Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull misc vfs updates from Al Viro:
 "All kinds of misc stuff, without any unifying topic, from various
  people.

  Neil's d_anon patch, several bugfixes, introduction of kvmalloc
  analogue of kmemdup_user(), extending bitfield.h to deal with
  fixed-endians, assorted cleanups all over the place..."

* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (28 commits)
  alpha: osf_sys.c: use timespec64 where appropriate
  alpha: osf_sys.c: fix put_tv32 regression
  jffs2: Fix use-after-free bug in jffs2_iget()'s error handling path
  dcache: delete unused d_hash_mask
  dcache: subtract d_hash_shift from 32 in advance
  fs/buffer.c: fold init_buffer() into init_page_buffers()
  fs: fold __inode_permission() into inode_permission()
  fs: add RWF_APPEND
  sctp: use vmemdup_user() rather than badly open-coding memdup_user()
  snd_ctl_elem_init_enum_names(): switch to vmemdup_user()
  replace_user_tlv(): switch to vmemdup_user()
  new primitive: vmemdup_user()
  memdup_user(): switch to GFP_USER
  eventfd: fold eventfd_ctx_get() into eventfd_ctx_fileget()
  eventfd: fold eventfd_ctx_read() into eventfd_read()
  eventfd: convert to use anon_inode_getfd()
  nfs4file: get rid of pointless include of btrfs.h
  uvc_v4l2: clean copyin/copyout up
  vme_user: don't use __copy_..._user()
  usx2y: don't bother with memdup_user() for 16-byte structure
  ...

28 files changed, 298 insertions, 405 deletions

diff --git a/Documentation/filesystems/nfs/Exporting b/Documentation/filesystems/nfs/Exporting
index 520a4becb75c..63889149f532 100644
--- a/Documentation/filesystems/nfs/Exporting
+++ b/Documentation/filesystems/nfs/Exporting
@@ -56,13 +56,25 @@ a/ A dentry flag DCACHE_DISCONNECTED which is set on
    any dentry that might not be part of the proper prefix.
    This is set when anonymous dentries are created, and cleared when a
    dentry is noticed to be a child of a dentry which is in the proper
-   prefix. 
-
-b/ A per-superblock list "s_anon" of dentries which are the roots of
-   subtrees that are not in the proper prefix.  These dentries, as
-   well as the proper prefix, need to be released at unmount time.  As
-   these dentries will not be hashed, they are linked together on the
-   d_hash list_head.
+   prefix.  If the refcount on a dentry with this flag set
+   becomes zero, the dentry is immediately discarded, rather than being
+   kept in the dcache.  If a dentry that is not already in the dcache
+   is repeatedly accessed by filehandle (as NFSD might do), an new dentry
+   will be a allocated for each access, and discarded at the end of
+   the access.
+
+   Note that such a dentry can acquire children, name, ancestors, etc.
+   without losing DCACHE_DISCONNECTED - that flag is only cleared when
+   subtree is successfully reconnected to root.  Until then dentries
+   in such subtree are retained only as long as there are references;
+   refcount reaching zero means immediate eviction, same as for unhashed
+   dentries.  That guarantees that we won't need to hunt them down upon
+   umount.
+
+b/ A primitive for creation of secondary roots - d_obtain_root(inode).
+   Those do _not_ bear DCACHE_DISCONNECTED.  They are placed on the
+   per-superblock list (->s_roots), so they can be located at umount
+   time for eviction purposes.
 
 c/ Helper routines to allocate anonymous dentries, and to help attach
    loose directory dentries at lookup time. They are:
@@ -77,7 +89,6 @@ c/ Helper routines to allocate anonymous dentries, and to help attach
       (such as an anonymous one created by d_obtain_alias), if appropriate.
       It returns NULL when the passed-in dentry is used, following the calling
       convention of ->lookup.
-
  
 Filesystem Issues
 -----------------
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index ce3a675c0c4b..fa1a392ca9a2 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -950,22 +950,31 @@ struct itimerval32
 };
 
 static inline long
-get_tv32(struct timeval *o, struct timeval32 __user *i)
+get_tv32(struct timespec64 *o, struct timeval32 __user *i)
 {
 	struct timeval32 tv;
 	if (copy_from_user(&tv, i, sizeof(struct timeval32)))
 		return -EFAULT;
 	o->tv_sec = tv.tv_sec;
-	o->tv_usec = tv.tv_usec;
+	o->tv_nsec = tv.tv_usec * NSEC_PER_USEC;
 	return 0;
 }
 
 static inline long
-put_tv32(struct timeval32 __user *o, struct timeval *i)
+put_tv32(struct timeval32 __user *o, struct timespec64 *i)
 {
 	return copy_to_user(o, &(struct timeval32){
-				.tv_sec = o->tv_sec,
-				.tv_usec = o->tv_usec},
+				.tv_sec = i->tv_sec,
+				.tv_usec = i->tv_nsec / NSEC_PER_USEC},
+			    sizeof(struct timeval32));
+}
+
+static inline long
+put_tv_to_tv32(struct timeval32 __user *o, struct timeval *i)
+{
+	return copy_to_user(o, &(struct timeval32){
+				.tv_sec = i->tv_sec,
+				.tv_usec = i->tv_usec},
 			    sizeof(struct timeval32));
 }
 
@@ -1004,9 +1013,10 @@ SYSCALL_DEFINE2(osf_gettimeofday, struct timeval32 __user *, tv,
 		struct timezone __user *, tz)
 {
 	if (tv) {
-		struct timeval ktv;
-		do_gettimeofday(&ktv);
-		if (put_tv32(tv, &ktv))
+		struct timespec64 kts;
+
+		ktime_get_real_ts64(&kts);
+		if (put_tv32(tv, &kts))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -1019,22 +1029,19 @@ SYSCALL_DEFINE2(osf_gettimeofday, struct timeval32 __user *, tv,
 SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
 		struct timezone __user *, tz)
 {
-	struct timespec64 kts64;
-	struct timespec kts;
+	struct timespec64 kts;
 	struct timezone ktz;
 
  	if (tv) {
-		if (get_tv32((struct timeval *)&kts, tv))
+		if (get_tv32(&kts, tv))
 			return -EFAULT;
-		kts.tv_nsec *= 1000;
-		kts64 = timespec_to_timespec64(kts);
 	}
 	if (tz) {
 		if (copy_from_user(&ktz, tz, sizeof(*tz)))
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday64(tv ? &kts64 : NULL, tz ? &ktz : NULL);
+	return do_sys_settimeofday64(tv ? &kts : NULL, tz ? &ktz : NULL);
 }
 
 asmlinkage long sys_ni_posix_timers(void);
@@ -1083,22 +1090,16 @@ SYSCALL_DEFINE3(osf_setitimer, int, which, struct itimerval32 __user *, in,
 SYSCALL_DEFINE2(osf_utimes, const char __user *, filename,
 		struct timeval32 __user *, tvs)
 {
-	struct timespec tv[2];
+	struct timespec64 tv[2];
 
 	if (tvs) {
-		struct timeval ktvs[2];
-		if (get_tv32(&ktvs[0], &tvs[0]) ||
-		    get_tv32(&ktvs[1], &tvs[1]))
+		if (get_tv32(&tv[0], &tvs[0]) ||
+		    get_tv32(&tv[1], &tvs[1]))
 			return -EFAULT;
 
-		if (ktvs[0].tv_usec < 0 || ktvs[0].tv_usec >= 1000000 ||
-		    ktvs[1].tv_usec < 0 || ktvs[1].tv_usec >= 1000000)
+		if (tv[0].tv_nsec < 0 || tv[0].tv_nsec >= 1000000000 ||
+		    tv[1].tv_nsec < 0 || tv[1].tv_nsec >= 1000000000)
 			return -EINVAL;
-
-		tv[0].tv_sec = ktvs[0].tv_sec;
-		tv[0].tv_nsec = 1000 * ktvs[0].tv_usec;
-		tv[1].tv_sec = ktvs[1].tv_sec;
-		tv[1].tv_nsec = 1000 * ktvs[1].tv_usec;
 	}
 
 	return do_utimes(AT_FDCWD, filename, tvs ? tv : NULL, 0);
@@ -1107,19 +1108,18 @@ SYSCALL_DEFINE2(osf_utimes, const char __user *, filename,
 SYSCALL_DEFINE5(osf_select, int, n, fd_set __user *, inp, fd_set __user *, outp,
 		fd_set __user *, exp, struct timeval32 __user *, tvp)
 {
-	struct timespec end_time, *to = NULL;
+	struct timespec64 end_time, *to = NULL;
 	if (tvp) {
-		struct timeval tv;
+		struct timespec64 tv;
 		to = &end_time;
 
 		if (get_tv32(&tv, tvp))
 		    	return -EFAULT;
 
-		if (tv.tv_sec < 0 || tv.tv_usec < 0)
+		if (tv.tv_sec < 0 || tv.tv_nsec < 0)
 			return -EINVAL;
 
-		if (poll_select_set_timeout(to, tv.tv_sec,
-					    tv.tv_usec * NSEC_PER_USEC))
+		if (poll_select_set_timeout(to, tv.tv_sec, tv.tv_nsec))
 			return -EINVAL;		
 
 	}
@@ -1192,9 +1192,9 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 		return -EFAULT;
 	if (!ur)
 		return err;
-	if (put_tv32(&ur->ru_utime, &r.ru_utime))
+	if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))
 		return -EFAULT;
-	if (put_tv32(&ur->ru_stime, &r.ru_stime))
+	if (put_tv_to_tv32(&ur->ru_stime, &r.ru_stime))
 		return -EFAULT;
 	if (copy_to_user(&ur->ru_maxrss, &r.ru_maxrss,
 	      sizeof(struct rusage32) - offsetof(struct rusage32, ru_maxrss)))
@@ -1210,18 +1210,18 @@ SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 SYSCALL_DEFINE2(osf_usleep_thread, struct timeval32 __user *, sleep,
 		struct timeval32 __user *, remain)
 {
-	struct timeval tmp;
+	struct timespec64 tmp;
 	unsigned long ticks;
 
 	if (get_tv32(&tmp, sleep))
 		goto fault;
 
-	ticks = timeval_to_jiffies(&tmp);
+	ticks = timespec64_to_jiffies(&tmp);
 
 	ticks = schedule_timeout_interruptible(ticks);
 
 	if (remain) {
-		jiffies_to_timeval(ticks, &tmp);
+		jiffies_to_timespec64(ticks, &tmp);
 		if (put_tv32(remain, &tmp))
 			goto fault;
 	}
@@ -1280,7 +1280,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p)
 	if (copy_to_user(txc_p, &txc, offsetof(struct timex32, time)) ||
 	    (copy_to_user(&txc_p->tick, &txc.tick, sizeof(struct timex32) - 
 			  offsetof(struct timex32, tick))) ||
-	    (put_tv32(&txc_p->time, &txc.time)))
+	    (put_tv_to_tv32(&txc_p->time, &txc.time)))
 	  return -EFAULT;
 
 	return ret;
diff --git a/drivers/gpu/drm/r128/r128_state.c b/drivers/gpu/drm/r128/r128_state.c
index 8fdc56c1c953..b9bfa806d346 100644
--- a/drivers/gpu/drm/r128/r128_state.c
+++ b/drivers/gpu/drm/r128/r128_state.c
@@ -982,25 +982,14 @@ static int r128_cce_dispatch_write_pixels(struct drm_device *dev,
 
 	xbuf_size = count * sizeof(*x);
 	ybuf_size = count * sizeof(*y);
-	x = kmalloc(xbuf_size, GFP_KERNEL);
-	if (x == NULL)
-		return -ENOMEM;
-	y = kmalloc(ybuf_size, GFP_KERNEL);
-	if (y == NULL) {
-		kfree(x);
-		return -ENOMEM;
-	}
-	if (copy_from_user(x, depth->x, xbuf_size)) {
-		kfree(x);
-		kfree(y);
-		return -EFAULT;
-	}
-	if (copy_from_user(y, depth->y, xbuf_size)) {
+	x = memdup_user(depth->x, xbuf_size);
+	if (IS_ERR(x))
+		return PTR_ERR(x);
+	y = memdup_user(depth->y, ybuf_size);
+	if (IS_ERR(y)) {
 		kfree(x);
-		kfree(y);
-		return -EFAULT;
+		return PTR_ERR(y);
 	}
-
 	buffer_size = depth->n * sizeof(u32);
 	buffer = memdup_user(depth->buffer, buffer_size);
 	if (IS_ERR(buffer)) {
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index ed3bf05e2462..381f614b2f4c 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -1284,36 +1284,30 @@ struct uvc_xu_control_mapping32 {
 static int uvc_v4l2_get_xu_mapping(struct uvc_xu_control_mapping *kp,
 			const struct uvc_xu_control_mapping32 __user *up)
 {
-	compat_caddr_t p;
+	struct uvc_xu_control_mapping32 *p = (void *)kp;
+	compat_caddr_t info;
+	u32 count;
 
-	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
-	    __copy_from_user(kp, up, offsetof(typeof(*up), menu_info)) ||
-	    __get_user(kp->menu_count, &up->menu_count))
+	if (copy_from_user(p, up, sizeof(*p)))
 		return -EFAULT;
 
-	memset(kp->reserved, 0, sizeof(kp->reserved));
-
-	if (kp->menu_count == 0) {
-		kp->menu_info = NULL;
-		return 0;
-	}
-
-	if (__get_user(p, &up->menu_info))
-		return -EFAULT;
-	kp->menu_info = compat_ptr(p);
+	count = p->menu_count;
+	info = p->menu_info;
 
+	memset(kp->reserved, 0, sizeof(kp->reserved));
+	kp->menu_info = count ? compat_ptr(info) : NULL;
+	kp->menu_count = count;
 	return 0;
 }
 
 static int uvc_v4l2_put_xu_mapping(const struct uvc_xu_control_mapping *kp,
 			struct uvc_xu_control_mapping32 __user *up)
 {
-	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
-	    __copy_to_user(up, kp, offsetof(typeof(*up), menu_info)) ||
-	    __put_user(kp->menu_count, &up->menu_count))
+	if (copy_to_user(up, kp, offsetof(typeof(*up), menu_info)) ||
+	    put_user(kp->menu_count, &up->menu_count))
 		return -EFAULT;
 
-	if (__clear_user(up->reserved, sizeof(up->reserved)))
+	if (clear_user(up->reserved, sizeof(up->reserved)))
 		return -EFAULT;
 
 	return 0;
@@ -1330,31 +1324,26 @@ struct uvc_xu_control_query32 {
 static int uvc_v4l2_get_xu_query(struct uvc_xu_control_query *kp,
 			const struct uvc_xu_control_query32 __user *up)
 {
-	compat_caddr_t p;
+	struct uvc_xu_control_query32 v;
 
-	if (!access_ok(VERIFY_READ, up, sizeof(*up)) ||
-	    __copy_from_user(kp, up, offsetof(typeof(*up), data)))
+	if (copy_from_user(&v, up, sizeof(v)))
 		return -EFAULT;
 
-	if (kp->size == 0) {
-		kp->data = NULL;
-		return 0;
-	}
-
-	if (__get_user(p, &up->data))
-		return -EFAULT;
-	kp->data = compat_ptr(p);
-
+	*kp = (struct uvc_xu_control_query){
+		.unit = v.unit,
+		.selector = v.selector,
+		.query = v.query,
+		.size = v.size,
+		.data = v.size ? compat_ptr(v.data) : NULL
+	};
 	return 0;
 }
 
 static int uvc_v4l2_put_xu_query(const struct uvc_xu_control_query *kp,
 			struct uvc_xu_control_query32 __user *up)
 {
-	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)) ||
-	    __copy_to_user(up, kp, offsetof(typeof(*up), data)))
+	if (copy_to_user(up, kp, offsetof(typeof(*up), data)))
 		return -EFAULT;
-
 	return 0;
 }
 
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index b133fd00c08c..0d62fcf016dc 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -1296,15 +1296,7 @@ static inline void d_lustre_invalidate(struct dentry *dentry, int nested)
 	spin_lock_nested(&dentry->d_lock,
 			 nested ? DENTRY_D_LOCK_NESTED : DENTRY_D_LOCK_NORMAL);
 	ll_d2d(dentry)->lld_invalid = 1;
-	/*
-	 * We should be careful about dentries created by d_obtain_alias().
-	 * These dentries are not put in the dentry tree, instead they are
-	 * linked to sb->s_anon through dentry->d_hash.
-	 * shrink_dcache_for_umount() shrinks the tree and sb->s_anon list.
-	 * If we unhashed such a dentry, unmount would not be able to find
-	 * it and busy inodes would be reported.
-	 */
-	if (d_count(dentry) == 0 && !(dentry->d_flags & DCACHE_DISCONNECTED))
+	if (d_count(dentry) == 0)
 		__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
 }
diff --git a/drivers/staging/vme/devices/vme_user.c b/drivers/staging/vme/devices/vme_user.c
index a3d4610fbdbe..4c8c6fa0a79f 100644
--- a/drivers/staging/vme/devices/vme_user.c
+++ b/drivers/staging/vme/devices/vme_user.c
@@ -134,7 +134,7 @@ static ssize_t resource_to_user(int minor, char __user *buf, size_t count,
 	if (copied < 0)
 		return (int)copied;
 
-	if (__copy_to_user(buf, image[minor].kern_buf, (unsigned long)copied))
+	if (copy_to_user(buf, image[minor].kern_buf, (unsigned long)copied))
 		return -EFAULT;
 
 	return copied;
@@ -146,7 +146,7 @@ static ssize_t resource_from_user(unsigned int minor, const char __user *buf,
 	if (count > image[minor].size_buf)
 		count = image[minor].size_buf;
 
-	if (__copy_from_user(image[minor].kern_buf, buf, (unsigned long)count))
+	if (copy_from_user(image[minor].kern_buf, buf, (unsigned long)count))
 		return -EFAULT;
 
 	return vme_master_write(image[minor].resource, image[minor].kern_buf,
@@ -159,7 +159,7 @@ static ssize_t buffer_to_user(unsigned int minor, char __user *buf,
 	void *image_ptr;
 
 	image_ptr = image[minor].kern_buf + *ppos;
-	if (__copy_to_user(buf, image_ptr, (unsigned long)count))
+	if (copy_to_user(buf, image_ptr, (unsigned long)count))
 		return -EFAULT;
 
 	return count;
@@ -171,7 +171,7 @@ static ssize_t buffer_from_user(unsigned int minor, const char __user *buf,
 	void *image_ptr;
 
 	image_ptr = image[minor].kern_buf + *ppos;
-	if (__copy_from_user(image_ptr, buf, (unsigned long)count))
+	if (copy_from_user(image_ptr, buf, (unsigned long)count))
 		return -EFAULT;
 
 	return count;
diff --git a/fs/buffer.c b/fs/buffer.c
index 8b26295a56fe..9a73924db22f 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -53,13 +53,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
-void init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private)
-{
-	bh->b_end_io = handler;
-	bh->b_private = private;
-}
-EXPORT_SYMBOL(init_buffer);
-
 inline void touch_buffer(struct buffer_head *bh)
 {
 	trace_block_touch_buffer(bh);
@@ -922,7 +915,8 @@ init_page_buffers(struct page *page, struct block_device *bdev,
 
 	do {
 		if (!buffer_mapped(bh)) {
-			init_buffer(bh, NULL, NULL);
+			bh->b_end_io = NULL;
+			bh->b_private = NULL;
 			bh->b_bdev = bdev;
 			bh->b_blocknr = block;
 			if (uptodate)
diff --git a/fs/dcache.c b/fs/dcache.c
index 379dce86f001..c6d996ee2d61 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -32,7 +32,6 @@
 #include <linux/swap.h>
 #include <linux/bootmem.h>
 #include <linux/fs_struct.h>
-#include <linux/hardirq.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rculist_bl.h>
 #include <linux/prefetch.h>
@@ -49,8 +48,8 @@
  *   - i_dentry, d_u.d_alias, d_inode of aliases
  * dcache_hash_bucket lock protects:
  *   - the dcache hash table
- * s_anon bl list spinlock protects:
- *   - the s_anon list (see __d_drop)
+ * s_roots bl list spinlock protects:
+ *   - the s_roots list (see __d_drop)
  * dentry->d_sb->s_dentry_lru_lock protects:
  *   - the dcache lru lists and counters
  * d_lock protects:
@@ -68,7 +67,7 @@
  *   dentry->d_lock
  *     dentry->d_sb->s_dentry_lru_lock
  *     dcache_hash_bucket lock
- *     s_anon lock
+ *     s_roots lock
  *
  * If there is an ancestor relationship:
  * dentry->d_parent->...->d_parent->d_lock
@@ -104,14 +103,13 @@ EXPORT_SYMBOL(slash_name);
  * information, yet avoid using a prime hash-size or similar.
  */
 
-static unsigned int d_hash_mask __read_mostly;
 static unsigned int d_hash_shift __read_mostly;
 
 static struct hlist_bl_head *dentry_hashtable __read_mostly;
 
 static inline struct hlist_bl_head *d_hash(unsigned int hash)
 {
-	return dentry_hashtable + (hash >> (32 - d_hash_shift));
+	return dentry_hashtable + (hash >> d_hash_shift);
 }
 
 #define IN_LOOKUP_SHIFT 10
@@ -477,10 +475,10 @@ void __d_drop(struct dentry *dentry)
 		/*
 		 * Hashed dentries are normally on the dentry hashtable,
 		 * with the exception of those newly allocated by
-		 * d_obtain_alias, which are always IS_ROOT:
+		 * d_obtain_root, which are always IS_ROOT:
 		 */
 		if (unlikely(IS_ROOT(dentry)))
-			b = &dentry->d_sb->s_anon;
+			b = &dentry->d_sb->s_roots;
 		else
 			b = d_hash(dentry->d_name.hash);
 
@@ -1500,8 +1498,8 @@ void shrink_dcache_for_umount(struct super_block *sb)
 	sb->s_root = NULL;
 	do_one_tree(dentry);
 
-	while (!hlist_bl_empty(&sb->s_anon)) {
-		dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash));
+	while (!hlist_bl_empty(&sb->s_roots)) {
+		dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash));
 		do_one_tree(dentry);
 	}
 }
@@ -1964,9 +1962,11 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
 	spin_lock(&tmp->d_lock);
 	__d_set_inode_and_type(tmp, inode, add_flags);
 	hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
-	hlist_bl_lock(&tmp->d_sb->s_anon);
-	hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
-	hlist_bl_unlock(&tmp->d_sb->s_anon);
+	if (!disconnected) {
+		hlist_bl_lock(&tmp->d_sb->s_roots);
+		hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_roots);
+		hlist_bl_unlock(&tmp->d_sb->s_roots);
+	}
 	spin_unlock(&tmp->d_lock);
 	spin_unlock(&inode->i_lock);
 
@@ -3585,9 +3585,10 @@ static void __init dcache_init_early(void)
 					13,
 					HASH_EARLY | HASH_ZERO,
 					&d_hash_shift,
-					&d_hash_mask,
+					NULL,
 					0,
 					0);
+	d_hash_shift = 32 - d_hash_shift;
 }
 
 static void __init dcache_init(void)
@@ -3611,9 +3612,10 @@ static void __init dcache_init(void)
 					13,
 					HASH_ZERO,
 					&d_hash_shift,
-					&d_hash_mask,
+					NULL,
 					0,
 					0);
+	d_hash_shift = 32 - d_hash_shift;
 }
 
 /* SLAB cache for __getname() consumers */
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 6318a9b57e53..04fd824142a1 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -80,24 +80,11 @@ static void eventfd_free(struct kref *kref)
 }
 
 /**
- * eventfd_ctx_get - Acquires a reference to the internal eventfd context.
- * @ctx: [in] Pointer to the eventfd context.
- *
- * Returns: In case of success, returns a pointer to the eventfd context.
- */
-struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx)
-{
-	kref_get(&ctx->kref);
-	return ctx;
-}
-EXPORT_SYMBOL_GPL(eventfd_ctx_get);
-
-/**
  * eventfd_ctx_put - Releases a reference to the internal eventfd context.
  * @ctx: [in] Pointer to eventfd context.
  *
  * The eventfd context reference must have been previously acquired either
- * with eventfd_ctx_get() or eventfd_ctx_fdget().
+ * with eventfd_ctx_fdget() or eventfd_ctx_fileget().
  */
 void eventfd_ctx_put(struct eventfd_ctx *ctx)
 {
@@ -207,36 +194,27 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *w
 }
 EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
 
-/**
- * eventfd_ctx_read - Reads the eventfd counter or wait if it is zero.
- * @ctx: [in] Pointer to eventfd context.
- * @no_wait: [in] Different from zero if the operation should not block.
- * @cnt: [out] Pointer to the 64-bit counter value.
- *
- * Returns %0 if successful, or the following error codes:
- *
- *  - -EAGAIN      : The operation would have blocked but @no_wait was non-zero.
- *  - -ERESTARTSYS : A signal interrupted the wait operation.
- *
- * If @no_wait is zero, the function might sleep until the eventfd internal
- * counter becomes greater than zero.
- */
-ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt)
+static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
 {
+	struct eventfd_ctx *ctx = file->private_data;
 	ssize_t res;
+	__u64 ucnt = 0;
 	DECLARE_WAITQUEUE(wait, current);
 
+	if (count < sizeof(ucnt))
+		return -EINVAL;
+
 	spin_lock_irq(&ctx->wqh.lock);
-	*cnt = 0;
 	res = -EAGAIN;
 	if (ctx->count > 0)
-		res = 0;
-	else if (!no_wait) {
+		res = sizeof(ucnt);
+	else if (!(file->f_flags & O_NONBLOCK)) {
 		__add_wait_queue(&ctx->wqh, &wait);
 		for (;;) {
 			set_current_state(TASK_INTERRUPTIBLE);
 			if (ctx->count > 0) {
-				res = 0;
+				res = sizeof(ucnt);
 				break;
 			}
 			if (signal_pending(current)) {
@@ -250,31 +228,17 @@ ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt)
 		__remove_wait_queue(&ctx->wqh, &wait);
 		__set_current_state(TASK_RUNNING);
 	}
-	if (likely(res == 0)) {
-		eventfd_ctx_do_read(ctx, cnt);
+	if (likely(res > 0)) {
+		eventfd_ctx_do_read(ctx, &ucnt);
 		if (waitqueue_active(&ctx->wqh))
 			wake_up_locked_poll(&ctx->wqh, POLLOUT);
 	}
 	spin_unlock_irq(&ctx->wqh.lock);
 
-	return res;
-}
-EXPORT_SYMBOL_GPL(eventfd_ctx_read);
-
-static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
-			    loff_t *ppos)
-{
-	struct eventfd_ctx *ctx = file->private_data;
-	ssize_t res;
-	__u64 cnt;
-
-	if (count < sizeof(cnt))
-		return -EINVAL;
-	res = eventfd_ctx_read(ctx, file->f_flags & O_NONBLOCK, &cnt);
-	if (res < 0)
-		return res;
+	if (res > 0 && put_user(ucnt, (__u64 __user *)buf))
+		return -EFAULT;
 
-	return put_user(cnt, (__u64 __user *) buf) ? -EFAULT : sizeof(cnt);
+	return res;
 }
 
 static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
@@ -405,79 +369,44 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
  */
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file)
 {
+	struct eventfd_ctx *ctx;
+
 	if (file->f_op != &eventfd_fops)
 		return ERR_PTR(-EINVAL);
 
-	return eventfd_ctx_get(file->private_data);
+	ctx = file->private_data;
+	kref_get(&ctx->kref);
+	return ctx;
 }
 EXPORT_SYMBOL_GPL(eventfd_ctx_fileget);
 
-/**
- * eventfd_file_create - Creates an eventfd file pointer.
- * @count: Initial eventfd counter value.
- * @flags: Flags for the eventfd file.
- *
- * This function creates an eventfd file pointer, w/out installing it into
- * the fd table. This is useful when the eventfd file is used during the
- * initialization of data structures that require extra setup after the eventfd
- * creation. So the eventfd creation is split into the file pointer creation
- * phase, and the file descriptor installation phase.
- * In this way races with userspace closing the newly installed file descriptor
- * can be avoided.
- * Returns an eventfd file pointer, or a proper error pointer.
- */
-struct file *eventfd_file_create(unsigned int count, int flags)
+SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
 {
-	struct file *file;
 	struct eventfd_ctx *ctx;
+	int fd;
 
 	/* Check the EFD_* constants for consistency.  */
 	BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
 	BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
 
 	if (flags & ~EFD_FLAGS_SET)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	kref_init(&ctx->kref);
 	init_waitqueue_head(&ctx->wqh);
 	ctx->count = count;
 	ctx->flags = flags;
 
-	file = anon_inode_getfile("[eventfd]", &eventfd_fops, ctx,
-				  O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS));
-	if (IS_ERR(file))
+	fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx,
+			      O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS));
+	if (fd < 0)
 		eventfd_free_ctx(ctx);
 
-	return file;
-}
-
-SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
-{
-	int fd, error;
-	struct file *file;
-
-	error = get_unused_fd_flags(flags & EFD_SHARED_FCNTL_FLAGS);
-	if (error < 0)
-		return error;
-	fd = error;
-
-	file = eventfd_file_create(count, flags);
-	if (IS_ERR(file)) {
-		error = PTR_ERR(file);
-		goto err_put_unused_fd;
-	}
-	fd_install(fd, file);
-
 	return fd;
-
-err_put_unused_fd:
-	put_unused_fd(fd);
-
-	return error;
 }
 
 SYSCALL_DEFINE1(eventfd, unsigned int, count)
diff --git a/fs/file.c b/fs/file.c
index fc0eeb812e2c..42f0db4bd0fb 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -11,18 +11,13 @@
 #include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
-#include <linux/mmzone.h>
-#include <linux/time.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/bitops.h>
-#include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
-#include <linux/workqueue.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;
diff --git a/fs/file_table.c b/fs/file_table.c
index 2dc9f38bd195..7ec0b3e5f05d 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -23,7 +23,6 @@
 #include <linux/sysctl.h>
 #include <linux/percpu_counter.h>
 #include <linux/percpu.h>
-#include <linux/hardirq.h>
 #include <linux/task_work.h>
 #include <linux/ima.h>
 #include <linux/swap.h>
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index d8c274d39ddb..eab04eca95a3 100644
--- a/