 0x%p name is: %s and dentry = 0x%p\n",
-		 inode, direntry->d_name.name, direntry);
+	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
+		 inode, direntry, direntry);
 
 	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
 	if (IS_ERR(tlink)) {
@@ -540,8 +540,8 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 	struct cifs_fid fid;
 	__u32 oplock;
 
-	cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n",
-		 inode, direntry->d_name.name, direntry);
+	cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
+		 inode, direntry, direntry);
 
 	tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
 	rc = PTR_ERR(tlink);
@@ -713,8 +713,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "parent inode = 0x%p name is: %s and dentry = 0x%p\n",
-		 parent_dir_inode, direntry->d_name.name, direntry);
+	cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n",
+		 parent_dir_inode, direntry, direntry);
 
 	/* check whether path exists */
 
@@ -833,7 +833,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
 {
 	int rc = 0;
 
-	cifs_dbg(FYI, "In cifs d_delete, name = %s\n", direntry->d_name.name);
+	cifs_dbg(FYI, "In cifs d_delete, name = %pd\n", direntry);
 
 	return rc;
 }     */

fs/cifs/file.c

@@ -1650,8 +1650,8 @@ cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
 
 	cifs_sb = CIFS_SB(dentry->d_sb);
 
-	cifs_dbg(FYI, "write %zd bytes to offset %lld of %s\n",
-		 write_size, *offset, dentry->d_name.name);
+	cifs_dbg(FYI, "write %zd bytes to offset %lld of %pd\n",
+		 write_size, *offset, dentry);
 
 	tcon = tlink_tcon(open_file->tlink);
 	server = tcon->ses->server;
@@ -2273,8 +2273,8 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "Sync file - name: %s datasync: 0x%x\n",
-		 file->f_path.dentry->d_name.name, datasync);
+	cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
+		 file, datasync);
 
 	if (!CIFS_CACHE_READ(CIFS_I(inode))) {
 		rc = cifs_zap_mapping(inode);
@@ -2315,8 +2315,8 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "Sync file - name: %s datasync: 0x%x\n",
-		 file->f_path.dentry->d_name.name, datasync);
+	cifs_dbg(FYI, "Sync file - name: %pD datasync: 0x%x\n",
+		 file, datasync);
 
 	tcon = tlink_tcon(smbfile->tlink);
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {

fs/cifs/inode.c

@@ -1419,8 +1419,8 @@ cifs_posix_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode,
 	d_instantiate(dentry, newinode);
 
 #ifdef CONFIG_CIFS_DEBUG2
-	cifs_dbg(FYI, "instantiated dentry %p %s to inode %p\n",
-		 dentry, dentry->d_name.name, newinode);
+	cifs_dbg(FYI, "instantiated dentry %p %pd to inode %p\n",
+		 dentry, dentry, newinode);
 
 	if (newinode->i_nlink != 2)
 		cifs_dbg(FYI, "unexpected number of links %d\n",
@@ -2111,8 +2111,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 	struct cifs_unix_set_info_args *args = NULL;
 	struct cifsFileInfo *open_file;
 
-	cifs_dbg(FYI, "setattr_unix on file %s attrs->ia_valid=0x%x\n",
-		 direntry->d_name.name, attrs->ia_valid);
+	cifs_dbg(FYI, "setattr_unix on file %pd attrs->ia_valid=0x%x\n",
+		 direntry, attrs->ia_valid);
 
 	xid = get_xid();
 
@@ -2254,8 +2254,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 
 	xid = get_xid();
 
-	cifs_dbg(FYI, "setattr on file %s attrs->iavalid 0x%x\n",
-		 direntry->d_name.name, attrs->ia_valid);
+	cifs_dbg(FYI, "setattr on file %pd attrs->iavalid 0x%x\n",
+		 direntry, attrs->ia_valid);
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
 		attrs->ia_valid |= ATTR_FORCE;

fs/cifs/readdir.c

@@ -87,8 +87,6 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 		return;
 
 	if (dentry) {
-		int err;
-
 		inode = dentry->d_inode;
 		if (inode) {
 			/*
@@ -105,10 +103,8 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 				goto out;
 			}
 		}
-		err = d_invalidate(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
-		if (err)
-			return;
 	}
 
 	/*

fs/compat.c

@@ -794,25 +794,21 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 	char *kernel_type;
 	unsigned long data_page;
 	char *kernel_dev;
-	struct filename *dir;
 	int retval;
 
-	retval = copy_mount_string(type, &kernel_type);
-	if (retval < 0)
+	kernel_type = copy_mount_string(type);
+	retval = PTR_ERR(kernel_type);
+	if (IS_ERR(kernel_type))
 		goto out;
 
-	dir = getname(dir_name);
-	retval = PTR_ERR(dir);
-	if (IS_ERR(dir))
+	kernel_dev = copy_mount_string(dev_name);
+	retval = PTR_ERR(kernel_dev);
+	if (IS_ERR(kernel_dev))
 		goto out1;
 
-	retval = copy_mount_string(dev_name, &kernel_dev);
-	if (retval < 0)
-		goto out2;
-
 	retval = copy_mount_options(data, &data_page);
 	if (retval < 0)
-		goto out3;
+		goto out2;
 
 	retval = -EINVAL;
 
@@ -821,19 +817,17 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
 			do_ncp_super_data_conv((void *)data_page);
 		} else if (!strcmp(kernel_type, NFS4_NAME)) {
 			if (do_nfs4_super_data_conv((void *) data_page))
-				goto out4;
+				goto out3;
 		}
 	}
 
-	retval = do_mount(kernel_dev, dir->name, kernel_type,
+	retval = do_mount(kernel_dev, dir_name, kernel_type,
 			flags, (void*)data_page);
 
- out4:
-	free_page(data_page);
  out3:
-	kfree(kernel_dev);
+	free_page(data_page);
  out2:
-	putname(dir);
+	kfree(kernel_dev);
  out1:
 	kfree(kernel_type);
  out:

fs/dcache.c

@@ -235,18 +235,49 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	return dentry_string_cmp(cs, ct, tcount);
 }
 
+struct external_name {
+	union {
+		atomic_t count;
+		struct rcu_head head;
+	} u;
+	unsigned char name[];
+};
+
+static inline struct external_name *external_name(struct dentry *dentry)
+{
+	return container_of(dentry->d_name.name, struct external_name, name[0]);
+}
+
 static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
 
 	WARN_ON(!hlist_unhashed(&dentry->d_alias));
-	if (dname_external(dentry))
-		kfree(dentry->d_name.name);
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
+static void __d_free_external(struct rcu_head *head)
+{
+	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
+	WARN_ON(!hlist_unhashed(&dentry->d_alias));
+	kfree(external_name(dentry));
+	kmem_cache_free(dentry_cache, dentry); 
+}
+
+static inline int dname_external(const struct dentry *dentry)
+{
+	return dentry->d_name.name != dentry->d_iname;
+}
+
 static void dentry_free(struct dentry *dentry)
 {
+	if (unlikely(dname_external(dentry))) {
+		struct external_name *p = external_name(dentry);
+		if (likely(atomic_dec_and_test(&p->u.count))) {
+			call_rcu(&dentry->d_u.d_rcu, __d_free_external);
+			return;
+		}
+	}
 	/* if dentry was never visible to RCU, immediate free is OK */
 	if (!(dentry->d_flags & DCACHE_RCUACCESS))
 		__d_free(&dentry->d_u.d_rcu);
@@ -456,7 +487,7 @@ static void __dentry_kill(struct dentry *dentry)
 	 * inform the fs via d_prune that this dentry is about to be
 	 * unhashed and destroyed.
 	 */
-	if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
+	if (dentry->d_flags & DCACHE_OP_PRUNE)
 		dentry->d_op->d_prune(dentry);
 
 	if (dentry->d_flags & DCACHE_LRU_LIST) {
@@ -619,62 +650,6 @@ kill_it:
 }
 EXPORT_SYMBOL(dput);
 
-/**
- * d_invalidate - invalidate a dentry
- * @dentry: dentry to invalidate
- *
- * Try to invalidate the dentry if it turns out to be
- * possible. If there are other dentries that can be
- * reached through this one we can't delete it and we
- * return -EBUSY. On success we return 0.
- *
- * no dcache lock.
- */
- 
-int d_invalidate(struct dentry * dentry)
-{
-	/*
-	 * If it's already been dropped, return OK.
-	 */
-	spin_lock(&dentry->d_lock);
-	if (d_unhashed(dentry)) {
-		spin_unlock(&dentry->d_lock);
-		return 0;
-	}
-	/*
-	 * Check whether to do a partial shrink_dcache
-	 * to get rid of unused child entries.
-	 */
-	if (!list_empty(&dentry->d_subdirs)) {
-		spin_unlock(&dentry->d_lock);
-		shrink_dcache_parent(dentry);
-		spin_lock(&dentry->d_lock);
-	}
-
-	/*
-	 * Somebody else still using it?
-	 *
-	 * If it's a directory, we can't drop it
-	 * for fear of somebody re-populating it
-	 * with children (even though dropping it
-	 * would make it unreachable from the root,
-	 * we might still populate it if it was a
-	 * working directory or similar).
-	 * We also need to leave mountpoints alone,
-	 * directory or not.
-	 */
-	if (dentry->d_lockref.count > 1 && dentry->d_inode) {
-		if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
-			spin_unlock(&dentry->d_lock);
-			return -EBUSY;
-		}
-	}
-
-	__d_drop(dentry);
-	spin_unlock(&dentry->d_lock);
-	return 0;
-}
-EXPORT_SYMBOL(d_invalidate);
 
 /* This must be called with d_lock held */
 static inline void __dget_dlock(struct dentry *dentry)
@@ -735,7 +710,8 @@ EXPORT_SYMBOL(dget_parent);
  * acquire the reference to alias and return it. Otherwise return NULL.
  * Notice that if inode is a directory there can be only one alias and
  * it can be unhashed only if it has no children, or if it is the root
- * of a filesystem.
+ * of a filesystem, or if the directory was renamed and d_revalidate
+ * was the first vfs operation to notice.
  *
  * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
  * any other hashed alias over that one.
@@ -799,20 +775,13 @@ restart:
 	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_lockref.count) {
-			/*
-			 * inform the fs via d_prune that this dentry
-			 * is about to be unhashed and destroyed.
-			 */
-			if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
-			    !d_unhashed(dentry))
-				dentry->d_op->d_prune(dentry);
-
-			__dget_dlock(dentry);
-			__d_drop(dentry);
-			spin_unlock(&dentry->d_lock);
-			spin_unlock(&inode->i_lock);
-			dput(dentry);
-			goto restart;
+			struct dentry *parent = lock_parent(dentry);
+			if (likely(!dentry->d_lockref.count)) {
+				__dentry_kill(dentry);
+				goto restart;
+			}
+			if (parent)
+				spin_unlock(&parent->d_lock);
 		}
 		spin_unlock(&dentry->d_lock);
 	}
@@ -1193,7 +1162,7 @@ EXPORT_SYMBOL(have_submounts);
  * reachable (e.g. NFS can unhash a directory dentry and then the complete
  * subtree can become unreachable).
  *
- * Only one of check_submounts_and_drop() and d_set_mounted() must succeed.  For
+ * Only one of d_invalidate() and d_set_mounted() must succeed.  For
  * this reason take rename_lock and d_lock on dentry and ancestors.
  */
 int d_set_mounted(struct dentry *dentry)
@@ -1202,7 +1171,7 @@ int d_set_mounted(struct dentry *dentry)
 	int ret = -ENOENT;
 	write_seqlock(&rename_lock);
 	for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
-		/* Need exclusion wrt. check_submounts_and_drop() */
+		/* Need exclusion wrt. d_invalidate() */
 		spin_lock(&p->d_lock);
 		if (unlikely(d_unhashed(p))) {
 			spin_unlock(&p->d_lock);
@@ -1346,70 +1315,84 @@ void shrink_dcache_for_umount(struct super_block *sb)
 	}
 }
 
-static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry)
+struct detach_data {
+	struct select_data select;
+	struct dentry *mountpoint;
+};
+static enum d_walk_ret detach_and_collect(void *_data, struct dentry *dentry)
 {
-	struct select_data *data = _data;
+	struct detach_data *data = _data;
 
 	if (d_mountpoint(dentry)) {
-		data->found = -EBUSY;
+		__dget_dlock(dentry);
+		data->mountpoint = dentry;
 		return D_WALK_QUIT;
 	}
 
-	return select_collect(_data, dentry);
+	return select_collect(&data->select, dentry);
 }
 
 static void check_and_drop(void *_data)
 {
-	struct select_data *data = _data;
+	struct detach_data *data = _data;
 
-	if (d_mountpoint(data->start))
-		data->found = -EBUSY;
-	if (!data->found)
-		__d_drop(data->start);
+	if (!data->mountpoint && !data->select.found)
+		__d_drop(data->select.start);
 }
 
 /**
- * check_submounts_and_drop - prune dcache, check for submounts and drop
+ * d_invalidate - detach submounts, prune dcache, and drop
+ * @dentry: dentry to invalidate (aka detach, prune and drop)
  *
- * All done as a single atomic operation relative to has_unlinked_ancestor().
- * Returns 0 if successfully unhashed @parent.  If there were submounts then
- * return -EBUSY.
+ * no dcache lock.
  *
- * @dentry: dentry to prune and drop
+ * The final d_drop is done as an atomic operation relative to
+ * rename_lock ensuring there are no races with d_set_mounted.  This
+ * ensures there are no unhashed dentries on the path to a mountpoint.
  */
-int check_submounts_and_drop(struct dentry *dentry)
+void d_invalidate(struct dentry *dentry)
 {
-	int ret = 0;
+	/*
+	 * If it's already been dropped, return OK.
+	 */
+	spin_lock(&dentry->d_lock);
+	if (d_unhashed(dentry)) {
+		spin_unlock(&dentry->d_lock);
+		return;
+	}
+	spin_unlock(&dentry->d_lock);
 
 	/* Negative dentries can be dropped without further checks */
 	if (!dentry->d_inode) {
 		d_drop(dentry);
-		goto out;
+		return;
 	}
 
 	for (;;) {
-		struct select_data data;
+		struct detach_data data;
 
-		INIT_LIST_HEAD(&data.dispose);
-		data.start = dentry;
-		data.found = 0;
+		data.mountpoint = NULL;
+		INIT_LIST_HEAD(&data.select.dispose);
+		data.select.start = dentry;
+		data.select.found = 0;
+
+		d_walk(dentry, &data, detach_and_collect, check_and_drop);
 
-		d_walk(dentry, &data, check_and_collect, check_and_drop);
-		ret = data.found;
+		if (data.select.found)
+			shrink_dentry_list(&data.select.dispose);
 
-		if (!list_empty(&data.dispose))
-			shrink_dentry_list(&data.dispose);
+		if (data.mountpoint) {
+			detach_mounts(data.mountpoint);
+			dput(data.mountpoint);
+		}
 
-		if (ret <= 0)
+		if (!data.mountpoint && !data.select.found)
 			break;
 
 		cond_resched();
 	}
-
-out:
-	return ret;
 }
-EXPORT_SYMBOL(check_submounts_and_drop);
+EXPORT_SYMBOL(d_invalidate);
 
 /**
  * __d_alloc	-	allocate a dcache entry
@@ -1438,11 +1421,14 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 */
 	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
 	if (name->len > DNAME_INLINE_LEN-1) {
-		dname = kmalloc(name->len + 1, GFP_KERNEL);
-		if (!dname) {
+		size_t size = offsetof(struct external_name, name[1]);
+		struct external_name *p = kmalloc(size + name->len, GFP_KERNEL);
+		if (!p) {
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
+		atomic_set(&p->u.count, 1);
+		dname = p->name;
 	} else  {
 		dname = dentry->d_iname;
 	}	
@@ -2112,10 +2098,10 @@ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
 	struct dentry *dentry;
 	unsigned seq;
 
-        do {
-                seq = read_seqbegin(&rename_lock);
-                dentry = __d_lookup(parent, name);
-                if (dentry)
+	do {
+		seq = read_seqbegin(&rename_lock);
+		dentry = __d_lookup(parent, name);
+		if (dentry)
 			break;
 	} while (read_seqretry(&rename_lock, seq));
 	return dentry;
@@ -2372,11 +2358,10 @@ void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
 }
 EXPORT_SYMBOL(dentry_update_name_case);
 
-static void switch_names(struct dentry *dentry, struct dentry *target,
-			 bool exchange)
+static void swap_names(struct dentry *dentry, struct dentry *target)
 {
-	if (dname_external(target)) {
-		if (dname_external(dentry)) {
+	if (unlikely(dname_external(target))) {
+		if (unlikely(dname_external(dentry))) {
 			/*
 			 * Both external: swap the pointers
 			 */
@@ -2392,7 +2377,7 @@ static void switch_names(struct dentry *dentry, struct dentry *target,
 			target->d_name.name = target->d_iname;
 		}
 	} else {
-		if (dname_external(dentry)) {
+		if (unlikely(dname_external(dentry))) {
 			/*
 			 * dentry:external, target:internal.  Give dentry's
 			 * storage to target and make dentry internal
@@ -2407,12 +2392,6 @@ static void switch_names(struct dentry *dentry, struct dentry *target,
 			 */
 			unsigned int i;
 			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
-			if (!exchange) {
-				memcpy(dentry->d_iname, target->d_name.name,
-						target->d_name.len + 1);
-				dentry->d_name.hash_len = target->d_name.hash_len;
-				return;
-			}
 			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
 				swap(((long *) &dentry->d_iname)[i],
 				     ((long *) &target->d_iname)[i]);
@@ -2422,6 +2401,24 @@ static void switch_names(struct dentry *dentry, struct dentry *target,
 	swap(dentry->d_name.hash_len, target->d_name.hash_len);
 }
 
+static void copy_name(struct dentry *dentry, struct dentry *target)
+{
+	struct external_name *old_name = NULL;
+	if (unlikely(dname_external(dentry)))
+		old_name = external_name(dentry);
+	if (unlikely(dname_external(target))) {
+		atomic_inc(&external_name(target)->u.count);
+		dentry->d_name = target->d_name;
+	} else {
+		memcpy(dentry->d_iname, target->d_name.name,
+				target->d_name.len + 1);
+		dentry->d_name.name = dentry->d_iname;
+		dentry->d_name.hash_len = target->d_name.hash_len;
+	}
+	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
+		kfree_rcu(old_name, u.head);
+}
+
 static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
 {
 	/*
@@ -2518,7 +2515,10 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 	}
 
 	/* Switch the names.. */
-	switch_names(dentry, target, exchange);
+	if (exchange)
+		swap_names(dentry, target);
+	else
+		copy_name(dentry, target);
 
 	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
@@ -2625,10 +2625,8 @@ static struct dentry *__d_unalias(struct inode *inode,
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
-	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry, false);
-		ret = alias;
-	}
+	__d_move(alias, dentry, false);
+	ret = alias;
 out_err:
 	spin_unlock(&inode->i_lock);
 	if (m2)
@@ -2810,6 +2808,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen)
  * the beginning of the name. The sequence number check at the caller will
  * retry it again when a d_move() does happen. So any garbage in the buffer
  * due to mismatched pointer and length will be discarded.
+ *
+ * Data dependency barrier is needed to make sure that we see that terminating
+ * NUL.  Alpha strikes again, film at 11...
  */
 static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 {
@@ -2817,6 +2818,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 	u32 dlen = ACCESS_ONCE(name->len);
 	char *p;
 
+	smp_read_barrier_depends();
+
 	*buflen -= dlen + 1;
 	if (*buflen < 0)
 		return -ENAMETOOLONG;

fs/ecryptfs/file.c

@@ -327,7 +327,7 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct file *lower_file = ecryptfs_file_to_lower(file);
 	long rc = -ENOIOCTLCMD;
 
-	if (lower_file->f_op && lower_file->f_op->compat_ioctl)
+	if (lower_file->f_op->compat_ioctl)
 		rc = lower_file->f_op->compat_ioctl(lower_file, cmd, arg);
 	return rc;
 }

fs/exec.c

@@ -1372,18 +1372,23 @@ int search_binary_handler(struct linux_binprm *bprm)
 		read_unlock(&binfmt_lock);
 		bprm->recursion_depth++;
 		retval = fmt->load_binary(bprm);
+		read_lock(&binfmt_lock);
+		put_binfmt(fmt);
 		bprm->recursion_depth--;
-		if (retval >= 0 || retval != -ENOEXEC ||
-		    bprm->mm == NULL || bprm->file == NULL) {
-			put_binfmt(fmt);
+		if (retval < 0 && !bprm->mm) {
+			/* we got to flush_old_exec() and failed after it */
+			read_unlock(&binfmt_lock);
+			force_sigsegv(SIGSEGV, current);
+			return retval;
+		}
+		if (retval != -ENOEXEC || !bprm->file) {
+			read_unlock(&binfmt_lock);
 			return retval;
 		}
-		read_lock(&binfmt_lock);
-		put_binfmt(fmt);
 	}
 	read_unlock(&binfmt_lock);
 
-	if (need_retry && retval == -ENOEXEC) {
+	if (need_retry) {
 		if (printable(bprm->buf[0]) && printable(bprm->buf[1]) &&
 		    printable(bprm->buf[2]) && printable(bprm->buf[3]))
 			return retval;

fs/file.c

@@ -750,6 +750,7 @@ bool get_close_on_exec(unsigned int fd)
 
 static int do_dup2(struct files_struct *files,
 	struct file *file, unsigned fd, unsigned flags)
+__releases(&files->file_lock)
 {
 	struct file *tofree;
 	struct fdtable *fdt;

fs/file_table.c

@@ -150,18 +150,10 @@ over:
 
 /**
  * alloc_file - allocate and initialize a 'struct file'
- * @mnt: the vfsmount on which the file will reside
- * @dentry: the dentry representing the new file
+ *
+ * @path: the (dentry, vfsmount) pair for the new file
  * @mode: the mode with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
- *
- * Use this instead of get_empty_filp() to get a new
- * 'struct file'.  Do so because of the same initialization
- * pitfalls reasons listed for init_file().  This is a
- * preferred interface to using init_file().
- *
- * If all the callers of init_file() are eliminated, its
- * code should be moved into this function.
  */
 struct file *alloc_file(struct path *path, fmode_t mode,
 		const struct file_operations *fop)

fs/fuse/dir.c

@@ -274,9 +274,6 @@ out:
 
 invalid:
 	ret = 0;
-
-	if (!(flags & LOOKUP_RCU) && check_submounts_and_drop(entry) != 0)
-		ret = 1;
 	goto out;
 }
 
@@ -1289,9 +1286,7 @@ static int fuse_direntplus_link(struct file *file,
 			d_drop(dentry);
 		} else if (get_node_id(inode) != o->nodeid ||
 			   ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
-			err = d_invalidate(dentry);
-			if (err)
-				goto out;
+			d_invalidate(dentry);
 		} else if (is_bad_inode(inode)) {
 			err = -EIO;
 			goto out;

fs/gfs2/dentry.c

@@ -93,9 +93,6 @@ invalid_gunlock:
 	if (!had_lock)
 		gfs2_glock_dq_uninit(&d_gh);
 invalid:
-	if (check_submounts_and_drop(dentry) != 0)
-		goto valid;
-
 	dput(parent);
 	return 0;
 

fs/gfs2/inode.c

@@ -1245,6 +1245,9 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct dentry *d;
 	bool excl = !!(flags & O_EXCL);
 
+	if (!d_unhashed(dentry))
+		goto skip_lookup;
+
 	d = __gfs2_lookup(dir, dentry, file, opened);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
@@ -1261,6 +1264,8 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	}
 
 	BUG_ON(d != NULL);
+
+skip_lookup:
 	if (!(flags & O_CREAT))
 		return -ENOENT;
 

fs/internal.h

@@ -56,7 +56,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
  * namespace.c
  */
 extern int copy_mount_options(const void __user *, unsigned long *);
-extern int copy_mount_string(const void __user *, char **);
+extern char *copy_mount_string(const void __user *);
 
 extern struct vfsmount *lookup_mnt(struct path *);
 extern int finish_automount(struct vfsmount *, struct path *);

fs/jffs2/jffs2_fs_sb.h

@@ -134,8 +134,6 @@ struct jffs2_sb_info {
 	struct rw_semaphore wbuf_sem;	/* Protects the write buffer */
 
 	struct delayed_work wbuf_dwork; /* write-buffer write-out work */
-	int wbuf_queued;                /* non-zero delayed work is queued */
-	spinlock_t wbuf_dwork_lock;     /* protects wbuf_dwork and and wbuf_queued */
 
 	unsigned char *oobbuf;
 	int oobavail; /* How many bytes are available for JFFS2 in OOB */

fs/jffs2/wbuf.c

@@ -1162,10 +1162,6 @@ static void delayed_wbuf_sync(struct work_struct *work)
 	struct jffs2_sb_info *c = work_to_sb(work);
 	struct super_block *sb = OFNI_BS_2SFFJ(c);
 
-	spin_lock(&c->wbuf_dwork_lock);
-	c->wbuf_queued = 0;
-	spin_unlock(&c->wbuf_dwork_lock);
-
 	if (!(sb->s_flags & MS_RDONLY)) {
 		jffs2_dbg(1, "%s()\n", __func__);
 		jffs2_flush_wbuf_gc(c, 0);
@@ -1180,14 +1176,9 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c)
 	if (sb->s_flags & MS_RDONLY)
 		return;
 
-	spin_lock(&c->wbuf_dwork_lock);
-	if (!c->wbuf_queued) {
+	delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+	if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay))
 		jffs2_dbg(1, "%s()\n", __func__);
-		delay = msecs_to_jiffies(dirty_writeback_interval * 10);
-		queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay);
-		c->wbuf_queued = 1;
-	}
-	spin_unlock(&c->wbuf_dwork_lock);
 }
 
 int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
@@ -1211,7 +1202,6 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
 
 	/* Initialise write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize = c->mtd->writesize;
 	c->wbuf_ofs = 0xFFFFFFFF;
@@ -1251,7 +1241,6 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 	c->wbuf_pagesize =  c->mtd->erasesize;
 
@@ -1311,7 +1300,6 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) {
 
 	/* Initialize write buffer */
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize = c->mtd->writesize;
@@ -1346,7 +1334,6 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) {
 		return 0;
 
 	init_rwsem(&c->wbuf_sem);
-	spin_lock_init(&c->wbuf_dwork_lock);
 	INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
 
 	c->wbuf_pagesize =  c->mtd->writesize;

fs/jfs/super.c

@@ -550,7 +550,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_ino = 0;
 	inode->i_size = sb->s_bdev->bd_inode->i_size;
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
-	insert_inode_hash(inode);
+	hlist_add_fake(&inode->i_hash);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	sbi->direct_inode = inode;

fs/kernfs/dir.c

@@ -463,21 +463,10 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out_bad;
 
 	mutex_unlock(&kernfs_mutex);
-out_valid:
 	return 1;
 out_bad:
 	mutex_unlock(&kernfs_mutex);
 out_bad_unlocked:
-	/*
-	 * @dentry doesn't match the underlying kernfs node, drop the
-	 * dentry and force lookup.  If we have submounts we must allow the
-	 * vfs caches to lie about the state of the filesystem to prevent
-	 * leaks and other nasty things, so use check_submounts_and_drop()
-	 * instead of d_drop().
-	 */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_valid;
-
 	return 0;
 }
 

fs/mount.h

@@ -21,6 +21,7 @@ struct mnt_pcp {
 struct mountpoint {
 	struct hlist_node m_hash;
 	struct dentry *m_dentry;
+	struct hlist_head m_list;
 	int m_count;
 };
 
@@ -29,7 +30,10 @@ struct mount {
 	struct mount *mnt_parent;
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;
-	struct rcu_head mnt_rcu;
+	union {
+		struct rcu_head mnt_rcu;
+		struct llist_node mnt_llist;
+	};
 #ifdef CONFIG_SMP
 	struct mnt_pcp __percpu *mnt_pcp;
 #else
@@ -48,6 +52,7 @@ struct mount {
 	struct mount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
+	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
 #ifdef CONFIG_FSNOTIFY
 	struct hlist_head mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
@@ -82,6 +87,15 @@ extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
 
+extern void __detach_mounts(struct dentry *dentry);
+
+static inline void detach_mounts(struct dentry *dentry)
+{
+	if (!d_mountpoint(dentry))
+		return;
+	__detach_mounts(dentry);
+}
+
 static inline void get_mnt_ns(struct mnt_namespace *ns)
 {
 	atomic_inc(&ns->count);
@@ -112,3 +126,12 @@ struct proc_mounts {
 #define proc_mounts(p) (container_of((p), struct proc_mounts, m))
 
 extern const struct seq_operations mounts_op;
+
+extern bool __is_local_mountpoint(struct dentry *dentry);
+static inline bool is_local_mountpoint(struct dentry *dentry)
+{
+	if (!d_mountpoint(dentry))
+		return false;
+
+	return __is_local_mountpoint(dentry);
+}

fs/namei.c

@@ -1306,7 +1306,8 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
 				if (error < 0) {
 					dput(dentry);
 					return ERR_PTR(error);
-				} else if (!d_invalidate(dentry)) {
+				} else {
+					d_invalidate(dentry);
 					dput(dentry);
 					dentry = NULL;
 				}
@@ -1435,10 +1436,9 @@ unlazy:
 			dput(dentry);
 			return status;
 		}
-		if (!d_invalidate(dentry)) {
-			dput(dentry);
-			goto need_lookup;
-		}
+		d_invalidate(dentry);
+		dput(dentry);
+		goto need_lookup;
 	}
 
 	path->mnt = mnt;
@@ -1950,7 +1950,7 @@ static int path_lookupat(int dfd, const char *name,
 	err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base);
 
 	if (unlikely(err))
-		return err;
+		goto out;
 
 	current->total_link_count = 0;
 	err = link_path_walk(name, nd);
@@ -1982,6 +1982,7 @@ static int path_lookupat(int dfd, const char *name,
 		}
 	}
 
+out:
 	if (base)
 		fput(base);
 
@@ -2301,7 +2302,7 @@ path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags
 
 	err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
 	if (unlikely(err))
-		return err;
+		goto out;
 
 	current->total_link_count = 0;
 	err = link_path_walk(name, &nd);
@@ -3565,7 +3566,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	mutex_lock(&dentry->d_inode->i_mutex);
 
 	error = -EBUSY;
-	if (d_mountpoint(dentry))
+	if (is_local_mountpoint(dentry))
 		goto out;
 
 	error = security_inode_rmdir(dir, dentry);
@@ -3579,6 +3580,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	dentry->d_inode->i_flags |= S_DEAD;
 	dont_mount(dentry);
+	detach_mounts(dentry);
 
 out:
 	mutex_unlock(&dentry->d_inode->i_mutex);
@@ -3681,7 +3683,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 		return -EPERM;
 
 	mutex_lock(&target->i_mutex);
-	if (d_mountpoint(dentry))
+	if (is_local_mountpoint(dentry))
 		error = -EBUSY;
 	else {
 		error = security_inode_unlink(dir, dentry);
@@ -3690,8 +3692,10 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 			if (error)
 				goto out;
 			error = dir->i_op->unlink(dir, dentry);
-			if (!error)
+			if (!error) {
 				dont_mount(dentry);
+				detach_mounts(dentry);
+			}
 		}
 	}
 out:
@@ -4126,7 +4130,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		mutex_lock(&target->i_mutex);
 
 	error = -EBUSY;
-	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
+	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
 		goto out;
 
 	if (max_links && new_dir != old_dir) {
@@ -4164,6 +4168,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (is_dir)
 			target->i_flags |= S_DEAD;
 		dont_mount(new_dentry);
+		detach_mounts(new_dentry);
 	}
 	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
 		if (!(flags & RENAME_EXCHANGE))

fs/namespace.c

@@ -23,6 +23,7 @@
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
 #include <linux/bootmem.h>
+#include <linux/task_work.h>
 #include "pnode.h"
 #include "internal.h"
 
@@ -224,6 +225,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_share);
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
+		INIT_HLIST_NODE(&mnt->mnt_mp_list);
 #ifdef CONFIG_FSNOTIFY
 		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
 #endif
@@ -666,11 +668,45 @@ struct vfsmount *lookup_mnt(struct path *path)
 	return m;
 }
 
-static struct mountpoint *new_mountpoint(struct dentry *dentry)
+/*
+ * __is_local_mountpoint - Test to see if dentry is a mountpoint in the
+ *                         current mount namespace.
+ *
+ * The common case is dentries are not mountpoints at all and that
+ * test is handled inline.  For the slow case when we are actually
+ * dealing with a mountpoint of some kind, walk through all of the
+ * mounts in the current mount namespace and test to see if the dentry
+ * is a mountpoint.
+ *
+ * The mount_hashtable is not usable in the context because we
+ * need to identify all mounts that may be in the current mount
+ * namespace not just a mount that happens to have some specified
+ * parent mount.
+ */
+bool __is_local_mountpoint(struct dentry *dentry)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mount *mnt;
+	bool is_covered = false;
+
+	if (!d_mountpoint(dentry))
+		goto out;
+
+	down_read(&namespace_sem);
+	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		is_covered = (mnt->mnt_mountpoint == dentry);
+		if (is_covered)
+			break;
+	}
+	up_read(&namespace_sem);
+out:
+	return is_covered;
+}
+
+static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
 {
 	struct hlist_head *chain = mp_hash(dentry);
 	struct mountpoint *mp;
-	int ret;
 
 	hlist_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
@@ -681,6 +717,14 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 			return mp;
 		}
 	}
+	return NULL;
+}
+
+static struct mountpoint *new_mountpoint(struct dentry *dentry)
+{
+	struct hlist_head *chain = mp_hash(dentry);
+	struct mountpoint *mp;
+	int ret;
 
 	mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
 	if (!mp)
@@ -695,6 +739,7 @@ static struct mountpoint *new_mountpoint(struct dentry *dentry)
 	mp->m_dentry = dentry;
 	mp->m_count = 1;
 	hlist_add_head(&mp->m_hash, chain);
+	INIT_HLIST_HEAD(&mp->m_list);
 	return mp;
 }
 
@@ -702,6 +747,7 @@ static void put_mountpoint(struct mountpoint *mp)
 {
 	if (!--mp->m_count) {
 		struct dentry *dentry = mp->m_dentry;
+		BUG_ON(!hlist_empty(&mp->m_list));
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
@@ -748,6 +794,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path)
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
 	hlist_del_init_rcu(&mnt->mnt_hash);
+	hlist_del_init(&mnt->mnt_mp_list);
 	put_mountpoint(mnt->mnt_mp);
 	mnt->mnt_mp = NULL;
 }
@@ -764,6 +811,7 @@ void mnt_set_mountpoint(struct mount *mnt,
 	child_mnt->mnt_mountpoint = dget(mp->m_dentry);
 	child_mnt->mnt_parent = mnt;
 	child_mnt->mnt_mp = mp;
+	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
 /*
@@ -957,6 +1005,46 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	return ERR_PTR(err);
 }
 
+static void cleanup_mnt(struct mount *mnt)
+{
+	/*
+	 * This probably indicates that somebody messed
+	 * up a mnt_want/drop_write() pair.  If this
+	 * happens, the filesystem was probably unable
+	 * to make r/w->r/o transitions.
+	 */
+	/*
+	 * The locking used to deal with mnt_count decrement provides barriers,
+	 * so mnt_get_writers() below is safe.
+	 */
+	WARN_ON(mnt_get_writers(mnt));
+	if (unlikely(mnt->mnt_pins.first))
+		mnt_pin_kill(mnt);
+	fsnotify_vfsmount_delete(&mnt->mnt);
+	dput(mnt->mnt.mnt_root);
+	deactivate_super(mnt->mnt.mnt_sb);
+	mnt_free_id(mnt);
+	call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
+}
+
+static void __cleanup_mnt(struct rcu_head *head)
+{
+	cleanup_mnt(container_of(head, struct mount, mnt_rcu));
+}
+
+static LLIST_HEAD(delayed_mntput_list);
+static void delayed_mntput(struct work_struct *unused)
+{
+	struct llist_node *node = llist_del_all(&delayed_mntput_list);
+	struct llist_node *next;
+
+	for (; node; node = next) {
+		next = llist_next(node);
+		cleanup_mnt(llist_entry(node, struct mount, mnt_llist));
+	}
+}
+static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
+
 static void mntput_no_expire(struct mount *mnt)
 {
 	rcu_read_lock();
@@ -982,24 +1070,18 @@ static void mntput_no_expire(struct mount *mnt)
 	list_del(&mnt->mnt_instance);
 	unlock_mount_hash();
 
-	/*
-	 * This probably indicates that somebody messed
-	 * up a mnt_want/drop_write() pair.  If this
-	 * happens, the filesystem was probably unable
-	 * to make r/w->r/o transitions.
-	 */
-	/*
-	 * The locking used to deal with mnt_count decrement provides barriers,
-	 * so mnt_get_writers() below is safe.
-	 */
-	WARN_ON(mnt_get_writers(mnt));
-	if (unlikely(mnt->mnt_pins.first))
-		mnt_pin_kill(mnt);
-	fsnotify_vfsmount_delete(&mnt->mnt);
-	dput(mnt->mnt.mnt_root);
-	deactivate_super(mnt->mnt.mnt_sb);
-	mnt_free_id(mnt);
-	call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
+	if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) {
+		struct task_struct *task = current;
+		if (likely(!(task->flags & PF_KTHREAD))) {
+			init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
+			if (!task_work_add(task, &mnt->mnt_rcu, true))
+				return;
+		}
+		if (llist_add(&mnt->mnt_llist, &delayed_mntput_list))
+			schedule_delayed_work(&delayed_mntput_work, 1);
+		return;
+	}
+	cleanup_mnt(mnt);
 }
 
 void mntput(struct vfsmount *mnt)
@@ -1272,6 +1354,7 @@ void umount_tree(struct mount *mnt, int how)
 		if (how < 2)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 		if (mnt_has_parent(p)) {
+			hlist_del_init(&p->mnt_mp_list);
 			put_mountpoint(p->mnt_mp);
 			mnt_add_count(p->mnt_parent, -1);
 			/* move the reference to mountpoint into ->mnt_ex_mountpoint */
@@ -1385,6 +1468,37 @@ static int do_umount(struct mount *mnt, int flags)
 	return retval;
 }
 
+/*
+ * __detach_mounts - lazily unmount all mounts on the specified dentry
+ *
+ * During unlink, rmdir, and d_drop it is possible to loose the path
+ * to an existing mountpoint, and wind up leaking the mount.
+ * detach_mounts allows lazily unmounting those mounts instead of
+ * leaking them.
+ *
+ * The caller may hold dentry->d_inode->i_mutex.
+ */
+void __detach_mounts(struct dentry *dentry)
+{
+	struct mountpoint *mp;
+	struct mount *mnt;
+
+	namespace_lock();
+	mp = lookup_mountpoint(dentry);
+	if (!mp)
+		goto out_unlock;
+
+	lock_mount_hash();
+	while (!hlist_empty(&mp->m_list)) {
+		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
+		umount_tree(mnt, 2);
+	}
+	unlock_mount_hash();
+	put_mountpoint(mp);
+out_unlock:
+	namespace_unlock();
+}
+
 /* 
  * Is the caller allowed to modify his namespace?
  */
@@ -1742,7 +1856,9 @@ retry:
 	namespace_lock();
 	mnt = lookup_mnt(path);
 	if (likely(!mnt)) {
-		struct mountpoint *mp = new_mountpoint(dentry);
+		struct mountpoint *mp = lookup_mountpoint(dentry);
+		if (!mp)
+			mp = new_mountpoint(dentry);
 		if (IS_ERR(mp)) {
 			namespace_unlock();
 			mutex_unlock(&dentry->d_inode->i_mutex);
@@ -2398,21 +2514,9 @@ int copy_mount_options(const void __user * data, unsigned long *where)
 	return 0;
 }
 
-int copy_mount_string(const void __user *data, char **where)
+char *copy_mount_string(const void __user *data)
 {
-	char *tmp;
-
-	if (!data) {
-		*where = NULL;
-		return 0;
-	}
-
-	tmp = strndup_user(data, PAGE_SIZE);
-	if (IS_ERR(tmp))
-		return PTR_ERR(tmp);
-
-	*where = tmp;
-	return 0;
+	return data ? strndup_user(data, PAGE_SIZE) : NULL;
 }
 
 /*
@@ -2429,7 +2533,7 @@ int copy_mount_string(const void __user *data, char **where)
  * Therefore, if this magic number is present, it carries no information
  * and must be discarded.
  */
-long do_mount(const char *dev_name, const char *dir_name,
+long do_mount(const char *dev_name, const char __user *dir_name,
 		const char *type_page, unsigned long flags, void *data_page)
 {
 	struct path path;
@@ -2441,15 +2545,11 @@ long do_mount(const char *dev_name, const char *dir_name,
 		flags &= ~MS_MGC_MSK;
 
 	/* Basic sanity checks */
-
-	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
-		return -EINVAL;
-
 	if (data_page)
 		((char *)data_page)[PAGE_SIZE - 1] = 0;
 
 	/* ... and get the mountpoint */
-	retval = kern_path(dir_name, LOOKUP_FOLLOW, &path);
+	retval = user_path(dir_name, &path);
 	if (retval)
 		return retval;
 
@@ -2674,37 +2774,30 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 {
 	int ret;
 	char *kernel_type;
-	struct filename *kernel_dir;
 	char *kernel_dev;
 	unsigned long data_page;
 
-	ret = copy_mount_string(type, &kernel_type);
-	if (ret < 0)
+	kernel_type = copy_mount_string(type);
+	ret = PTR_ERR(kernel_type);
+	if (IS_ERR(kernel_type))
 		goto out_type;
 
-	kernel_dir = getname(dir_name);
-	if (IS_ERR(kernel_dir)) {
-		ret = PTR_ERR(kernel_dir);
-		goto out_dir;
-	}
-
-	ret = copy_mount_string(dev_name, &kernel_dev);
-	if (ret < 0)
+	kernel_dev = copy_mount_string(dev_name);
+	ret = PTR_ERR(kernel_dev);
+	if (IS_ERR(kernel_dev))
 		goto out_dev;
 
 	ret = copy_mount_options(data, &data_page);
 	if (ret < 0)
 		goto out_data;
 
-	ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags,
+	ret = do_mount(kernel_dev, dir_name, kernel_type, flags,
 		(void *) data_page);
 
 	free_page(data_page);
 out_data:
 	kfree(kernel_dev);
 out_dev:
-	putname(kernel_dir);
-out_dir:
 	kfree(kernel_type);
 out_type:
 	return ret;

fs/ncpfs/dir.c

@@ -388,7 +388,6 @@ static struct dentry *
 ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 {
 	struct dentry *dent = dentry;
-	struct list_head *next;
 
 	if (d_validate(dent, parent)) {
 		if (dent->d_name.len <= NCP_MAXPATHLEN &&
@@ -404,9 +403,7 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 
 	/* If a pointer is invalid, we search the dentry. */
 	spin_lock(&parent->d_lock);
-	next = parent->d_subdirs.next;
-	while (next != &parent->d_subdirs) {
-		dent = list_entry(next, struct dentry, d_u.d_child);
+	list_for_each_entry(dent, &parent->d_subdirs, d_u.d_child) {
 		if ((unsigned long)dent->d_fsdata == fpos) {
 			if (dent->d_inode)
 				dget(dent);
@@ -415,7 +412,6 @@ ncp_dget_fpos(struct dentry *dentry, struct dentry *parent, unsigned long fpos)
 			spin_unlock(&parent->d_lock);
 			goto out;
 		}
-		next = next->next;
 	}
 	spin_unlock(&parent->d_lock);
 	return NULL;

fs/ncpfs/ncplib_kernel.h

@@ -188,20 +188,14 @@ static inline void
 ncp_renew_dentries(struct dentry *parent)
 {
 	struct ncp_server *server = NCP_SERVER(parent->d_inode);
-	struct list_head *next;
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	next = parent->d_subdirs.next;
-	while (next != &parent->d_subdirs) {
-		dentry = list_entry(next, struct dentry, d_u.d_child);
-
+	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
 		if (dentry->d_fsdata == NULL)
 			ncp_age_dentry(server, dentry);
 		else
 			ncp_new_dentry(dentry);
-
-		next = next->next;
 	}
 	spin_unlock(&parent->d_lock);
 }
@@ -210,16 +204,12 @@ static inline void
 ncp_invalidate_dircache_entries(struct dentry *parent)
 {
 	struct ncp_server *server = NCP_SERVER(parent->d_inode);
-	struct list_head *next;
 	struct dentry *dentry;
 
 	spin_lock(&parent->d_lock);
-	next = parent->d_subdirs.next;
-	while (next != &parent->d_subdirs) {
-		dentry = list_entry(next, struct dentry, d_u.d_child);
+	list_for_each_entry(dentry, &parent->d_subdirs, d_u.d_child) {
 		dentry->d_fsdata = NULL;
 		ncp_age_dentry(server, dentry);
-		next = next->next;
 	}
 	spin_unlock(&parent->d_lock);
 }

fs/nfs/dir.c

@@ -486,8 +486,7 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 				nfs_setsecurity(dentry->d_inode, entry->fattr, entry->label);
 			goto out;
 		} else {
-			if (d_invalidate(dentry) != 0)
-				goto out;
+			d_invalidate(dentry);
 			dput(dentry);
 		}
 	}
@@ -1211,10 +1210,6 @@ out_zap_parent:
 		if (IS_ROOT(dentry))
 			goto out_valid;
 	}
-	/* If we have submounts, don't unhash ! */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_valid;
-
 	dput(parent);
 	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
 			__func__, dentry);

fs/proc/base.c

@@ -1565,7 +1565,6 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
 		put_task_struct(task);
 		return 1;
 	}
-	d_drop(dentry);
 	return 0;
 }
 
@@ -1702,9 +1701,6 @@ out:
 	put_task_struct(task);
 
 out_notask:
-	if (status <= 0)
-		d_drop(dentry);
-
 	return status;
 }
 
@@ -2618,8 +2614,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 	/* no ->d_hash() rejects on procfs */
 	dentry = d_hash_and_lookup(mnt->mnt_root, &name);
 	if (dentry) {
-		shrink_dcache_parent(dentry);
-		d_drop(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
 	}
 
@@ -2639,8 +2634,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 	name.len = snprintf(buf, sizeof(buf), "%d", pid);
 	dentry = d_hash_and_lookup(dir, &name);
 	if (dentry) {
-		shrink_dcache_parent(dentry);
-		d_drop(dentry);
+		d_invalidate(dentry);
 		dput(dentry);
 	}
 

fs/proc/fd.c

@@ -129,8 +129,6 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 		}
 		put_task_struct(task);
 	}
-
-	d_drop(dentry);
 	return 0;
 }
 

fs/read_write.c

@@ -513,6 +513,8 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t
 	return ret;
 }
 
+EXPORT_SYMBOL(__kernel_write);
+
 ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
 {
 	ssize_t ret;

fs/reiserfs/xattr.h

@@ -7,7 +7,6 @@ struct inode;
 struct dentry;
 struct iattr;
 struct super_block;
-struct nameidata;
 
 int reiserfs_xattr_register_handlers(void) __init;
 void reiserfs_xattr_unregister_handlers(void);

fs/super.c

@@ -80,6 +80,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
 	dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
 	total_objects = dentries + inodes + fs_objects + 1;
+	if (!total_objects)
+		total_objects = 1;
 
 	/* proportion the scan between the caches */
 	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);

fs/xattr.c

@@ -364,13 +364,12 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
-		const char __user *, name, const void __user *, value,
-		size_t, size, int, flags)
+static int path_setxattr(const char __user *pathname,
+			 const char __user *name, const void __user *value,
+			 size_t size, int flags, unsigned int lookup_flags)
 {
 	struct path path;
 	int error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -388,28 +387,18 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
+		const char __user *, name, const void __user *, value,
+		size_t, size, int, flags)
+{
+	return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 		const char __user *, name, const void __user *, value,
 		size_t, size, int, flags)
 {
-	struct path path;
-	int error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = mnt_want_write(path.mnt);
-	if (!error) {
-		error = setxattr(path.dentry, name, value, size, flags);
-		mnt_drop_write(path.mnt);
-	}
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_setxattr(pathname, name, value, size, flags, 0);
 }
 
 SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
@@ -481,12 +470,12 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 	return error;
 }
 
-SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
-		const char __user *, name, void __user *, value, size_t, size)
+static ssize_t path_getxattr(const char __user *pathname,
+			     const char __user *name, void __user *value,
+			     size_t size, unsigned int lookup_flags)
 {
 	struct path path;
 	ssize_t error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -500,23 +489,16 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
+		const char __user *, name, void __user *, value, size_t, size)
+{
+	return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
 		const char __user *, name, void __user *, value, size_t, size)
 {
-	struct path path;
-	ssize_t error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = getxattr(path.dentry, name, value, size);
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_getxattr(pathname, name, value, size, 0);
 }
 
 SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
@@ -571,12 +553,11 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 	return error;
 }
 
-SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
-		size_t, size)
+static ssize_t path_listxattr(const char __user *pathname, char __user *list,
+			      size_t size, unsigned int lookup_flags)
 {
 	struct path path;
 	ssize_t error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -590,23 +571,16 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
+		size_t, size)
+{
+	return path_listxattr(pathname, list, size, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
 		size_t, size)
 {
-	struct path path;
-	ssize_t error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = listxattr(path.dentry, list, size);
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_listxattr(pathname, list, size, 0);
 }
 
 SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
@@ -640,12 +614,11 @@ removexattr(struct dentry *d, const char __user *name)
 	return vfs_removexattr(d, kname);
 }
 
-SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
-		const char __user *, name)
+static int path_removexattr(const char __user *pathname,
+			    const char __user *name, unsigned int lookup_flags)
 {
 	struct path path;
 	int error;
-	unsigned int lookup_flags = LOOKUP_FOLLOW;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
@@ -663,27 +636,16 @@ retry:
 	return error;
 }
 
+SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
+		const char __user *, name)
+{
+	return path_removexattr(pathname, name, LOOKUP_FOLLOW);
+}
+
 SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 		const char __user *, name)
 {
-	struct path path;
-	int error;
-	unsigned int lookup_flags = 0;
-retry:
-	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
-	if (error)
-		return error;
-	error = mnt_want_write(path.mnt);
-	if (!error) {
-		error = removexattr(path.dentry, name);
-		mnt_drop_write(path.mnt);
-	}
-	path_put(&path);
-	if (retry_estale(error, lookup_flags)) {
-		lookup_flags |= LOOKUP_REVAL;
-		goto retry;
-	}
-	return error;
+	return path_removexattr(pathname, name, 0);
 }
 
 SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)

include/linux/dcache.h

@@ -11,7 +11,6 @@
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 
-struct nameidata;
 struct path;
 struct vfsmount;
 
@@ -226,11 +225,6 @@ struct dentry_operations {
 
 extern seqlock_t rename_lock;
 
-static inline int dname_external(const struct dentry *dentry)
-{
-	return dentry->d_name.name != dentry->d_iname;
-}
-
 /*
  * These are the low-level FS interfaces to the dcache..
  */
@@ -254,7 +248,7 @@ extern struct dentry * d_obtain_root(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
 extern void shrink_dcache_for_umount(struct super_block *);
-extern int d_invalidate(struct dentry *);
+extern void d_invalidate(struct dentry *);
 
 /* only used at mount-time */
 extern struct dentry * d_make_root(struct inode *);
@@ -269,7 +263,6 @@ extern void d_prune_aliases(struct inode *);
 
 /* test whether we have any submounts in a subdir tree */
 extern int have_submounts(struct dentry *);
-extern int check_submounts_and_drop(struct dentry *);
 
 /*
  * This adds the entry to the hash queues.

include/linux/fs.h

@@ -1839,7 +1839,8 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char *, const char *, unsigned long, void *);
+extern long do_mount(const char *, const char __user *,
+		     const char *, unsigned long, void *);
 extern struct vfsmount *collect_mounts(struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
 extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
@@ -1858,7 +1859,7 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 
-static inline struct inode *file_inode(struct file *f)
+static inline struct inode *file_inode(const struct file *f)
 {
 	return f->f_inode;
 }

include/linux/uio.h

@@ -80,6 +80,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
 size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
+size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
 			unsigned long nr_segs, size_t count);

kernel/printk/printk.c

@@ -519,14 +519,13 @@ struct devkmsg_user {
 	char buf[8192];
 };
 
-static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
-			      unsigned long count, loff_t pos)
+static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	char *buf, *line;
 	int i;
 	int level = default_message_loglevel;
 	int facility = 1;	/* LOG_USER */
-	size_t len = iov_length(iv, count);
+	size_t len = iocb->ki_nbytes;
 	ssize_t ret = len;
 
 	if (len > LOG_LINE_MAX)
@@ -535,13 +534,10 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
 	if (buf == NULL)
 		return -ENOMEM;
 
-	line = buf;
-	for (i = 0; i < count; i++) {
-		if (copy_from_user(line, iv[i].iov_base, iv[i].iov_len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		line += iv[i].iov_len;
+	buf[len] = '\0';
+	if (copy_from_iter(buf, len, from) != len) {
+		kfree(buf);
+		return -EFAULT;
 	}
 
 	/*
@@ -567,10 +563,8 @@ static ssize_t devkmsg_writev(struct kiocb *iocb, const struct iovec *iv,
 			line = endp;
 		}
 	}
-	line[len] = '\0';
 
 	printk_emit(facility, level, NULL, 0, "%s", line);
-out:
 	kfree(buf);
 	return ret;
 }
@@ -802,7 +796,7 @@ static int devkmsg_release(struct inode *inode, struct file *file)
 const struct file_operations kmsg_fops = {
 	.open = devkmsg_open,
 	.read = devkmsg_read,
-	.aio_write = devkmsg_writev,
+	.write_iter = devkmsg_write,
 	.llseek = devkmsg_llseek,
 	.poll = devkmsg_poll,
 	.release = devkmsg_release,

mm/iov_iter.c

@@ -4,6 +4,96 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
+static size_t copy_to_iter_iovec(void *from, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_from_iter_iovec(void *to, size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __copy_from_user(to, buf, copy);
+	copy -= left;
+	skip += copy;
+	to += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_from_user(to, buf, copy);
+		copy -= left;
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
@@ -166,6 +256,50 @@ done:
 	return wanted - bytes;
 }
 
+static size_t zero_iovec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	left = __clear_user(buf, copy);
+	copy -= left;
+	skip += copy;
+	bytes -= copy;
+
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __clear_user(buf, copy);
+		copy -= left;
+		skip = copy;
+		bytes -= copy;
+	}
+
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
@@ -414,12 +548,17 @@ static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t
 	kunmap_atomic(to);
 }
 
-static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
+static void memzero_page(struct page *page, size_t offset, size_t len)
+{
+	char *addr = kmap_atomic(page);
+	memset(addr + offset, 0, len);
+	kunmap_atomic(addr);
+}
+
+static size_t copy_to_iter_bvec(void *from, size_t bytes, struct iov_iter *i)
 {
 	size_t skip, copy, wanted;
 	const struct bio_vec *bvec;
-	void *kaddr, *from;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
@@ -432,8 +571,6 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 	skip = i->iov_offset;
 	copy = min_t(size_t, bytes, bvec->bv_len - skip);
 
-	kaddr = kmap_atomic(page);
-	from = kaddr + offset;
 	memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy);
 	skip += copy;
 	from += copy;
@@ -446,7 +583,6 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 		from += copy;
 		bytes -= copy;
 	}
-	kunmap_atomic(kaddr);
 	if (skip == bvec->bv_len) {
 		bvec++;
 		skip = 0;
@@ -458,12 +594,10 @@ static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t by
 	return wanted - bytes;
 }
 
-static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t bytes,
-			 struct iov_iter *i)
+static size_t copy_from_iter_bvec(void *to, size_t bytes, struct iov_iter *i)
 {
 	size_t skip, copy, wanted;
 	const struct bio_vec *bvec;
-	void *kaddr, *to;
 
 	if (unlikely(bytes > i->count))
 		bytes = i->count;
@@ -475,10 +609,6 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 	bvec = i->bvec;
 	skip = i->iov_offset;
 
-	kaddr = kmap_atomic(page);
-
-	to = kaddr + offset;
-
 	copy = min(bytes, bvec->bv_len - skip);
 
 	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy);
@@ -495,7 +625,6 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 		to += copy;
 		bytes -= copy;
 	}
-	kunmap_atomic(kaddr);
 	if (skip == bvec->bv_len) {
 		bvec++;
 		skip = 0;
@@ -507,6 +636,61 @@ static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t
 	return wanted;
 }
 
+static size_t copy_page_to_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_to_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t copy_page_from_iter_bvec(struct page *page, size_t offset,
+					size_t bytes, struct iov_iter *i)
+{
+	void *kaddr = kmap_atomic(page);
+	size_t wanted = copy_from_iter_bvec(kaddr + offset, bytes, i);
+	kunmap_atomic(kaddr);
+	return wanted;
+}
+
+static size_t zero_bvec(size_t bytes, struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+	copy = min_t(size_t, bytes, bvec->bv_len - skip);
+
+	memzero_page(bvec->bv_page, skip + bvec->bv_offset, copy);
+	skip += copy;
+	bytes -= copy;
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memzero_page(bvec->bv_page, bvec->bv_offset, copy);
+		skip = copy;
+		bytes -= copy;
+	}
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
 static size_t copy_from_user_bvec(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {
@@ -672,6 +856,34 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
 }
 EXPORT_SYMBOL(copy_page_from_iter);
 
+size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_to_iter_bvec(addr, bytes, i);
+	else
+		return copy_to_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_to_iter);
+
+size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_from_iter_bvec(addr, bytes, i);
+	else
+		return copy_from_iter_iovec(addr, bytes, i);
+}
+EXPORT_SYMBOL(copy_from_iter);
+
+size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC) {
+		return zero_bvec(bytes, i);
+	} else {
+		return zero_iovec(bytes, i);
+	}
+}
+EXPORT_SYMBOL(iov_iter_zero);
+
 size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {

net/netlink/af_netlink.c

@@ -715,7 +715,7 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 	 * after validation, the socket and the ring may only be used by a
 	 * single process, otherwise we fall back to copying.
 	 */
-	if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 ||
+	if (atomic_long_read(&sk->sk_socket->file->f_count) > 1 ||
 	    atomic_read(&nlk->mapped) > 1)
 		excl = false;
 

tools/perf/util/string.c

@@ -9,78 +9,48 @@
  */
 s64 perf_atoll(const char *str)
 {
-	unsigned int i;
-	s64 length = -1, unit = 1;
+	s64 length;
+	char *p;
+	char c;
 
 	if (!isdigit(str[0]))
 		goto out_err;
 
-	for (i = 1; i < strlen(str); i++) {
-		switch (str[i]) {
-		case 'B':
-		case 'b':
-			break;
-		case 'K':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto kilo;
-		case 'k':
-			if (str[i + 1] != 'b')
-				goto out_err;
-kilo:
-			unit = K;
-			break;
-		case 'M':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto mega;
-		case 'm':
-			if (str[i + 1] != 'b')
+	length = strtoll(str, &p, 10);
+	switch (c = *p++) {
+		case 'b': case 'B':
+			if (*p)
 				goto out_err;
-mega:
-			unit = K * K;
+		case '\0':
+			return length;
+		default:
+			goto out_err;
+		/* two-letter suffices */
+		case 'k': case 'K':
+			length <<= 10;
 			break;
-		case 'G':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto giga;
-		case 'g':
-			if (str[i + 1] != 'b')
-				goto out_err;
-giga:
-			unit = K * K * K;
+		case 'm': case 'M':
+			length <<= 20;
 			break;
-		case 'T':
-			if (str[i + 1] != 'B')
-				goto out_err;
-			else
-				goto tera;
-		case 't':
-			if (str[i + 1] != 'b')
-				goto out_err;
-tera:
-			unit = K * K * K * K;
+		case 'g': case 'G':
+			length <<= 30;
 			break;
-		case '\0':	/* only specified figures */
-			unit = 1;
+		case 't': case 'T':
+			length <<= 40;
 			break;
-		default:
-			if (!isdigit(str[i]))
-				goto out_err;
-			break;
-		}
 	}
-
-	length = atoll(str) * unit;
-	goto out;
+	/* we want the cases to match */
+	if (islower(c)) {
+		if (strcmp(p, "b") != 0)
+			goto out_err;
+	} else {
+		if (strcmp(p, "B") != 0)
+			goto out_err;
+	}
+	return length;
 
 out_err:
-	length = -1;
-out:
-	return length;
+	return -1;
 }
 
 /*