Merge branch 'akpm' (fixes from Andrew Morton)

Merge four more fixes from Andrew Morton.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  lib/scatterlist.c: don't flush_kernel_dcache_page on slab page
  mm: memcg: fix test for child groups
  mm: memcg: lockdep annotation for memcg OOM lock
  mm: memcg: use proper memcg in limit bypass
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index db59bb9..10d1de5 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -107,8 +107,6 @@
 static void intel_crt_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_config *pipe_config)
 {
-	struct drm_device *dev = encoder->base.dev;
-
 	pipe_config->adjusted_mode.flags |= intel_crt_get_flags(encoder);
 }
 
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index fe1de85..57fcc4b 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -291,6 +291,7 @@
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
 	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
+	       HDMI_ACR_SOURCE | /* select SW CTS value */
 	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 7139906..b419055 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2635,7 +2635,7 @@
 	pi->caps_sclk_ds = true;
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
-	pi->bapm_enable = true;
+	pi->bapm_enable = false;
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a400ac1..24f4960 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1272,8 +1272,8 @@
 struct radeon_clock_and_voltage_limits {
 	u32 sclk;
 	u32 mclk;
-	u32 vddc;
-	u32 vddci;
+	u16 vddc;
+	u16 vddci;
 };
 
 struct radeon_clock_array {
diff --git a/drivers/input/input.c b/drivers/input/input.c
index c044699..e75d015 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1734,6 +1734,7 @@
  */
 struct input_dev *input_allocate_device(void)
 {
+	static atomic_t input_no = ATOMIC_INIT(0);
 	struct input_dev *dev;
 
 	dev = kzalloc(sizeof(struct input_dev), GFP_KERNEL);
@@ -1743,9 +1744,13 @@
 		device_initialize(&dev->dev);
 		mutex_init(&dev->mutex);
 		spin_lock_init(&dev->event_lock);
+		init_timer(&dev->timer);
 		INIT_LIST_HEAD(&dev->h_list);
 		INIT_LIST_HEAD(&dev->node);
 
+		dev_set_name(&dev->dev, "input%ld",
+			     (unsigned long) atomic_inc_return(&input_no) - 1);
+
 		__module_get(THIS_MODULE);
 	}
 
@@ -2019,7 +2024,6 @@
  */
 int input_register_device(struct input_dev *dev)
 {
-	static atomic_t input_no = ATOMIC_INIT(0);
 	struct input_devres *devres = NULL;
 	struct input_handler *handler;
 	unsigned int packet_size;
@@ -2059,7 +2063,6 @@
 	 * If delay and period are pre-set by the driver, then autorepeating
 	 * is handled by the driver itself and we don't do it in input.c.
 	 */
-	init_timer(&dev->timer);
 	if (!dev->rep[REP_DELAY] && !dev->rep[REP_PERIOD]) {
 		dev->timer.data = (long) dev;
 		dev->timer.function = input_repeat_key;
@@ -2073,9 +2076,6 @@
 	if (!dev->setkeycode)
 		dev->setkeycode = input_default_setkeycode;
 
-	dev_set_name(&dev->dev, "input%ld",
-		     (unsigned long) atomic_inc_return(&input_no) - 1);
-
 	error = device_add(&dev->dev);
 	if (error)
 		goto err_free_vals;
diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index 134c3b4..a2e758d 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -786,10 +786,17 @@
 	input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP);
 	input_set_capability(input_dev, EV_MSC, MSC_SCAN);
 
-	if (pdata)
+	if (pdata) {
 		error = pxa27x_keypad_build_keycode(keypad);
-	else
+	} else {
 		error = pxa27x_keypad_build_keycode_from_dt(keypad);
+		/*
+		 * Data that we get from DT resides in dynamically
+		 * allocated memory so we need to update our pdata
+		 * pointer.
+		 */
+		pdata = keypad->pdata;
+	}
 	if (error) {
 		dev_err(&pdev->dev, "failed to build keycode\n");
 		goto failed_put_clk;
diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c
index 082684e..9365535 100644
--- a/drivers/input/misc/cm109.c
+++ b/drivers/input/misc/cm109.c
@@ -351,7 +351,9 @@
 	if (status) {
 		if (status == -ESHUTDOWN)
 			return;
-		dev_err(&dev->intf->dev, "%s: urb status %d\n", __func__, status);
+		dev_err_ratelimited(&dev->intf->dev, "%s: urb status %d\n",
+				    __func__, status);
+		goto out;
 	}
 
 	/* Special keys */
@@ -418,8 +420,12 @@
 	     dev->ctl_data->byte[2],
 	     dev->ctl_data->byte[3]);
 
-	if (status)
-		dev_err(&dev->intf->dev, "%s: urb status %d\n", __func__, status);
+	if (status) {
+		if (status == -ESHUTDOWN)
+			return;
+		dev_err_ratelimited(&dev->intf->dev, "%s: urb status %d\n",
+				    __func__, status);
+	}
 
 	spin_lock(&dev->ctl_submit_lock);
 
@@ -427,7 +433,7 @@
 
 	if (likely(!dev->shutdown)) {
 
-		if (dev->buzzer_pending) {
+		if (dev->buzzer_pending || status) {
 			dev->buzzer_pending = 0;
 			dev->ctl_urb_pending = 1;
 			cm109_submit_buzz_toggle(dev);
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 7c5d72a..8365847 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -103,6 +103,7 @@
 	/* Dell Latitude E5500, E6400, E6500, Precision M4400 */
 	{ { 0x62, 0x02, 0x14 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf,
 		ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED },
+	{ { 0x73, 0x00, 0x14 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_DUALPOINT },		/* Dell XT2 */
 	{ { 0x73, 0x02, 0x50 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_FOUR_BUTTONS },		/* Dell Vostro 1400 */
 	{ { 0x52, 0x01, 0x14 }, 0x00, ALPS_PROTO_V2, 0xff, 0xff,
 		ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED },				/* Toshiba Tecra A11-11L */
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 78e4de4..52c9ebf 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -223,21 +223,26 @@
 {
 	unsigned long flags;
 	unsigned char data, str;
-	int i = 0;
+	int count = 0;
+	int retval = 0;
 
 	spin_lock_irqsave(&i8042_lock, flags);
 
-	while (((str = i8042_read_status()) & I8042_STR_OBF) && (i < I8042_BUFFER_SIZE)) {
-		udelay(50);
-		data = i8042_read_data();
-		i++;
-		dbg("%02x <- i8042 (flush, %s)\n",
-		    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
+	while ((str = i8042_read_status()) & I8042_STR_OBF) {
+		if (count++ < I8042_BUFFER_SIZE) {
+			udelay(50);
+			data = i8042_read_data();
+			dbg("%02x <- i8042 (flush, %s)\n",
+			    data, str & I8042_STR_AUXDATA ? "aux" : "kbd");
+		} else {
+			retval = -EIO;
+			break;
+		}
 	}
 
 	spin_unlock_irqrestore(&i8042_lock, flags);
 
-	return i;
+	return retval;
 }
 
 /*
@@ -849,7 +854,7 @@
 
 static int i8042_controller_check(void)
 {
-	if (i8042_flush() == I8042_BUFFER_SIZE) {
+	if (i8042_flush()) {
 		pr_err("No controller found\n");
 		return -ENODEV;
 	}
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index 79b69ea..e53416a 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -1031,6 +1031,7 @@
 }
 
 static enum power_supply_property wacom_battery_props[] = {
+	POWER_SUPPLY_PROP_SCOPE,
 	POWER_SUPPLY_PROP_CAPACITY
 };
 
@@ -1042,6 +1043,9 @@
 	int ret = 0;
 
 	switch (psp) {
+		case POWER_SUPPLY_PROP_SCOPE:
+			val->intval = POWER_SUPPLY_SCOPE_DEVICE;
+			break;
 		case POWER_SUPPLY_PROP_CAPACITY:
 			val->intval =
 				wacom->wacom_wac.battery_capacity * 100 / 31;
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index b2aa503..c59b797 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -2054,6 +2054,12 @@
 static const struct wacom_features wacom_features_0x10D =
 	{ "Wacom ISDv4 10D",      WACOM_PKGLEN_MTTPC,     26202, 16325,  255,
 	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x10E =
+	{ "Wacom ISDv4 10E",      WACOM_PKGLEN_MTTPC,     27760, 15694,  255,
+	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x10F =
+	{ "Wacom ISDv4 10F",      WACOM_PKGLEN_MTTPC,     27760, 15694,  255,
+	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x4001 =
 	{ "Wacom ISDv4 4001",      WACOM_PKGLEN_MTTPC,     26202, 16325,  255,
 	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
@@ -2248,6 +2254,8 @@
 	{ USB_DEVICE_WACOM(0x100) },
 	{ USB_DEVICE_WACOM(0x101) },
 	{ USB_DEVICE_WACOM(0x10D) },
+	{ USB_DEVICE_WACOM(0x10E) },
+	{ USB_DEVICE_WACOM(0x10F) },
 	{ USB_DEVICE_WACOM(0x300) },
 	{ USB_DEVICE_WACOM(0x301) },
 	{ USB_DEVICE_WACOM(0x304) },
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index be12fbf..1ea7523 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -552,9 +552,8 @@
 	struct acpiphp_func *func;
 	int max, pass;
 	LIST_HEAD(add_list);
-	int nr_found;
 
-	nr_found = acpiphp_rescan_slot(slot);
+	acpiphp_rescan_slot(slot);
 	max = acpiphp_max_busnr(bus);
 	for (pass = 0; pass < 2; pass++) {
 		list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -574,9 +573,6 @@
 		}
 	}
 	__pci_bus_assign_resources(bus, &add_list, NULL);
-	/* Nothing more to do here if there are no new devices on this bus. */
-	if (!nr_found && (slot->flags & SLOT_ENABLED))
-		return;
 
 	acpiphp_sanitize_bus(bus);
 	acpiphp_set_hpp_values(bus);
diff --git a/fs/dcache.c b/fs/dcache.c
index 20532cb..ae6ebb8 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -542,7 +542,7 @@
  * If ref is non-zero, then decrement the refcount too.
  * Returns dentry requiring refcount drop, or NULL if we're done.
  */
-static inline struct dentry *
+static struct dentry *
 dentry_kill(struct dentry *dentry, int unlock_on_failure)
 	__releases(dentry->d_lock)
 {
@@ -630,7 +630,8 @@
 			goto kill_it;
 	}
 
-	dentry->d_flags |= DCACHE_REFERENCED;
+	if (!(dentry->d_flags & DCACHE_REFERENCED))
+		dentry->d_flags |= DCACHE_REFERENCED;
 	dentry_lru_add(dentry);
 
 	dentry->d_lockref.count--;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 473e09d..810c28f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -34,7 +34,6 @@
 #include <linux/mutex.h>
 #include <linux/anon_inodes.h>
 #include <linux/device.h>
-#include <linux/freezer.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/mman.h>
@@ -1605,8 +1604,7 @@
 			}
 
 			spin_unlock_irqrestore(&ep->lock, flags);
-			if (!freezable_schedule_hrtimeout_range(to, slack,
-								HRTIMER_MODE_ABS))
+			if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
 				timed_out = 1;
 
 			spin_lock_irqsave(&ep->lock, flags);
diff --git a/fs/select.c b/fs/select.c
index 35d4adc7..dfd5cb1 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -238,8 +238,7 @@
 
 	set_current_state(state);
 	if (!pwq->triggered)
-		rc = freezable_schedule_hrtimeout_range(expires, slack,
-							HRTIMER_MODE_ABS);
+		rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
 	__set_current_state(TASK_RUNNING);
 
 	/*
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 610e3df..cca80d9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1278,64 +1278,90 @@
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	int page_nid = -1, this_nid = numa_node_id();
 	int target_nid;
-	int current_nid = -1;
-	bool migrated;
+	bool page_locked;
+	bool migrated = false;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
-	get_page(page);
-	current_nid = page_to_nid(page);
+	page_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == this_nid)
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
+	/*
+	 * Acquire the page lock to serialise THP migrations but avoid dropping
+	 * page_table_lock if at all possible
+	 */
+	page_locked = trylock_page(page);
 	target_nid = mpol_misplaced(page, vma, haddr);
 	if (target_nid == -1) {
-		put_page(page);
-		goto clear_pmdnuma;
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked)
+			goto clear_pmdnuma;
+
+		/*
+		 * Otherwise wait for potential migrations and retry. We do
+		 * relock and check_same as the page may no longer be mapped.
+		 * As the fault is being retried, do not account for it.
+		 */
+		spin_unlock(&mm->page_table_lock);
+		wait_on_page_locked(page);
+		page_nid = -1;
+		goto out;
 	}
 
-	/* Acquire the page lock to serialise THP migrations */
+	/* Page is misplaced, serialise migrations and parallel THP splits */
+	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	if (!page_locked)
+		lock_page(page);
+	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PTE did not while locked */
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp))) {
 		unlock_page(page);
 		put_page(page);
+		page_nid = -1;
 		goto out_unlock;
 	}
-	spin_unlock(&mm->page_table_lock);
 
-	/* Migrate the THP to the requested node */
+	/*
+	 * Migrate the THP to the requested node, returns with page unlocked
+	 * and pmd_numa cleared.
+	 */
+	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
 				pmdp, pmd, addr, page, target_nid);
-	if (!migrated)
-		goto check_same;
+	if (migrated)
+		page_nid = target_nid;
 
-	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
-	return 0;
-
-check_same:
-	spin_lock(&mm->page_table_lock);
-	if (unlikely(!pmd_same(pmd, *pmdp)))
-		goto out_unlock;
+	goto out;
 clear_pmdnuma:
+	BUG_ON(!PageLocked(page));
 	pmd = pmd_mknonnuma(pmd);
 	set_pmd_at(mm, haddr, pmdp, pmd);
 	VM_BUG_ON(pmd_numa(*pmdp));
 	update_mmu_cache_pmd(vma, addr, pmdp);
+	unlock_page(page);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
-	if (current_nid != -1)
-		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+
+out:
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
+	if (page_nid != -1)
+		task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 1311f26..d176154 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3521,12 +3521,12 @@
 }
 
 int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
-				unsigned long addr, int current_nid)
+				unsigned long addr, int page_nid)
 {
 	get_page(page);
 
 	count_vm_numa_event(NUMA_HINT_FAULTS);
-	if (current_nid == numa_node_id())
+	if (page_nid == numa_node_id())
 		count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
 
 	return mpol_misplaced(page, vma, addr);
@@ -3537,7 +3537,7 @@
 {
 	struct page *page = NULL;
 	spinlock_t *ptl;
-	int current_nid = -1;
+	int page_nid = -1;
 	int target_nid;
 	bool migrated = false;
 
@@ -3567,15 +3567,10 @@
 		return 0;
 	}
 
-	current_nid = page_to_nid(page);
-	target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+	page_nid = page_to_nid(page);
+	target_nid = numa_migrate_prep(page, vma, addr, page_nid);
 	pte_unmap_unlock(ptep, ptl);
 	if (target_nid == -1) {
-		/*
-		 * Account for the fault against the current node if it not
-		 * being replaced regardless of where the page is located.
-		 */
-		current_nid = numa_node_id();
 		put_page(page);
 		goto out;
 	}
@@ -3583,11 +3578,11 @@
 	/* Migrate to the requested node */
 	migrated = migrate_misplaced_page(page, target_nid);
 	if (migrated)
-		current_nid = target_nid;
+		page_nid = target_nid;
 
 out:
-	if (current_nid != -1)
-		task_numa_fault(current_nid, 1, migrated);
+	if (page_nid != -1)
+		task_numa_fault(page_nid, 1, migrated);
 	return 0;
 }
 
@@ -3602,7 +3597,6 @@
 	unsigned long offset;
 	spinlock_t *ptl;
 	bool numa = false;
-	int local_nid = numa_node_id();
 
 	spin_lock(&mm->page_table_lock);
 	pmd = *pmdp;
@@ -3625,9 +3619,10 @@
 	for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
 		pte_t pteval = *pte;
 		struct page *page;
-		int curr_nid = local_nid;
+		int page_nid = -1;
 		int target_nid;
-		bool migrated;
+		bool migrated = false;
+
 		if (!pte_present(pteval))
 			continue;
 		if (!pte_numa(pteval))
@@ -3649,25 +3644,19 @@
 		if (unlikely(page_mapcount(page) != 1))
 			continue;
 
-		/*
-		 * Note that the NUMA fault is later accounted to either
-		 * the node that is currently running or where the page is
-		 * migrated to.
-		 */
-		curr_nid = local_nid;
-		target_nid = numa_migrate_prep(page, vma, addr,
-					       page_to_nid(page));
-		if (target_nid == -1) {
+		page_nid = page_to_nid(page);
+		target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+		pte_unmap_unlock(pte, ptl);
+		if (target_nid != -1) {
+			migrated = migrate_misplaced_page(page, target_nid);
+			if (migrated)
+				page_nid = target_nid;
+		} else {
 			put_page(page);
-			continue;
 		}
 
-		/* Migrate to the requested node */
-		pte_unmap_unlock(pte, ptl);
-		migrated = migrate_misplaced_page(page, target_nid);
-		if (migrated)
-			curr_nid = target_nid;
-		task_numa_fault(curr_nid, 1, migrated);
+		if (page_nid != -1)
+			task_numa_fault(page_nid, 1, migrated);
 
 		pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 	}
diff --git a/mm/migrate.c b/mm/migrate.c
index 7a7325e..c046927 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1715,12 +1715,12 @@
 		unlock_page(new_page);
 		put_page(new_page);		/* Free it */
 
-		unlock_page(page);
+		/* Retake the callers reference and putback on LRU */
+		get_page(page);
 		putback_lru_page(page);
-
-		count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-		isolated = 0;
-		goto out;
+		mod_zone_page_state(page_zone(page),
+			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
+		goto out_fail;
 	}
 
 	/*
@@ -1737,9 +1737,9 @@
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
 
-	page_add_new_anon_rmap(new_page, vma, haddr);
-
+	pmdp_clear_flush(vma, haddr, pmd);
 	set_pmd_at(mm, haddr, pmd, entry);
+	page_add_new_anon_rmap(new_page, vma, haddr);
 	update_mmu_cache_pmd(vma, address, &entry);
 	page_remove_rmap(page);
 	/*
@@ -1758,7 +1758,6 @@
 	count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
 	count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
 
-out:
 	mod_zone_page_state(page_zone(page),
 			NR_ISOLATED_ANON + page_lru,
 			-HPAGE_PMD_NR);
@@ -1767,6 +1766,10 @@
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
+	entry = pmd_mknonnuma(entry);
+	set_pmd_at(mm, haddr, pmd, entry);
+	update_mmu_cache_pmd(vma, address, &entry);
+
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a3af058..412ba2b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -148,7 +148,7 @@
 				split_huge_page_pmd(vma, addr, pmd);
 			else if (change_huge_pmd(vma, pmd, addr, newprot,
 						 prot_numa)) {
-				pages += HPAGE_PMD_NR;
+				pages++;
 				continue;
 			}
 			/* fall through */