23 files changed, 766 insertions, 524 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 8f619342f14c..b4f0e360e414 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -7,7 +7,7 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 ifeq ($(CONFIG_PPC64),y)
-CFLAGS_prom_init.o	+= -mno-minimal-toc
+CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)
 endif
 ifeq ($(CONFIG_PPC32),y)
 CFLAGS_prom_init.o      += -fPIC
@@ -75,8 +75,8 @@ endif
 obj64-$(CONFIG_HIBERNATION)	+= swsusp_asm64.o
 obj-$(CONFIG_MODULES)		+= module.o module_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_44x)		+= cpu_setup_44x.o
-obj-$(CONFIG_PPC_FSL_BOOK3E)	+= cpu_setup_fsl_booke.o dbell.o
-obj-$(CONFIG_PPC_BOOK3E_64)	+= dbell.o
+obj-$(CONFIG_PPC_FSL_BOOK3E)	+= cpu_setup_fsl_booke.o
+obj-$(CONFIG_PPC_DOORBELL)	+= dbell.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 
 extra-y				:= head_$(CONFIG_WORD_SIZE).o
@@ -91,7 +91,6 @@ obj-$(CONFIG_RELOCATABLE_PPC32)	+= reloc_32.o
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
-obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)	+= prom_init.o
 obj-$(CONFIG_MODULES)		+= ppc_ksyms.o
 obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
 obj-$(CONFIG_SMP)		+= smp.o
@@ -142,6 +141,7 @@ GCOV_PROFILE_kprobes.o := n
 extra-$(CONFIG_PPC_FPU)		+= fpu.o
 extra-$(CONFIG_ALTIVEC)		+= vector.o
 extra-$(CONFIG_PPC64)		+= entry_64.o
+extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE)	+= prom_init.o
 
 extra-y				+= systbl_chk.i
 $(obj)/systbl.o:		systbl_chk
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4e23ba2f3ca7..e39ca556e87f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -77,6 +77,7 @@ int main(void)
 	DEFINE(NMI_MASK, NMI_MASK);
 	DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr));
 	DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit));
+	DEFINE(TASKTHREADPPR, offsetof(struct task_struct, thread.ppr));
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index a892680668d8..9ebbc24bb23c 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -21,7 +21,7 @@
 #ifdef CONFIG_SMP
 void doorbell_setup_this_cpu(void)
 {
-	unsigned long tag = mfspr(SPRN_PIR) & 0x3fff;
+	unsigned long tag = mfspr(SPRN_DOORBELL_CPUTAG) & PPC_DBELL_TAG_MASK;
 
 	smp_muxed_ipi_set_data(smp_processor_id(), tag);
 }
@@ -30,7 +30,7 @@ void doorbell_cause_ipi(int cpu, unsigned long data)
 {
 	/* Order previous accesses vs. msgsnd, which is treated as a store */
 	mb();
-	ppc_msgsnd(PPC_DBELL, 0, data);
+	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, data);
 }
 
 void doorbell_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3d990d3bd8ba..44c733f4f829 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -62,8 +62,9 @@ system_call_common:
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
+	beq	2f			/* if from kernel mode */
 	ACCOUNT_CPU_USER_ENTRY(r10, r11)
-	std	r2,GPR2(r1)
+2:	std	r2,GPR2(r1)
 	std	r3,GPR3(r1)
 	mfcr	r2
 	std	r4,GPR4(r1)
@@ -226,6 +227,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	beq-	1f
 	ACCOUNT_CPU_USER_EXIT(r11, r12)
+	HMT_MEDIUM_LOW_HAS_PPR
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
@@ -302,6 +304,7 @@ syscall_exit_work:
 	subi	r12,r12,TI_FLAGS
 
 4:	/* Anything else left to do? */
+	SET_DEFAULT_THREAD_PPR(r3, r9)		/* Set thread.ppr = 3 */
 	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
 	beq	.ret_from_except_lite
 
@@ -770,6 +773,7 @@ fast_exception_return:
 	andi.	r0,r3,MSR_PR
 	beq	1f
 	ACCOUNT_CPU_USER_EXIT(r2, r4)
+	RESTORE_PPR(r2, r4)
 	REST_GPR(13, r1)
 1:
 	mtspr	SPRN_SRR1,r3
@@ -849,13 +853,22 @@ restore_check_irq_replay:
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
 	bl	.timer_interrupt
 	b	.ret_from_except
+#ifdef CONFIG_PPC_DOORBELL
+1:
 #ifdef CONFIG_PPC_BOOK3E
-1:	cmpwi	cr0,r3,0x280
+	cmpwi	cr0,r3,0x280
+#else
+	BEGIN_FTR_SECTION
+		cmpwi	cr0,r3,0xe80
+	FTR_SECTION_ELSE
+		cmpwi	cr0,r3,0xa00
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+#endif /* CONFIG_PPC_BOOK3E */
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
 	bl	.doorbell_exception
 	b	.ret_from_except
-#endif /* CONFIG_PPC_BOOK3E */
+#endif /* CONFIG_PPC_DOORBELL */
 1:	b	.ret_from_except /* What else to do here ? */
  
 unrecov_restore:
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 4684e33a26c3..ae54553eacd9 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -159,8 +159,9 @@ exc_##n##_common:							    \
 	std	r9,GPR9(r1);		/* save r9 in stackframe */	    \
 	std	r10,_NIP(r1);		/* save SRR0 to stackframe */	    \
 	std	r11,_MSR(r1);		/* save SRR1 to stackframe */	    \
+	beq	2f;			/* if from kernel mode */	    \
 	ACCOUNT_CPU_USER_ENTRY(r10,r11);/* accounting (uses cr0+eq) */	    \
-	ld	r3,excf+EX_R10(r13);	/* get back r10 */		    \
+2:	ld	r3,excf+EX_R10(r13);	/* get back r10 */		    \
 	ld	r4,excf+EX_R11(r13);	/* get back r11 */		    \
 	mfspr	r5,SPRN_SPRG_GEN_SCRATCH;/* get back r13 */		    \
 	std	r12,GPR12(r1);		/* save r12 in stackframe */	    \
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4665e82fa377..7a1c87cbb890 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -104,7 +104,7 @@ __start_interrupts:
 
 	.globl system_reset_pSeries;
 system_reset_pSeries:
-	HMT_MEDIUM;
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -158,7 +158,7 @@ machine_check_pSeries_1:
 	. = 0x300
 	.globl data_access_pSeries
 data_access_pSeries:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 BEGIN_FTR_SECTION
 	b	data_access_check_stab
@@ -170,7 +170,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -201,7 +201,7 @@ data_access_slb_pSeries:
 	. = 0x480
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -252,7 +252,7 @@ hardware_interrupt_hv:
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
 	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
-	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
+	MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
 
 	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
@@ -293,6 +293,8 @@ hv_exception_trampoline:
 	b	hmi_exception_hv
 	. = 0xe60
 	b	hmi_exception_hv
+	. = 0xe80
+	b	h_doorbell_hv
 
 	/* We need to deal with the Altivec unavailable exception
 	 * here which is at 0xf20, thus in the middle of the
@@ -322,10 +324,11 @@ vsx_unavailable_pSeries_1:
 	. = 0x1500
 	.global denorm_exception_hv
 denorm_exception_hv:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	mtspr	SPRN_SPRG_HSCRATCH0,r13
 	mfspr	r13,SPRN_SPRG_HPACA
 	std	r9,PACA_EXGEN+EX_R9(r13)
+	HMT_MEDIUM_PPR_SAVE(PACA_EXGEN, r9)
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	std	r11,PACA_EXGEN+EX_R11(r13)
 	std	r12,PACA_EXGEN+EX_R12(r13)
@@ -367,7 +370,7 @@ denorm_exception_hv:
 machine_check_pSeries:
 	.globl machine_check_fwnmi
 machine_check_fwnmi:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common,
 				 EXC_STD, KVMTEST, 0x200)
@@ -496,6 +499,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
 	mtspr	SPRN_HSRR0,r11
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
+	RESTORE_PPR_PACA(PACA_EXGEN, r10)
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
@@ -514,6 +518,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42)
 	STD_EXCEPTION_HV(., 0xe62, hmi_exception) /* need to flush cache ? */
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62)
+	MASKABLE_EXCEPTION_HV(., 0xe82, h_doorbell)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe82)
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
@@ -524,10 +530,12 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
 
 /*
- * An interrupt came in while soft-disabled. We set paca->irq_happened,
- * then, if it was a decrementer interrupt, we bump the dec to max and
- * and return, else we hard disable and return. This is called with
- * r10 containing the value to OR to the paca field.
+ * An interrupt came in while soft-disabled. We set paca->irq_happened, then:
+ * - If it was a decrementer interrupt, we bump the dec to max and and return.
+ * - If it was a doorbell we return immediately since doorbells are edge
+ *   triggered and won't automatically refire.
+ * - else we hard disable and return.
+ * This is called with r10 containing the value to OR to the paca field.
  */
 #define MASKED_INTERRUPT(_H)				\
 masked_##_H##interrupt:					\
@@ -535,13 +543,15 @@ masked_##_H##interrupt:					\
 	lbz	r11,PACAIRQHAPPENED(r13);		\
 	or	r11,r11,r10;				\
 	stb	r11,PACAIRQHAPPENED(r13);		\
-	andi.	r10,r10,PACA_IRQ_DEC;			\
-	beq	1f;					\
+	cmpwi	r10,PACA_IRQ_DEC;			\
+	bne	1f;					\
 	lis	r10,0x7fff;				\
 	ori	r10,r10,0xffff;				\
 	mtspr	SPRN_DEC,r10;				\
 	b	2f;					\
-1:	mfspr	r10,SPRN_##_H##SRR1;			\
+1:	cmpwi	r10,PACA_IRQ_DBELL;			\
+	beq	2f;					\
+	mfspr	r10,SPRN_##_H##SRR1;			\
 	rldicl	r10,r10,48,1; /* clear MSR_EE */	\
 	rotldi	r10,r10,16;				\
 	mtspr	SPRN_##_H##SRR1,r10;			\
@@ -558,8 +568,8 @@ masked_##_H##interrupt:					\
 
 /*
  * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains 0x500 or 0x900 to indicate which
- * kind of interrupt. MSR:EE is already off. We generate a
+ * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate
+ * which kind of interrupt. MSR:EE is already off. We generate a
  * stackframe like if a real interrupt had happened.
  *
  * Note: While MSR:EE is off, we need to make sure that _MSR
@@ -575,9 +585,18 @@ _GLOBAL(__replay_interrupt)
 	mflr	r11
 	mfcr	r9
 	ori	r12,r12,MSR_EE
-	andi.	r3,r3,0x0800
-	bne	decrementer_common
-	b	hardware_interrupt_common
+	cmpwi	r3,0x900
+	beq	decrementer_common
+	cmpwi	r3,0x500
+	beq	hardware_interrupt_common
+BEGIN_FTR_SECTION
+	cmpwi	r3,0xe80
+	beq	h_doorbell_common
+FTR_SECTION_ELSE
+	cmpwi	r3,0xa00
+	beq	doorbell_super_common
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
+	blr
 
 #ifdef CONFIG_PPC_PSERIES
 /*
@@ -586,7 +605,7 @@ _GLOBAL(__replay_interrupt)
 	.globl system_reset_fwnmi
       .align 7
 system_reset_fwnmi:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
 				 NOTEST, 0x100)
@@ -651,12 +670,21 @@ machine_check_common:
 	STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
 	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
 	STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
-	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
+#ifdef CONFIG_PPC_DOORBELL
+	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .doorbell_exception)
+#else
+	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .unknown_exception)
+#endif
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
 	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception)
 	STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
+#ifdef CONFIG_PPC_DOORBELL
+	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception)
+#else
+	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .unknown_exception)
+#endif
 	STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception)
 	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
 	STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception)
@@ -690,7 +718,7 @@ machine_check_common:
 	. = 0x4380
 	.globl data_access_slb_relon_pSeries
 data_access_slb_relon_pSeries:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -715,7 +743,7 @@ data_access_slb_relon_pSeries:
 	. = 0x4480
 	.globl instruction_access_slb_relon_pSeries
 instruction_access_slb_relon_pSeries:
-	HMT_MEDIUM
+	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, NOTEST, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -746,6 +774,7 @@ hardware_interrupt_relon_hv:
 	STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable)
 	MASKABLE_RELON_EXCEPTION_PSERIES(0x4900, 0x900, decrementer)
 	STD_RELON_EXCEPTION_HV(0x4980, 0x982, hdecrementer)
+	MASKABLE_RELON_EXCEPTION_PSERIES(0x4a00, 0xa00, doorbell_super)
 	STD_RELON_EXCEPTION_PSERIES(0x4b00, 0xb00, trap_0b)
 
 	. = 0x4c00
@@ -773,9 +802,8 @@ system_call_relon_pSeries:
 	. = 0x4e60
 	b	hmi_exception_relon_hv
 
-	/* For when we support the doorbell interrupt:
-	STD_RELON_EXCEPTION_HYPERVISOR(0x4e80, 0xe80, doorbell_hyper)
-	*/
+	. = 0x4e80
+	b	h_doorbell_relon_hv
 
 performance_monitor_relon_pSeries_1:
 	. = 0x4f00
@@ -1036,6 +1064,7 @@ _GLOBAL(slb_miss_realmode)
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
 .machine	pop
 
+	RESTORE_PPR_PACA(PACA_EXSLB, r9)
 	ld	r9,PACA_EXSLB+EX_R9(r13)
 	ld	r10,PACA_EXSLB+EX_R10(r13)
 	ld	r11,PACA_EXSLB+EX_R11(r13)
@@ -1151,6 +1180,61 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	.globl	__end_handlers
 __end_handlers:
 
+	/* Equivalents to the above handlers for relocation-on interrupt vectors */
+	STD_RELON_EXCEPTION_HV(., 0xe00, h_data_storage)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe00)
+	STD_RELON_EXCEPTION_HV(., 0xe20, h_instr_storage)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe20)
+	STD_RELON_EXCEPTION_HV(., 0xe40, emulation_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe40)
+	STD_RELON_EXCEPTION_HV(., 0xe60, hmi_exception)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe60)
+	MASKABLE_RELON_EXCEPTION_HV(., 0xe80, h_doorbell)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe80)
+
+	STD_RELON_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
+	STD_RELON_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
+	STD_RELON_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
+
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+/*
+ * Data area reserved for FWNMI option.
+ * This address (0x7000) is fixed by the RPA.
+ */
+	.= 0x7000
+	.globl fwnmi_data_area
+fwnmi_data_area:
+
+	/* pseries and powernv need to keep the whole page from
+	 * 0x7000 to 0x8000 free for use by the firmware
+	 */
+	. = 0x8000
+#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
+
+/* Space for CPU0's segment table */
+	.balign 4096
+	.globl initial_stab
+initial_stab:
+	.space	4096
+
+#ifdef CONFIG_PPC_POWERNV
+_GLOBAL(opal_mc_secondary_handler)
+	HMT_MEDIUM_PPR_DISCARD
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	clrldi	r3,r3,2
+	tovirt(r3,r3)
+	std	r3,PACA_OPAL_MC_EVT(r13)
+	ld	r13,OPAL_MC_SRR0(r3)
+	mtspr	SPRN_SRR0,r13
+	ld	r13,OPAL_MC_SRR1(r3)
+	mtspr	SPRN_SRR1,r13
+	ld	r3,OPAL_MC_GPR3(r3)
+	GET_SCRATCH0(r13)
+	b	machine_check_pSeries
+#endif /* CONFIG_PPC_POWERNV */
+
+
 /*
  * Hash table stuff
  */
@@ -1222,7 +1306,7 @@ handle_dabr_fault:
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      .do_dabr
+	bl      .do_break
 12:	b       .ret_from_except_lite
 
 
@@ -1344,56 +1428,3 @@ _GLOBAL(do_stab_bolted)
 	ld	r13,PACA_EXSLB+EX_R13(r13)
 	rfid
 	b	.	/* prevent speculative execution */
-
-
-	/* Equivalents to the above handlers for relocation-on interrupt vectors */
-	STD_RELON_EXCEPTION_HV(., 0xe00, h_data_storage)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe00)
-	STD_RELON_EXCEPTION_HV(., 0xe20, h_instr_storage)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe20)
-	STD_RELON_EXCEPTION_HV(., 0xe40, emulation_assist)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe40)
-	STD_RELON_EXCEPTION_HV(., 0xe60, hmi_exception)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe60)
-
-	STD_RELON_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
-	STD_RELON_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
-	STD_RELON_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
-
-#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
-/*
- * Data area reserved for FWNMI option.
- * This address (0x7000) is fixed by the RPA.
- */
-	.= 0x7000
-	.globl fwnmi_data_area
-fwnmi_data_area:
-
-	/* pseries and powernv need to keep the whole page from
-	 * 0x7000 to 0x8000 free for use by the firmware
-	 */
-	. = 0x8000
-#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
-
-/* Space for CPU0's segment table */
-	.balign 4096
-	.globl initial_stab
-initial_stab:
-	.space	4096
-
-#ifdef CONFIG_PPC_POWERNV
-_GLOBAL(opal_mc_secondary_handler)
-	HMT_MEDIUM
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	clrldi	r3,r3,2
-	tovirt(r3,r3)
-	std	r3,PACA_OPAL_MC_EVT(r13)
-	ld	r13,OPAL_MC_SRR0(r3)
-	mtspr	SPRN_SRR0,r13
-	ld	r13,OPAL_MC_SRR1(r3)
-	mtspr	SPRN_SRR1,r13
-	ld	r3,OPAL_MC_GPR3(r3)
-	GET_SCRATCH0(r13)
-	b	machine_check_pSeries
-#endif /* CONFIG_PPC_POWERNV */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 4989661b710b..8a9b6f59822d 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -430,30 +430,18 @@ label:
 	EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_EE)
 
 /* 0x1000 - Programmable Interval Timer (PIT) Exception */
-	START_EXCEPTION(0x1000, Decrementer)
-	NORMAL_EXCEPTION_PROLOG
-	lis	r0,TSR_PIS@h
-	mtspr	SPRN_TSR,r0		/* Clear the PIT exception */
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_LITE(0x1000, timer_interrupt)
-
-#if 0
-/* NOTE:
- * FIT and WDT handlers are not implemented yet.
- */
+	. = 0x1000
+	b Decrementer
 
 /* 0x1010 - Fixed Interval Timer (FIT) Exception
 */
-	STND_EXCEPTION(0x1010,	FITException,		unknown_exception)
+	. = 0x1010
+	b FITException
 
 /* 0x1020 - Watchdog Timer (WDT) Exception
 */
-#ifdef CONFIG_BOOKE_WDT
-	CRITICAL_EXCEPTION(0x1020, WDTException, WatchdogException)
-#else
-	CRITICAL_EXCEPTION(0x1020, WDTException, unknown_exception)
-#endif
-#endif
+	. = 0x1020
+	b WDTException
 
 /* 0x1100 - Data TLB Miss Exception
  * As the name implies, translation is not in the MMU, so search the
@@ -738,6 +726,29 @@ label:
 		(MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
 		NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
 
+	/* Programmable Interval Timer (PIT) Exception. (from 0x1000) */
+Decrementer:
+	NORMAL_EXCEPTION_PROLOG
+	lis	r0,TSR_PIS@h
+	mtspr	SPRN_TSR,r0		/* Clear the PIT exception */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_LITE(0x1000, timer_interrupt)
+
+	/* Fixed Interval Timer (FIT) Exception. (from 0x1010) */
+FITException:
+	NORMAL_EXCEPTION_PROLOG
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	EXC_XFER_EE(0x1010, unknown_exception)
+
+	/* Watchdog Timer (WDT) Exception. (from 0x1020) */
+WDTException:
+	CRITICAL_EXCEPTION_PROLOG;
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	EXC_XFER_TEMPLATE(WatchdogException, 0x1020+2,
+	                  (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)),
+			  NOCOPY, crit_transfer_to_handler,
+			  ret_from_crit_exc)
+
 /*
  * The other Data TLB exceptions bail out to this point
  * if they can't resolve the lightweight TLB fault.
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 116f0868695b..0886ae6dd5be 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -122,6 +122,8 @@ __secondary_hold:
 #endif
 	/* Grab our physical cpu number */
 	mr	r24,r3
+	/* stash r4 for book3e */
+	mr	r25,r4
 
 	/* Tell the master cpu we're here */
 	/* Relocation is off & we are located at an address less */
@@ -129,16 +131,31 @@ __secondary_hold:
 	std	r24,__secondary_hold_acknowledge-_stext(0)
 	sync
 
+	li	r26,0
+#ifdef CONFIG_PPC_BOOK3E
+	tovirt(r26,r26)
+#endif
 	/* All secondary cpus wait here until told to start. */
-100:	ld	r4,__secondary_hold_spinloop-_stext(0)
+100:	ld	r4,__secondary_hold_spinloop-_stext(r26)
 	cmpdi	0,r4,0
 	beq	100b
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
+#ifdef CONFIG_PPC_BOOK3E
+	tovirt(r4,r4)
+#endif
 	ld	r4,0(r4)		/* deref function descriptor */
 	mtctr	r4
 	mr	r3,r24
+	/*
+	 * it may be the case that other platforms have r4 right to
+	 * begin with, this gives us some safety in case it is not
+	 */
+#ifdef CONFIG_PPC_BOOK3E
+	mr	r4,r25
+#else
 	li	r4,0
+#endif
 	/* Make sure that patched code is visible */
 	isync
 	bctr
@@ -169,6 +186,7 @@ _GLOBAL(generic_secondary_thread_init)
 
 	/* get a valid TOC pointer, wherever we're mapped at */
 	bl	.relative_toc
+	tovirt(r2,r2)
 
 #ifdef CONFIG_PPC_BOOK3E
 	/* Book3E initialization */
@@ -195,6 +213,7 @@ _GLOBAL(generic_secondary_smp_init)
 
 	/* get a valid TOC pointer, wherever we're mapped at */
 	bl	.relative_toc
+	tovirt(r2,r2)
 
 #ifdef CONFIG_PPC_BOOK3E
 	/* Book3E initialization */
@@ -531,6 +550,7 @@ _GLOBAL(pmac_secondary_start)
 
 	/* get TOC pointer (real address) */
 	bl	.relative_toc
+	tovirt(r2,r2)
 
 	/* Copy some CPU settings from CPU 0 */
 	bl	.__restore_cpu_ppc970
@@ -665,6 +685,13 @@ _GLOBAL(enable_64b_mode)
  * This puts the TOC pointer into r2, offset by 0x8000 (as expected
  * by the toolchain).  It computes the correct value for wherever we
  * are running at the moment, using position-independent code.
+ *
+ * Note: The compiler constructs pointers using offsets from the
+ * TOC in -mcmodel=medium mode. After we relocate to 0 but before
+ * the MMU is on we need our TOC to be a virtual address otherwise
+ * these pointers will be real addresses which may get stored and
+ * accessed later with the MMU on. We use tovirt() at the call
+ * sites to handle this.
  */
 _GLOBAL(relative_toc)
 	mflr	r0
@@ -681,8 +708,9 @@ p_toc:	.llong	__toc_start + 0x8000 - 0b
  * This is where the main kernel code starts.
  */
 _INIT_STATIC(start_here_multiplatform)
-	/* set up the TOC (real address) */
-	bl	.relative_toc
+	/* set up the TOC */
+	bl      .relative_toc
+	tovirt(r2,r2)
 
 	/* Clear out the BSS. It may have been done in prom_init,
 	 * already but that's irrelevant since prom_init will soon
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index a89cae481b04..2a3e8dd547ec 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -73,7 +73,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	 * If so, DABR will be populated in single_step_dabr_instruction().
 	 */
 	if (current->thread.last_hit_ubp != bp)
-		set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx);
+		set_breakpoint(info);
 
 	return 0;
 }
@@ -97,7 +97,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	}
 
 	*slot = NULL;
-	set_dabr(0, 0);
+	hw_breakpoint_disable();
 }
 
 /*
@@ -127,19 +127,13 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 
 int arch_bp_generic_fields(int type, int *gen_bp_type)
 {
-	switch (type) {
-	case DABR_DATA_READ:
-		*gen_bp_type = HW_BREAKPOINT_R;
-		break;
-	case DABR_DATA_WRITE:
-		*gen_bp_type = HW_BREAKPOINT_W;
-		break;
-	case (DABR_DATA_WRITE | DABR_DATA_READ):
-		*gen_bp_type = (HW_BREAKPOINT_W | HW_BREAKPOINT_R);
-		break;
-	default:
+	*gen_bp_type = 0;
+	if (type & HW_BRK_TYPE_READ)
+		*gen_bp_type |= HW_BREAKPOINT_R;
+	if (type & HW_BRK_TYPE_WRITE)
+		*gen_bp_type |= HW_BREAKPOINT_W;
+	if (*gen_bp_type == 0)
 		return -EINVAL;
-	}
 	return 0;
 }
 
@@ -154,29 +148,22 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (!bp)
 		return ret;
 
-	switch (bp->attr.bp_type) {
-	case HW_BREAKPOINT_R:
-		info->type = DABR_DATA_READ;
-		break;
-	case HW_BREAKPOINT_W:
-		info->type = DABR_DATA_WRITE;
-		break;
-	case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
-		info->type = (DABR_DATA_READ | DABR_DATA_WRITE);
-		break;
-	default:
+	info->type = HW_BRK_TYPE_TRANSLATE;
+	if (bp->attr.bp_type & HW_BREAKPOINT_R)
+		info->type |= HW_BRK_TYPE_READ;
+	if (bp->attr.bp_type & HW_BREAKPOINT_W)
+		info->type |= HW_BRK_TYPE_WRITE;
+	if (info->type == HW_BRK_TYPE_TRANSLATE)
+		/* must set alteast read or write */
 		return ret;
-	}
-
+	if (!(bp->attr.exclude_user))
+		info->type |= HW_BRK_TYPE_USER;
+	if (!(bp->attr.exclude_kernel))
+		info->type |= HW_BRK_TYPE_KERNEL;
+	if (!(bp->attr.exclude_hv))
+		info->type |= HW_BRK_TYPE_HYP;
 	info->address = bp->attr.bp_addr;
 	info->len = bp->attr.bp_len;
-	info->dabrx = DABRX_ALL;
-	if (bp->attr.exclude_user)
-		info->dabrx &= ~DABRX_USER;
-	if (bp->attr.exclude_kernel)
-		info->dabrx &= ~DABRX_KERNEL;
-	if (bp->attr.exclude_hv)
-		info->dabrx &= ~DABRX_HYP;
 
 	/*
 	 * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
@@ -204,7 +191,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
 
 	info = counter_arch_bp(tsk->thread.last_hit_ubp);
 	regs->msr &= ~MSR_SE;
-	set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx);
+	set_breakpoint(info);
 	tsk->thread.last_hit_ubp = NULL;
 }
 
@@ -222,7 +209,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	unsigned long dar = regs->dar;
 
 	/* Disable breakpoints during exception handling */
-	set_dabr(0, 0);
+	hw_breakpoint_disable();
 
 	/*
 	 * The counter may be concurrently released but that can only
@@ -255,8 +242,9 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	 * we still need to single-step the instruction, but we don't
 	 * generate an event.
 	 */
-	info->extraneous_interrupt = !((bp->attr.bp_addr <= dar) &&
-			(dar - bp->attr.bp_addr < bp->attr.bp_len));
+	if (!((bp->attr.bp_addr <= dar) &&
+	      (dar - bp->attr.bp_addr < bp->attr.bp_len)))
+		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
 
 	/* Do not emulate user-space instructions, instead single-step them */
 	if (user_mode(regs)) {
@@ -285,10 +273,10 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	 * As a policy, the callback is invoked in a 'trigger-after-execute'
 	 * fashion
 	 */
-	if (!info->extraneous_interrupt)
+	if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
 		perf_bp_event(bp, regs);
 
-	set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx);
+	set_breakpoint(info);
 out:
 	rcu_read_unlock();
 	return rc;
@@ -317,10 +305,10 @@ int __kprobes single_step_dabr_instruction(struct die_args *args)
 	 * We shall invoke the user-defined callback function in the single
 	 * stepping handler to confirm to 'trigger-after-execute' semantics
 	 */
-	if (!info->extraneous_interrupt)
+	if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
 		perf_bp_event(bp, regs);
 
-	set_dabr(info->address | info->type | DABR_TRANSLATION, info->dabrx);
+	set_breakpoint(info);
 	current->thread.last_hit_ubp = NULL;
 
 	/*
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index c862fd716fe3..31c4fdc6859c 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -717,6 +717,13 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 		return;
 	}
 
+	/*
+	 * In case we have reserved the first bit, we should not emit
+	 * the warning below.
+	 */
+	if (tbl->it_offset == 0)
+		clear_bit(0, tbl->it_map);