diff --git a/Documentation/devicetree/bindings/hwmon/jc42.txt b/Documentation/devicetree/bindings/hwmon/jc42.txt
index 07a250498fbb..f569db58f64a 100644
--- a/Documentation/devicetree/bindings/hwmon/jc42.txt
+++ b/Documentation/devicetree/bindings/hwmon/jc42.txt
@@ -34,6 +34,10 @@ Required properties:
 
 - reg: I2C address
 
+Optional properties:
+- smbus-timeout-disable: When set, the smbus timeout function will be disabled.
+			 This is not supported on all chips.
+
 Example:
 
 temp-sensor@1a {
diff --git a/Makefile b/Makefile
index 8e62f9e2a08c..70546af61a0a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 9
-SUBLEVEL = 66
+SUBLEVEL = 67
 EXTRAVERSION =
 NAME = Roaring Lionus
 
diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
index 08cce17a25a0..b4575bbaf085 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
+++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts
@@ -192,7 +192,7 @@
 	interrupts-extended = <&intc 83 &omap3_pmx_core 0x11a>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins &mmc1_cd>;
-	cd-gpios = <&gpio4 31 IRQ_TYPE_LEVEL_LOW>;		/* gpio127 */
+	cd-gpios = <&gpio4 31 GPIO_ACTIVE_LOW>;		/* gpio127 */
 	vmmc-supply = <&vmmc1>;
 	bus-width = <4>;
 	cap-power-off-card;
@@ -249,9 +249,9 @@
 			OMAP3_CORE1_IOPAD(0x2110, PIN_INPUT | MUX_MODE0)   /* cam_xclka.cam_xclka */
 			OMAP3_CORE1_IOPAD(0x2112, PIN_INPUT | MUX_MODE0)   /* cam_pclk.cam_pclk */
 
-			OMAP3_CORE1_IOPAD(0x2114, PIN_INPUT | MUX_MODE0)   /* cam_d0.cam_d0 */
-			OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0)   /* cam_d1.cam_d1 */
-			OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0)   /* cam_d2.cam_d2 */
+			OMAP3_CORE1_IOPAD(0x2116, PIN_INPUT | MUX_MODE0)   /* cam_d0.cam_d0 */
+			OMAP3_CORE1_IOPAD(0x2118, PIN_INPUT | MUX_MODE0)   /* cam_d1.cam_d1 */
+			OMAP3_CORE1_IOPAD(0x211a, PIN_INPUT | MUX_MODE0)   /* cam_d2.cam_d2 */
 			OMAP3_CORE1_IOPAD(0x211c, PIN_INPUT | MUX_MODE0)   /* cam_d3.cam_d3 */
 			OMAP3_CORE1_IOPAD(0x211e, PIN_INPUT | MUX_MODE0)   /* cam_d4.cam_d4 */
 			OMAP3_CORE1_IOPAD(0x2120, PIN_INPUT | MUX_MODE0)   /* cam_d5.cam_d5 */
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 770216baa737..da310bb779b9 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -162,7 +162,7 @@ static struct ti_st_plat_data wilink7_pdata = {
 	.nshutdown_gpio = 162,
 	.dev_name = "/dev/ttyO1",
 	.flow_cntrl = 1,
-	.baud_rate = 300000,
+	.baud_rate = 3000000,
 };
 
 static struct platform_device wl128x_device = {
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index be9df513141e..e7b0e7ff4c58 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -54,19 +54,15 @@ ENTRY(native_usergs_sysret64)
 ENDPROC(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
-.macro TRACE_IRQS_FLAGS flags:req
+.macro TRACE_IRQS_IRETQ
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt	$9, \flags		/* interrupts off? */
+	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON
 1:
 #endif
 .endm
 
-.macro TRACE_IRQS_IRETQ
-	TRACE_IRQS_FLAGS EFLAGS(%rsp)
-.endm
-
 /*
  * When dynamic function tracer is enabled it will add a breakpoint
  * to all locations that it is about to modify, sync CPUs, update
@@ -872,13 +868,11 @@ idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
 ENTRY(native_load_gs_index)
 	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
-	TRACE_IRQS_OFF
 	SWAPGS
 .Lgs_change:
 	movl	%edi, %gs
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	SWAPGS
-	TRACE_IRQS_FLAGS (%rsp)
 	popfq
 	ret
 END(native_load_gs_index)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3f05c044720b..b24b3c6d686e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -246,9 +246,14 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
+static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
+{
+	return ((id >> 4) << 16) | (1 << (id & 0xf));
+}
+
 static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 {
-	u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+	u32 ldr = kvm_apic_calc_x2apic_ldr(id);
 
 	kvm_lapic_set_reg(apic, APIC_ID, id);
 	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
@@ -2029,6 +2034,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 {
 	if (apic_x2apic_mode(vcpu->arch.apic)) {
 		u32 *id = (u32 *)(s->regs + APIC_ID);
+		u32 *ldr = (u32 *)(s->regs + APIC_LDR);
 
 		if (vcpu->kvm->arch.x2apic_format) {
 			if (*id != vcpu->vcpu_id)
@@ -2039,6 +2045,10 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 			else
 				*id <<= 24;
 		}
+
+		/* In x2APIC mode, the LDR is fixed and based on the id */
+		if (set)
+			*ldr = kvm_apic_calc_x2apic_ldr(*id);
 	}
 
 	return 0;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 4fbf0c94f2d1..23f1a6bd7a0d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2149,6 +2149,8 @@ static int ud_interception(struct vcpu_svm *svm)
 	int er;
 
 	er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
+	if (er == EMULATE_USER_EXIT)
+		return 0;
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0f0b27d96f27..f0d3de153e29 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5502,6 +5502,8 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 			return 1;
 		}
 		er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+		if (er == EMULATE_USER_EXIT)
+			return 0;
 		if (er != EMULATE_DONE)
 			kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 595f8149c0d9..02d45296a97c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1797,6 +1797,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
 	 */
 	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
 
+	if (guest_hv_clock.version & 1)
+		++guest_hv_clock.version;  /* first time write, random junk */
+
 	vcpu->hv_clock.version = guest_hv_clock.version + 1;
 	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
 				&vcpu->hv_clock,
@@ -5576,6 +5579,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 						emulation_type))
 				return EMULATE_DONE;
+			if (ctxt->have_exception && inject_emulated_exception(vcpu))
+				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
 			return handle_emulation_failure(vcpu);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index f8fdbd1378a7..26afdffab5a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1788,34 +1788,32 @@ void amdgpu_atombios_scratch_regs_restore(struct amdgpu_device *adev)
 		WREG32(mmBIOS_SCRATCH_0 + i, adev->bios_scratch[i]);
 }
 
-/* Atom needs data in little endian format
- * so swap as appropriate when copying data to
- * or from atom. Note that atom operates on
- * dw units.
+/* Atom needs data in little endian format so swap as appropriate when copying
+ * data to or from atom. Note that atom operates on dw units.
+ *
+ * Use to_le=true when sending data to atom and provide at least
+ * ALIGN(num_bytes,4) bytes in the dst buffer.
+ *
+ * Use to_le=false when receiving data from atom and provide ALIGN(num_bytes,4)
+ * byes in the src buffer.
  */
 void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
-	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
-	u32 *dst32, *src32;
+	u32 src_tmp[5], dst_tmp[5];
 	int i;
+	u8 align_num_bytes = ALIGN(num_bytes, 4);
 
-	memcpy(src_tmp, src, num_bytes);
-	src32 = (u32 *)src_tmp;
-	dst32 = (u32 *)dst_tmp;
 	if (to_le) {
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = cpu_to_le32(src32[i]);
-		memcpy(dst, dst_tmp, num_bytes);
+		memcpy(src_tmp, src, num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = cpu_to_le32(src_tmp[i]);
+		memcpy(dst, dst_tmp, align_num_bytes);
 	} else {
-		u8 dws = num_bytes & ~3;
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = le32_to_cpu(src32[i]);
-		memcpy(dst, dst_tmp, dws);
-		if (num_bytes % 4) {
-			for (i = 0; i < (num_bytes % 4); i++)
-				dst[dws+i] = dst_tmp[dws+i];
-		}
+		memcpy(src_tmp, src, align_num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = le32_to_cpu(src_tmp[i]);
+		memcpy(dst, dst_tmp, num_bytes);
 	}
 #else
 	memcpy(dst, src, num_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 743a12df6971..3bb2b9b5ef9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -648,7 +648,7 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx)
 	uint32_t allocated = 0;
 	uint32_t tmp, handle = 0;
 	uint32_t *size = &tmp;
-	int i, r, idx = 0;
+	int i, r = 0, idx = 0;
 
 	r = amdgpu_cs_sysvm_access_required(p);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 968c4260d7a7..47503759906b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -744,7 +744,7 @@ static int amdgpu_vm_update_pd_or_shadow(struct amdgpu_device *adev,
 int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
                                    struct amdgpu_vm *vm)
 {
-	int r;
+	int r = 0;
 
 	r = amdgpu_vm_update_pd_or_shadow(adev, vm, true);
 	if (r)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index 4477c55a58e3..a8b59b3decd8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -850,9 +850,9 @@ static int init_over_drive_limits(
 		const ATOM_Tonga_POWERPLAYTABLE *powerplay_table)
 {
 	hwmgr->platform_descriptor.overdriveLimit.engineClock =
-		le16_to_cpu(powerplay_table->ulMaxODEngineClock);
+		le32_to_cpu(powerplay_table->ulMaxODEngineClock);
 	hwmgr->platform_descriptor.overdriveLimit.memoryClock =
-		le16_to_cpu(powerplay_table->ulMaxODMemoryClock);
+		le32_to_cpu(powerplay_table->ulMaxODMemoryClock);
 
 	hwmgr->platform_descriptor.minOverdriveVDDC = 0;
 	hwmgr->platform_descriptor.maxOverdriveVDDC = 0;
diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
index 7e7a4d43d6b6..0f563c954520 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
@@ -521,9 +521,12 @@ static void ade_crtc_atomic_begin(struct drm_crtc *crtc,
 {
 	struct ade_crtc *acrtc = to_ade_crtc(crtc);
 	struct ade_hw_ctx *ctx = acrtc->ctx;
+	struct drm_display_mode *mode = &crtc->state->mode;
+	struct drm_display_mode *adj_mode = &crtc->state->adjusted_mode;
 
 	if (!ctx->power_on)
 		(void)ade_power_up(ctx);
+	ade_ldi_set_mode(acrtc, mode, adj_mode);
 }
 
 static void ade_crtc_atomic_flush(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 79aab9ad6faa..6769aa1b6922 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -430,7 +430,9 @@ static bool
 gmbus_is_index_read(struct i2c_msg *msgs, int i, int num)
 {
 	return (i + 1 < num &&
-		!(msgs[i].flags & I2C_M_RD) && msgs[i].len <= 2 &&
+		msgs[i].addr == msgs[i + 1].addr &&
+		!(msgs[i].flags & I2C_M_RD) &&
+		(msgs[i].len == 1 || msgs[i].len == 2) &&
 		(msgs[i + 1].flags & I2C_M_RD));
 }
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 27cb42467b20..6f65846b1783 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -369,6 +369,7 @@ static int panel_simple_remove(struct device *dev)
 	drm_panel_remove(&panel->base);
 
 	panel_simple_disable(&panel->base);
+	panel_simple_unprepare(&panel->base);
 
 	if (panel->ddc)
 		put_device(&panel->ddc->dev);
@@ -384,6 +385,7 @@ static void panel_simple_shutdown(struct device *dev)
 	struct panel_simple *panel = dev_get_drvdata(dev);
 
 	panel_simple_disable(&panel->base);
+	panel_simple_unprepare(&panel->base);
 }
 
 static const struct drm_display_mode ampire_am800480r3tmqwa1h_mode = {
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 432cb46f6a34..fd7682bf335d 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -45,34 +45,32 @@ static char *pre_emph_names[] = {
 
 /***** radeon AUX functions *****/
 
-/* Atom needs data in little endian format
- * so swap as appropriate when copying data to
- * or from atom. Note that atom operates on
- * dw units.
+/* Atom needs data in little endian format so swap as appropriate when copying
+ * data to or from atom. Note that atom operates on dw units.
+ *
+ * Use to_le=true when sending data to atom and provide at least
+ * ALIGN(num_bytes,4) bytes in the dst buffer.
+ *
+ * Use to_le=false when receiving data from atom and provide ALIGN(num_bytes,4)
+ * byes in the src buffer.
  */
 void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
 {
 #ifdef __BIG_ENDIAN
-	u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
-	u32 *dst32, *src32;
+	u32 src_tmp[5], dst_tmp[5];
 	int i;
+	u8 align_num_bytes = ALIGN(num_bytes, 4);
 
-	memcpy(src_tmp, src, num_bytes);
-	src32 = (u32 *)src_tmp;
-	dst32 = (u32 *)dst_tmp;
 	if (to_le) {
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = cpu_to_le32(src32[i]);
-		memcpy(dst, dst_tmp, num_bytes);
+		memcpy(src_tmp, src, num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = cpu_to_le32(src_tmp[i]);
+		memcpy(dst, dst_tmp, align_num_bytes);
 	} else {
-		u8 dws = num_bytes & ~3;
-		for (i = 0; i < ((num_bytes + 3) / 4); i++)
-			dst32[i] = le32_to_cpu(src32[i]);
-		memcpy(dst, dst_tmp, dws);
-		if (num_bytes % 4) {
-			for (i = 0; i < (num_bytes % 4); i++)
-				dst[dws+i] = dst_tmp[dws+i];
-		}
+		memcpy(src_tmp, src, align_num_bytes);
+		for (i = 0; i < align_num_bytes / 4; i++)
+			dst_tmp[i] = le32_to_cpu(src_tmp[i]);
+		memcpy(dst, dst_tmp, num_bytes);
 	}
 #else
 	memcpy(dst, src, num_bytes);
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 0daad446d2c7..af84705b82ed 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -252,7 +252,6 @@ static int radeonfb_create(struct drm_fb_helper *helper,
 	}
 
 	info->par = rfbdev;
-	info->skip_vt_switch = true;
 
 	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->rfb, &mode_cmd, gobj);
 	if (ret) {
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index bf6e21655c57..7d22f9874d5f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -473,6 +473,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->lru);
 	INIT_LIST_HEAD(&fbo->swap);
 	INIT_LIST_HEAD(&fbo->io_reserve_lru);
+	mutex_init(&fbo->wu_mutex);
 	fbo->moving = NULL;
 	drm_vma_node_reset(&fbo->vma_node);
 	atomic_set(&fbo->cpu_writers, 0);
diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c
index 1bf22eff0b08..0f1f6421845f 100644
--- a/drivers/hwmon/jc42.c
+++ b/drivers/hwmon/jc42.c
@@ -22,6 +22,7 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -45,6 +46,7 @@ static const unsigned short normal_i2c[] = {
 #define JC42_REG_TEMP		0x05
 #define JC42_REG_MANID		0x06
 #define JC42_REG_DEVICEID	0x07
+#define JC42_REG_SMBUS		0x22 /* NXP and Atmel, possibly others? */
 
 /* Status bits in temperature register */
 #define JC42_ALARM_CRIT_BIT	15
@@ -73,6 +75,9 @@ static const unsigned short normal_i2c[] = {
 #define ONS_MANID		0x1b09  /* ON Semiconductor */
 #define STM_MANID		0x104a  /* ST Microelectronics */
 
+/* SMBUS register */
+#define SMBUS_STMOUT		BIT(7)  /* SMBus time-out, active low */
+
 /* Supported chips */
 
 /* Analog Devices */
@@ -476,6 +481,22 @@ static int jc42_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 	data->extended = !!(cap & JC42_CAP_RANGE);
 
+	if (device_property_read_bool(dev, "smbus-timeout-disable")) {
+		int smbus;
+
+		/*
+		 * Not all chips support this register, but from a
+		 * quick read of various datasheets no chip appears
+		 * incompatible with the below attempt to disable
+		 * the timeout. And the whole thing is opt-in...
+		 */
+		smbus = i2c_smbus_read_word_swapped(client, JC42_REG_SMBUS);
+		if (smbus < 0)
+			return smbus;
+		i2c_smbus_write_word_swapped(client, JC42_REG_SMBUS,
+					     smbus | SMBUS_STMOUT);
+	}
+
 	config = i2c_smbus_read_word_swapped(client, JC42_REG_CONFIG);
 	if (config < 0)
 		return config;
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index eb3627f35d12..e6fe21a6135b 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1592,6 +1592,9 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* Default timeout in interrupt mode: 200 ms */
 	priv->adapter.timeout = HZ / 5;
 
+	if (dev->irq == IRQ_NOTCONNECTED)
+		priv->features &= ~FEATURE_IRQ;
+
 	if (priv->features & FEATURE_IRQ) {
 		u16 pcictl, pcists;
 
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 3fba31cea66e..537903bf9add 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -477,7 +477,7 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
 		if (b == -1)
 			goto err;
 
-		k->ptr[i] = PTR(ca->buckets[b].gen,
+		k->ptr[i] = MAKE_PTR(ca->buckets[b].gen,
 				bucket_to_sector(c, b),
 				ca->sb.nr_this_dev);
 
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index 243de0bf15cd..4bf15182c4da 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -584,7 +584,7 @@ static bool bch_extent_merge(struct btree_keys *bk, struct bkey *l, struct bkey
 		return false;
 
 	for (i = 0; i < KEY_PTRS(l); i++)
-		if (l->ptr[i] + PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
+		if (l->ptr[i] + MAKE_PTR(0, KEY_SIZE(l), 0) != r->ptr[i] ||
 		    PTR_BUCKET_NR(b->c, l, i) != PTR_BUCKET_NR(b->c, r, i))
 			return false;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 6925023e12d4..08f20b7cd199 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -508,7 +508,7 @@ static void journal_reclaim(struct cache_set *c)
 			continue;
 
 		ja->cur_idx = next;
-		k->ptr[n++] = PTR(0,
+		k->ptr[n++] = MAKE_PTR(0,
 				  bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
 				  ca->sb.nr_this_dev);
 	}
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 1beb722f6080..e1e69a480c56 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -701,6 +701,7 @@ static struct twl4030_ins omap3_wrst_seq[] = {
 	TWL_RESOURCE_RESET(RES_MAIN_REF),
 	TWL_RESOURCE_GROUP_RESET(RES_GRP_ALL, RES_TYPE_R0, RES_TYPE2_R2),
 	TWL_RESOURCE_RESET(RES_VUSB_3V1),
+	TWL_RESOURCE_RESET(RES_VMMC1),
 	TWL_RESOURCE_GROUP_RESET(RES_GRP_ALL, RES_TYPE_R0, RES_TYPE2_R1),
 	TWL_RESOURCE_GROUP_RESET(RES_GRP_RC, RES_TYPE_ALL, RES_TYPE2_R0),
 	TWL_RESOURCE_ON(RES_RESET),
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 051b14766ef9..19c10dc56513 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -365,7 +365,8 @@ static ssize_t at24_eeprom_read_mac(struct at24_data *at24, char *buf,
 	memset(msg, 0, sizeof(msg));
 	msg[0].addr = client->addr;
 	msg[0].buf = addrbuf;
-	addrbuf[0] = 0x90 + offset;
+	/* EUI-48 starts from 0x9a, EUI-64 from 0x98 */
+	addrbuf[0] = 0xa0 - at24->chip.byte_len + offset;
 	msg[0].len = 1;
 	msg[1].addr = client->addr;
 	msg[1].flags = I2C_M_RD;
@@ -506,6 +507,9 @@ static int at24_read(void *priv, unsigned int off, void *val, size_t count)
 	if (unlikely(!count))
 		return count;
 
+	if (off + count > at24->chip.byte_len)
+		return -EINVAL;
+
 	/*
 	 * Read data from chip, protecting against concurrent updates
 	 * from this host, but not from other I2C masters.
@@ -538,6 +542,9 @@ static int at24_write(void *priv, unsigned int off, void *val, size_t count)
 	if (unlikely(!count))
 		return -EINVAL;
 
+	if (off + count > at24->chip.byte_len)
+		return -EINVAL;
+
 	/*
 	 * Write data to chip, protecting against concurrent updates
 	 * from this host, but not from other I2C masters.
@@ -638,6 +645,16 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		dev_warn(&client->dev,
 			"page_size looks suspicious (no power of 2)!\n");
 
+	/*
+	 * REVISIT: the size of the EUI-48 byte array is 6 in at24mac402, while
+	 * the call to ilog2() in AT24_DEVICE_MAGIC() rounds it down to 4.
+	 *
+	 * Eventually we'll get rid of the magic values altoghether in favor of
+	 * real structs, but for now just manually set the right size.
+	 */
+	if (chip.flags & AT24_FLAG_MAC && chip.byte_len == 4)
+		chip.byte_len = 6;
+
 	/* Use I2C operations unless we're stuck with SMBus extensions. */
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		if (chip.flags & AT24_FLAG_ADDR16)
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index c64266f5a399..60ebe5b4500b 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -155,6 +155,9 @@ static int mmc_bus_suspend(struct device *dev)
 		return ret;
 
 	ret = host->bus_ops->suspend(host);
+	if (ret)
+		pm_generic_resume(dev);
+
 	return ret;
 }
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 4f4a627f6b20..0c6de9f12ee8 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -752,7 +752,7 @@ MMC_DEV_ATTR(enhanced_area_offset, "%llu\n",
 MMC_DEV_ATTR(enhanced_area_size, "%u\n", card->ext_csd.enhanced_area_size);
 MMC_DEV_ATTR(raw_rpmb_size_mult, "%#x\n", card->ext_csd.raw_rpmb_size_mult);
 MMC_DEV_ATTR(rel_sectors, "%#x\n", card->ext_csd.rel_sectors);
-MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
+MMC_DEV_ATTR(ocr, "0x%08x\n", card->ocr);
 
 static ssize_t mmc_fwrev_show(struct device *dev,
 			      struct device_attribute *attr,
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index f6f40a1673ae..f09148a4ab55 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -683,7 +683,7 @@ MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
 MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name);
 MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid);
 MMC_DEV_ATTR(serial, "0x%08x\n", card->cid.serial);
-MMC_DEV_ATTR(ocr, "%08x\n", card->ocr);
+MMC_DEV_ATTR(ocr, "0x%08x\n", card->ocr);
 
 
 static ssize_t mmc_dsr_show(struct device *dev,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 8edafd8cb8ce..5c52a6182765 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -84,7 +84,7 @@ enum nvme_quirks {
  * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
  * found empirically.
  */
-#define NVME_QUIRK_DELAY_AMOUNT		2000
+#define NVME_QUIRK_DELAY_AMOUNT		2300
 
 enum nvme_ctrl_state {
 	NVME_CTRL_NEW,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 54ea90f89b70..e48ecb9303ca 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2109,6 +2109,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
 	{ PCI_DEVICE(0x1c58, 0x0003),	/* HGST adapter */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+	{ PCI_DEVICE(0x1c58, 0x0023),	/* WDC SN200 adapter */
+		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE(0x1c5f, 0x0540),	/* Memblaze Pblaze4 adapter */
 		.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 705bb5f5a87f..c4cff5cc9c93 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3397,13 +3397,6 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 		goto again;
 	}
 
-	/* We've already setup this transaction, go ahead and exit */
-	if (block_group->cache_generation == trans->transid &&
-	    i_size_read(inode)) {
-		dcs = BTRFS_DC_SETUP;
-		goto out_put;
-	}
-
 	/*
 	 * We want to set the generation to 0, that way if anything goes wrong
 	 * from here on out we know not to trust this cache when we load up next
@@ -3427,6 +3420,13 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	}
 	WARN_ON(ret);
 
+	/* We've already setup this transaction, go ahead and exit */
+	if (block_group->cache_generation == trans->transid &&
+	    i_size_read(inode)) {
+		dcs = BTRFS_DC_SETUP;
+		goto out_put;
+	}
+
 	if (i_size_read(inode) > 0) {
 		ret = btrfs_check_trunc_cache_free_space(root,
 					&root->fs_info->global_block_rsv);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index d04ec3814779..65566d5fcf39 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1292,7 +1292,7 @@ static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
 		return 0;
 	}
 
-	error = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	error = nfs_lookup_verify_inode(inode, flags);
 	dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
 			__func__, inode->i_ino, error ? "invalid" : "valid");
 	return !error;
@@ -1443,6 +1443,7 @@ static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
 
 const struct dentry_operations nfs4_dentry_operations = {
 	.d_revalidate	= nfs4_lookup_revalidate,
+	.d_weak_revalidate	= nfs_weak_revalidate,
 	.d_delete	= nfs_dentry_delete,
 	.d_iput		= nfs_dentry_iput,
 	.d_automount	= nfs_d_automount,
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ec2a69dac536..9ebb2d7c8182 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3513,7 +3513,9 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 		/* ignore lock owners */
 		if (local->st_stateowner->so_is_open_owner == 0)
 			continue;
-		if (local->st_stateowner == &oo->oo_owner) {
+		if (local->st_stateowner != &oo->oo_owner)
+			continue;
+		if (local->st_stid.sc_type == NFS4_OPEN_STID) {
 			ret = local;
 			atomic_inc(&ret->st_stid.sc_count);
 			break;
@@ -3522,6 +3524,52 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
 	return ret;
 }
 
+static __be32
+nfsd4_verify_open_stid(struct nfs4_stid *s)
+{
+	__be32 ret = nfs_ok;
+
+	switch (s->sc_type) {
+	default:
+		break;
+	case NFS4_CLOSED_STID:
+	case NFS4_CLOSED_DELEG_STID:
+		ret = nfserr_bad_stateid;
+		break;
+	case NFS4_REVOKED_DELEG_STID:
+		ret = nfserr_deleg_revoked;
+	}
+	return ret;
+}
+
+/* Lock the stateid st_mutex, and deal with races with CLOSE */
+static __be32
+nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp)
+{
+	__be32 ret;
+
+	mutex_lock(&stp->st_mutex);
+	ret = nfsd4_verify_open_stid(&stp->st_stid);
+	if (ret != nfs_ok)
+		mutex_unlock(&stp->st_mutex);
+	return ret;
+}
+
+static struct nfs4_ol_stateid *
+nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
+{
+	struct nfs4_ol_stateid *stp;
+	for (;;) {
+		spin_lock(&fp->fi_lock);
+		stp = nfsd4_find_existing_open(fp, open);
+		spin_unlock(&fp->fi_lock);
+		if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok)
+			break;
+		nfs4_put_stid(&stp->st_stid);
+	}
+	return stp;
+}
+
 static struct nfs4_openowner *
 alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
 			   struct nfsd4_compound_state *cstate)
@@ -3566,6 +3614,7 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 	mutex_init(&stp->st_mutex);
 	mutex_lock(&stp->st_mutex);
 
+retry:
 	spin_lock(&oo->oo_owner.so_client->cl_lock);
 	spin_lock(&fp->fi_lock);
 
@@ -3590,7 +3639,11 @@ init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open)
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&oo->oo_owner.so_client->cl_lock);
 	if (retstp) {
-		mutex_lock(&retstp->st_mutex);
+		/* Handle races with CLOSE */
+		if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+			nfs4_put_stid(&retstp->st_stid);
+			goto retry;
+		}
 		/* To keep mutex tracking happy */
 		mutex_unlock(&stp->st_mutex);
 		stp = retstp;
@@ -4400,6 +4453,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	struct nfs4_ol_stateid *stp = NULL;
 	struct nfs4_delegation *dp = NULL;
 	__be32 status;
+	bool new_stp = false;
 
 	/*
 	 * Lookup file; if found, lookup stateid and check open request,
@@ -4411,9 +4465,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfs4_check_deleg(cl, open, &dp);
 		if (status)
 			goto out;
-		spin_lock(&fp->fi_lock);
-		stp = nfsd4_find_existing_open(fp, open);
-		spin_unlock(&fp->fi_lock);
+		stp = nfsd4_find_and_lock_existing_open(fp, open);
 	} else {
 		open->op_file = NULL;
 		status = nfserr_bad_stateid;
@@ -4421,35 +4473,31 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 			goto out;
 	}
 
+	if (!stp) {
+		stp = init_open_stateid(fp, open);
+		if (!open->op_stp)
+			new_stp = true;
+	}
+
 	/*
 	 * OPEN the file, or upgrade an existing OPEN.
 	 * If truncate fails, the OPEN fails.
+	 *
+	 * stp is already locked.
 	 */
-	if (stp) {
+	if (!new_stp) {
 		/* Stateid was found, this is an OPEN upgrade */
-		mutex_lock(&stp->st_mutex);
 		status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open);
 		if (status) {
 			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 	} else {
-		/* stp is returned locked. */
-		stp = init_open_stateid(fp, open);
-		/* See if we lost the race to some other thread */
-		if (stp->st_access_bmap != 0) {
-			status = nfs4_upgrade_open(rqstp, fp, current_fh,
-						stp, open);
-			if (status) {
-				mutex_unlock(&stp->st_mutex);
-				goto out;
-			}
-			goto upgrade_out;
-		}
 		status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
 		if (status) {
-			mutex_unlock(&stp->st_mutex);
+			stp->st_stid.sc_type = NFS4_CLOSED_STID;
 			release_open_stateid(stp);
+			mutex_unlock(&stp->st_mutex);
 			goto out;
 		}
 
@@ -4458,7 +4506,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		if (stp->st_clnt_odstate == open->op_odstate)
 			open->op_odstate = NULL;
 	}
-upgrade_out:
+
 	nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid);
 	mutex_unlock(&stp->st_mutex);
 
@@ -4684,7 +4732,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
-		nbl = list_first_entry(&nn->blocked_locks_lru,
+		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_del_init(&nbl->nbl_lru);
 		posix_unblock_lock(&nbl->nbl_lock);
@@ -5314,7 +5362,6 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
 	bool unhashed;
 	LIST_HEAD(reaplist);
 
-	s->st_stid.sc_type = NFS4_CLOSED_STID;
 	spin_lock(&clp->cl_lock);
 	unhashed = unhash_open_stateid(s, &reaplist);
 
@@ -5353,10 +5400,12 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	nfsd4_bump_seqid(cstate, status);
 	if (status)
 		goto out; 
+
+	stp->st_stid.sc_type = NFS4_CLOSED_STID;
 	nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid);
-	mutex_unlock(&stp->st_mutex);
 
 	nfsd4_close_open_stateid(stp);
+	mutex_unlock(&stp->st_mutex);
 
 	/* put reference from nfs4_preprocess_seqid_op */
 	nfs4_put_stid(&stp->st_stid);
@@ -7094,7 +7143,7 @@ nfs4_state_shutdown_net(struct net *net)
 	spin_unlock(&nn->blocked_locks_lock);
 
 	while (!list_empty(&reaplist)) {
-		nbl = list_first_entry(&nn->blocked_locks_lru,
+		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_del_init(&nbl->nbl_lru);
 		posix_unblock_lock(&nbl->nbl_lock);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6c9e1ad12831..2217e2f18247 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -347,6 +347,7 @@ struct fault_env {
 struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
+	int (*split)(struct vm_area_struct * area, unsigned long addr);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 22b6ad31c706..8562b1cb776b 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -90,7 +90,7 @@ PTR_FIELD(PTR_GEN,			0,  8)
 
 #define PTR_CHECK_DEV			((1 << PTR_DEV_BITS) - 1)
 
-#define PTR(gen, offset, dev)						\
+#define MAKE_PTR(gen, offset, dev)					\
 	((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen)
 
 /* Bkey utility code */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8258e9eee806..3cae1dcf069c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -745,20 +745,15 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd)
+		pmd_t *pmd, int flags)
 {
 	pmd_t _pmd;
 
-	/*
-	 * We should set the dirty bit only for FOLL_WRITE but for now
-	 * the dirty bit in the pmd is meaningless.  And if the dirty
-	 * bit will become meaningful and we'll only set it with
-	 * FOLL_WRITE, an atomic set_bit will be required on the pmd to
-	 * set the young bit, instead of the current set_pmd_at.
-	 */
-	_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+	_pmd = pmd_mkyoung(*pmd);
+	if (flags & FOLL_WRITE)
+		_pmd = pmd_mkdirty(_pmd);
 	if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
-				pmd, _pmd,  1))
+				pmd, _pmd, flags & FOLL_WRITE))
 		update_mmu_cache_pmd(vma, addr, pmd);
 }
 
@@ -787,7 +782,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 		return NULL;
 
 	if (flags & FOLL_TOUCH)
-		touch_pmd(vma, addr, pmd);
+		touch_pmd(vma, addr, pmd, flags);
 
 	/*
 	 * device mapped pages can only be returned if the
@@ -1158,7 +1153,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
 	if (flags & FOLL_TOUCH)
-		touch_pmd(vma, addr, pmd);
+		touch_pmd(vma, addr, pmd, flags);
 	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
 		/*
 		 * We don't mlock() pte-mapped THPs. This way we can avoid
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65c36acf8a6b..6ff65c405243 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3135,6 +3135,13 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 	}
 }
 
+static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	if (addr & ~(huge_page_mask(hstate_vma(vma))))
+		return -EINVAL;
+	return 0;
+}
+
 /*
  * We cannot handle pagefaults against hugetlb pages at all.  They cause
  * handle_mm_fault() to try to instantiate regular-sized pages in the
@@ -3151,6 +3158,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.fault = hugetlb_vm_op_fault,
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
+	.split = hugetlb_vm_op_split,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
diff --git a/mm/madvise.c b/mm/madvise.c
index 55f30ec32e5b..a49afe08698b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -228,15 +228,14 @@ static long madvise_willneed(struct vm_area_struct *vma,
 {
 	struct file *file = vma->vm_file;
 
+	*prev = vma;
 #ifdef CONFIG_SWAP
 	if (!file) {
-		*prev = vma;
 		force_swapin_readahead(vma, start, end);
 		return 0;
 	}
 
 	if (shmem_mapping(file->f_mapping)) {
-		*prev = vma;
 		force_shm_swapin_readahead(vma, start, end,
 					file->f_mapping);
 		return 0;
@@ -251,7 +250,6 @@ static long madvise_willneed(struct vm_area_struct *vma,
 		return 0;
 	}
 
-	*prev = vma;
 	start = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 	if (end > vma->vm_end)
 		end = vma->vm_end;
diff --git a/mm/mmap.c b/mm/mmap.c
index 75d263bd8739..5b48adb4aa56 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2538,9 +2538,11 @@ static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct vm_area_struct *new;
 	int err;
 
-	if (is_vm_hugetlb_page(vma) && (addr &
-					~(huge_page_mask(hstate_vma(vma)))))
-		return -EINVAL;
+	if (vma->vm_ops && vma->vm_ops->split) {
+		err = vma->vm_ops->split(vma, addr);
+		if (err)
+			return err;
+	}
 
 	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4a044134ce84..ef5ee56095e8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7309,11 +7309,18 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/*
 	 * In case of -EBUSY, we'd like to know which page causes problem.
-	 * So, just fall through. We will check it in test_pages_isolated().
+	 * So, just fall through. test_pages_isolated() has a tracepoint
+	 * which will report the busy page.
+	 *
+	 * It is possible that busy pages could become available before
+	 * the call to test_pages_isolated, and the range will actually be
+	 * allocated.  So, if we fall through be sure to clear ret so that
+	 * -EBUSY is not accidentally used or returned to caller.
 	 */
 	ret = __alloc_contig_migrate_range(&cc, start, end);
 	if (ret && ret != -EBUSY)
 		goto done;
+	ret =0;
 
 	/*
 	 * Pages from [start, end) are within a MAX_ORDER_NR_PAGES