Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "20 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  rapidio/rio_cm: avoid GFP_KERNEL in atomic context
  Revert "ocfs2: bump up o2cb network protocol version"
  ocfs2: fix start offset to ocfs2_zero_range_for_truncate()
  cgroup: duplicate cgroup reference when cloning sockets
  mm: memcontrol: make per-cpu charge cache IRQ-safe for socket accounting
  ocfs2: fix double unlock in case retry after free truncate log
  fanotify: fix list corruption in fanotify_get_response()
  fsnotify: add a way to stop queueing events on group shutdown
  ocfs2: fix trans extend while free cached blocks
  ocfs2: fix trans extend while flush truncate log
  ipc/shm: fix crash if CONFIG_SHMEM is not set
  mm: fix the page_swap_info() BUG_ON check
  autofs: use dentry flags to block walks during expire
  MAINTAINERS: update email for VLYNQ bus entry
  mm: avoid endless recursion in dump_page()
  mm, thp: fix leaking mapped pte in __collapse_huge_page_swapin()
  khugepaged: fix use-after-free in collapse_huge_page()
  MAINTAINERS: Maik has moved
  ocfs2/dlm: fix race between convert and migration
  mem-hotplug: don't clear the only node in new_node_page()

MAINTAINERS

@@ -6103,7 +6103,7 @@ S:	Supported
 F:	drivers/cpufreq/intel_pstate.c
 
 INTEL FRAMEBUFFER DRIVER (excluding 810 and 815)
-M:	Maik Broemme <mbroemme@plusserver.de>
+M:	Maik Broemme <mbroemme@libmpq.org>
 L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/fb/intelfb.txt
@@ -12569,7 +12569,7 @@ F:	include/linux/if_*vlan.h
 F:	net/8021q/
 
 VLYNQ BUS
-M:	Florian Fainelli <florian@openwrt.org>
+M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
 S:	Maintained
 F:	drivers/vlynq/vlynq.c

drivers/rapidio/rio_cm.c

@@ -2247,17 +2247,30 @@ static int rio_cm_shutdown(struct notifier_block *nb, unsigned long code,
 {
 	struct rio_channel *ch;
 	unsigned int i;
+	LIST_HEAD(list);
 
 	riocm_debug(EXIT, ".");
 
+	/*
+	 * If there are any channels left in connected state send
+	 * close notification to the connection partner.
+	 * First build a list of channels that require a closing
+	 * notification because function riocm_send_close() should
+	 * be called outside of spinlock protected code.
+	 */
 	spin_lock_bh(&idr_lock);
 	idr_for_each_entry(&ch_idr, ch, i) {
+		if (ch->state == RIO_CM_CONNECTED) {
 			riocm_debug(EXIT, "close ch %d", ch->id);
-		if (ch->state == RIO_CM_CONNECTED)
-			riocm_send_close(ch);
+			idr_remove(&ch_idr, ch->id);
+			list_add(&ch->ch_node, &list);
+		}
 	}
 	spin_unlock_bh(&idr_lock);
 
+	list_for_each_entry(ch, &list, ch_node)
+		riocm_send_close(ch);
+
 	return NOTIFY_DONE;
 }
 

fs/autofs4/expire.c

@@ -417,6 +417,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 	return NULL;
 }
+
 /*
  * Find an eligible tree to time-out
  * A tree is eligible if :-
@@ -432,6 +433,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	struct dentry *root = sb->s_root;
 	struct dentry *dentry;
 	struct dentry *expired;
+	struct dentry *found;
 	struct autofs_info *ino;
 
 	if (!root)
@@ -442,31 +444,46 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
 	dentry = NULL;
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
+		int flags = how;
+
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
-		if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
-			expired = NULL;
-		else
-			expired = should_expire(dentry, mnt, timeout, how);
-		if (!expired) {
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
 			spin_unlock(&sbi->fs_lock);
 			continue;
 		}
+		spin_unlock(&sbi->fs_lock);
+
+		expired = should_expire(dentry, mnt, timeout, flags);
+		if (!expired)
+			continue;
+
+		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(expired);
 		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
-		spin_lock(&sbi->fs_lock);
-		if (should_expire(expired, mnt, timeout, how)) {
+
+		/* Make sure a reference is not taken on found if
+		 * things have changed.
+		 */
+		flags &= ~AUTOFS_EXP_LEAVES;
+		found = should_expire(expired, mnt, timeout, how);
+		if (!found || found != expired)
+			/* Something has changed, continue */
+			goto next;
+
 		if (expired != dentry)
 			dput(dentry);
-			goto found;
-		}
 
+		spin_lock(&sbi->fs_lock);
+		goto found;
+next:
+		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
+		spin_unlock(&sbi->fs_lock);
 		if (expired != dentry)
 			dput(expired);
-		spin_unlock(&sbi->fs_lock);
 	}
 	return NULL;
 
@@ -483,6 +500,7 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
+	int state;
 
 	/* Block on any pending expire */
 	if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
@@ -490,8 +508,19 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	if (rcu_walk)
 		return -ECHILD;
 
+retry:
 	spin_lock(&sbi->fs_lock);
-	if (ino->flags & AUTOFS_INF_EXPIRING) {
+	state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+	if (state == AUTOFS_INF_WANT_EXPIRE) {
+		spin_unlock(&sbi->fs_lock);
+		/*
+		 * Possibly being selected for expire, wait until
+		 * it's selected or not.
+		 */
+		schedule_timeout_uninterruptible(HZ/10);
+		goto retry;
+	}
+	if (state & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
 		pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);

fs/notify/fanotify/fanotify.c

@@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	wait_event(group->fanotify_data.access_waitq, event->response ||
-				atomic_read(&group->fanotify_data.bypass_perm));
-
-	if (!event->response) {	/* bypass_perm set */
-		/*
-		 * Event was canceled because group is being destroyed. Remove
-		 * it from group's event list because we are responsible for
-		 * freeing the permission event.
-		 */
-		fsnotify_remove_event(group, &event->fae.fse);
-		return 0;
-	}
+	wait_event(group->fanotify_data.access_waitq, event->response);
 
 	/* userspace responded, convert to something usable */
 	switch (event->response) {

fs/notify/fanotify/fanotify_user.c

@@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
+	struct fsnotify_event *fsn_event;
 
 	/*
-	 * There may be still new events arriving in the notification queue
-	 * but since userspace cannot use fanotify fd anymore, no event can
-	 * enter or leave access_list by now.
+	 * Stop new events from arriving in the notification queue. since
+	 * userspace cannot use fanotify fd anymore, no event can enter or
+	 * leave access_list by now either.
 	 */
-	spin_lock(&group->fanotify_data.access_lock);
-
-	atomic_inc(&group->fanotify_data.bypass_perm);
+	fsnotify_group_stop_queueing(group);
 
+	/*
+	 * Process all permission events on access_list and notification queue
+	 * and simulate reply from userspace.
+	 */
+	spin_lock(&group->fanotify_data.access_lock);
 	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
 				 fae.fse.list) {
 		pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	spin_unlock(&group->fanotify_data.access_lock);
 
 	/*
-	 * Since bypass_perm is set, newly queued events will not wait for
-	 * access response. Wake up the already sleeping ones now.
-	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
-	 * processes sleeping in fanotify_handle_event() waiting for access
-	 * response and thus also for all permission events to be freed.
+	 * Destroy all non-permission events. For permission events just
+	 * dequeue them and set the response. They will be freed once the
+	 * response is consumed and fanotify_get_response() returns.
 	 */
+	mutex_lock(&group->notification_mutex);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		fsn_event = fsnotify_remove_first_event(group);
+		if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+			fsnotify_destroy_event(group, fsn_event);
+		else
+			FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+	}
+	mutex_unlock(&group->notification_mutex);
+
+	/* Response for all permission events it set, wakeup waiters */
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 
@@ -755,7 +768,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
-	atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
 	switch (flags & FAN_ALL_CLASS_BITS) {
 	case FAN_CLASS_NOTIF:

fs/notify/group.c

@@ -39,6 +39,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 	kfree(group);
 }
 
+/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+	mutex_lock(&group->notification_mutex);
+	group->shutdown = true;
+	mutex_unlock(&group->notification_mutex);
+}
+
 /*
  * Trying to get rid of a group. Remove all marks, flush all events and release
  * the group reference.
@@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
  */
 void fsnotify_destroy_group(struct fsnotify_group *group)
 {
+	/*
+	 * Stop queueing new events. The code below is careful enough to not
+	 * require this but fanotify needs to stop queuing events even before
+	 * fsnotify_destroy_group() is called and this makes the other callers
+	 * of fsnotify_destroy_group() to see the same behavior.
+	 */
+	fsnotify_group_stop_queueing(group);
+
 	/* clear all inode marks for this group, attach them to destroy_list */
 	fsnotify_detach_group_marks(group);
 

fs/notify/notification.c

@@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
  * added to the queue, 1 if the event was merged with some other queued event,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
  */
 int fsnotify_add_event(struct fsnotify_group *group,
 		       struct fsnotify_event *event,
@@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group,
 
 	mutex_lock(&group->notification_mutex);
 
+	if (group->shutdown) {
+		mutex_unlock(&group->notification_mutex);
+		return 2;
+	}
+
 	if (group->q_len >= group->max_events) {
 		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
@@ -125,21 +131,6 @@ int fsnotify_add_event(struct fsnotify_group *group,
 	return ret;
 }
 
-/*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
-			   struct fsnotify_event *event)
-{
-	mutex_lock(&group->notification_mutex);
-	if (!list_empty(&event->list)) {
-		list_del_init(&event->list);
-		group->q_len--;
-	}
-	mutex_unlock(&group->notification_mutex);
-}
-
 /*
  * Remove and return the first event from the notification list.  It is the
  * responsibility of the caller to destroy the obtained event

fs/ocfs2/alloc.c

@@ -5922,7 +5922,6 @@ int ocfs2_truncate_log_append(struct ocfs2_super *osb,
 }
 
 static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
-					 handle_t *handle,
 					 struct inode *data_alloc_inode,
 					 struct buffer_head *data_alloc_bh)
 {
@@ -5935,11 +5934,19 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 	struct ocfs2_truncate_log *tl;
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct buffer_head *tl_bh = osb->osb_tl_bh;
+	handle_t *handle;
 
 	di = (struct ocfs2_dinode *) tl_bh->b_data;
 	tl = &di->id2.i_dealloc;
 	i = le16_to_cpu(tl->tl_used) - 1;
 	while (i >= 0) {
+		handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+		if (IS_ERR(handle)) {
+			status = PTR_ERR(handle);
+			mlog_errno(status);
+			goto bail;
+		}
+
 		/* Caller has given us at least enough credits to
 		 * update the truncate log dinode */
 		status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
@@ -5974,12 +5981,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 			}
 		}
 
-		status = ocfs2_extend_trans(handle,
-				OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
+		ocfs2_commit_trans(osb, handle);
 		i--;
 	}
 
@@ -5994,7 +5996,6 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 {
 	int status;
 	unsigned int num_to_flush;
-	handle_t *handle;
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct inode *data_alloc_inode = NULL;
 	struct buffer_head *tl_bh = osb->osb_tl_bh;
@@ -6038,21 +6039,11 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out_mutex;
 	}
 
-	handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
-	if (IS_ERR(handle)) {
-		status = PTR_ERR(handle);
-		mlog_errno(status);
-		goto out_unlock;
-	}
-
-	status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode,
+	status = ocfs2_replay_truncate_records(osb, data_alloc_inode,
 					       data_alloc_bh);
 	if (status < 0)
 		mlog_errno(status);
 
-	ocfs2_commit_trans(osb, handle);
-
-out_unlock:
 	brelse(data_alloc_bh);
 	ocfs2_inode_unlock(data_alloc_inode, 1);
 
@@ -6413,6 +6404,12 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb,
 		goto out_mutex;
 	}
 
+	while (head) {
+		if (head->free_bg)
+			bg_blkno = head->free_bg;
+		else
+			bg_blkno = ocfs2_which_suballoc_group(head->free_blk,
+							      head->free_bit);
 		handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
@@ -6420,36 +6417,21 @@ static int ocfs2_free_cached_blocks(struct ocfs2_super *osb,
 			goto out_unlock;
 		}
 
-	while (head) {
-		if (head->free_bg)
-			bg_blkno = head->free_bg;
-		else
-			bg_blkno = ocfs2_which_suballoc_group(head->free_blk,
-							      head->free_bit);
 		trace_ocfs2_free_cached_blocks(
 		     (unsigned long long)head->free_blk, head->free_bit);
 
 		ret = ocfs2_free_suballoc_bits(handle, inode, di_bh,
 					       head->free_bit, bg_blkno, 1);
-		if (ret) {
+		if (ret)
 			mlog_errno(ret);
-			goto out_journal;
-		}
 
-		ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE);
-		if (ret) {
-			mlog_errno(ret);
-			goto out_journal;
-		}
+		ocfs2_commit_trans(osb, handle);
 
 		tmp = head;
 		head = head->free_next;
 		kfree(tmp);
 	}
 
-out_journal:
-	ocfs2_commit_trans(osb, handle);
-
 out_unlock:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);

fs/ocfs2/cluster/tcp_internal.h

@@ -44,9 +44,6 @@
  * version here in tcp_internal.h should not need to be bumped for
  * filesystem locking changes.
  *
- * New in version 12
- *	- Negotiate hb timeout when storage is down.
- *
  * New in version 11
  * 	- Negotiation of filesystem locking in the dlm join.
  *
@@ -78,7 +75,7 @@
  * 	- full 64 bit i_size in the metadata lock lvbs
  * 	- introduction of "rw" lock and pushing meta/data locking down
  */
-#define O2NET_PROTOCOL_VERSION 12ULL
+#define O2NET_PROTOCOL_VERSION 11ULL
 struct o2net_handshake {
 	__be64	protocol_version;
 	__be64	connector_id;

fs/ocfs2/dlm/dlmconvert.c

@@ -268,7 +268,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 				  struct dlm_lock *lock, int flags, int type)
 {
 	enum dlm_status status;
-	u8 old_owner = res->owner;
 
 	mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
 	     lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -335,7 +334,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
-	lock->convert_pending = 0;
 	/* if it failed, move it back to granted queue.
 	 * if master returns DLM_NORMAL and then down before sending ast,
 	 * it may have already been moved to granted queue, reset to
@@ -344,12 +342,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
-	} else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
-			(old_owner != res->owner)) {
-		mlog(0, "res %.*s is in recovering or has been recovered.\n",
-				res->lockname.len, res->lockname.name);
+	} else if (!lock->convert_pending) {
+		mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+				"to granted list, retry convert.\n",
+				dlm->name, res->lockname.len, res->lockname.name);
 		status = DLM_RECOVERING;
 	}
+
+	lock->convert_pending = 0;
 bail:
 	spin_unlock(&res->spinlock);
 

fs/ocfs2/file.c

@@ -1506,7 +1506,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 				       u64 start, u64 len)
 {
 	int ret = 0;
-	u64 tmpend, end = start + len;
+	u64 tmpend = 0;
+	u64 end = start + len;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	unsigned int csize = osb->s_clustersize;
 	handle_t *handle;
@@ -1538,18 +1539,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 	}
 
 	/*
-	 * We want to get the byte offset of the end of the 1st cluster.
+	 * If start is on a cluster boundary and end is somewhere in another
+	 * cluster, we have not COWed the cluster starting at start, unless
+	 * end is also within the same cluster. So, in this case, we skip this
+	 * first call to ocfs2_zero_range_for_truncate() truncate and move on
+	 * to the next one.
+	 */
+	if ((start & (csize - 1)) != 0) {
+		/*
+		 * We want to get the byte offset of the end of the 1st
+		 * cluster.
 		 */
-	tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
+		tmpend = (u64)osb->s_clustersize +
+			(start & ~(osb->s_clustersize - 1));
 		if (tmpend > end)
 			tmpend = end;
 
-	trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
+		trace_ocfs2_zero_partial_clusters_range1(
+			(unsigned long long)start,
 			(unsigned long long)tmpend);
 
-	ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
+		ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+						    tmpend);
 		if (ret)
 			mlog_errno(ret);
+	}
 
 	if (tmpend < end) {
 		/*

fs/ocfs2/suballoc.c

@@ -1199,14 +1199,24 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 			inode_unlock((*ac)->ac_inode);
 
 			ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
-			if (ret == 1)
+			if (ret == 1) {
+				iput((*ac)->ac_inode);
+				(*ac)->ac_inode = NULL;
 				goto retry;
+			}
 
 			if (ret < 0)
 				mlog_errno(ret);
 
 			inode_lock((*ac)->ac_inode);
-			ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+			ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				inode_unlock((*ac)->ac_inode);
+				iput((*ac)->ac_inode);
+				(*ac)->ac_inode = NULL;
+				goto bail;
+			}
 		}
 		if (status < 0) {
 			if (status != -ENOSPC)

fs/ramfs/file-mmu.c

@@ -27,9 +27,17 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/ramfs.h>
+#include <linux/sched.h>
 
 #include "internal.h"
 
+static unsigned long ramfs_mmu_get_unmapped_area(struct file *file,
+		unsigned long addr, unsigned long len, unsigned long pgoff,
+		unsigned long flags)
+{
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
 const struct file_operations ramfs_file_operations = {
 	.read_iter	= generic_file_read_iter,
 	.write_iter	= generic_file_write_iter,
@@ -38,6 +46,7 @@ const struct file_operations ramfs_file_operations = {
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.llseek		= generic_file_llseek,
+	.get_unmapped_area	= ramfs_mmu_get_unmapped_area,
 };
 
 const struct inode_operations ramfs_file_inode_operations = {

include/linux/fsnotify_backend.h

@@ -148,6 +148,7 @@ struct fsnotify_group {
 	#define FS_PRIO_1	1 /* fanotify content based access control */
 	#define FS_PRIO_2	2 /* fanotify pre-content access */
 	unsigned int priority;
+	bool shutdown;		/* group is being shut down, don't queue more events */
 
 	/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
 	struct mutex mark_mutex;	/* protect marks_list */
@@ -179,7 +180,6 @@ struct fsnotify_group {
 			spinlock_t access_lock;
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
-			atomic_t bypass_perm;
 #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
 			int f_flags;
 			unsigned int max_marks;
@@ -292,6 +292,8 @@ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *op
 extern void fsnotify_get_group(struct fsnotify_group *group);
 /* drop reference on a group from fsnotify_alloc_group */
 extern void fsnotify_put_group(struct fsnotify_group *group);
+/* group destruction begins, stop queuing new events */
+extern void fsnotify_group_stop_queueing(struct fsnotify_group *group);
 /* destroy group */
 extern void fsnotify_destroy_group(struct fsnotify_group *group);
 /* fasync handler function */
@@ -304,8 +306,6 @@ extern int fsnotify_add_event(struct fsnotify_group *group,
 			      struct fsnotify_event *event,
 			      int (*merge)(struct list_head *,
 					   struct fsnotify_event *));
-/* Remove passed event from groups notification queue */
-extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
 /* true if the group notification queue is empty */
 extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 /* return, but do not dequeue the first event on the notification queue */

kernel/cgroup.c

@@ -6270,6 +6270,12 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	if (cgroup_sk_alloc_disabled)
 		return;
 
+	/* Socket clone path */
+	if (skcd->val) {
+		cgroup_get(sock_cgroup_ptr(skcd));
+		return;
+	}
+
 	rcu_read_lock();
 
 	while (true) {

mm/debug.c

@@ -42,9 +42,11 @@ const struct trace_print_flags vmaflag_names[] = {
 
 void __dump_page(struct page *page, const char *reason)
 {
+	int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+
 	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
-		  page, page_ref_count(page), page_mapcount(page),
-		  page->mapping, page->index);
+		  page, page_ref_count(page), mapcount,
+		  page->mapping, page_to_pgoff(page));
 	if (PageCompound(page))
 		pr_cont(" compound_mapcount: %d", compound_mapcount(page));
 	pr_cont("\n");

mm/khugepaged.c

@@ -838,7 +838,8 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
  * value (scan code).
  */
 
-static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address)
+static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
+		struct vm_area_struct **vmap)
 {
 	struct vm_area_struct *vma;
 	unsigned long hstart, hend;
@@ -846,7 +847,7 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address)
 	if (unlikely(khugepaged_test_exit(mm)))
 		return SCAN_ANY_PROCESS;
 
-	vma = find_vma(mm, address);
+	*vmap = vma = find_vma(mm, address);
 	if (!vma)
 		return SCAN_VMA_NULL;
 
@@ -881,6 +882,11 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		.pmd = pmd,
 	};
 
+	/* we only decide to swapin, if there is enough young ptes */
+	if (referenced < HPAGE_PMD_NR/2) {
+		trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
+		return false;
+	}
 	fe.pte = pte_offset_map(pmd, address);
 	for (; fe.address < address + HPAGE_PMD_NR*PAGE_SIZE;
 			fe.pte++, fe.address += PAGE_SIZE) {
@@ -888,17 +894,12 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		if (!is_swap_pte(pteval))
 			continue;
 		swapped_in++;
-		/* we only decide to swapin, if there is enough young ptes */
-		if (referenced < HPAGE_PMD_NR/2) {
-			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
-			return false;
-		}
 		ret = do_swap_page(&fe, pteval);
 
 		/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
 		if (ret & VM_FAULT_RETRY) {
 			down_read(&mm->mmap_sem);
-			if (hugepage_vma_revalidate(mm, address)) {
+			if (hugepage_vma_revalidate(mm, address, &fe.vma)) {
 				/* vma is no longer available, don't continue to swapin */
 				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
@@ -923,7 +924,6 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 static void collapse_huge_page(struct mm_struct *mm,
 				   unsigned long address,
 				   struct page **hpage,
-				   struct vm_area_struct *vma,
 				   int node, int referenced)
 {
 	pmd_t *pmd, _pmd;
@@ -933,6 +933,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	spinlock_t *pmd_ptl, *pte_ptl;
 	int isolated = 0, result = 0;
 	struct mem_cgroup *memcg;
+	struct vm_area_struct *vma;
 	unsigned long mmun_start;	/* For mmu_notifiers */
 	unsigned long mmun_end;		/* For mmu_notifiers */
 	gfp_t gfp;
@@ -961,7 +962,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	}
 
 	down_read(&mm->mmap_sem);
-	result = hugepage_vma_revalidate(mm, address);
+	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result) {
 		mem_cgroup_cancel_charge(new_page, memcg, true);
 		up_read(&mm->mmap_sem);
@@ -994,7 +995,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
-	result = hugepage_vma_revalidate(mm, address);
+	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
 	/* check if the pmd is still valid */
@@ -1202,7 +1203,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (ret) {
 		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
-		collapse_huge_page(mm, address, hpage, vma, node, referenced);
+		collapse_huge_page(mm, address, hpage, node, referenced);
 	}
 out:
 	trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,

mm/memcontrol.c

@@ -1740,17 +1740,22 @@ static DEFINE_MUTEX(percpu_charge_mutex);
 static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
+	unsigned long flags;
 	bool ret = false;
 
 	if (nr_pages > CHARGE_BATCH)
 		return ret;
 
-	stock = &get_cpu_var(memcg_stock);
+	local_irq_save(flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
 	if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
 		stock->nr_pages -= nr_pages;
 		ret = true;
 	}
-	put_cpu_var(memcg_stock);
+
+	local_irq_restore(flags);
+
 	return ret;
 }
 
@@ -1771,15 +1776,18 @@ static void drain_stock(struct memcg_stock_pcp *stock)
 	stock->cached = NULL;
 }
 
-/*
- * This must be called under preempt disabled or must be called by
- * a thread which is pinned to local cpu.
- */
 static void drain_local_stock(struct work_struct *dummy)
 {
-	struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock);
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	stock = this_cpu_ptr(&memcg_stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
+
+	local_irq_restore(flags);
 }
 
 /*
@@ -1788,14 +1796,19 @@ static void drain_local_stock(struct work_struct *dummy)
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
+	stock = this_cpu_ptr(&memcg_stock);
 	if (stock->cached != memcg) { /* reset if necessary */
 		drain_stock(stock);
 		stock->cached = memcg;
 	}
 	stock->nr_pages += nr_pages;
-	put_cpu_var(memcg_stock);
+
+	local_irq_restore(flags);
 }
 
 /*

mm/memory_hotplug.c

@@ -1567,7 +1567,9 @@ static struct page *new_node_page(struct page *page, unsigned long private,
 		return alloc_huge_page_node(page_hstate(compound_head(page)),
 					next_node_in(nid, nmask));
 
+	if (nid != next_node_in(nid, nmask))
 		node_clear(nid, nmask);
+
 	if (PageHighMem(page)
 	    || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
 		gfp_mask |= __GFP_HIGHMEM;

mm/page_io.c

@@ -264,6 +264,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	int ret;
 	struct swap_info_struct *sis = page_swap_info(page);
 
+	BUG_ON(!PageSwapCache(page));
 	if (sis->flags & SWP_FILE) {
 		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
@@ -337,6 +338,7 @@ int swap_readpage(struct page *page)
 	int ret = 0;
 	struct swap_info_struct *sis = page_swap_info(page);
 
+	BUG_ON(!PageSwapCache(page));
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageUptodate(page), page);
 	if (frontswap_load(page) == 0) {
@@ -386,6 +388,7 @@ int swap_set_page_dirty(struct page *page)
 
 	if (sis->flags & SWP_FILE) {
 		struct address_space *mapping = sis->swap_file->f_mapping;
+		BUG_ON(!PageSwapCache(page));
 		return mapping->a_ops->set_page_dirty(page);
 	} else {
 		return __set_page_dirty_no_writeback(page);

mm/swapfile.c

@@ -2724,7 +2724,6 @@ int swapcache_prepare(swp_entry_t entry)
 struct swap_info_struct *page_swap_info(struct page *page)
 {
 	swp_entry_t swap = { .val = page_private(page) };
-	BUG_ON(!PageSwapCache(page));
 	return swap_info[swp_type(swap)];
 }
 

net/core/sock.c

@@ -1362,7 +1362,6 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
 		if (!try_module_get(prot->owner))
 			goto out_free_sec;
 		sk_tx_queue_clear(sk);
-		cgroup_sk_alloc(&sk->sk_cgrp_data);
 	}
 
 	return sk;
@@ -1422,6 +1421,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		sock_net_set(sk, net);
 		atomic_set(&sk->sk_wmem_alloc, 1);
 
+		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
 	}
@@ -1566,6 +1566,9 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		newsk->sk_priority = 0;
 		newsk->sk_incoming_cpu = raw_smp_processor_id();
 		atomic64_set(&newsk->sk_cookie, 0);
+
+		cgroup_sk_alloc(&newsk->sk_cgrp_data);
+
 		/*
 		 * Before updating sk_refcnt, we must commit prior changes to memory
 		 * (Documentation/RCU/rculist_nulls.txt for details)