Merge tag 'omap-for-v3.13/intc-ldp-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes

From Tony Lindgren:
Fix a regression for wrong interrupt numbers for some devices after
the sparse IRQ conversion, fix DRA7 console output for earlyprintk,
and fix the LDP LCD backlight when DSS is built into the kernel and
not as a loadable module.

* tag 'omap-for-v3.13/intc-ldp-fix' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap:
  ARM: OMAP2+: Fix LCD panel backlight regression for LDP legacy booting
  ARM: OMAP2+: hwmod_data: fix missing OMAP_INTC_START in irq data
  ARM: DRA7: hwmod: Fix boot crash with DEBUG_LL
  + v3.13-rc5

Signed-off-by: Olof Johansson <olof@lixom.net>

39 files changed, 269 insertions, 169 deletions

diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 68125dd766c..39e58d1cdf9 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -8,7 +8,11 @@
 
 /******** no-legacy-syscalls-ABI *******/
 
-#ifndef _UAPI_ASM_ARC_UNISTD_H
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
 #define _UAPI_ASM_ARC_UNISTD_H
 
 #define __ARCH_WANT_SYS_EXECVE
@@ -36,4 +40,6 @@ __SYSCALL(__NR_arc_gettls, sys_arc_gettls)
 #define __NR_sysfs		(__NR_arch_specific_syscall + 3)
 __SYSCALL(__NR_sysfs, sys_sysfs)
 
+#undef __SYSCALL
+
 #endif
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index 4ec8d82b049..44a59c3abfb 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -242,12 +242,18 @@ static void __init ldp_display_init(void)
 
 static int ldp_twl_gpio_setup(struct device *dev, unsigned gpio, unsigned ngpio)
 {
+	int res;
+
 	/* LCD enable GPIO */
 	ldp_lcd_pdata.enable_gpio = gpio + 7;
 
 	/* Backlight enable GPIO */
 	ldp_lcd_pdata.backlight_gpio = gpio + 15;
 
+	res = platform_device_register(&ldp_lcd_device);
+	if (res)
+		pr_err("Unable to register LCD: %d\n", res);
+
 	return 0;
 }
 
@@ -346,7 +352,6 @@ static struct omap2_hsmmc_info mmc[] __initdata = {
 
 static struct platform_device *ldp_devices[] __initdata = {
 	&ldp_gpio_keys_device,
-	&ldp_lcd_device,
 };
 
 #ifdef CONFIG_OMAP_MUX
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index 56cebb05509..d23c77fadb3 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -796,7 +796,7 @@ struct omap_hwmod omap2xxx_counter_32k_hwmod = {
 
 /* gpmc */
 static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = {
-	{ .irq = 20 },
+	{ .irq = 20 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -841,7 +841,7 @@ static struct omap_hwmod_class omap2_rng_hwmod_class = {
 };
 
 static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = {
-	{ .irq = 52 },
+	{ .irq = 52 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index d33742908f9..4c3b1e6df50 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -2165,7 +2165,7 @@ static struct omap_hwmod_class omap3xxx_gpmc_hwmod_class = {
 };
 
 static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = {
-	{ .irq = 20 },
+	{ .irq = 20 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -2999,7 +2999,7 @@ static struct omap_mmu_dev_attr mmu_isp_dev_attr = {
 
 static struct omap_hwmod omap3xxx_mmu_isp_hwmod;
 static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = {
-	{ .irq = 24 },
+	{ .irq = 24 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
@@ -3041,7 +3041,7 @@ static struct omap_mmu_dev_attr mmu_iva_dev_attr = {
 
 static struct omap_hwmod omap3xxx_mmu_iva_hwmod;
 static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = {
-	{ .irq = 28 },
+	{ .irq = 28 + OMAP_INTC_START, },
 	{ .irq = -1 }
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index db32d5380b1..18f333c440d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1637,7 +1637,7 @@ static struct omap_hwmod dra7xx_uart1_hwmod = {
 	.class		= &dra7xx_uart_hwmod_class,
 	.clkdm_name	= "l4per_clkdm",
 	.main_clk	= "uart1_gfclk_mux",
-	.flags		= HWMOD_SWSUP_SIDLE_ACT,
+	.flags		= HWMOD_SWSUP_SIDLE_ACT | DEBUG_OMAP2UART1_FLAGS,
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = DRA7XX_CM_L4PER_UART1_CLKCTRL_OFFSET,
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 83e4f959ee4..85501238b42 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -96,7 +96,7 @@ static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
 	struct remap_data *info = data;
 	struct page *page = info->pages[info->index++];
 	unsigned long pfn = page_to_pfn(page);
-	pte_t pte = pfn_pte(pfn, info->prot);
+	pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
 
 	if (map_foreign_page(pfn, info->fgmfn, info->domid))
 		return -EFAULT;
@@ -224,10 +224,10 @@ static int __init xen_guest_init(void)
 	}
 	if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
 		return 0;
-	xen_hvm_resume_frames = res.start >> PAGE_SHIFT;
+	xen_hvm_resume_frames = res.start;
 	xen_events_irq = irq_of_parse_and_map(node, 0);
 	pr_info("Xen %s support found, events_irq=%d gnttab_frame_pfn=%lx\n",
-			version, xen_events_irq, xen_hvm_resume_frames);
+			version, xen_events_irq, (xen_hvm_resume_frames >> PAGE_SHIFT));
 	xen_domain_type = XEN_HVM_DOMAIN;
 
 	xen_setup_features();
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
index 2820f1a6eeb..dde3fc9c49f 100644
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ b/arch/arm64/include/asm/xen/page-coherent.h
@@ -23,25 +23,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     struct dma_attrs *attrs)
 {
-	__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 }
 
 static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
 		struct dma_attrs *attrs)
 {
-	__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
 }
 
 static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	__generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
 }
 
 static inline void xen_dma_sync_single_for_device(struct device *hwdev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	__generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
 }
 #endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6777a2192b8..6a8928bba03 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -214,31 +214,29 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 {
 	int err, len, type, disabled = !ctrl.enabled;
 
-	if (disabled) {
-		len = 0;
-		type = HW_BREAKPOINT_EMPTY;
-	} else {
-		err = arch_bp_generic_fields(ctrl, &len, &type);
-		if (err)
-			return err;
-
-		switch (note_type) {
-		case NT_ARM_HW_BREAK:
-			if ((type & HW_BREAKPOINT_X) != type)
-				return -EINVAL;
-			break;
-		case NT_ARM_HW_WATCH:
-			if ((type & HW_BREAKPOINT_RW) != type)
-				return -EINVAL;
-			break;
-		default:
+	attr->disabled = disabled;
+	if (disabled)
+		return 0;
+
+	err = arch_bp_generic_fields(ctrl, &len, &type);
+	if (err)
+		return err;
+
+	switch (note_type) {
+	case NT_ARM_HW_BREAK:
+		if ((type & HW_BREAKPOINT_X) != type)
 			return -EINVAL;
-		}
+		break;
+	case NT_ARM_HW_WATCH:
+		if ((type & HW_BREAKPOINT_RW) != type)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->disabled	= disabled;
 
 	return 0;
 }
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4a594b76674..bc23b1ba798 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -192,6 +192,10 @@ extern void kvmppc_load_up_vsx(void);
 extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
 extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
 extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
+extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
+				 struct kvm_vcpu *vcpu);
+extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
+				   struct kvmppc_book3s_shadow_vcpu *svcpu);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 0bd9348a4db..192917d2239 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -79,6 +79,7 @@ struct kvmppc_host_state {
 	ulong vmhandler;
 	ulong scratch0;
 	ulong scratch1;
+	ulong scratch2;
 	u8 in_guest;
 	u8 restore_hid5;
 	u8 napping;
@@ -106,6 +107,7 @@ struct kvmppc_host_state {
 };
 
 struct kvmppc_book3s_shadow_vcpu {
+	bool in_use;
 	ulong gpr[14];
 	u32 cr;
 	u32 xer;
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 033c06be1d8..7bdcf340016 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -720,13 +720,13 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val);
+int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
 int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		       uint32_t addr, uint32_t data, uint32_t sz);
 int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
-		      uint32_t addr, uint32_t *data, uint32_t sz);
+		      uint32_t addr, __be32 *data, uint32_t sz);
 int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
 int64_t opal_manage_flash(uint8_t op);
 int64_t opal_update_flash(uint64_t blk_list);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 9ee12610af0..aace9054761 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -35,7 +35,7 @@ extern void giveup_vsx(struct task_struct *);
 extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
-extern void switch_booke_debug_regs(struct thread_struct *new_thread);
+extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
 #ifndef CONFIG_SMP
 extern void discard_lazy_cpu_state(void);
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2ea5cc033ec..d3de01066f7 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -576,6 +576,7 @@ int main(void)
 	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
 	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
 	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+	HSTATE_FIELD(HSTATE_SCRATCH2, scratch2);
 	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
 	HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
 	HSTATE_FIELD(HSTATE_NAPPING, napping);
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 779a78c2643..11c1d069d92 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -124,15 +124,15 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 {
 	unsigned long addr;
-	const u32 *basep, *sizep;
+	const __be32 *basep, *sizep;
 	unsigned int rtas_start = 0, rtas_end = 0;
 
 	basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
 	sizep = of_get_property(rtas.dev, "rtas-size", NULL);
 
 	if (basep && sizep) {
-		rtas_start = *basep;
-		rtas_end = *basep + *sizep;
+		rtas_start = be32_to_cpup(basep);
+		rtas_end = rtas_start + be32_to_cpup(sizep);
 	}
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3386d8ab7eb..4a96556fd2d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -339,7 +339,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread)
 #endif
 }
 
-static void prime_debug_regs(struct thread_struct *thread)
+static void prime_debug_regs(struct debug_reg *debug)
 {
 	/*
 	 * We could have inherited MSR_DE from userspace, since
@@ -348,22 +348,22 @@ static void prime_debug_regs(struct thread_struct *thread)
 	 */
 	mtmsr(mfmsr() & ~MSR_DE);
 
-	mtspr(SPRN_IAC1, thread->debug.iac1);
-	mtspr(SPRN_IAC2, thread->debug.iac2);
+	mtspr(SPRN_IAC1, debug->iac1);
+	mtspr(SPRN_IAC2, debug->iac2);
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
-	mtspr(SPRN_IAC3, thread->debug.iac3);
-	mtspr(SPRN_IAC4, thread->debug.iac4);
+	mtspr(SPRN_IAC3, debug->iac3);
+	mtspr(SPRN_IAC4, debug->iac4);
 #endif
-	mtspr(SPRN_DAC1, thread->debug.dac1);
-	mtspr(SPRN_DAC2, thread->debug.dac2);
+	mtspr(SPRN_DAC1, debug->dac1);
+	mtspr(SPRN_DAC2, debug->dac2);
 #if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-	mtspr(SPRN_DVC1, thread->debug.dvc1);
-	mtspr(SPRN_DVC2, thread->debug.dvc2);
+	mtspr(SPRN_DVC1, debug->dvc1);
+	mtspr(SPRN_DVC2, debug->dvc2);
 #endif
-	mtspr(SPRN_DBCR0, thread->debug.dbcr0);
-	mtspr(SPRN_DBCR1, thread->debug.dbcr1);
+	mtspr(SPRN_DBCR0, debug->dbcr0);
+	mtspr(SPRN_DBCR1, debug->dbcr1);
 #ifdef CONFIG_BOOKE
-	mtspr(SPRN_DBCR2, thread->debug.dbcr2);
+	mtspr(SPRN_DBCR2, debug->dbcr2);
 #endif
 }
 /*
@@ -371,11 +371,11 @@ static void prime_debug_regs(struct thread_struct *thread)
  * debug registers, set the debug registers from the values
  * stored in the new thread.
  */
-void switch_booke_debug_regs(struct thread_struct *new_thread)
+void switch_booke_debug_regs(struct debug_reg *new_debug)
 {
 	if ((current->thread.debug.dbcr0 & DBCR0_IDM)
-		|| (new_thread->debug.dbcr0 & DBCR0_IDM))
-			prime_debug_regs(new_thread);
+		|| (new_debug->dbcr0 & DBCR0_IDM))
+			prime_debug_regs(new_debug);
 }
 EXPORT_SYMBOL_GPL(switch_booke_debug_regs);
 #else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
@@ -683,7 +683,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	switch_booke_debug_regs(&new->thread);
+	switch_booke_debug_regs(&new->thread.debug);
 #else
 /*
  * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 75fb40498b4..2e3d2bf536c 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1555,7 +1555,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			flush_fp_to_thread(child);
 			if (fpidx < (PT_FPSCR - PT_FPR0))
-				memcpy(&tmp, &child->thread.fp_state.fpr,
+				memcpy(&tmp, &child->thread.TS_FPR(fpidx),
 				       sizeof(long));
 			else
 				tmp = child->thread.fp_state.fpscr;
@@ -1588,7 +1588,7 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			flush_fp_to_thread(child);
 			if (fpidx < (PT_FPSCR - PT_FPR0))
-				memcpy(&child->thread.fp_state.fpr, &data,
+				memcpy(&child->thread.TS_FPR(fpidx), &data,
 				       sizeof(long));
 			else
 				child->thread.fp_state.fpscr = data;
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index febc80445d2..bc76cc6b419 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -479,7 +479,7 @@ void __init smp_setup_cpu_maps(void)
 	if (machine_is(pseries) && firmware_has_feature(FW_FEATURE_LPAR) &&
 	    (dn = of_find_node_by_path("/rtas"))) {
 		int num_addr_cell, num_size_cell, maxcpus;
-		const unsigned int *ireg;
+		const __be32 *ireg;
 
 		num_addr_cell = of_n_addr_cells(dn);
 		num_size_cell = of_n_size_cells(dn);
@@ -489,7 +489,7 @@ void __init smp_setup_cpu_maps(void)
 		if (!ireg)
 			goto out;
 
-		maxcpus = ireg[num_addr_cell + num_size_cell];
+		maxcpus = be32_to_cpup(ireg + num_addr_cell + num_size_cell);
 
 		/* Double maxcpus for processors which have SMT capability */
 		if (cpu_has_feature(CPU_FTR_SMT))
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index a3b64f3bf9a..c1cf4a1522d 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -580,7 +580,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 int cpu_to_core_id(int cpu)
 {
 	struct device_node *np;
-	const int *reg;
+	const __be32 *reg;
 	int id = -1;
 
 	np = of_get_cpu_node(cpu, NULL);
@@ -591,7 +591,7 @@ int cpu_to_core_id(int cpu)
 	if (!reg)
 		goto out;
 
-	id = *reg;
+	id = be32_to_cpup(reg);
 out:
 	of_node_put(np);
 	return id;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index f3ff587a8b7..c5d148434c0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -469,11 +469,14 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		slb_v = vcpu->kvm->arch.vrma_slb_v;
 	}
 
+	preempt_disable();
 	/* Find the HPTE in the hash table */
 	index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
 					 HPTE_V_VALID | HPTE_V_ABSENT);
-	if (index < 0)
+	if (index < 0) {
+		preempt_enable();
 		return -ENOENT;
+	}
 	hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
 	v = hptep[0] & ~HPTE_V_HVLOCK;
 	gr = kvm->arch.revmap[index].guest_rpte;
@@ -481,6 +484,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	/* Unlock the HPTE */
 	asm volatile("lwsync" : : : "memory");
 	hptep[0] = v;
+	preempt_enable();
 
 	gpte->eaddr = eaddr;
 	gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
@@ -665,6 +669,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			return -EFAULT;
 	} else {
 		page = pages[0];
+		pfn = page_to_pfn(page);
 		if (PageHuge(page)) {
 			page = compound_head(page);
 			pte_size <<= compound_order(page);
@@ -689,7 +694,6 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			}
 			rcu_read_unlock_sched();
 		}
-		pfn = page_to_pfn(page);
 	}
 
 	ret = -EFAULT;
@@ -707,8 +711,14 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
 	}
 
-	/* Set the HPTE to point to pfn */
-	r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+	/*
+	 * Set the HPTE to point to pfn.
+	 * Since the pfn is at PAGE_SIZE granularity, make sure we
+	 * don't mask out lower-order bits if psize < PAGE_SIZE.
+	 */
+	if (psize < PAGE_SIZE)
+		psize = PAGE_SIZE;
+	r = (r & ~(HPTE_R_PP0 - psize)) | ((pfn << PAGE_SHIFT) & ~(psize - 1));
 	if (hpte_is_writable(r) && !write_ok)
 		r = hpte_make_readonly(r);
 	ret = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 072287f1c3b..b51d5db7806 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -131,8 +131,9 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
 	    vc->preempt_tb != TB_NIL) {
 		vc->stolen_tb += mftb() - vc->preempt_tb;
@@ -143,19 +144,20 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
 		vcpu->arch.busy_preempt = TB_NIL;
 	}
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
 static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
 
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
 		vc->preempt_tb = mftb();
 	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
 		vcpu->arch.busy_preempt = mftb();
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
 static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
@@ -486,11 +488,11 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
 	 */
 	if (vc->vcore_state != VCORE_INACTIVE &&
 	    vc->runner->arch.run_task != current) {
-		spin_lock(&vc->runner->arch.tbacct_lock);
+		spin_lock_irq(&vc->runner->arch.tbacct_lock);
 		p = vc->stolen_tb;
 		if (vc->preempt_tb != TB_NIL)
 			p += now - vc->preempt_tb;
-		spin_unlock(&vc->runner->arch.tbacct_lock);
+		spin_unlock_irq(&vc->runner->arch.tbacct_lock);
 	} else {
 		p = vc->stolen_tb;
 	}
@@ -512,10 +514,10 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	core_stolen = vcore_stolen_time(vc, now);
 	stolen = core_stolen - vcpu->arch.stolen_logged;
 	vcpu->arch.stolen_logged = core_stolen;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	stolen += vcpu->arch.busy_stolen;
 	vcpu->arch.busy_stolen = 0;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	if (!dt || !vpa)
 		return;
 	memset(dt, 0, sizeof(struct dtl_entry));
@@ -589,7 +591,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
 			return RESUME_HOST;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		rc = kvmppc_rtas_hcall(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 		if (rc == -ENOENT)
 			return RESUME_HOST;
@@ -1115,13 +1119,13 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	spin_lock(&vcpu->arch.tbacct_lock);
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
 	now = mftb();
 	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
 		vcpu->arch.stolen_logged;
 	vcpu->arch.busy_preempt = now;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
-	spin_unlock(&vcpu->arch.tbacct_lock);
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
 	list_del(&vcpu->arch.run_list);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 9c515440ad1..8689e2e3085 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -225,6 +225,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		is_io = pa & (HPTE_R_I | HPTE_R_W);
 		pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
 		pa &= PAGE_MASK;
+		pa |= gpa & ~PAGE_MASK;
 	} else {
 		/* Translate to host virtual address */
 		hva = __gfn_to_hva_memslot(memslot, gfn);
@@ -238,13 +239,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 				ptel = hpte_make_readonly(ptel);
 			is_io = hpte_cache_bits(pte_val(pte));
 			pa = pte_pfn(pte) << PAGE_SHIFT;
+			pa |= hva & (pte_size - 1);
+			pa |= gpa & ~PAGE_MASK;
 		}
 	}
 
 	if (pte_size < psize)
 		return H_PARAMETER;
-	if (pa && pte_size > psize)
-		pa |= gpa & (pte_size - 1);
 
 	ptel &= ~(HPTE_R_PP0 - psize);
 	ptel |= pa;
@@ -749,6 +750,10 @@ static int slb_base_page_shift[4] = {
 	20,	/* 1M, unsupported */
 };
 
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
 long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			      unsigned long valid)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bc8de75b192..be4fa04a37c 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -153,7 +153,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 13:	b	machine_check_fwnmi
 
-
 /*
  * We come in here when wakened from nap mode on a secondary hw thread.
  * Relocation is off and most register values are lost.
@@ -224,6 +223,11 @@ kvm_start_guest:
 	/* Clear our vcpu pointer so we don't come back in early */
 	li	r0, 0
 	std	r0, HSTATE_KVM_VCPU(r13)
+	/*
+	 * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
+	 * the nap_count, because once the increment to nap_count is
+	 * visible we could be given another vcpu.
+	 */
 	lwsync
 	/* Clear any pending IPI - we're an offline thread */
 	ld	r5, HSTATE_XICS_PHYS(r13)
@@ -241,7 +245,6 @@ kvm_start_guest:
 	/* increment the nap count and then go to nap mode */
 	ld	r4, HSTATE_KVM_VCORE(r13)
 	addi	r4, r4, VCORE_NAP_COUNT
-	lwsync				/* make previous updates visible */
 51:	lwarx	r3, 0, r4
 	addi	r3, r3, 1
 	stwcx.	r3, 0, r4
@@ -751,15 +754,14 @@ kvmppc_interrupt_hv:
 	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
-	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
-	std	r9, HSTATE_HOST_R2(r13)
+	std	r9, HSTATE_SCRATCH2(r13)
 
 	lbz	r9, HSTATE_IN_GUEST(r13)
 	cmpwi	r9, KVM_GUEST_MODE_HOST_HV
 	beq	kvmppc_bad_host_intr
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	cmpwi	r9, KVM_GUEST_MODE_GUEST
-	ld	r9, HSTATE_HOST_R2(r13)
+	ld	r9, HSTATE_SCRATCH2(r13)
 	beq	kvmppc_interrupt_pr
 #endif
 	/* We're now back in the host but in guest MMU context */
@@ -779,7 +781,7 @@ kvmppc_interrupt_hv:
 	std	r6, VCPU_GPR(R6)(r9)
 	std	r7, VCPU_GPR(R7)(r9)
 	std	r8, VCPU_GPR(R8)(r9)
-	ld	r0, HSTATE_HOST_R2(r13)
+	ld	r0, HSTATE_SCRATCH2(r13)
 	std	r0, VCPU_GPR(R9)(r9)
 	std	r10, VCPU_GPR(R10)(r9)
 	std	r11, VCPU_GPR(R11)(r9)
@@ -990,14 +992,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	 */
 	/* Increment the threads-exiting-guest count in the 0xff00
 	   bits of vcore->entry_exit_count */
-	lwsync
 	ld	r5,HSTATE_KVM_VCORE(r13)
 	addi	r6,r5,VCORE_ENTRY_EXIT
 41:	lwarx	r3,0,r6
 	addi	r0,r3,0x100
 	stwcx.	r0,0,r6
 	bne	41b
-	lwsync
+	isync		/* order stwcx. vs. reading napping_threads */
 
 	/*
 	 * At this point we have an interrupt that we have to pass
@@ -1030,6 +1031,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	sld	r0,r0,r4
 	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
 	beq	43f
+	/* Order entry/exit update vs. IPIs */
+	sync
 	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
 	subf	r6,r4,r13
 42:	andi.	r0,r3,1
@@ -1638,10 +1641,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	bge	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
+	/* order napping_threads update vs testing entry_exit_count */
+	isync
 	li	r0,1
 	stb	r0,HSTATE_NAPPING(r13)
-	/* order napping_threads update vs testing entry_exit_count */
-	lwsync
 	mr	r4,r3
 	lwz	r7,VCORE_ENTRY_EXIT(r5)
 	cmpwi	r7,0x100
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index f4dd041c14e..f779450cb07 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -129,29 +129,32 @@ kvm_start_lightweight:
 	 * R12      = exit handler id
 	 * R13      = PACA
 	 * SVCPU.*  = guest *
+	 * MSR.EE   = 1
 	 *
 	 */
 
+	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
+	/*
+	 * kvmppc_copy_from_svcpu can clobber volatile registers, save
+	 * the exit handler id to the vcpu and restore it from there later.
+	 */
+	stw	r12, VCPU_TRAP(r3)
+
 	/* Transfer reg values from shadow vcpu back to vcpu struct */
 	/* On 64-bit, interrupts are still off at this point */
-	PPC_LL	r3, GPR4(r1)		/* vcpu pointer */
+
 	GET_SHADOW_VCPU(r4)
 	bl	FUNC(kvmppc_copy_from_svcpu)
 	nop
 
 #ifdef CONFIG_PPC_BOOK3S_64
-	/* Re-enable interrupts */
-	ld	r3, HSTATE_HOST_MSR(r13)
-	ori	r3, r3, MSR_EE
-	MTMSR_EERI(r3)
-
 	/*
 	 * Reload kernel SPRG3 value.
 	 * No need to save guest value as usermode can't modify SPRG3.
 	 */
 	ld	r3, PACA_SPRG3(r13)
 	mtspr	SPRN_SPRG3, r3
-
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	/* R7 = vcpu */
@@ -177,7 +180,7 @@ kvm_start_lightweight:
 	PPC_STL	r31, VCPU_GPR(R31)(r7)
 
 	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
-	mr	r5, r12
+	lwz	r5, VCPU_TRAP(r7)
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index fe14ca3dd17..5b9e9063cfa 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -66,6 +66,7 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu)
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 	memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
 	svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+	svcpu->in_use = 0;
 	svcpu_put(svcpu);
 #endif
 	vcpu->cpu = smp_processor_id();
@@ -78,6 +79,9 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	if (svcpu->in_use) {
+		kvmppc_copy_from_svcpu(vcpu, svcpu);
+	}
 	memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
 	to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
 	svcpu_put(svcpu);
@@ -110,12 +114,26 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
 	svcpu->ctr = vcpu->arch.ctr;
 	svcpu->lr  = vcpu->arch.lr;
 	svcpu->pc  = vcpu->arch.pc;
+	svcpu->in_use = true;
 }
 
 /* Copy data touched by real-mode code from shadow vcpu back to vcpu */
 void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 			    struct kvmppc_book3s_shadow_vcpu *svcpu)
 {
+	/*
+	 * vcpu_put would just call us again because in_use hasn't
+	 * been updated yet.
+	 */
+	preempt_disable();
+
+	/*
+	 * Maybe we were already preempted and synced the svcpu from
+	 * our preempt notifiers. Don't bother touching this svcpu then.
+	 */
+	if (!svcpu->in_use)
+		goto out;
+
 	vcpu->arch.gpr[0] = svcpu->gpr[0];
 	vcpu->arch.gpr[1] = svcpu->gpr[1];
 	vcpu->arch.gpr[2] = svcpu->gpr[2];
@@ -139,6 +157,10 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 	vcpu->arch.fault_dar   = svcpu->fault_dar;
 	vcpu->arch.fault_dsisr = svcpu->fault_dsisr;
 	vcpu->arch.last_inst   = svcpu->last_inst;
+	svcpu->in_use = false;
+
+out:
+	preempt_enable();
 }
 
 static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index a38c4c9edab..c3c5231adad 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -153,15 +153,11 @@ _GLOBAL(kvmppc_entry_trampoline)
 
 	li	r6, MSR_IR | MSR_DR
 	andc	r6, r5, r6	/* Clear DR and IR in MSR value */
-#ifdef CONFIG_PPC_BOOK3S_32
 	/*
 	 * Set EE in HOST_MSR so that it's enabled when we get into our
-	 * C exit handler function.  On 64-bit we delay enabling
-	 * interrupts until we have finished transferring stuff
-	 * to or from the PACA.
+	 * C exit handler function.
 	 */
 	ori	r5, r5, MSR_EE
-#endif
 	mtsrr0	r7
 	mtsrr1	r6
 	RFI
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 53e65a210b9..0591e05db74 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -681,7 +681,7 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret, s;
-	struct thread_struct thread;
+	struct debug_reg debug;
 #ifdef CONFIG_PPC_FPU
 	struct thread_fp_state fp;
 	int fpexc_mode;
@@ -723,9 +723,9 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
 
 	/* Switch to guest debug context */
-	thread.debug = vcpu->arch.shadow_dbg_reg;
-	switch_booke_debug_regs(&thread);
-	thread.debug = current->thread.debug;
+	debug = vcpu->arch.shadow_dbg_reg;
+	switch_booke_debug_regs(&debug);
+	debug = current->thread.debug;
 	current->thread.debug = vcpu->arch.shadow_dbg_reg;
 
 	kvmppc_fix_ee_before_entry();
@@ -736,8 +736,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	   We also get here with interrupts enabled. */
 
 	/* Switch back to user space debug context */
-	switch_booke_debug_regs(&thread);
-	current->thread.debug = thread.debug;
+	switch_booke_debug_regs(&debug);
+	current->thread.debug = debug;
 
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index e7e59e4f989..79d83cad3d6 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -24,25 +24,25 @@ static int opal_lpc_chip_id = -1;
 static u8 opal_lpc_inb(unsigned long port)
 {
 	int64_t rc;
-	uint32_t data;
+	__be32 data;
 
 	if (opal_lpc_chip_id < 0 || port > 0xffff)
 		return 0xff;
 	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 1);
-	return rc ? 0xff : data;
+	return rc ? 0xff : be32_to_cpu(data);
 }
 
 static __le16 __opal_lpc_inw(unsigned long port)
 {
 	int64_t rc;
-	uint32_t data;
+	__be32 data;
 
 	if (opal_lpc_chip_id < 0 || port > 0xfffe)
 		return 0xffff;
 	if (port & 1)
 		return (__le16)opal_lpc_inb(port) << 8 | opal_lpc_inb(port + 1);
 	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 2);
-	return rc ? 0xffff : data;
+	return rc ? 0xffff : be32_to_cpu(data);
 }
 static u16 opal_lpc_inw(unsigned long port)
 {
@@ -52,7 +52,7 @@ static u16 opal_lpc_inw(unsigned long port)
 static __le32 __opal_lpc_inl(unsigned long port)
 {
 	int64_t rc;
-	uint32_t data;
+	__be32 data;
 
 	if (opal_lpc_chip_id < 0 || port > 0xfffc)
 		return 0xffffffff;
@@ -62,7 +62,7 @@ static __le32 __opal_lpc_inl(unsigned long port)
 		       (__le32)opal_lpc_inb(port + 2) <<  8 |
 			       opal_lpc_inb(port + 3);
 	rc = opal_lpc_read(opal_lpc_chip_id, OPAL_LPC_IO, port, &data, 4);
-	return rc ? 0xffffffff : data;
+	return rc ? 0xffffffff : be32_to_cpu(data);
 }
 
 static u32 opal_lpc_inl(unsigned long port)
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4d99a8fd55a..4fbf276ac99 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -96,9 +96,11 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
 {
 	struct opal_scom_map *m = map;
 	int64_t rc;
+	__be64 v;
 
 	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_read(m->chip, m->addr + reg, (uint64_t *)__pa(value));
+	rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+	*value = be64_to_cpu(v);
 	return opal_xscom_err_xlate(rc);
 }
 
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e738007eae6..c9fecf09b8f 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -157,7 +157,7 @@ static void parse_ppp_data(struct seq_file *m)
 {
 	struct hvcall_ppp_data ppp_data;
 	struct device_node *root;
-	const int *perf_level;
+	const __be32 *perf_level;
 	int rc;
 
 	rc = h_get_ppp(&ppp_data);
@@ -201,7 +201,7 @@ static void parse_ppp_data(struct seq_file *m)
 		perf_level = of_get_property(root,
 				"ibm,partition-performance-parameters-level",
 					     NULL);
-		if (perf_level && (*perf_level >= 1)) {
+		if (perf_level && (be32_to_cpup(perf_level) >= 1)) {
 			seq_printf(m,
 			    "physical_procs_allocated_to_virtualization=%d\n",
 				   ppp_data.phys_platform_procs);
@@ -435,7 +435,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	int partition_potential_processors;
 	int partition_active_processors;
 	struct device_node *rtas_node;
-	const int *lrdrp = NULL;
+	const __be32 *lrdrp = NULL;
 
 	rtas_node = of_find_node_by_path("/rtas");
 	if (rtas_node)
@@ -444,7 +444,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	if (lrdrp == NULL) {
 		partition_potential_processors = vdso_data->processorCount;
 	} else {
-		partition_potential_processors = *(lrdrp + 4);
+		partition_potential_processors = be32_to_cpup(lrdrp + 4);
 	}
 	of_node_put(rtas_node);
 
@@ -654,7 +654,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
 	const char *model = "";
 	const char *system_id = "";
 	const char *tmp;
-	const unsigned int *lp_index_ptr;
+	const __be32 *lp_index_ptr;
 	unsigned int lp_index = 0;
 
 	seq_printf(m, "%s %s\n", MODULE_NAME, MODULE_VERS);
@@ -670,7 +670,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
 		lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
 					NULL);
 		if (lp_index_ptr)
-			lp_index = *lp_index_ptr;
+			lp_index = be32_to_cpup(lp_index_ptr);
 		of_node_put(rootdn);
 	}
 	seq_printf(m, "serial_number=%s\n", system_id);
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 6d2f0abce6f..0c882e83c4c 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -130,7 +130,8 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 {
 	struct device_node *dn;
 	struct pci_dn *pdn;
-	const u32 *req_msi;
+	const __be32 *p;
+	u32 req_msi;
 
 	pdn = pci_get_pdn(pdev);
 	if (!pdn)
@@ -138,19 +139,20 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
 
 	dn = pdn->node;
 
-	req_msi = of_get_property(dn, prop_name, NULL);
-	if (!req_msi) {
+	p = of_get_property(dn, prop_name, NULL);
+	if (!p) {
 		pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name);
 		return -ENOENT;
 	}
 
-	if (*req_msi < nvec) {
+	req_msi = be32_to_cpup(p);
+	if (req_msi < nvec) {
 		pr_debug("rtas_msi: %s requests < %d MSIs\n", prop_name, nvec);
 
-		if (*req_msi == 0) /* Be paranoid */
+		if (req_msi == 0) /* Be paranoid */
 			return -ENOSPC;
 
-		return *req_msi;
+		return req_msi;
 	}
 
 	return 0;
@@ -171,7 +173,7 @@ static int check_req_msix(struct pci_dev *pdev, int nvec)
 static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 {
 	struct device_node *dn;
-	const u32 *p;
+	const __be32 *p;
 
 	dn = of_node_get(pci_device_to_OF_node(dev));
 	while (dn) {
@@ -179,7 +181,7 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total)
 		if (p) {
 			pr_debug("rtas_msi: found prop on dn %s\n",
 				dn->full_name);
-			*total = *p;
+			*total = be32_to_cpup(p);
 			return dn;
 		}
 
@@ -232,13 +234,13 @@ struct msi_counts {
 static void *count_non_bridge_devices(struct device_node *dn, void *data)
 {
 	struct msi_counts *counts = data;
-	const u32 *p;
+	const __be32 *p;
 	u32 class;
 
 	pr_debug("rtas_msi: counting %s\n", dn->full_name);
 
 	p = of_get_property(dn, "class-code", NULL);
-	class = p ? *p : 0;
+	class = p ? be32_to_cpup(p) : 0;
 
 	if ((class >> 8) != PCI_CLASS_BRIDGE_PCI)
 		counts->num_devices++;
@@ -249,7 +251,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data)
 static void *count_spare_msis(struct device_node *dn, void *data)
 {
 	struct msi_counts *counts = data;
-	const u32 *p;
+	const __be32 *p;
 	int req;
 
 	if (dn == counts->requestor)
@@ -260,11 +262,11 @@ static void *count_spare_msis(struct device_node *dn, void *data)
 		req = 0;
 		p = of_get_property(dn, "ibm,req#msi", NULL);
 		if (p)
-			req = *p;
+			req = be32_to_cpup(p);
 
 		p = of_get_property(dn, "ibm,req#msi-x", NULL);
 		if (p)
-			req = max(req, (int)*p);
+			req = max(req, (int)be32_to_cpup(p));
 	}
 
 	if (req < counts->quota)
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 7bfaf58d466..d7096f2f775 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -43,8 +43,8 @@ static char nvram_buf[NVRW_CNT];	/* assume this is in the first 4GB */
 static DEFINE_SPINLOCK(nvram_lock);
 
 struct err_log_info {
-	int error_type;
-	unsigned int seq_num;
+	__be32 error_type;
+	__be32 seq_num;
 };
 
 struct nvram_os_partition {
@@ -79,9 +79,9 @@ static const char *pseries_nvram_os_partitions[] = {
 };
 
 struct oops_log_info {
-	u16 version;
-	u16 report_length;
-	u64 timestamp;
+	__be16 version;
+	__be16 report_length;
+	__be64 timestamp;
 } __attribute__((packed));
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
@@ -291,8 +291,8 @@ int nvram_write_os_partition(struct nvram_os_partition *part, char * buff,
 		length = part->size;
 	}
 
-	info.error_type = err_type;
-	info.seq_num = error_log_cnt;
+	info.error_type = cpu_to_be32(err_type);
+	info.seq_num = cpu_to_be32(error_log_cnt);
 
 	tmp_index = part->index;
 
@@ -364,8 +364,8 @@ int nvram_read_partition(struct nvram_os_partition *part, char *buff,
 	}
 
 	if (part->os_partition) {
-		*error_log_cnt = info.seq_num;
-		*err_type = info.error_type;
+		*error_log_cnt = be32_to_cpu(info.seq_num);
+		*err_type = be32_to_cpu(info.error_type);
 	}
 
 	return 0;
@@ -529,9 +529,9 @@ static int zip_oops(size_t text_len)
 		pr_err("nvram: logging uncompressed oops/panic report\n");
 		return -1;
 	}
-	oops_hdr->version = OOPS_HDR_VERSION;
-	oops_hdr->report_length = (u16) zipped_len;
-	oops_hdr->timestamp = get_seconds();
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(zipped_len);
+	oops_hdr->timestamp = cpu_to_be64(get_seconds());
 	return 0;
 }
 
@@ -574,9 +574,9 @@ static int nvram_pstore_write(enum pstore_type_id type,
 				clobbering_unread_rtas_event())
 		return -1;
 
-	oops_hdr->version = OOPS_HDR_VERSION;
-	oops_hdr->report_length = (u16) size;
-	oops_hdr->timestamp = get_seconds();
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(size);
+	oops_hdr->timestamp = cpu_to_be64(get_seconds());
 
 	if (compressed)
 		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
@@ -670,16 +670,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		size_t length, hdr_size;
 
 		oops_hdr = (struct oops_log_info *)buff;
-		if (oops_hdr->version < OOPS_HDR_VERSION) {
+		if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
 			/* Old format oops header had 2-byte record size */
 			hdr_size = sizeof(u16);
-			length = oops_hdr->version;
+			length = be16_to_cpu(oops_hdr->version);
 			time->tv_sec = 0;
 			time->tv_nsec = 0;
 		} else {
 			hdr_size = sizeof(*oops_hdr);
-			length = oops_hdr->report_length;
-			time->tv_sec = oops_hdr->timestamp;
+			length = be16_to_cpu(oops_hdr->report_length);
+			time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
 			time->tv_nsec = 0;
 		}
 		*buf = kmalloc(length, GFP_KERNEL);
@@ -889,13 +889,13 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 		kmsg_dump_get_buffer(dumper, false,
 				     oops_data, oops_data_sz, &text_len);
 		err_type = ERR_TYPE_KERNEL_PANIC;
-		oops_hdr->version = OOPS_HDR_VERSION;
-		oops_hdr->report_length = (u16) text_len;
-		oops_hdr->timestamp = get_seconds();
+		oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+		oops_hdr->report_length = cpu_to_be16(text_len);
+		oops_hdr->timestamp = cpu_to_be64(get_seconds());
 	}
 
 	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-		(int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type,
+		(int) (sizeof(*oops_hdr) + text_len), err_type,
 		++oops_count);
 
 	spin_unlock_irqrestore(&lock, flags);
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 5f93856cdf4..70670a2d9cf 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -113,7 +113,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
 	struct device_node *dn, *pdn;
 	struct pci_bus *bus;
-	const uint32_t *pcie_link_speed_stats;
+	const __be32 *pcie_link_speed_stats;
 
 	bus = bridge->bus;
 
@@ -122,7 +122,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		return 0;
 
 	for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
-		pcie_link_speed_stats = (const uint32_t *) of_get_property(pdn,
+		pcie_link_speed_stats = of_get_property(pdn,
 			"ibm,pcie-link-speed-stats", NULL);
 		if (pcie_link_speed_stats)
 			break;
@@ -135,7 +135,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		return 0;
 	}
 
-	switch (pcie_link_speed_stats[0]) {
+	switch (be32_to_cpup(pcie_link_speed_stats)) {
 	case 0x01:
 		bus->max_bus_speed = PCIE_SPEED_2_5GT;
 		break;
@@ -147,7 +147,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
 		break;
 	}
 
-	switch (pcie_link_speed_stats[1]) {
+	switch (be32_to_cpup(pcie_link_speed_stats)) {
 	case 0x01:
 		bus->cur_bus_speed = PCIE_SPEED_2_5GT;
 		break;
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 7b95f29e317..3baff31e58c 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -6,7 +6,7 @@ lib-y  = delay.o memmove.o memchr.o \
 	 checksum.o strlen.o div64.o div64-generic.o
 
 # Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
 	 ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
 	 udiv_qrnnd.o
 
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 8358dc14495..0f9e94537ee 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -619,7 +619,7 @@ static inline unsigned long pte_present(pte_t pte)
 }
 
 #define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 {
 	return pte_val(a) & _PAGE_VALID;
 }
@@ -847,7 +847,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
 	 *             and SUN4V pte layout, so this inline test is fine.
 	 */
-	if (likely(mm != &init_mm) && pte_accessible(orig))
+	if (likely(mm != &init_mm) && pte_accessible(mm, orig))
 		tlb_batch_add(mm, addr, ptep, orig, fullmm);
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e903c71f7e6..0952ecd60ec 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -26,6 +26,7 @@ config X86
 	select HAVE_AOUT if X86_32
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_INT128 if X86_64
 	select ARCH_WANTS_PROT_NUMA_PROT_NONE
 	select HAVE_IDE
 	select HAVE_OPROFILE
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3d199945870..bbc8b12fa44 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -452,9 +452,16 @@ static inline int pte_present(pte_t a)
 }
 
 #define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
-	return pte_flags(a) & _PAGE_PRESENT;
+	if (pte_flags(a) & _PAGE_PRESENT)
+		return true;
+
+	if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+			mm_tlb_flush_pending(mm))
+		return true;
+
+	return false;
 }
 
 static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 8729723636f..c8b051933b1 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -8,6 +8,12 @@
 DECLARE_PER_CPU(int, __preempt_count);
 
 /*
+ * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
+ * that a decrement hitting 0 means we can and should reschedule.
+ */
+#define PREEMPT_ENABLED	(0 + PREEMPT_NEED_RESCHED)
+
+/*
  * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
  * that think a non-zero value indicates we cannot preempt.
  */
@@ -74,6 +80,11 @@ static __always_inline void __preempt_count_sub(int val)
 	__this_cpu_add_4(__preempt_count, -val);
 }
 
+/*
+ * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
+ * a decrement which hits zero means we have no preempt_count and should
+ * reschedule.
+ */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
 	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fd00bb29425..c1a861829d8 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -262,11 +262,20 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
-#define EVENT_CONSTRAINT_END		\
-	EVENT_CONSTRAINT(0, 0, 0)
+/*
+ * We define the end marker as having a weight of -1
+ * to enable blacklisting of events using a counter bitmask
+ * of zero and thus a weight of zero.
+ * The end marker has a weight that cannot possibly be
+ * obtained from counting the bits in the bitmask.
+ */
+#define EVENT_CONSTRAINT_END { .weight = -1 }
 
+/*
+ * Check for end marker with weight == -1
+ */
 #define for_each_event_constraint(e, c)	\
-	for ((e) = (c); (e)->weight; (e)++)
+	for ((e) = (c); (e)->weight != -1; (e)++)
 
 /*
  * Extra registers for specific events.
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dd74e46828c..0596e8e0cc1 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -83,6 +83,12 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		pte_t pte = gup_get_pte(ptep);
 		struct page *page;
 
+		/* Similar to the PMD case, NUMA hinting must take slow path */
+		if (pte_numa(pte)) {
+			pte_unmap(ptep);
+			return 0;
+		}
+
 		if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
 			pte_unmap(ptep);
 			return 0;
@@ -167,6 +173,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
 			return 0;
 		if (unlikely(pmd_large(pmd))) {
+			/*
+			 * NUMA hinting faults need to be handled in the GUP
+			 * slowpath for accounting purposes and so that they
+			 * can be serialised against THP migration.
+			 */
+			if (pmd_numa(pmd))
+				return 0;
 			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
 				return 0;
 		} else {