Merge branch 'perf/urgent' into perf/core

Pick up the latest fixes, refresh the development tree.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

32 files changed, 253 insertions, 169 deletions

diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 4177b62240c2..a618dfc13e4c 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -58,7 +58,6 @@
 		compatible = "fsl,mpc5121-immr";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		#interrupt-cells = <2>;
 		ranges = <0x0 0x80000000 0x400000>;
 		reg = <0x80000000 0x400000>;
 		bus-frequency = <66000000>;	// 66 MHz ips bus
@@ -189,6 +188,10 @@
 			reg = <0xA000 0x1000>;
 		};
 
+		// disable USB1 port
+		// TODO:
+		// correct pinmux config and fix USB3320 ulpi dependency
+		// before re-enabling it
 		usb@3000 {
 			compatible = "fsl,mpc5121-usb2-dr";
 			reg = <0x3000 0x400>;
@@ -197,6 +200,7 @@
 			interrupts = <43 0x8>;
 			dr_mode = "host";
 			phy_type = "ulpi";
+			status = "disabled";
 		};
 
 		// 5125 PSCs are not 52xx or 5121 PSC compatible
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 894662a5d4d5..243ce69ad685 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -284,7 +284,7 @@ do_kvm_##n:								\
 	subi	r1,r1,INT_FRAME_SIZE;	/* alloc frame on kernel stack	*/ \
 	beq-	1f;							   \
 	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
-1:	cmpdi	cr1,r1,0;		/* check if r1 is in userspace	*/ \
+1:	cmpdi	cr1,r1,-INT_FRAME_SIZE;	/* check if r1 is in userspace	*/ \
 	blt+	cr1,3f;			/* abort if it is		*/ \
 	li	r1,(n);			/* will be reloaded later	*/ \
 	sth	r1,PACA_TRAP_SAVE(r13);					   \
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 4a594b76674d..bc23b1ba7980 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 0bd9348a4db9..192917d2239c 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 033c06be1d84..7bdcf340016c 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 9ee12610af02..aace90547614 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/include/asm/unaligned.h b/arch/powerpc/include/asm/unaligned.h
index 5f1b1e3c2137..8296381ae432 100644
--- a/arch/powerpc/include/asm/unaligned.h
+++ b/arch/powerpc/include/asm/unaligned.h
@@ -4,13 +4,18 @@
 #ifdef __KERNEL__
 
 /*
- * The PowerPC can do unaligned accesses itself in big endian mode.
+ * The PowerPC can do unaligned accesses itself based on its endian mode.
  */
 #include <linux/unaligned/access_ok.h>
 #include <linux/unaligned/generic.h>
 
+#ifdef __LITTLE_ENDIAN__
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
+#else
 #define get_unaligned	__get_unaligned_be
 #define put_unaligned	__put_unaligned_be
+#endif
 
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_UNALIGNED_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2ea5cc033ec8..d3de01066f7d 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 779a78c26435..11c1d069d920 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/head_64.S b/arch/powerpc/kernel/head_64.S
index 2ae41aba4053..4f0946de2d5c 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -80,6 +80,7 @@ END_FTR_SECTION(0, 1)
 	 * of the function that the cpu should jump to to continue
 	 * initialization.
 	 */
+	.balign 8
 	.globl  __secondary_hold_spinloop
 __secondary_hold_spinloop:
 	.llong	0x0
@@ -470,6 +471,7 @@ _STATIC(__after_prom_start)
 	mtctr	r8
 	bctr
 
+.balign 8
 p_end:	.llong	_end - _stext
 
 4:	/* Now copy the rest of the kernel up to _end */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3386d8ab7eb0..4a96556fd2d4 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/prom_init.c b/arch/powerpc/kernel/prom_init.c
index cb64a6e1dc51..078145acf7fb 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1986,19 +1986,23 @@ static void __init prom_init_stdout(void)
 	/* Get the full OF pathname of the stdout device */
 	memset(path, 0, 256);
 	call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
-	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
-	val = cpu_to_be32(stdout_node);
-	prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
-		     &val, sizeof(val));
 	prom_printf("OF stdout device is: %s\n", of_stdout_device);
 	prom_setprop(prom.chosen, "/chosen", "linux,stdout-path",
 		     path, strlen(path) + 1);
 
-	/* If it's a display, note it */
-	memset(type, 0, sizeof(type));
-	prom_getprop(stdout_node, "device_type", type, sizeof(type));
-	if (strcmp(type, "display") == 0)
-		prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+	/* instance-to-package fails on PA-Semi */
+	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
+	if (stdout_node != PROM_ERROR) {
+		val = cpu_to_be32(stdout_node);
+		prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
+			     &val, sizeof(val));
+
+		/* If it's a display, note it */
+		memset(type, 0, sizeof(type));
+		prom_getprop(stdout_node, "device_type", type, sizeof(type));
+		if (strcmp(type, "display") == 0)
+			prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+	}
 }
 
 static int __init prom_find_machine_type(void)
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 75fb40498b41..2e3d2bf536c5 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 febc80445d25..bc76cc6b419c 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 a3b64f3bf9a2..c1cf4a1522d9 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 f3ff587a8b7d..c5d148434c08 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 072287f1c3bc..b51d5db78068 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 9c515440ad1a..8689e2e30857 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 bc8de75b1925..be4fa04a37c9 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 f4dd041c14ea..f779450cb07c 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 fe14ca3dd171..5b9e9063cfaf 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 a38c4c9edab8..c3c5231adade 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 53e65a210b9a..0591e05db74b 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/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index d73a59014900..596a285c0755 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -9,6 +9,14 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 
+#ifdef __BIG_ENDIAN__
+#define sLd sld		/* Shift towards low-numbered address. */
+#define sHd srd		/* Shift towards high-numbered address. */
+#else
+#define sLd srd		/* Shift towards low-numbered address. */
+#define sHd sld		/* Shift towards high-numbered address. */
+#endif
+
 	.align	7
 _GLOBAL(__copy_tofrom_user)
 BEGIN_FTR_SECTION
@@ -118,10 +126,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 24:	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
 25:	ld	r0,8(r4)
-	sld	r6,r9,r10
+	sLd	r6,r9,r10
 26:	ldu	r9,16(r4)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	or	r7,r7,r6
 	blt	cr6,79f
 27:	ld	r0,8(r4)
@@ -129,35 +137,35 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 28:	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
 29:	ldu	r9,8(r4)
-	sld	r8,r0,r10
+	sLd	r8,r0,r10
 	addi	r3,r3,-8
 	blt	cr6,5f
 30:	ld	r0,8(r4)
-	srd	r12,r9,r11
-	sld	r6,r9,r10
+	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 31:	ldu	r9,16(r4)
 	or	r12,r8,r12
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	addi	r3,r3,16
 	beq	cr6,78f
 
 1:	or	r7,r7,r6
 32:	ld	r0,8(r4)
 76:	std	r12,8(r3)
-2:	srd	r12,r9,r11
-	sld	r6,r9,r10
+2:	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 33:	ldu	r9,16(r4)
 	or	r12,r8,r12
 77:	stdu	r7,16(r3)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	bdnz	1b
 
 78:	std	r12,8(r3)
 	or	r7,r7,r6
 79:	std	r7,16(r3)
-5:	srd	r12,r9,r11
+5:	sHd	r12,r9,r11
 	or	r12,r8,r12
 80:	std	r12,24(r3)
 	bne	6f
@@ -165,23 +173,38 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	blr
 6:	cmpwi	cr1,r5,8
 	addi	r3,r3,32
-	sld	r9,r9,r10
+	sLd	r9,r9,r10
 	ble	cr1,7f
 34:	ld	r0,8(r4)
-	srd	r7,r0,r11
+	sHd	r7,r0,r11
 	or	r9,r7,r9
 7:
 	bf	cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,32
+#endif
 94:	stw	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,32
+#endif
 	addi	r3,r3,4
 1:	bf	cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,16
+#endif
 95:	sth	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,16
+#endif
 	addi	r3,r3,2
 2:	bf	cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,8
+#endif
 96:	stb	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,8
+#endif
 3:	li	r3,0
 	blr
 
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 02245cee7818..d7ddcee7feb8 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -36,7 +36,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static char *hub_diag = NULL;
 static int ioda_eeh_nb_init = 0;
 
 static int ioda_eeh_event(struct notifier_block *nb,
@@ -140,15 +139,6 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 		ioda_eeh_nb_init = 1;
 	}
 
-	/* We needn't HUB diag-data on PHB3 */
-	if (phb->type == PNV_PHB_IODA1 && !hub_diag) {
-		hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-		if (!hub_diag) {
-			pr_err("%s: Out of memory !\n", __func__);
-			return -ENOMEM;
-		}
-	}
-
 #ifdef CONFIG_DEBUG_FS
 	if (phb->dbgfs) {
 		debugfs_create_file("err_injct_outbound", 0600,
@@ -633,11 +623,10 @@ static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 static void ioda_eeh_hub_diag(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
-	struct OpalIoP7IOCErrorData *data;
+	struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag;
 	long rc;
 
-	data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag;
-	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE);
+	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n",
 			   __func__, phb->hub_id, rc);
@@ -820,14 +809,15 @@ static void ioda_eeh_phb_diag(struct pci_controller *hose)
 	struct OpalIoPhbErrorCommon *common;
 	long rc;
 
-	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
 			    __func__, hose->global_number, rc);
 		return;
 	}
 
+	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
 	switch (common->ioType) {
 	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
 		ioda_eeh_p7ioc_phb_diag(hose, common);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index e7e59e4f9892..79d83cad3d67 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 4d99a8fd55ac..4fbf276ac99e 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/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 911c24ef033e..1ed8d5f40f5a 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -172,11 +172,13 @@ struct pnv_phb {
 		} ioda;
 	};
 
-	/* PHB status structure */
+	/* PHB and hub status structure */
 	union {
 		unsigned char			blob[PNV_PCI_DIAG_BUF_SIZE];
 		struct OpalIoP7IOCPhbErrorData	p7ioc;
+		struct OpalIoP7IOCErrorData 	hub_diag;
 	} diag;
+
 };
 
 extern struct pci_ops pnv_pci_ops;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e738007eae64..c9fecf09b8fa 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 6d2f0abce6fa..0c882e83c4ce 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 7bfaf58d4664..d7096f2f7751 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 5f93856cdf47..70670a2d9cf2 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;