20 files changed, 181 insertions, 266 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index e624f9646350..4717859fdd04 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -644,8 +644,19 @@ int main(void)
 	HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
 	HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
 	HSTATE_FIELD(HSTATE_PTID, ptid);
-	HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
-	HSTATE_FIELD(HSTATE_PMC, host_pmc);
+	HSTATE_FIELD(HSTATE_MMCR0, host_mmcr[0]);
+	HSTATE_FIELD(HSTATE_MMCR1, host_mmcr[1]);
+	HSTATE_FIELD(HSTATE_MMCRA, host_mmcr[2]);
+	HSTATE_FIELD(HSTATE_SIAR, host_mmcr[3]);
+	HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]);
+	HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]);
+	HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]);
+	HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]);
+	HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]);
+	HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]);
+	HSTATE_FIELD(HSTATE_PMC4, host_pmc[3]);
+	HSTATE_FIELD(HSTATE_PMC5, host_pmc[4]);
+	HSTATE_FIELD(HSTATE_PMC6, host_pmc[5]);
 	HSTATE_FIELD(HSTATE_PURR, host_purr);
 	HSTATE_FIELD(HSTATE_SPURR, host_spurr);
 	HSTATE_FIELD(HSTATE_DSCR, host_dscr);
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 40198d50b4c2..ae77b7e59889 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -607,19 +607,16 @@ static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *att
 {
 	struct cache_index_dir *index;
 	struct cache *cache;
-	int len;
-	int n = 0;
+	int ret;
 
 	index = kobj_to_cache_index_dir(k);
 	cache = index->cache;
-	len = PAGE_SIZE - 2;
 
-	if (len > 1) {
-		n = cpumask_scnprintf(buf, len, &cache->shared_cpu_map);
-		buf[n++] = '\n';
-		buf[n] = '\0';
-	}
-	return n;
+	ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb\n",
+			cpumask_pr_args(&cache->shared_cpu_map));
+	buf[ret++] = '\n';
+	buf[ret] = '\0';
+	return ret;
 }
 
 static struct kobj_attribute cache_shared_cpu_map_attr =
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 808405906336..f337666768a7 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1133,6 +1133,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.cpu_setup		= __setup_cpu_603,
+		.machine_check		= machine_check_generic,
 		.num_pmcs		= 4,
 		.oprofile_cpu_type	= "ppc/e300",
 		.oprofile_type		= PPC_OPROFILE_FSL_EMB,
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index e1b6d8e17289..3b2252e7731b 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -104,6 +104,13 @@
 int eeh_subsystem_flags;
 EXPORT_SYMBOL(eeh_subsystem_flags);
 
+/*
+ * EEH allowed maximal frozen times. If one particular PE's
+ * frozen count in last hour exceeds this limit, the PE will
+ * be forced to be offline permanently.
+ */
+int eeh_max_freezes = 5;
+
 /* Platform dependent EEH operations */
 struct eeh_ops *eeh_ops = NULL;
 
@@ -1652,8 +1659,22 @@ static int eeh_enable_dbgfs_get(void *data, u64 *val)
 	return 0;
 }
 
+static int eeh_freeze_dbgfs_set(void *data, u64 val)
+{
+	eeh_max_freezes = val;
+	return 0;
+}
+
+static int eeh_freeze_dbgfs_get(void *data, u64 *val)
+{
+	*val = eeh_max_freezes;
+	return 0;
+}
+
 DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get,
 			eeh_enable_dbgfs_set, "0x%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(eeh_freeze_dbgfs_ops, eeh_freeze_dbgfs_get,
+			eeh_freeze_dbgfs_set, "0x%llx\n");
 #endif
 
 static int __init eeh_init_proc(void)
@@ -1664,6 +1685,9 @@ static int __init eeh_init_proc(void)
 		debugfs_create_file("eeh_enable", 0600,
                                     powerpc_debugfs_root, NULL,
                                     &eeh_enable_dbgfs_ops);
+		debugfs_create_file("eeh_max_freezes", 0600,
+				    powerpc_debugfs_root, NULL,
+				    &eeh_freeze_dbgfs_ops);
 #endif
 	}
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index b17e793ba67e..d099540c0f56 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -667,7 +667,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 
 	eeh_pe_update_time_stamp(pe);
 	pe->freeze_count++;
-	if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
+	if (pe->freeze_count > eeh_max_freezes)
 		goto excess_failures;
 	pr_warn("EEH: This PCI device has failed %d times in the last hour\n",
 		pe->freeze_count);
@@ -806,7 +806,7 @@ perm_error:
 	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
 
 	/* Mark the PE to be removed permanently */
-	pe->freeze_count = EEH_MAX_ALLOWED_FREEZES + 1;
+	eeh_pe_state_mark(pe, EEH_PE_REMOVED);
 
 	/*
 	 * Shut down the device drivers for good. We mark
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 5a63e2b0f65b..1e4946c36f9e 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -239,10 +239,18 @@ static void *__eeh_pe_get(void *data, void *flag)
 	if (pe->type & EEH_PE_PHB)
 		return NULL;
 
-	/* We prefer PE address */
-	if (edev->pe_config_addr &&
-	   (edev->pe_config_addr == pe->addr))
+	/*
+	 * We prefer PE address. For most cases, we should
+	 * have non-zero PE address
+	 */
+	if (eeh_has_flag(EEH_VALID_PE_ZERO)) {
+		if (edev->pe_config_addr == pe->addr)
+			return pe;
+	} else {
+		if (edev->pe_config_addr &&
+		    (edev->pe_config_addr == pe->addr))
 		return pe;
+	}
 
 	/* Try BDF address */
 	if (edev->config_addr &&
@@ -518,8 +526,7 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 	struct pci_dev *pdev;
 
 	/* Keep the state of permanently removed PE intact */
-	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
-	    (state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING)))
+	if (pe->state & EEH_PE_REMOVED)
 		return NULL;
 
 	pe->state |= state;
@@ -592,8 +599,7 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 	struct pci_dev *pdev;
 
 	/* Keep the state of permanently removed PE intact */
-	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
-	    (state & EEH_PE_ISOLATED))
+	if (pe->state & EEH_PE_REMOVED)
 		return NULL;
 
 	pe->state &= ~state;
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 10a093579191..46fc0f4d8982 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -33,9 +33,6 @@
 #include <asm/ftrace.h>
 #include <asm/ptrace.h>
 
-#undef SHOW_SYSCALLS
-#undef SHOW_SYSCALLS_TASK
-
 /*
  * MSR_KERNEL is > 0x10000 on 4xx/Book-E since it include MSR_CE.
  */
@@ -307,9 +304,6 @@ _GLOBAL(DoSyscall)
 	lwz	r11,_CCR(r1)	/* Clear SO bit in CR */
 	rlwinm	r11,r11,0,4,2
 	stw	r11,_CCR(r1)
-#ifdef SHOW_SYSCALLS
-	bl	do_show_syscall
-#endif /* SHOW_SYSCALLS */
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* Return from syscalls can (and generally will) hard enable
 	 * interrupts. You aren't supposed to call a syscall with
@@ -337,7 +331,7 @@ _GLOBAL(DoSyscall)
 #endif /* CONFIG_TRACE_IRQFLAGS */
 	CURRENT_THREAD_INFO(r10, r1)
 	lwz	r11,TI_FLAGS(r10)
-	andi.	r11,r11,_TIF_SYSCALL_T_OR_A
+	andi.	r11,r11,_TIF_SYSCALL_DOTRACE
 	bne-	syscall_dotrace
 syscall_dotrace_cont:
 	cmplwi	0,r0,NR_syscalls
@@ -352,9 +346,6 @@ syscall_dotrace_cont:
 	blrl			/* Call handler */
 	.globl	ret_from_syscall
 ret_from_syscall:
-#ifdef SHOW_SYSCALLS
-	bl	do_show_syscall_exit
-#endif
 	mr	r6,r3
 	CURRENT_THREAD_INFO(r12, r1)
 	/* disable interrupts so current_thread_info()->flags can't change */
@@ -364,7 +355,7 @@ ret_from_syscall:
 	MTMSRD(r10)
 	lwz	r9,TI_FLAGS(r12)
 	li	r8,-_LAST_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
+	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	syscall_exit_work
 	cmplw	0,r3,r8
 	blt+	syscall_exit_cont
@@ -501,7 +492,7 @@ syscall_exit_work:
 	subi	r12,r12,TI_FLAGS
 	
 4:	/* Anything which requires enabling interrupts? */
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
+	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
 	beq	ret_from_except
 
 	/* Re-enable interrupts. There is no need to trace that with
@@ -523,74 +514,6 @@ syscall_exit_work:
 	bl	do_syscall_trace_leave
 	b	ret_from_except_full
 
-#ifdef SHOW_SYSCALLS
-do_show_syscall:
-#ifdef SHOW_SYSCALLS_TASK
-	lis	r11,show_syscalls_task@ha
-	lwz	r11,show_syscalls_task@l(r11)
-	cmp	0,r2,r11
-	bnelr
-#endif
-	stw	r31,GPR31(r1)
-	mflr	r31
-	lis	r3,7f@ha
-	addi	r3,r3,7f@l
-	lwz	r4,GPR0(r1)
-	lwz	r5,GPR3(r1)
-	lwz	r6,GPR4(r1)
-	lwz	r7,GPR5(r1)
-	lwz	r8,GPR6(r1)
-	lwz	r9,GPR7(r1)
-	bl	printk
-	lis	r3,77f@ha
-	addi	r3,r3,77f@l
-	lwz	r4,GPR8(r1)
-	mr	r5,r2
-	bl	printk
-	lwz	r0,GPR0(r1)
-	lwz	r3,GPR3(r1)
-	lwz	r4,GPR4(r1)
-	lwz	r5,GPR5(r1)
-	lwz	r6,GPR6(r1)
-	lwz	r7,GPR7(r1)
-	lwz	r8,GPR8(r1)
-	mtlr	r31
-	lwz	r31,GPR31(r1)
-	blr
-
-do_show_syscall_exit:
-#ifdef SHOW_SYSCALLS_TASK
-	lis	r11,show_syscalls_task@ha
-	lwz	r11,show_syscalls_task@l(r11)
-	cmp	0,r2,r11
-	bnelr
-#endif
-	stw	r31,GPR31(r1)
-	mflr	r31
-	stw	r3,RESULT(r1)	/* Save result */
-	mr	r4,r3
-	lis	r3,79f@ha
-	addi	r3,r3,79f@l
-	bl	printk
-	lwz	r3,RESULT(r1)
-	mtlr	r31
-	lwz	r31,GPR31(r1)
-	blr
-
-7:	.string	"syscall %d(%x, %x, %x, %x, %x, "
-77:	.string	"%x), current=%p\n"
-79:	.string	" -> %x\n"
-	.align	2,0
-
-#ifdef SHOW_SYSCALLS_TASK
-	.data
-	.globl	show_syscalls_task
-show_syscalls_task:
-	.long	-1
-	.text
-#endif
-#endif /* SHOW_SYSCALLS */
-
 /*
  * The fork/clone functions need to copy the full register set into
  * the child process. Therefore we need to save all the nonvolatile
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 194e46dcf08d..d180caf2d6de 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -49,8 +49,6 @@ exception_marker:
 	.section	".text"
 	.align 7
 
-#undef SHOW_SYSCALLS
-
 	.globl system_call_common
 system_call_common:
 	andi.	r10,r12,MSR_PR
@@ -142,16 +140,9 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	li	r10,1
 	std	r10,SOFTE(r1)
 
-#ifdef SHOW_SYSCALLS
-	bl	do_show_syscall
-	REST_GPR(0,r1)
-	REST_4GPRS(3,r1)
-	REST_2GPRS(7,r1)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-#endif
 	CURRENT_THREAD_INFO(r11, r1)
 	ld	r10,TI_FLAGS(r11)
-	andi.	r11,r10,_TIF_SYSCALL_T_OR_A
+	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
 	bne	syscall_dotrace
 .Lsyscall_dotrace_cont:
 	cmpldi	0,r0,NR_syscalls
@@ -178,12 +169,8 @@ system_call:			/* label this so stack traces look sane */
 	mtctr   r12
 	bctrl			/* Call handler */
 
-syscall_exit:
+.Lsyscall_exit:
 	std	r3,RESULT(r1)
-#ifdef SHOW_SYSCALLS
-	bl	do_show_syscall_exit
-	ld	r3,RESULT(r1)
-#endif
 	CURRENT_THREAD_INFO(r12, r1)
 
 	ld	r8,_MSR(r1)
@@ -214,7 +201,7 @@ syscall_exit:
 
 	ld	r9,TI_FLAGS(r12)
 	li	r11,-_LAST_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
+	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
 	bne-	syscall_exit_work
 	cmpld	r3,r11
 	ld	r5,_CCR(r1)
@@ -270,7 +257,7 @@ syscall_dotrace:
 
 syscall_enosys:
 	li	r3,-ENOSYS
-	b	syscall_exit
+	b	.Lsyscall_exit
 	
 syscall_exit_work:
 #ifdef CONFIG_PPC_BOOK3S
@@ -307,7 +294,7 @@ syscall_exit_work:
 
 4:	/* Anything else left to do? */
 	SET_DEFAULT_THREAD_PPR(r3, r10)		/* Set thread.ppr = 3 */
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
+	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
 	beq	ret_from_except_lite
 
 	/* Re-enable interrupts */
@@ -347,33 +334,33 @@ _GLOBAL(save_nvgprs)
 _GLOBAL(ppc_fork)
 	bl	save_nvgprs
 	bl	sys_fork
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 _GLOBAL(ppc_vfork)
 	bl	save_nvgprs
 	bl	sys_vfork
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 _GLOBAL(ppc_clone)
 	bl	save_nvgprs
 	bl	sys_clone
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 _GLOBAL(ppc32_swapcontext)
 	bl	save_nvgprs
 	bl	compat_sys_swapcontext
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 _GLOBAL(ppc64_swapcontext)
 	bl	save_nvgprs
 	bl	sys_swapcontext
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
 	REST_NVGPRS(r1)
 	li	r3,0
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 _GLOBAL(ret_from_kernel_thread)
 	bl	schedule_tail
@@ -385,7 +372,7 @@ _GLOBAL(ret_from_kernel_thread)
 #endif
 	blrl
 	li	r3,0
-	b	syscall_exit
+	b	.Lsyscall_exit
 
 /*
  * This routine switches between two different tasks.  The process
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index d99aac0d69f1..9b53fe139bf6 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -319,36 +319,29 @@ InstructionTLBMiss:
 	 * pin the first 8MB of kernel memory */
 	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
 #endif
-	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
 #ifdef CONFIG_MODULES
 	beq	3f
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
-	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 3:
 #endif
-	/* Extract level 1 index */
-	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
-	lwzx	r11, r10, r11	/* Get the level 1 entry */
-	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
-	beq	2f		/* If zero, don't try to find a pte */
-
-	/* We have a pte table, so load the MI_TWC with the attributes
-	 * for this "segment."
-	 */
+	/* Insert level 1 index */
+	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+
+	/* Load the MI_TWC with the attributes for this "segment." */
 	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
-	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
+	rlwinm	r11, r11,0,0,19	/* Extract page descriptor page address */
 	/* Extract level 2 index */
-	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
 	lwzx	r10, r10, r11	/* Get the pte */
 
 #ifdef CONFIG_SWAP
-	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
-	cmpwi	cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT
-	li	r11, RPN_PATTERN
-	bne-	cr0, 2f
-#else
-	li	r11, RPN_PATTERN
+	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
+	and	r11, r11, r10
+	rlwimi	r10, r11, 0, _PAGE_PRESENT
 #endif
+	li	r11, RPN_PATTERN
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 21 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
@@ -366,21 +359,6 @@ InstructionTLBMiss:
 	mfspr	r10, SPRN_SPRG_SCRATCH2
 	EXCEPTION_EPILOG_0
 	rfi
-2:
-	mfspr	r10, SPRN_SRR1
-	/* clear all error bits as TLB Miss
-	 * sets a few unconditionally
-	*/
-	rlwinm	r10, r10, 0, 0xffff
-	mtspr	SPRN_SRR1, r10
-
-	/* Restore registers */
-#ifdef CONFIG_8xx_CPU6
-	mfspr	r3, SPRN_DAR
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
-#endif
-	mfspr	r10, SPRN_SPRG_SCRATCH2
-	b	InstructionTLBError1
 
 	. = 0x1200
 DataStoreTLBMiss:
@@ -395,20 +373,16 @@ DataStoreTLBMiss:
 	 * kernel page tables.
 	 */
 	andis.	r11, r10, 0x8000
-	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
 	beq	3f
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
-	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
 3:
-	/* Extract level 1 index */
-	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
-	lwzx	r11, r10, r11	/* Get the level 1 entry */
-	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
-	beq	2f		/* If zero, don't try to find a pte */
+	/* Insert level 1 index */
+	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
 
 	/* We have a pte table, so load fetch the pte from the table.
 	 */
-	mfspr	r10, SPRN_MD_EPN	/* Get address of fault */
 	/* Extract level 2 index */
 	rlwinm	r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
 	rlwimi	r10, r11, 0, 0, 32 - PAGE_SHIFT - 1	/* Add level 2 base */
@@ -441,16 +415,13 @@ DataStoreTLBMiss:
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
 #endif
-	/* invert RW */
-	xori	r10, r10, _PAGE_RW
-
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-2:	li	r11, RPN_PATTERN
+	li	r11, RPN_PATTERN
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	MTSPR_CPU6(SPRN_MD_RPN, r10, r3)	/* Update TLB entry */
 
@@ -469,10 +440,7 @@ DataStoreTLBMiss:
  */
 	. = 0x1300
 InstructionTLBError:
-	EXCEPTION_PROLOG_0
-InstructionTLBError1:
-	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
+	EXCEPTION_PROLOG
 	mr	r4,r12
 	mr	r5,r9
 	andis.	r10,r5,0x4000
@@ -532,30 +500,21 @@ DARFixed:/* Return from dcbx instruction bug workaround */
  /* define if you don't want to use self modifying code */
 #define NO_SELF_MODIFYING_CODE
 FixupDAR:/* Entry point for dcbx workaround. */
-#ifdef CONFIG_8xx_CPU6
-	mtspr	SPRN_DAR, r3
-#endif
 	mtspr	SPRN_SPRG_SCRATCH2, r10
 	/* fetch instruction from memory. */
 	mfspr	r10, SPRN_SRR0
 	andis.	r11, r10, 0x8000	/* Address >= 0x80000000 */
-	mfspr	r11, SPRN_M_TW	/* Get level 1 table base address */
-	beq-	3f		/* Branch if user space */
-	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
-	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
-	/* Extract level 1 index */
-3:	rlwinm	r10, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
-	lwzx	r11, r10, r11	/* Get the level 1 entry */
-	rlwinm	r10, r11,0,0,19	/* Extract page descriptor page address */
-	mfspr	r11, SPRN_SRR0	/* Get effective address of fault */
-	/* Extract level 2 index */
-	rlwinm	r11, r11, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
-	lwzx	r11, r10, r11	/* Get the pte */
-#ifdef CONFIG_8xx_CPU6
-	mfspr	r3, SPRN_DAR
-#endif
+	mfspr	r11, SPRN_M_TW	/* Get level 1 table */
+	beq	3f
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@ha
+	/* Insert level 1 index */
+3:	rlwimi	r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29
+	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
+	rlwinm	r11, r11,0,0,19	/* Extract page descriptor page address */
+	/* Insert level 2 index */
+	rlwimi	r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29
+	lwz	r11, 0(r11)	/* Get the pte */
 	/* concat physical page address(r11) and page offset(r10) */
-	mfspr	r10, SPRN_SRR0
 	rlwimi	r11, r10, 0, 32 - PAGE_SHIFT, 31
 	lwz	r11,0(r11)
 /* Check if it really is a dcbx instruction. */
@@ -705,8 +664,7 @@ start_here:
 	 * init's THREAD like the context switch code does, but this is
 	 * easier......until someone changes init's static structures.
 	 */
-	lis	r6, swapper_pg_dir@h
-	ori	r6, r6, swapper_pg_dir@l
+	lis	r6, swapper_pg_dir@ha
 	tophys(r6,r6)
 #ifdef CONFIG_8xx_CPU6
 	lis	r4, cpu6_errata_word@h
@@ -885,23 +843,28 @@ _GLOBAL(set_context)
 	stw	r4, 0x4(r5)
 #endif
 
+	/* Register M_TW will contain base address of level 1 table minus the
+	 * lower part of the kernel PGDIR base address, so that all accesses to
+	 * level 1 table are done relative to lower part of kernel PGDIR base
+	 * address.
+	 */
+	li	r5, (swapper_pg_dir-PAGE_OFFSET)@l
+	sub	r4, r4, r5
+	tophys	(r4, r4)
 #ifdef CONFIG_8xx_CPU6
 	lis	r6, cpu6_errata_word@h
 	ori	r6, r6, cpu6_errata_word@l
-	tophys	(r4, r4)
 	li	r7, 0x3f80
 	stw	r7, 12(r6)
 	lwz	r7, 12(r6)
-        mtspr   SPRN_M_TW, r4               /* Update MMU base address */
+#endif
+	mtspr	SPRN_M_TW, r4		/* Update pointeur to level 1 table */
+#ifdef CONFIG_8xx_CPU6
 	li	r7, 0x3380
 	stw	r7, 12(r6)
 	lwz	r7, 12(r6)
-        mtspr   SPRN_M_CASID, r3             /* Update context */
-#else
-        mtspr   SPRN_M_CASID,r3		/* Update context */
-	tophys	(r4, r4)
-	mtspr	SPRN_M_TW, r4		/* and pgd */
 #endif
+	mtspr	SPRN_M_CASID, r3	/* Update context */
 	SYNC
 	blr
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index f96d1ec24189..1a74446fd9e5 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -96,8 +96,6 @@ int default_machine_kexec_prepare(struct kimage *image)
 	return 0;
 }
 
-#define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)
-
 static void copy_segments(unsigned long ind)
 {
 	unsigned long entry;
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index d6e195e8cd4c..5a23b69f8129 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -115,6 +115,14 @@ static struct slb_shadow * __init init_slb_shadow(int cpu)
 {
 	struct slb_shadow *s = &slb_shadow[cpu];
 
+	/*
+	 * When we come through here to initialise boot_paca, the slb_shadow
+	 * buffers are not allocated yet. That's OK, we'll get one later in
+	 * boot, but make sure we don't corrupt memory at 0.
+	 */
+	if (!slb_shadow)
+		return NULL;
+
 	s->persistent = cpu_to_be32(SLB_NUM_BOLTED);
 	s->buffer_length = cpu_to_be32(sizeof(*s));
 
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 1f61fab59d9b..83df3075d3df 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -147,10 +147,8 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
 	/* PHB nodes themselves must not match */
 	update_dn_pci_info(dn, phb);
 	pdn = dn->data;
-	if (pdn) {
+	if (pdn)
 		pdn->devfn = pdn->busno = -1;
-		pdn->phb = phb;
-	}
 
 	/* Update dn->phb ptrs for new phb and children devices */
 	traverse_pci_devices(dn, update_dn_pci_info, phb);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 6a799b3cc6b4..b8e15c678960 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -652,9 +652,6 @@ void __init early_init_devtree(void *params)
 	if (!early_init_dt_verify(params))
 		panic("BUG: Failed verifying flat device tree, bad version?");
 
-	/* Setup flat device-tree pointer */
-	initial_boot_params = params;
-
 #ifdef CONFIG_PPC_RTAS
 	/* Some machines might need RTAS info for debugging, grab it now. */
 	of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 4af905e81ab0..21c45a2d0706 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -897,7 +897,7 @@ int rtas_offline_cpus_mask(cpumask_var_t cpus)
 }
 EXPORT_SYMBOL(rtas_offline_cpus_mask);
 
-int rtas_ibm_suspend_me(struct rtas_args *args)
+int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
 {
 	long state;
 	long rc;
@@ -911,8 +911,7 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 		return -ENOSYS;
 
 	/* Make sure the state is valid */
-	rc = plpar_hcall(H_VASI_STATE, retbuf,
-			 ((u64)args->args[0] << 32) | args->args[1]);
+	rc = plpar_hcall(H_VASI_STATE, retbuf, handle);
 
 	state = retbuf[0];
 
@@ -920,12 +919,12 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc);
 		return rc;
 	} else if (state == H_VASI_ENABLED) {
-		args->args[args->nargs] = RTAS_NOT_SUSPENDABLE;
+		*vasi_return = RTAS_NOT_SUSPENDABLE;
 		return 0;
 	} else if (state != H_VASI_SUSPENDING) {
 		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n",
 		       state);
-		args->args[args->nargs] = -1;
+		*vasi_return = -1;
 		return 0;
 	}
 
@@ -973,7 +972,7 @@ out:
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
-int rtas_ibm_suspend_me(struct rtas_args *args)
+int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
 {
 	return -ENOSYS;
 }
@@ -1053,7 +1052,16 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 
 	/* Need to handle ibm,suspend_me call specially */
 	if (token == ibm_suspend_me_token) {
-		rc = rtas_ibm_suspend_me(&args);
+
+		/*
+		 * rtas_ibm_suspend_me assumes args are in cpu endian, or at least the
+		 * hcall within it requires it.
+		 */
+		int vasi_rc = 0;
+		u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
+		              | be32_to_cpu(args.args[1]);
+		rc = rtas_ibm_suspend_me(handle, &vasi_rc);
+		args.rets[0] = cpu_to_be32(vasi_rc);
 		if (rc)
 			return rc;
 		goto copy_return;
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b171001698ff..d3a831ac0f92 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1231,7 +1231,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 	int tm_restore = 0;
 #endif
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	rt_sf = (struct rt_sigframe __user *)
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
@@ -1504,7 +1504,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
 	sc = &sf->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 2cb0c94cafa5..c7c24d2e2bdb 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -666,7 +666,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
 		goto badframe;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8b2d2dc8ef10..6e19afa35a15 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -434,20 +434,6 @@ void generic_cpu_die(unsigned int cpu)
 	printk(KERN_ERR "CPU%d didn't die...\n", cpu);
 }
 
-void generic_mach_cpu_die(void)
-{
-	unsigned int cpu;
-
-	local_irq_disable();
-	idle_task_exit();
-	cpu = smp_processor_id();
-	printk(KERN_DEBUG "CPU%d offline\n", cpu);
-	__this_cpu_write(cpu_state, CPU_DEAD);
-	smp_wmb();
-	while (__this_cpu_read(cpu_state) != CPU_UP_PREPARE)
-		cpu_relax();
-}
-
 void generic_set_cpu_dead(unsigned int cpu)
 {
 	per_cpu(cpu_state, cpu) = CPU_DEAD;
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index cd9be9aa016d..b2702e87db0d 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -121,17 +121,3 @@ long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
 	return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low,
 			     (u64)len_high << 32 | len_low, advice);
 }
-
-void do_show_syscall(unsigned long r3, unsigned long r4, unsigned long r5,
-		     unsigned long r6, unsigned long r7, unsigned long r8,
-		     struct pt_regs *regs)
-{
-	printk("syscall %ld(%lx, %lx, %lx, %lx, %lx, %lx) regs=%p current=%p"
-	       " cpu=%d\n", regs->gpr[0], r3, r4, r5, r6, r7, r8, regs,
-	       current, smp_processor_id());
-}
-
-void do_show_syscall_exit(unsigned long r3)
-{
-	printk(" -> %lx, current=%p cpu=%d\n", r3, current, smp_processor_id());
-}
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index fa7c4f12104f..2d7b33fab953 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -54,6 +54,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/irq_work.h>
+#include <linux/clk-provider.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
@@ -621,6 +622,38 @@ unsigned long long sched_clock(void)
 	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
 }
 
+
+#ifdef CONFIG_PPC_PSERIES
+
+/*
+ * Running clock - attempts to give a view of time passing for a virtualised
+ * kernels.
+ * Uses the VTB register if available otherwise a next best guess.
+ */
+unsigned long long running_clock(void)
+{
+	/*
+	 * Don't read the VTB as a host since KVM does not switch in host
+	 * timebase into the VTB when it takes a guest off the CPU, reading the
+	 * VTB would result in reading 'last switched out' guest VTB.
+	 *
+	 * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it
+	 * would be unsafe to rely only on the #ifdef above.
+	 */
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    cpu_has_feature(CPU_FTR_ARCH_207S))
+		return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
+
+	/*
+	 * This is a next best approximation without a VTB.
+	 * On a host which is running bare metal there should never be any stolen
+	 * time and on a host which doesn't do any virtualisation TB *should* equal
+	 * VTB so it makes no difference anyway.
+	 */
+	return local_clock() - cputime_to_nsecs(kcpustat_this_cpu->cpustat[CPUTIME_STEAL]);
+}
+#endif
+
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
@@ -943,6 +976,10 @@ void __init time_init(void)
 
 	init_decrementer_clockevent();
 	tick_setup_hrtimer_broadcast();
+
+#ifdef CONFIG_COMMON_CLK
+	of_clk_init(NULL);
+#endif
 }
 
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e6595b72269b..19e4744b6eba 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1707,21 +1707,6 @@ void altivec_assist_exception(struct pt_regs *regs)
 }
 #endif /* CONFIG_ALTIVEC */
 
-#ifdef CONFIG_VSX
-void vsx_assist_exception(struct pt_regs *regs)
-{
-	if (!user_mode(regs)) {
-		printk(KERN_EMERG "VSX assist exception in kernel mode"
-		       " at %lx\n", regs->nip);
-		die("Kernel VSX assist exception", regs, SIGILL);
-	}
-
-	flush_vsx_to_thread(current);
-	printk(KERN_INFO "VSX assist not supported at %lx\n", regs->nip);
-	_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-}
-#endif /* CONFIG_VSX */
-
 #ifdef CONFIG_FSL_BOOKE
 void CacheLockingException(struct pt_regs *regs, unsigned long address,
 			   unsigned long error_code)