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/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -362,7 +362,6 @@ error_io:
 	ret = -EIO;
 error:
 	mutex_unlock(&f->sem);
-	jffs2_do_clear_inode(c, f);
 	iget_failed(inode);
 	return ERR_PTR(ret);
 }
diff --git a/fs/namei.c b/fs/namei.c
index 7c221fb0836b..921ae32dbc80 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -391,50 +391,6 @@ static inline int do_inode_permission(struct inode *inode, int mask)
 }
 
 /**
- * __inode_permission - Check for access rights to a given inode
- * @inode: Inode to check permission on
- * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
- *
- * Check for read/write/execute permissions on an inode.
- *
- * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
- *
- * This does not check for a read-only file system.  You probably want
- * inode_permission().
- */
-int __inode_permission(struct inode *inode, int mask)
-{
-	int retval;
-
-	if (unlikely(mask & MAY_WRITE)) {
-		/*
-		 * Nobody gets write access to an immutable file.
-		 */
-		if (IS_IMMUTABLE(inode))
-			return -EPERM;
-
-		/*
-		 * Updating mtime will likely cause i_uid and i_gid to be
-		 * written back improperly if their true value is unknown
-		 * to the vfs.
-		 */
-		if (HAS_UNMAPPED_ID(inode))
-			return -EACCES;
-	}
-
-	retval = do_inode_permission(inode, mask);
-	if (retval)
-		return retval;
-
-	retval = devcgroup_inode_permission(inode, mask);
-	if (retval)
-		return retval;
-
-	return security_inode_permission(inode, mask);
-}
-EXPORT_SYMBOL(__inode_permission);
-
-/**
  * sb_permission - Check superblock-level permissions
  * @sb: Superblock of inode to check permission on
  * @inode: Inode to check permission on
@@ -472,7 +428,32 @@ int inode_permission(struct inode *inode, int mask)
 	retval = sb_permission(inode->i_sb, inode, mask);
 	if (retval)
 		return retval;
-	return __inode_permission(inode, mask);
+
+	if (unlikely(mask & MAY_WRITE)) {
+		/*
+		 * Nobody gets write access to an immutable file.
+		 */
+		if (IS_IMMUTABLE(inode))
+			return -EPERM;
+
+		/*
+		 * Updating mtime will likely cause i_uid and i_gid to be
+		 * written back improperly if their true value is unknown
+		 * to the vfs.
+		 */
+		if (HAS_UNMAPPED_ID(inode))
+			return -EACCES;
+	}
+
+	retval = do_inode_permission(inode, mask);
+	if (retval)
+		return retval;
+
+	retval = devcgroup_inode_permission(inode, mask);
+	if (retval)
+		return retval;
+
+	return security_inode_permission(inode, mask);
 }
 EXPORT_SYMBOL(inode_permission);
 
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 626d1382002e..6b3b372b59b9 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -8,7 +8,6 @@
 #include <linux/file.h>
 #include <linux/falloc.h>
 #include <linux/nfs_fs.h>
-#include <uapi/linux/btrfs.h>	/* BTRFS_IOC_CLONE/BTRFS_IOC_CLONE_RANGE */
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
diff --git a/fs/super.c b/fs/super.c
index 06bd25d90ba5..672538ca9831 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -225,7 +225,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	if (s->s_user_ns != &init_user_ns)
 		s->s_iflags |= SB_I_NODEV;
 	INIT_HLIST_NODE(&s->s_instances);
-	INIT_HLIST_BL_HEAD(&s->s_anon);
+	INIT_HLIST_BL_HEAD(&s->s_roots);
 	mutex_init(&s->s_sync_lock);
 	INIT_LIST_HEAD(&s->s_inodes);
 	spin_lock_init(&s->s_inode_list_lock);
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 1030651f8309..cf2588d81148 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -16,6 +16,7 @@
 #define _LINUX_BITFIELD_H
 
 #include <linux/build_bug.h>
+#include <asm/byteorder.h>
 
 /*
  * Bitfield access macros
@@ -103,4 +104,49 @@
 		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask));	\
 	})
 
+extern void __compiletime_warning("value doesn't fit into mask")
+__field_overflow(void);
+extern void __compiletime_error("bad bitfield mask")
+__bad_mask(void);
+static __always_inline u64 field_multiplier(u64 field)
+{
+	if ((field | (field - 1)) & ((field | (field - 1)) + 1))
+		__bad_mask();
+	return field & -field;
+}
+static __always_inline u64 field_mask(u64 field)
+{
+	return field / field_multiplier(field);
+}
+#define ____MAKE_OP(type,base,to,from)					\
+static __always_inline __##type type##_encode_bits(base v, base field)	\
+{									\
+        if (__builtin_constant_p(v) &&	(v & ~field_multiplier(field)))	\
+			    __field_overflow();				\
+	return to((v & field_mask(field)) * field_multiplier(field));	\
+}									\
+static __always_inline __##type type##_replace_bits(__##type old,	\
+					base val, base field)		\
+{									\
+	return (old & ~to(field)) | type##_encode_bits(val, field);	\
+}									\
+static __always_inline void type##p_replace_bits(__##type *p,		\
+					base val, base field)		\
+{									\
+	*p = (*p & ~to(field)) | type##_encode_bits(val, field);	\
+}									\
+static __always_inline base type##_get_bits(__##type v, base field)	\
+{									\
+	return (from(v) & field)/field_multiplier(field);		\
+}
+#define __MAKE_OP(size)							\
+	____MAKE_OP(le##size,u##size,cpu_to_le##size,le##size##_to_cpu)	\
+	____MAKE_OP(be##size,u##size,cpu_to_be##size,be##size##_to_cpu)	\
+	____MAKE_OP(u##size,u##size,,)
+__MAKE_OP(16)
+__MAKE_OP(32)
+__MAKE_OP(64)
+#undef __MAKE_OP
+#undef ____MAKE_OP
+
 #endif
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 8b1bf8d3d4a2..58a82f58e44e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -151,7 +151,6 @@ void buffer_check_dirty_writeback(struct page *page,
 
 void mark_buffer_dirty(struct buffer_head *bh);
 void mark_buffer_write_io_error(struct buffer_head *bh);
-void init_buffer(struct buffer_head *, bh_end_io_t *, void *);
 void touch_buffer(struct buffer_head *bh);
 void set_bh_page(struct buffer_head *bh,
 		struct page *page, unsigned long offset);
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 60b2985e8a18..7094718b653b 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -26,18 +26,16 @@
 #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE)
 
+struct eventfd_ctx;
 struct file;
 
 #ifdef CONFIG_EVENTFD
 
-struct file *eventfd_file_create(unsigned int count, int flags);
-struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx);
 void eventfd_ctx_put(struct eventfd_ctx *ctx);
 struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
-ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait, __u64 *cnt);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 
@@ -47,10 +45,6 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *w
  * Ugly ugly ugly error layer to support modules that uses eventfd but
  * pretend to work in !CONFIG_EVENTFD configurations. Namely, AIO.
  */
-static inline struct file *eventfd_file_create(unsigned int count, int flags)
-{
-	return ERR_PTR(-ENOSYS);
-}
 
 static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
 {
@@ -67,12 +61,6 @@ static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
 
 }
 
-static inline ssize_t eventfd_ctx_read(struct eventfd_ctx *ctx, int no_wait,
-				       __u64 *cnt)
-{
-	return -ENOSYS;
-}
-
 static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
 						wait_queue_entry_t *wait, __u64 *cnt)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9798a133e718..8f6654c21711 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1359,7 +1359,7 @@ struct super_block {
 
 	const struct fscrypt_operations	*s_cop;
 
-	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
+	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;
 	struct backing_dev_info *s_bdi;
@@ -2688,7 +2688,6 @@ extern sector_t bmap(struct inode *, sector_t);
 #endif
 extern int notify_change(struct dentry *, struct iattr *, struct inode **);
 extern int inode_permission(struct inode *, int);
-extern int __inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int);
 extern int __check_sticky(struct inode *dir, struct inode *inode);
 
@@ -3228,6 +3227,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 		ki->ki_flags |= IOCB_DSYNC;
 	if (flags & RWF_SYNC)
 		ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	if (flags & RWF_APPEND)
+		ki->ki_flags |= IOCB_APPEND;
 	return 0;
 }
 
diff --git a/include/linux/string.h b/include/linux/string.h
index 96115bf561b4..dd39a690c841 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -11,6 +11,7 @@
 
 extern char *strndup_user(const char __user *, long);
 extern void *memdup_user(const void __user *, size_t);
+extern void *vmemdup_user(const void __user *, size_t);
 extern void *memdup_user_nul(const void __user *, size_t);
 
 /*
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 4199f8acbce5..d2a8313fabd7 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -377,7 +377,11 @@ typedef int __bitwise __kernel_rwf_t;
 /* per-IO, return -EAGAIN if operation would block */
 #define RWF_NOWAIT	((__force __kernel_rwf_t)0x00000008)
 
+/* per-IO O_APPEND */
+#define RWF_APPEND	((__force __kernel_rwf_t)0x00000010)
+
 /* mask of flags supported by the kernel */
-#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT)
+#define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
+			 RWF_APPEND)
 
 #endif /* _UAPI_LINUX_FS_H */
diff --git a/lib/usercopy.c b/lib/usercopy.c
index 15e2e6fb060e..3744b2a8e591 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -20,7 +20,7 @@ EXPORT_SYMBOL(_copy_from_user);
 #endif
 
 #ifndef INLINE_COPY_TO_USER
-unsigned long _copy_to_user(void *to, const void __user *from, unsigned long n)
+unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	might_fault();
 	if (likely(access_ok(VERIFY_WRITE, to, n))) {
diff --git a/mm/util.c b/mm/util.c
index 34e57fae959d..c1250501364f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -150,18 +150,14 @@ EXPORT_SYMBOL(kmemdup_nul);
  * @src: source address in user space
  * @len: number of bytes to copy
  *
- * Returns an ERR_PTR() on failure.
+ * Returns an ERR_PTR() on failure.  Result is physically
+ * contiguous, to be freed by kfree().
  */
 void *memdup_user(const void __user *src, size_t len)
 {
 	void *p;
 
-	/*
-	 * Always use GFP_KERNEL, since copy_from_user() can sleep and
-	 * cause pagefault, which makes it pointless to use GFP_NOFS
-	 * or GFP_ATOMIC.
-	 */
-	p = kmalloc_track_caller(len, GFP_KERNEL);
+	p = kmalloc_track_caller(len, GFP_USER);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
@@ -174,6 +170,32 @@ void *memdup_user(const void __user *src, size_t len)
 }
 EXPORT_SYMBOL(memdup_user);
 
+/**
+ * vmemdup_user - duplicate memory region from user space
+ *
+ * @src: source address in user space
+ * @len: number of bytes to copy
+ *
+ * Returns an ERR_PTR() on failure.  Result may be not
+ * physically contiguous.  Use kvfree() to free.
+ */
+void *vmemdup_user(const void __user *src, size_t len)
+{
+	void *p;
+
+	p = kvmalloc(len, GFP_USER);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(p, src, len)) {
+		kvfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return p;
+}
+EXPORT_SYMBOL(vmemdup_user);
+
 /*
  * strndup_user - duplicate an existing string from user space
  * @s: The string to duplicate
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 37382317fba4..737e551fbf67 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -968,13 +968,6 @@ int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw)
  * This is used for tunneling the sctp_bindx() request through sctp_setsockopt()
  * from userspace.
  *
- * We don't use copy_from_user() for optimization: we first do the
- * sanity checks (buffer size -fast- and access check-healthy
- * pointer); if all of those succeed, then we can alloc the memory
- * (expensive operation) needed to copy the data to kernel. Then we do
- * the copying without checking the user space area
- * (__copy_from_user()).
- *
  * On exit there is no need to do sockfd_put(), sys_setsockopt() does
  * it.
  *
@@ -1004,25 +997,15 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	/* Check the user passed a healthy pointer.  */
-	if (unlikely(!access_ok(VERIFY_READ, addrs, addrs_size)))
-		return -EFAULT;
-
-	/* Alloc space for the address array in kernel memory.  */
-	kaddrs = kmalloc(addrs_size, GFP_USER | __GFP_NOWARN);
-	if (unlikely(!kaddrs))
-		return -ENOMEM;
-
-	if (__copy_from_user(kaddrs, addrs, addrs_size)) {
-		kfree(kaddrs);
-		return -EFAULT;
-	}
+	kaddrs = vmemdup_user(addrs, addrs_size);
+	if (unlikely(IS_ERR(kaddrs)))
+		return PTR_ERR(kaddrs);
 
 	/* Walk through the addrs buffer and count the number of addresses. */
 	addr_buf = kaddrs;
 	while (walk_size < addrs_size) {
 		if (walk_size + sizeof(sa_family_t) > addrs_size) {
-			kfree(kaddrs);
+			kvfree(kaddrs);
 			return -EINVAL;
 		}
 
@@ -1033,7 +1016,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 		 * causes the address buffer to overflow return EINVAL.
 		 */
 		if (!af || (walk_size + af->sockaddr_len) > addrs_size) {
-			kfree(kaddrs);
+			kvfree(kaddrs);
 			return -EINVAL;
 		}
 		addrcnt++;
@@ -1063,7 +1046,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	}
 
 out:
-	kfree(kaddrs);
+	kvfree(kaddrs);
 
 	return err;
 }
@@ -1321,13 +1304,6 @@ out_free:
  * land and invoking either sctp_connectx(). This is used for tunneling
  * the sctp_connectx() request through sctp_setsockopt() from userspace.
  *
- * We don't use copy_from_user() for optimization: we first do the
- * sanity checks (buffer size -fast- and access check-healthy
- * pointer); if all of those succeed, then we can alloc the memory
- * (expensive operation) needed to copy the data to kernel. Then we do
- * the copying without checking the user space area
- * (__copy_from_user()).
- *
  * On exit there is no need to do sockfd_put(), sys_setsockopt() does
  * it.
  *
@@ -1343,7 +1319,6 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 				      sctp_assoc_t *assoc_id)
 {
 	struct sockaddr *kaddrs;
-	gfp_t gfp = GFP_KERNEL;
 	int err = 0;
 
 	pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n",
@@ -1352,24 +1327,12 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	/* Check the user passed a healthy pointer.  */
-	if (unlikely(!access_ok(VERIFY_READ, addrs, addrs_size)))
-		return -EFAULT;
-
-	/* Alloc space for the address array in kernel memory.  */
-	if (sk->sk_socket->file)
-		gfp = GFP_USER | __GFP_NOWARN;
-	kaddrs = kmalloc(addrs_size, gfp);
-	if (unlikely(!kaddrs))
-		return -ENOMEM;
-
-	if (__copy_from_user(kaddrs, addrs, addrs_size)) {
-		err = -EFAULT;
-	} else {
-		err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id);
-	}
+	kaddrs = vmemdup_user(addrs, addrs_size);
+	if (unlikely(IS_ERR(kaddrs)))
+		return PTR_ERR(kaddrs);
 
-	kfree(kaddrs);
+	err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id);
+	kvfree(kaddrs);
 
 	return err;
 }
diff --git a/sound/core/control.c b/sound/core/control.c
index 494389fb966c..50fa16022f1f 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/time.h>
+#include <linux/mm.h>
 #include <linux/sched/signal.h>
 #include <sound/core.h>
 #include <sound/minors.h>
@@ -1129,7 +1130,7 @@ static int replace_user_tlv(struct snd_kcontrol *kctl, unsigned int __user *buf,
 	if (size > 1024 * 128)	/* sane value */
 		return -EINVAL;
 
-	container = memdup_user(buf, size);
+	container = vmemdup_user(buf, size);
 	if (IS_ERR(container))
 		return PTR_ERR(container);
 
@@ -1137,7 +1138,7 @@ static int replace_user_tlv(struct snd_kcontrol *kctl, unsigned int __user *buf,
 	if (!change)
 		change = memcmp(ue->tlv_data, container, size) != 0;
 	if (!change) {
-		kfree(container);
+		kvfree(container);
 		return 0;
 	}
 
@@ -1148,7 +1149,7 @@ static int replace_user_tlv(struct snd_kcontrol *kctl, unsigned int __user *buf,
 		mask = SNDRV_CTL_EVENT_MASK_INFO;
 	}
 
-	kfree(ue->tlv_data);
+	kvfree(ue->tlv_data);
 	ue->tlv_data = container;
 	ue->tlv_data_size = size;
 
@@ -1197,7 +1198,7 @@ static int snd_ctl_elem_init_enum_names(struct user_element *ue)
 	if (ue->info.value.enumerated.names_length > 64 * 1024)
 		return -EINVAL;
 
-	names = memdup_user((const void __user *)user_ptrval,
+	names = vmemdup_user((const void __user *)user_ptrval,
 		ue->info.value.enumerated.names_length);
 	if (IS_ERR(names))
 		return PTR_ERR(names);
@@ -1208,7 +1209,7 @@ static int snd_ctl_elem_init_enum_names(struct user_element *ue)
 	for (i = 0; i < ue->info.value.enumerated.items; ++i) {
 		name_len = strnlen(p, buf_len);
 		if (name_len == 0 || name_len >= 64 || name_len == buf_len) {
-			kfree(names);
+			kvfree(names);
 			return -EINVAL;
 		}
 		p += name_len + 1;
@@ -1225,8 +1226,8 @@ static void snd_ctl_elem_user_free(struct snd_kcontrol *kcontrol)
 {
 	struct user_element *ue = kcontrol->private_data;
 
-	kfree(ue->tlv_data);
-	kfree(ue->priv_data);
+	kvfree(ue->tlv_data);
+	kvfree(ue->priv_data);
 	kfree(ue);
 }
 
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index cbda5c8b675f..26e71cf05f1e 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -233,8 +233,6 @@ static int snd_hwdep_dsp_load(struct snd_hwdep *hw,
 	/* check whether the dsp was already loaded */
 	if (hw->dsp_loaded & (1 << info.index))
 		return -EBUSY;
-	if (!access_ok(VERIFY_READ, info.image, info.length))
-		return -EFAULT;
 	err = hw->ops.dsp_load(hw, &info);
 	if (err < 0)
 		return err;
diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index 509680d9b698..e2be10d17118 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -378,7 +378,7 @@ out:
 static int usb_stream_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
 				  unsigned cmd, unsigned long arg)
 {
-	struct usb_stream_config *cfg;
+	struct usb_stream_config cfg;
 	struct us122l *us122l = hw->private_data;
 	struct usb_stream *s;
 	unsigned min_period_frames;
@@ -388,24 +388,21 @@ static int usb_stream_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
 	if (cmd != SNDRV_USB_STREAM_IOCTL_SET_PARAMS)
 		return -ENOTTY;
 
-	cfg = memdup_user((void *)arg, sizeof(*cfg));
-	if (IS_ERR(cfg))
-		return PTR_ERR(cfg);
+	if (copy_from_user(&cfg, (void __user *)arg, sizeof(cfg)))
+		return -EFAULT;
+
+	if (cfg.version != USB_STREAM_INTERFACE_VERSION)
+		return -ENXIO;
 
-	if (cfg->version != USB_STREAM_INTERFACE_VERSION) {
-		err = -ENXIO;
-		goto free;
-	}
 	high_speed = us122l->dev->speed == USB_SPEED_HIGH;
-	if ((cfg->sample_rate != 44100 && cfg->sample_rate != 48000  &&
+	if ((cfg.sample_rate != 44100 && cfg.sample_rate != 48000  &&
 	     (!high_speed ||
-	      (cfg->sample_rate != 88200 && cfg->sample_rate != 96000))) ||
-	    cfg->frame_size != 6 ||
-	    cfg->period_frames > 0x3000) {
-		err = -EINVAL;
-		goto free;
-	}
-	switch (cfg->sample_rate) {
+	      (cfg.sample_rate != 88200 && cfg.sample_rate != 96000))) ||
+	    cfg.frame_size != 6 ||
+	    cfg.period_frames > 0x3000)
+		return -EINVAL;
+
+	switch (cfg.sample_rate) {
 	case 44100:
 		min_period_frames = 48;
 		break;
@@ -418,10 +415,8 @@ static int usb_stream_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
 	}
 	if (!high_speed)
 		min_period_frames <<= 1;
-	if (cfg->period_frames < min_period_frames) {
-		err = -EINVAL;
-		goto free;
-	}
+	if (cfg.period_frames < min_period_frames)
+		return -EINVAL;
 
 	snd_power_wait(hw->card, SNDRV_CTL_POWER_D0);
 
@@ -430,24 +425,22 @@ static int usb_stream_hwdep_ioctl(struct snd_hwdep *hw, struct file *file,
 	if (!us122l->master)
 		us122l->master = file;
 	else if (us122l->master != file) {
-		if (!s || memcmp(cfg, &s->cfg, sizeof(*cfg))) {
+		if (!s || memcmp(&cfg, &s->cfg, sizeof(cfg))) {
 			err = -EIO;
 			goto unlock;
 		}
 		us122l->slave = file;
 	}
-	if (!s || memcmp(cfg, &s->cfg, sizeof(*cfg)) ||
+	if (!s || memcmp(&cfg, &s->cfg, sizeof(cfg)) ||
 	    s->state == usb_stream_xrun) {
 		us122l_stop(us122l);
-		if (!us122l_start(us122l, cfg->sample_rate, cfg->period_frames))
+		if (!us122l_start(us122l, cfg.sample_rate, cfg.period_frames))
 			err = -EIO;
 		else
 			err = 1;
 	}
 unlock:
 	mutex_unlock(&us122l->mutex);
-free:
-	kfree(cfg);
 	wake_up_all(&us122l->sk.sleep);
 	return err;
 }
diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c
index 8b0a1eae573c..07d15bae75bc 100644
--- a/sound/usb/usx2y/usX2Yhwdep.c
+++ b/sound/usb/usx2y/usX2Yhwdep.c
@@ -198,24 +198,22 @@ static int snd_usX2Y_hwdep_dsp_load(struct snd_hwdep *hw,
 				    struct snd_hwdep_dsp_image *dsp)
 {
 	struct usX2Ydev *priv = hw->private_data;
-	int	lret, err = -EINVAL;
-	snd_printdd( "dsp_load %s\n", dsp->name);
+	struct usb_device* dev = priv->dev;
+	int lret, err;
+	char *buf;
 
-	if (access_ok(VERIFY_READ, dsp->image, dsp->length)) {
-		struct usb_device* dev = priv->dev;
-		char *buf;
+	snd_printdd( "dsp_load %s\n", dsp->name);
 
-		buf = memdup_user(dsp->image, dsp->length);
-		if (IS_ERR(buf))
-			return PTR_ERR(buf);
+	buf = memdup_user(dsp->image, dsp->length);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
-		err = usb_set_interface(dev, 0, 1);
-		if (err)
-			snd_printk(KERN_ERR "usb_set_interface error \n");
-		else
-			err = usb_bulk_msg(dev, usb_sndbulkpipe(dev, 2), buf, dsp->length, &lret, 6000);
-		kfree(buf);
-	}
+	err = usb_set_interface(dev, 0, 1);
+	if (err)
+		snd_printk(KERN_ERR "usb_set_interface error \n");
+	else
+		err = usb_bulk_msg(dev, usb_sndbulkpipe(dev, 2), buf, dsp->length, &lret, 6000);
+	kfree(buf);
 	if (err)
 		return err;
 	if (dsp->index == 1) {