Merge tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Core:
   - Ground work for the new Power9 MMU from Aneesh Kumar K.V
   - Optimise FP/VMX/VSX context switching from Anton Blanchard

  Misc:
   - Various cleanups from Krzysztof Kozlowski, John Ogness, Rashmica
     Gupta, Russell Currey, Gavin Shan, Daniel Axtens, Michael Neuling,
     Andrew Donnellan
   - Allow wrapper to work on non-english system from Laurent Vivier
   - Add rN aliases to the pt_regs_offset table from Rashmica Gupta
   - Fix module autoload for rackmeter & axonram drivers from Luis de
     Bethencourt
   - Include KVM guest test in all interrupt vectors from Paul Mackerras
   - Fix DSCR inheritance over fork() from Anton Blanchard
   - Make value-returning atomics & {cmp}xchg* & their atomic_ versions
     fully ordered from Boqun Feng
   - Print MSR TM bits in oops messages from Michael Neuling
   - Add TM signal return & invalid stack selftests from Michael Neuling
   - Limit EPOW reset event warnings from Vipin K Parashar
   - Remove the Cell QPACE code from Rashmica Gupta
   - Append linux_banner to exception information in xmon from Rashmica
     Gupta
   - Add selftest to check if VSRs are corrupted from Rashmica Gupta
   - Remove broken GregorianDay() from Daniel Axtens
   - Import Anton's context_switch2 benchmark into selftests from
     Michael Ellerman
   - Add selftest script to test HMI functionality from Daniel Axtens
   - Remove obsolete OPAL v2 support from Stewart Smith
   - Make enter_rtas() private from Michael Ellerman
   - PPR exception cleanups from Michael Ellerman
   - Add page soft dirty tracking from Laurent Dufour
   - Add support for Nvlink NPUs from Alistair Popple
   - Add support for kexec on 476fpe from Alistair Popple
   - Enable kernel CPU dlpar from sysfs from Nathan Fontenot
   - Copy only required pieces of the mm_context_t to the paca from
     Michael Neuling
   - Add a kmsg_dumper that flushes OPAL console output on panic from
     Russell Currey
   - Implement save_stack_trace_regs() to enable kprobe stack tracing
     from Steven Rostedt
   - Add HWCAP bits for Power9 from Michael Ellerman
   - Fix _PAGE_PTE breaking swapoff from Aneesh Kumar K.V
   - Fix _PAGE_SWP_SOFT_DIRTY breaking swapoff from Hugh Dickins
   - scripts/recordmcount.pl: support data in text section on powerpc
     from Ulrich Weigand
   - Handle R_PPC64_ENTRY relocations in modules from Ulrich Weigand

  cxl:
   - cxl: Fix possible idr warning when contexts are released from
     Vaibhav Jain
   - cxl: use correct operator when writing pcie config space values
     from Andrew Donnellan
   - cxl: Fix DSI misses when the context owning task exits from Vaibhav
     Jain
   - cxl: fix build for GCC 4.6.x from Brian Norris
   - cxl: use -Werror only with CONFIG_PPC_WERROR from Brian Norris
   - cxl: Enable PCI device ID for future IBM CXL adapter from Uma
     Krishnan

  Freescale:
   - Freescale updates from Scott: Highlights include moving QE code out
     of arch/powerpc (to be shared with arm), device tree updates, and
     minor fixes"

* tag 'powerpc-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (149 commits)
  powerpc/module: Handle R_PPC64_ENTRY relocations
  scripts/recordmcount.pl: support data in text section on powerpc
  powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
  powerpc/mm: fix _PAGE_SWP_SOFT_DIRTY breaking swapoff
  powerpc/mm: Fix _PAGE_PTE breaking swapoff
  cxl: Enable PCI device ID for future IBM CXL adapter
  cxl: use -Werror only with CONFIG_PPC_WERROR
  cxl: fix build for GCC 4.6.x
  powerpc: Add HWCAP bits for Power9
  powerpc/powernv: Reserve PE#0 on NPU
  powerpc/powernv: Change NPU PE# assignment
  powerpc/powernv: Fix update of NVLink DMA mask
  powerpc/powernv: Remove misleading comment in pci.c
  powerpc: Implement save_stack_trace_regs() to enable kprobe stack tracing
  powerpc: Fix build break due to paca mm_context_t changes
  cxl: Fix DSI misses when the context owning task exits
  MAINTAINERS: Update Scott Wood's e-mail address
  powerpc/powernv: Fix minor off-by-one error in opal_mce_check_early_recovery()
  powerpc: Fix style of self-test config prompts
  powerpc/powernv: Only delay opal_rtc_read() retry when necessary
  ...

26 files changed, 478 insertions, 679 deletions

diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 86150fbb42c3..8e7cb8e2b21a 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -960,6 +960,7 @@ int fix_alignment(struct pt_regs *regs)
 			preempt_disable();
 			enable_kernel_fp();
 			cvt_df(&data.dd, (float *)&data.x32.low32);
+			disable_kernel_fp();
 			preempt_enable();
 #else
 			return 0;
@@ -1000,6 +1001,7 @@ int fix_alignment(struct pt_regs *regs)
 		preempt_disable();
 		enable_kernel_fp();
 		cvt_fd((float *)&data.x32.low32, &data.dd);
+		disable_kernel_fp();
 		preempt_enable();
 #else
 		return 0;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 221d584d089f..07cebc3514f3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -185,14 +185,16 @@ int main(void)
 	DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
 	DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
 	DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
-	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
+#ifdef CONFIG_PPC_BOOK3S
+	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, mm_ctx_id));
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
-					    context.low_slices_psize));
+					    mm_ctx_low_slices_psize));
 	DEFINE(PACAHIGHSLICEPSIZE, offsetof(struct paca_struct,
-					    context.high_slices_psize));
+					    mm_ctx_high_slices_psize));
 	DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
 #endif /* CONFIG_PPC_MM_SLICES */
+#endif
 
 #ifdef CONFIG_PPC_BOOK3E
 	DEFINE(PACAPGD, offsetof(struct paca_struct, pgd));
@@ -222,7 +224,7 @@ int main(void)
 #ifdef CONFIG_PPC_MM_SLICES
 	DEFINE(MMUPSIZESLLP, offsetof(struct mmu_psize_def, sllp));
 #else
-	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, context.sllp));
+	DEFINE(PACACONTEXTSLLP, offsetof(struct paca_struct, mm_ctx_sllp));
 #endif /* CONFIG_PPC_MM_SLICES */
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a94f155db78e..0d525ce3717f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -223,7 +223,11 @@ END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	beq-	1f
 	ACCOUNT_CPU_USER_EXIT(r11, r12)
-	HMT_MEDIUM_LOW_HAS_PPR
+
+BEGIN_FTR_SECTION
+	HMT_MEDIUM_LOW
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
@@ -312,7 +316,13 @@ syscall_exit_work:
 	subi	r12,r12,TI_FLAGS
 
 4:	/* Anything else left to do? */
-	SET_DEFAULT_THREAD_PPR(r3, r10)		/* Set thread.ppr = 3 */
+BEGIN_FTR_SECTION
+	lis	r3,INIT_PPR@highest	/* Set thread.ppr = 3 */
+	ld	r10,PACACURRENT(r13)
+	sldi	r3,r3,32	/* bits 11-13 are used for ppr */
+	std	r3,TASKTHREADPPR(r10)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
 	beq	ret_from_except_lite
 
@@ -452,43 +462,11 @@ _GLOBAL(_switch)
 	/* r3-r13 are caller saved -- Cort */
 	SAVE_8GPRS(14, r1)
 	SAVE_10GPRS(22, r1)
-	mflr	r20		/* Return to switch caller */
-	mfmsr	r22
-	li	r0, MSR_FP
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r0,r0,MSR_VSX@h	/* Disable VSX */
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_ALTIVEC
-BEGIN_FTR_SECTION
-	oris	r0,r0,MSR_VEC@h	/* Disable altivec */
-	mfspr	r24,SPRN_VRSAVE	/* save vrsave register value */
-	std	r24,THREAD_VRSAVE(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif /* CONFIG_ALTIVEC */
-	and.	r0,r0,r22
-	beq+	1f
-	andc	r22,r22,r0
-	MTMSRD(r22)
-	isync
-1:	std	r20,_NIP(r1)
+	std	r0,_NIP(r1)	/* Return to switch caller */
 	mfcr	r23
 	std	r23,_CCR(r1)
 	std	r1,KSP(r3)	/* Set old stack pointer */
 
-#ifdef CONFIG_PPC_BOOK3S_64
-BEGIN_FTR_SECTION
-	/* Event based branch registers */
-	mfspr	r0, SPRN_BESCR
-	std	r0, THREAD_BESCR(r3)
-	mfspr	r0, SPRN_EBBHR
-	std	r0, THREAD_EBBHR(r3)
-	mfspr	r0, SPRN_EBBRR
-	std	r0, THREAD_EBBRR(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-#endif
-
 #ifdef CONFIG_SMP
 	/* We need a sync somewhere here to make sure that if the
 	 * previous task gets rescheduled on another CPU, it sees all
@@ -576,47 +554,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 	mr	r1,r8		/* start using new stack pointer */
 	std	r7,PACAKSAVE(r13)
 
-#ifdef CONFIG_PPC_BOOK3S_64
-BEGIN_FTR_SECTION
-	/* Event based branch registers */
-	ld	r0, THREAD_BESCR(r4)
-	mtspr	SPRN_BESCR, r0
-	ld	r0, THREAD_EBBHR(r4)
-	mtspr	SPRN_EBBHR, r0
-	ld	r0, THREAD_EBBRR(r4)
-	mtspr	SPRN_EBBRR, r0
-
-	ld	r0,THREAD_TAR(r4)
-	mtspr	SPRN_TAR,r0
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
-#endif
-
-#ifdef CONFIG_ALTIVEC
-BEGIN_FTR_SECTION
-	ld	r0,THREAD_VRSAVE(r4)
-	mtspr	SPRN_VRSAVE,r0		/* if G4, restore VRSAVE reg */
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_PPC64
-BEGIN_FTR_SECTION
-	lwz	r6,THREAD_DSCR_INHERIT(r4)
-	ld	r0,THREAD_DSCR(r4)
-	cmpwi	r6,0
-	bne	1f
-	ld	r0,PACA_DSCR_DEFAULT(r13)
-1:
-BEGIN_FTR_SECTION_NESTED(70)
-	mfspr	r8, SPRN_FSCR
-	rldimi	r8, r6, FSCR_DSCR_LG, (63 - FSCR_DSCR_LG)
-	mtspr	SPRN_FSCR, r8
-END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
-	cmpd	r0,r25
-	beq	2f
-	mtspr	SPRN_DSCR,r0
-2:
-END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
-#endif
-
 	ld	r6,_CCR(r1)
 	mtcrf	0xFF,r6
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0a0399c2af11..7716cebf4b8e 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -96,7 +96,6 @@ __start_interrupts:
 
 	.globl system_reset_pSeries;
 system_reset_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -164,7 +163,6 @@ machine_check_pSeries_1:
 	 * some code path might still want to branch into the original
 	 * vector
 	 */
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -199,7 +197,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 	. = 0x300
 	.globl data_access_pSeries
 data_access_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
 				 KVMTEST, 0x300)
@@ -207,7 +204,6 @@ data_access_pSeries:
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
 	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
@@ -234,15 +230,14 @@ data_access_slb_pSeries:
 	bctr
 #endif
 
-	STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access)
+	STD_EXCEPTION_PSERIES(0x400, instruction_access)
 
 	. = 0x480
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 #ifdef __DISABLED__
@@ -269,25 +264,24 @@ instruction_access_slb_pSeries:
 	.globl hardware_interrupt_hv;
 hardware_interrupt_pSeries:
 hardware_interrupt_hv:
-	HMT_MEDIUM_PPR_DISCARD
 	BEGIN_FTR_SECTION
 		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
 					    EXC_HV, SOFTEN_TEST_HV)
 		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
 	FTR_SECTION_ELSE
 		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
-					    EXC_STD, SOFTEN_TEST_HV_201)
+					    EXC_STD, SOFTEN_TEST_PR)
 		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 
-	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600)
+	STD_EXCEPTION_PSERIES(0x600, alignment)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600)
 
-	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700)
+	STD_EXCEPTION_PSERIES(0x700, program_check)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700)
 
-	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
+	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800)
 
 	. = 0x900
 	.globl decrementer_pSeries
@@ -297,10 +291,10 @@ decrementer_pSeries:
 	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
 
 	MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00)
 
-	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00)
+	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00)
 
 	. = 0xc00
 	.globl	system_call_pSeries
@@ -331,8 +325,8 @@ system_call_pSeries:
 	SYSCALL_PSERIES_3
 	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00)
 
-	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00)
+	STD_EXCEPTION_PSERIES(0xd00, single_step)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00)
 
 	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
 	 * out of line to handle them
@@ -407,13 +401,12 @@ hv_facility_unavailable_trampoline:
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
 
-	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
-	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
 
 	. = 0x1500
 	.global denorm_exception_hv
 denorm_exception_hv:
-	HMT_MEDIUM_PPR_DISCARD
 	mtspr	SPRN_SPRG_HSCRATCH0,r13
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0x1500)
@@ -435,8 +428,8 @@ denorm_exception_hv:
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
 
-	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700)
+	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700)
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
@@ -527,7 +520,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 machine_check_pSeries:
 	.globl machine_check_fwnmi
 machine_check_fwnmi:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_0(PACA_EXMC)
 machine_check_pSeries_0:
@@ -536,9 +528,9 @@ machine_check_pSeries_0:
 	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
-	KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400)
+	KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
 
 #ifdef CONFIG_PPC_DENORMALISATION
@@ -621,13 +613,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
 	STD_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40)
 	STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
-	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf60)
 	STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82)
 
@@ -711,7 +703,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 	.globl system_reset_fwnmi
       .align 7
 system_reset_fwnmi:
-	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
 				 NOTEST, 0x100)
@@ -1556,29 +1547,19 @@ do_hash_page:
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
 	bne	77f			/* then don't call hash_page now */
-	/*
-	 * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
-	 * accessing a userspace segment (even from the kernel). We assume
-	 * kernel addresses always have the high bit set.
-	 */
-	rlwinm	r4,r4,32-25+9,31-9,31-9	/* DSISR_STORE -> _PAGE_RW */
-	rotldi	r0,r3,15		/* Move high bit into MSR_PR posn */
-	orc	r0,r12,r0		/* MSR_PR | ~high_bit */
-	rlwimi	r4,r0,32-13,30,30	/* becomes _PAGE_USER access bit */
-	ori	r4,r4,1			/* add _PAGE_PRESENT */
-	rlwimi	r4,r5,22+2,31-2,31-2	/* Set _PAGE_EXEC if trap is 0x400 */
 
 	/*
 	 * r3 contains the faulting address
-	 * r4 contains the required access permissions
+	 * r4 msr
 	 * r5 contains the trap number
 	 * r6 contains dsisr
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
+        mr 	r4,r12
 	ld      r6,_DSISR(r1)
-	bl	hash_page		/* build HPTE if possible */
-	cmpdi	r3,0			/* see if hash_page succeeded */
+	bl	__hash_page		/* build HPTE if possible */
+        cmpdi	r3,0			/* see if __hash_page succeeded */
 
 	/* Success */
 	beq	fast_exc_return_irq	/* Return from exception on success */
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 9ad236e5d2c9..2117eaca3d28 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -73,30 +73,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	MTFSF_L(fr0)
 	REST_32FPVSRS(0, R4, R7)
 
-	/* FP/VSX off again */
-	MTMSRD(r6)
-	SYNC
-
 	blr
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
 /*
- * Enable use of the FPU, and VSX if possible, for the caller.
- */
-_GLOBAL(fp_enable)
-	mfmsr	r3
-	ori	r3,r3,MSR_FP
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r3,r3,MSR_VSX@h
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif
-	SYNC
-	MTMSRD(r3)
-	isync			/* (not necessary for arch 2.02 and later) */
-	blr
-
-/*
  * Load state from memory into FP registers including FPSCR.
  * Assumes the caller has enabled FP in the MSR.
  */
@@ -136,31 +116,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	SYNC
 	MTMSRD(r5)			/* enable use of fpu now */
 	isync
-/*
- * For SMP, we don't do lazy FPU switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_fpu in switch_to.
- */
-#ifndef CONFIG_SMP
-	LOAD_REG_ADDRBASE(r3, last_task_used_math)
-	toreal(r3)
-	PPC_LL	r4,ADDROFF(last_task_used_math)(r3)
-	PPC_LCMPI	0,r4,0
-	beq	1f
-	toreal(r4)
-	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
-	addi	r10,r4,THREAD_FPSTATE
-	SAVE_32FPVSRS(0, R5, R10)
-	mffs	fr0
-	stfd	fr0,FPSTATE_FPSCR(r10)
-	PPC_LL	r5,PT_REGS(r4)
-	toreal(r5)
-	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	li	r10,MSR_FP|MSR_FE0|MSR_FE1
-	andc	r4,r4,r10		/* disable FP for previous task */
-	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
 	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
@@ -179,36 +134,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	lfd	fr0,FPSTATE_FPSCR(r10)
 	MTFSF_L(fr0)
 	REST_32FPVSRS(0, R4, R10)
-#ifndef CONFIG_SMP
-	subi	r4,r5,THREAD
-	fromreal(r4)
-	PPC_STL	r4,ADDROFF(last_task_used_math)(r3)
-#endif /* CONFIG_SMP */
 	/* restore registers and return */
 	/* we haven't used ctr or xer or lr */
 	blr
 
 /*
- * giveup_fpu(tsk)
+ * __giveup_fpu(tsk)
  * Disable FP for the task given as the argument,
  * and save the floating-point registers in its thread_struct.
  * Enables the FPU for use in the kernel on return.
  */
-_GLOBAL(giveup_fpu)
-	mfmsr	r5
-	ori	r5,r5,MSR_FP
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r5,r5,MSR_VSX@h
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif
-	SYNC_601
-	ISYNC_601
-	MTMSRD(r5)			/* enable use of fpu now */
-	SYNC_601
-	isync
-	PPC_LCMPI	0,r3,0
-	beqlr-				/* if no previous owner, done */
+_GLOBAL(__giveup_fpu)
 	addi	r3,r3,THREAD	        /* want THREAD of task */
 	PPC_LL	r6,THREAD_FPSAVEAREA(r3)
 	PPC_LL	r5,PT_REGS(r3)
@@ -230,11 +166,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	andc	r4,r4,r3		/* disable FP for previous task */
 	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	LOAD_REG_ADDRBASE(r4,last_task_used_math)
-	PPC_STL	r5,ADDROFF(last_task_used_math)(r4)
-#endif /* CONFIG_SMP */
 	blr
 
 /*
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index fffd1f96bb1d..f705171b924b 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -857,29 +857,6 @@ _GLOBAL(load_up_spe)
 	oris	r5,r5,MSR_SPE@h
 	mtmsr	r5			/* enable use of SPE now */
 	isync
-/*
- * For SMP, we don't do lazy SPE switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_spe in switch_to.
- */
-#ifndef CONFIG_SMP
-	lis	r3,last_task_used_spe@ha
-	lwz	r4,last_task_used_spe@l(r3)
-	cmpi	0,r4,0
-	beq	1f
-	addi	r4,r4,THREAD	/* want THREAD of last_task_used_spe */
-	SAVE_32EVRS(0,r10,r4,THREAD_EVR0)
-	evxor	evr10, evr10, evr10	/* clear out evr10 */
-	evmwumiaa evr10, evr10, evr10	/* evr10 <- ACC = 0 * 0 + ACC */
-	li	r5,THREAD_ACC
-	evstddx	evr10, r4, r5		/* save off accumulator */
-	lwz	r5,PT_REGS(r4)
-	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r10,MSR_SPE@h
-	andc	r4,r4,r10	/* disable SPE for previous task */
-	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* !CONFIG_SMP */
 	/* enable use of SPE after return */
 	oris	r9,r9,MSR_SPE@h
 	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
@@ -889,10 +866,6 @@ _GLOBAL(load_up_spe)
 	evlddx	evr4,r10,r5
 	evmra	evr4,evr4
 	REST_32EVRS(0,r10,r5,THREAD_EVR0)
-#ifndef CONFIG_SMP
-	subi	r4,r5,THREAD
-	stw	r4,last_task_used_spe@l(r3)
-#endif /* !CONFIG_SMP */
 	blr
 
 /*
@@ -1011,16 +984,10 @@ _GLOBAL(__setup_ehv_ivors)
 
 #ifdef CONFIG_SPE
 /*
- * extern void giveup_spe(struct task_struct *prev)
+ * extern void __giveup_spe(struct task_struct *prev)
  *
  */
-_GLOBAL(giveup_spe)
-	mfmsr	r5
-	oris	r5,r5,MSR_SPE@h
-	mtmsr	r5			/* enable use of SPE now */
-	isync
-	cmpi	0,r3,0
-	beqlr-				/* if no previous owner, done */
+_GLOBAL(__giveup_spe)
 	addi	r3,r3,THREAD		/* want THREAD of task */
 	lwz	r5,PT_REGS(r3)
 	cmpi	0,r5,0
@@ -1035,11 +1002,6 @@ _GLOBAL(giveup_spe)
 	andc	r4,r4,r3		/* disable SPE for previous task */
 	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	lis	r4,last_task_used_spe@ha
-	stw	r5,last_task_used_spe@l(r4)
-#endif /* !CONFIG_SMP */
 	blr
 #endif /* CONFIG_SPE */
 
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 112ccf497562..cf4fb5429cf1 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -89,13 +89,6 @@ _GLOBAL(power7_powersave_common)
 	std	r0,_LINK(r1)
 	std	r0,_NIP(r1)
 
-#ifndef CONFIG_SMP
-	/* Make sure FPU, VSX etc... are flushed as we may lose
-	 * state when going to nap mode
-	 */
-	bl	discard_lazy_cpu_state
-#endif /* CONFIG_SMP */
-
 	/* Hard disable interrupts */
 	mfmsr	r9
 	rldicl	r9,r9,48,1
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index ed3ab509faca..be8edd67f05b 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -743,6 +743,8 @@ relocate_new_kernel:
 	/* Check for 47x cores */
 	mfspr	r3,SPRN_PVR
 	srwi	r3,r3,16
+	cmplwi	cr0,r3,PVR_476FPE@h
+	beq	setup_map_47x
 	cmplwi	cr0,r3,PVR_476@h
 	beq	setup_map_47x
 	cmplwi	cr0,r3,PVR_476_ISS@h
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 68384514506b..59663af9315f 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			 */
 			break;
 
+		case R_PPC64_ENTRY:
+			/*
+			 * Optimize ELFv2 large code model entry point if
+			 * the TOC is within 2GB range of current location.
+			 */
+			value = my_r2(sechdrs, me) - (unsigned long)location;
+			if (value + 0x80008000 > 0xffffffff)
+				break;
+			/*
+			 * Check for the large code model prolog sequence:
+		         *	ld r2, ...(r12)
+			 *	add r2, r2, r12
+			 */
+			if ((((uint32_t *)location)[0] & ~0xfffc)
+			    != 0xe84c0000)
+				break;
+			if (((uint32_t *)location)[1] != 0x7c426214)
+				break;
+			/*
+			 * If found, replace it with:
+			 *	addis r2, r12, (.TOC.-func)@ha
+			 *	addi r2, r12, (.TOC.-func)@l
+			 */
+			((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value);
+			((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value);
+			break;
+
 		case R_PPC64_REL16_HA:
 			/* Subtract location pointer */
 			value -= (unsigned long)location;
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 202963ee013a..41e1607e800c 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -19,13 +19,11 @@ EXPORT_SYMBOL(_mcount);
 #endif
 
 #ifdef CONFIG_PPC_FPU
-EXPORT_SYMBOL(giveup_fpu);
 EXPORT_SYMBOL(load_fp_state);
 EXPORT_SYMBOL(store_fp_state);
 #endif
 
 #ifdef CONFIG_ALTIVEC
-EXPORT_SYMBOL(giveup_altivec);
 EXPORT_SYMBOL(load_vr_state);
 EXPORT_SYMBOL(store_vr_state);
 #endif
@@ -34,10 +32,6 @@ EXPORT_SYMBOL(store_vr_state);
 EXPORT_SYMBOL_GPL(__giveup_vsx);
 #endif
 
-#ifdef CONFIG_SPE
-EXPORT_SYMBOL(giveup_spe);
-#endif
-
 #ifdef CONFIG_EPAPR_PARAVIRT
 EXPORT_SYMBOL(epapr_hypercall_start);
 #endif
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 646bf4d222c1..dccc87e8fee5 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -67,15 +67,8 @@
 
 extern unsigned long _get_SP(void);
 
-#ifndef CONFIG_SMP
-struct task_struct *last_task_used_math = NULL;
-struct task_struct *last_task_used_altivec = NULL;
-struct task_struct *last_task_used_vsx = NULL;
-struct task_struct *last_task_used_spe = NULL;
-#endif
-
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void giveup_fpu_maybe_transactional(struct task_struct *tsk)
+static void check_if_tm_restore_required(struct task_struct *tsk)
 {
 	/*
 	 * If we are saving the current thread's registers, and the
@@ -89,34 +82,67 @@ void giveup_fpu_maybe_transactional(struct task_struct *tsk)
 		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
 		set_thread_flag(TIF_RESTORE_TM);
 	}
+}
+#else
+static inline void check_if_tm_restore_required(struct task_struct *tsk) { }
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+bool strict_msr_control;
+EXPORT_SYMBOL(strict_msr_control);
+
+static int __init enable_strict_msr_control(char *str)
+{
+	strict_msr_control = true;
+	pr_info("Enabling strict facility control\n");
 
-	giveup_fpu(tsk);
+	return 0;
 }
+early_param("ppc_strict_facility_enable", enable_strict_msr_control);
 
-void giveup_altivec_maybe_transactional(struct task_struct *tsk)
+void msr_check_and_set(unsigned long bits)
 {
-	/*
-	 * If we are saving the current thread's registers, and the
-	 * thread is in a transactional state, set the TIF_RESTORE_TM
-	 * bit so that we know to restore the registers before
-	 * returning to userspace.
-	 */
-	if (tsk == current && tsk->thread.regs &&
-	    MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
-	    !test_thread_flag(TIF_RESTORE_TM)) {
-		tsk->thread.ckpt_regs.msr = tsk->thread.regs->msr;
-		set_thread_flag(TIF_RESTORE_TM);
-	}
+	unsigned long oldmsr = mfmsr();
+	unsigned long newmsr;
 
-	giveup_altivec(tsk);
+	newmsr = oldmsr | bits;
+
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
+		newmsr |= MSR_VSX;
+#endif
+
+	if (oldmsr != newmsr)
+		mtmsr_isync(newmsr);
 }
 
-#else
-#define giveup_fpu_maybe_transactional(tsk)	giveup_fpu(tsk)
-#define giveup_altivec_maybe_transactional(tsk)	giveup_altivec(tsk)
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+void __msr_check_and_clear(unsigned long bits)
+{
+	unsigned long oldmsr = mfmsr();
+	unsigned long newmsr;
+
+	newmsr = oldmsr & ~bits;
+
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP))
+		newmsr &= ~MSR_VSX;
+#endif
+
+	if (oldmsr != newmsr)
+		mtmsr_isync(newmsr);
+}
+EXPORT_SYMBOL(__msr_check_and_clear);
 
 #ifdef CONFIG_PPC_FPU
+void giveup_fpu(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_FP);
+	__giveup_fpu(tsk);
+	msr_check_and_clear(MSR_FP);
+}
+EXPORT_SYMBOL(giveup_fpu);
+
 /*
  * Make sure the floating-point register state in the
  * the thread_struct is up to date for task tsk.
@@ -134,52 +160,56 @@ void flush_fp_to_thread(struct task_struct *tsk)
 		 */
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_FP) {
-#ifdef CONFIG_SMP
 			/*
 			 * This should only ever be called for current or
 			 * for a stopped child process.  Since we save away
-			 * the FP register state on context switch on SMP,
+			 * the FP register state on context switch,
 			 * there is something wrong if a stopped child appears
 			 * to still have its FP state in the CPU registers.
 			 */
 			BUG_ON(tsk != current);
-#endif
-			giveup_fpu_maybe_transactional(tsk);
+			giveup_fpu(tsk);
 		}
 		preempt_enable();
 	}
 }
 EXPORT_SYMBOL_GPL(flush_fp_to_thread);
-#endif /* CONFIG_PPC_FPU */
 
 void enable_kernel_fp(void)
 {
 	WARN_ON(preemptible());
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_FP))
-		giveup_fpu_maybe_transactional(current);
-	else
-		giveup_fpu(NULL);	/* just enables FP for kernel */
-#else
-	giveup_fpu_maybe_transactional(last_task_used_math);
-#endif /* CONFIG_SMP */
+	msr_check_and_set(MSR_FP);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_FP)) {
+		check_if_tm_restore_required(current);
+		__giveup_fpu(current);
+	}
 }
 EXPORT_SYMBOL(enable_kernel_fp);
+#endif /* CONFIG_PPC_FPU */
 
 #ifdef CONFIG_ALTIVEC
+void giveup_altivec(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_VEC);
+	__giveup_altivec(tsk);
+	msr_check_and_clear(MSR_VEC);
+}
+EXPORT_SYMBOL(giveup_altivec);
+
 void enable_kernel_altivec(void)
 {
 	WARN_ON(preemptible());
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VEC))
-		giveup_altivec_maybe_transactional(current);
-	else
-		giveup_altivec_notask();
-#else
-	giveup_altivec_maybe_transactional(last_task_used_altivec);
-#endif /* CONFIG_SMP */
+	msr_check_and_set(MSR_VEC);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_VEC)) {
+		check_if_tm_restore_required(current);
+		__giveup_altivec(current);
+	}
 }
 EXPORT_SYMBOL(enable_kernel_altivec);
 
@@ -192,10 +222,8 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 	if (tsk->thread.regs) {
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_VEC) {
-#ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
-#endif
-			giveup_altivec_maybe_transactional(tsk);
+			giveup_altivec(tsk);
 		}
 		preempt_enable();
 	}
@@ -204,37 +232,43 @@ EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
-void enable_kernel_vsx(void)
+void giveup_vsx(struct task_struct *tsk)
 {
-	WARN_ON(preemptible());
+	check_if_tm_restore_required(tsk);
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX))
-		giveup_vsx(current);
-	else
-		giveup_vsx(NULL);	/* just enable vsx for kernel - force */
-#else
-	giveup_vsx(last_task_used_vsx);
-#endif /* CONFIG_SMP */
+	msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
+	if (tsk->thread.regs->msr & MSR_FP)
+		__giveup_fpu(tsk);
+	if (tsk->thread.regs->msr & MSR_VEC)
+		__giveup_altivec(tsk);
+	__giveup_vsx(tsk);
+	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
-EXPORT_SYMBOL(enable_kernel_vsx);
+EXPORT_SYMBOL(giveup_vsx);
 
-void giveup_vsx(struct task_struct *tsk)
+void enable_kernel_vsx(void)
 {
-	giveup_fpu_maybe_transactional(tsk);
-	giveup_altivec_maybe_transactional(tsk);
-	__giveup_vsx(tsk);
+	WARN_ON(preemptible());
+
+	msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) {
+		check_if_tm_restore_required(current);
+		if (current->thread.regs->msr & MSR_FP)
+			__giveup_fpu(current);
+		if (current->thread.regs->msr & MSR_VEC)
+			__giveup_altivec(current);
+		__giveup_vsx(current);
+	}
 }
-EXPORT_SYMBOL(giveup_vsx);
+EXPORT_SYMBOL(enable_kernel_vsx);
 
 void flush_vsx_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_VSX) {
-#ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
-#endif
 			giveup_vsx(tsk);
 		}
 		preempt_enable();
@@ -244,19 +278,26 @@ EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
+void giveup_spe(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_SPE);
+	__giveup_spe(tsk);
+	msr_check_and_clear(MSR_SPE);
+}
+EXPORT_SYMBOL(giveup_spe);
 
 void enable_kernel_spe(void)
 {
 	WARN_ON(preemptible());
 
-#ifdef CONFIG_SMP
-	if (current->thread.regs && (current->thread.regs->msr & MSR_SPE))
-		giveup_spe(current);
-	else
-		giveup_spe(NULL);	/* just enable SPE for kernel - force */
-#else
-	giveup_spe(last_task_used_spe);
-#endif /* __SMP __ */
+	msr_check_and_set(MSR_SPE);
+
+	if (current->thread.regs && (current->thread.regs->msr & MSR_SPE)) {
+		check_if_tm_restore_required(current);
+		__giveup_spe(current);
+	}
 }
 EXPORT_SYMBOL(enable_kernel_spe);
 
@@ -265,9 +306,7 @@ void flush_spe_to_thread(struct task_struct *tsk)
 	if (tsk->thread.regs) {
 		preempt_disable();
 		if (tsk->thread.regs->msr & MSR_SPE) {
-#ifdef CONFIG_SMP
 			BUG_ON(tsk != current);
-#endif
 			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
 			giveup_spe(tsk);
 		}
@@ -276,31 +315,81 @@ void flush_spe_to_thread(struct task_struct *tsk)
 }
 #endif /* CONFIG_SPE */
 
-#ifndef CONFIG_SMP
-/*
- * If we are doing lazy switching of CPU state (FP, altivec or SPE),
- * and the current task has some state, discard it.
- */
-void discard_lazy_cpu_state(void)
+static unsigned long msr_all_available;
+
+static int __init init_msr_all_available(void)
 {
-	preempt_disable();
-	if (last_task_used_math == current)
-		last_task_used_math = NULL;
+#ifdef CONFIG_PPC_FPU
+	msr_all_available |= MSR_FP;
+#endif
 #ifdef CONFIG_ALTIVEC
-	if (last_task_used_altivec == current)
-		last_task_used_altivec = NULL;
-#endif /* CONFIG_ALTIVEC */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		msr_all_available |= MSR_VEC;
+#endif
 #ifdef CONFIG_VSX
-	if (last_task_used_vsx == current)
-		last_task_used_vsx = NULL;
-#endif /* CONFIG_VSX */
+	if (cpu_has_feature(CPU_FTR_VSX))
+		msr_all_available |= MSR_VSX;
+#endif
 #ifdef CONFIG_SPE
-	if (last_task_used_spe == current)
-		last_task_used_spe = NULL;
+	if (cpu_has_feature(CPU_FTR_SPE))
+		msr_all_available |= MSR_SPE;
 #endif
-	preempt_enable();
+
+	return 0;
+}
+early_initcall(init_msr_all_available);
+
+void giveup_all(struct task_struct *tsk)
+{
+	unsigned long usermsr;
+
+	if (!tsk->thread.regs)
+		return;
+
+	usermsr = tsk->thread.regs->msr;
+
+	if ((usermsr & msr_all_available) == 0)
+		return;
+
+	msr_check_and_set(msr_all_available);
+
+#ifdef CONFIG_PPC_FPU
+	if (usermsr & MSR_FP)
+		__giveup_fpu(tsk);
+#endif
+#ifdef CONFIG_ALTIVEC
+	if (usermsr & MSR_VEC)
+		__giveup_altivec(tsk);
+#endif
+#ifdef CONFIG_VSX
+	if (usermsr & MSR_VSX)
+		__giveup_vsx(tsk);
+#endif
+#ifdef CONFIG_SPE
+	if (usermsr & MSR_SPE)
+		__giveup_spe(tsk);
+#endif
+
+	msr_check_and_clear(msr_all_available);
+}
+EXPORT_SYMBOL(giveup_all);
+
+void flush_all_to_thread(struct task_struct *tsk)
+{
+	if (tsk->thread.regs) {
+		preempt_disable();
+		BUG_ON(tsk != current);
+		giveup_all(tsk);
+
+#ifdef CONFIG_SPE
+		if (tsk->thread.regs->msr & MSR_SPE)
+			tsk->thread.spefscr = mfspr(SPRN_SPEFSCR);
+#endif
+
+		preempt_enable();
+	}
 }
-#endif /* CONFIG_SMP */
+EXPORT_SYMBOL(flush_all_to_thread);
 
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 void do_send_trap(struct pt_regs *regs, unsigned long address,
@@ -744,13 +833,15 @@ void restore_tm_state(struct pt_regs *regs)
 	msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
 	msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
 	if (msr_diff & MSR_FP) {
-		fp_enable();
+		msr_check_and_set(MSR_FP);
 		load_fp_state(&current->thread.fp_state);
+		msr_check_and_clear(MSR_FP);
 		regs->msr |= current->thread.fpexc_mode;
 	}
 	if (msr_diff & MSR_VEC) {
-		vec_enable();
+		msr_check_and_set(MSR_VEC);
 		load_vr_state(&current->thread.vr_state);
+		msr_check_and_clear(MSR_VEC);
 	}
 	regs->msr |= msr_diff;
 }
@@ -760,112 +851,87 @@ void restore_tm_state(struct pt_regs *regs)
 #define __switch_to_tm(prev)
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 
-struct task_struct *__switch_to(struct task_struct *prev,
-	struct task_struct *new)
+static inline void save_sprs(struct thread_struct *t)
 {
-	struct thread_struct *new_thread, *old_thread;
-	struct task_struct *last;
-#ifdef CONFIG_PPC_BOOK3S_64
-	struct ppc64_tlb_batch *batch;
+#ifdef CONFIG_ALTIVEC
+	if (cpu_has_feature(cpu_has_feature(CPU_FTR_ALTIVEC)))
+		t->vrsave = mfspr(SPRN_VRSAVE);
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_DSCR))
+		t->dscr = mfspr(SPRN_DSCR);
 
-	WARN_ON(!irqs_disabled());
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		t->bescr = mfspr(SPRN_BESCR);
+		t->ebbhr = mfspr(SPRN_EBBHR);
+		t->ebbrr = mfspr(SPRN_EBBRR);
 
-	/* Back up the TAR and DSCR across context switches.
-	 * Note that the TAR is not available for use in the kernel.  (To
-	 * provide this, the TAR should be backed up/restored on exception
-	 * entry/exit instead, and be in pt_regs.  FIXME, this should be in
-	 * pt_regs anyway (for debug).)
-	 * Save the TAR and DSCR here before we do treclaim/trecheckpoint as
-	 * these will change them.
-	 */
-	save_early_sprs(&prev->thread);
+		t->fscr = mfspr(SPRN_FSCR);
 
-	__switch_to_tm(prev);
+		/*
+		 * Note that the TAR is not available for use in the kernel.
+		 * (To provide this, the TAR should be backed up/restored on
+		 * exception entry/exit instead, and be in pt_regs.  FIXME,
+		 * this should be in pt_regs anyway (for debug).)
+		 */
+		t->tar = mfspr(SPRN_TAR);
+	}
+#endif
+}
 
-#ifdef CONFIG_SMP
-	/* avoid complexity of lazy save/restore of fpu
-	 * by just saving it every time we switch out if
-	 * this task used the fpu during the last quantum.
-	 *
-	 * If it tries to use the fpu again, it'll trap and
-	 * reload its fp regs.  So we don't have to do a restore
-	 * every switch, just a save.
-	 *  -- Cort
-	 */
-	if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP))
-		giveup_fpu(prev);
+static inline void restore_sprs(struct thread_struct *old_thread,
+				struct thread_struct *new_thread)
+{
 #ifdef CONFIG_ALTIVEC
-	/*
-	 * If the previous thread used altivec in the last quantum
-	 * (thus changing altivec regs) then save them.
-	 * We used to check the VRSAVE register but not all apps
-	 * set it, so we don't rely on it now (and in fact we need
-	 * to save & restore VSCR even if VRSAVE == 0).  -- paulus
-	 *
-	 * On SMP we always save/restore altivec regs just to avoid the
-	 * complexity of changing processors.
-	 *  -- Cort
-	 */
-	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC))
-		giveup_altivec(prev);
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_VSX
-	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VSX))
-		/* VMX and FPU registers are already save here */
-		__giveup_vsx(prev);
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_SPE
-	/*
-	 * If the previous thread used spe in the last quantum
-	 * (thus changing spe regs) then save them.
-	 *
-	 * On SMP we always save/restore spe regs just to avoid the
-	 * complexity of changing processors.
-	 */
-	if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE)))
-		giveup_spe(prev);
-#endif /* CONFIG_SPE */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC) &&
+	    old_thread->vrsave != new_thread->vrsave)
+		mtspr(SPRN_VRSAVE, new_thread->vrsave);
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (cpu_has_feature(CPU_FTR_DSCR)) {
+		u64 dscr = get_paca()->dscr_default;
+		u64 fscr = old_thread->fscr & ~FSCR_DSCR;
 
-#else  /* CONFIG_SMP */
-#ifdef CONFIG_ALTIVEC
-	/* Avoid the trap.  On smp this this never happens since
-	 * we don't set last_task_used_altivec -- Cort
-	 */
-	if (new->thread.regs && last_task_used_altivec == new)
-		new->thread.regs->msr |= MSR_VEC;
-#endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_VSX
-	if (new->thread.regs && last_task_used_vsx == new)
-		new->thread.regs->msr |= MSR_VSX;
-#endif /* CONFIG_VSX */
-#ifdef CONFIG_SPE
-	/* Avoid the trap.  On smp this this never happens since
-	 * we don't set last_task_used_spe
-	 */
-	if (new->thread.regs && last_task_used_spe == new)
-		new->thread.regs->msr |= MSR_SPE;
-#endif /* CONFIG_SPE */
+		if (new_thread->dscr_inherit) {
+			dscr = new_thread->dscr;
+			fscr |= FSCR_DSCR;
+		}
 
-#endif /* CONFIG_SMP */
+		if (old_thread->dscr != dscr)
+			mtspr(SPRN_DSCR, dscr);
 
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	switch_booke_debug_regs(&new->thread.debug);
-#else
-/*
- * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
- * schedule DABR
- */
-#ifndef CONFIG_HAVE_HW_BREAKPOINT
-	if (unlikely(!hw_brk_match(this_cpu_ptr(&current_brk), &new->thread.hw_brk)))
-		__set_breakpoint(&new->thread.hw_brk);
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+		if (old_thread->fscr != fscr)
+			mtspr(SPRN_FSCR, fscr);
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		if (old_thread->bescr != new_thread->bescr)
+			mtspr(SPRN_BESCR, new_thread->bescr);
+		if (old_thread->ebbhr != new_thread->ebbhr)
+			mtspr(SPRN_EBBHR, new_thread->ebbhr);
+		if (old_thread->ebbrr != new_thread->ebbrr)
+			mtspr(SPRN_EBBRR, new_thread->ebbrr);
+
+		if (old_thread->tar != new_thread->tar)
+			mtspr(SPRN_TAR, new_thread->tar);
+	}
 #endif
+}
 
+struct task_struct *__switch_to(struct task_struct *prev,
+	struct task_struct *new)
+{
+	struct thread_struct *new_thread, *old_thread;
+	struct task_struct *last;
+#ifdef CONFIG_PPC_BOOK3S_64
+	struct ppc64_tlb_batch *batch;
+#endif
 
 	new_thread = &new->thread;
 	old_thread = &current->thread;
 
+	WARN_ON(!irqs_disabled());
+
 #ifdef CONFIG_PPC64
 	/*
 	 * Collect processor utilization data per process
@@ -890,6 +956,30 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	switch_booke_debug_regs(&new->thread.debug);
+#else
+/*
+ * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
+ * schedule DABR
+ */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
+	if (unlikely(!hw_brk_match(this_cpu_ptr(&current_brk), &new->thread.hw_brk)))
+		__set_breakpoint(&new->thread.hw_brk);
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+#endif
+
+	/*
+	 * We need to save SPRs before treclaim/trecheckpoint as these will
+	 * change a number of them.
+	 */
+	save_sprs(&prev->thread);
+
+	__switch_to_tm(prev);
+
+	/* Save FPU, Altivec, VSX and SPE state */
+	giveup_all(prev);
+
 	/*
 	 * We can't take a PMU exception inside _switch() since there is a
 	 * window where the kernel stack SLB and the kernel stack are out
@@ -899,6 +989,15 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 	tm_recheckpoint_new_task(new);
 
+	/*
+	 * Call restore_sprs() before calling _switch(). If we move it after
+	 * _switch() then we miss out on calling it for new tasks. The reason
+	 * for this is we manually create a stack frame for new tasks that
+	 * directly returns through ret_from_fork() or
+	 * ret_from_kernel_thread(). See copy_thread() for details.
+	 */
+	restore_sprs(old_thread, new_thread);
+
 	last = _switch(old_thread, new_thread);
 
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -952,10 +1051,12 @@ static void show_instructions(struct pt_regs *regs)
 	printk("\n");
 }
 
-static struct regbit {
+struct regbit {
 	unsigned long bit;
 	const char *name;
-} msr_bits[] = {
+};
+
+static struct regbit msr_bits[] = {
 #if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE)
 	{MSR_SF,	"SF"},
 	{MSR_HV,	"HV"},
@@ -985,16 +1086,49 @@ static struct regbit {
 	{0,		NULL}
 };
 
-static void printbits(unsigned long val, struct regbit *bits)
+static void print_bits(unsigned long val, struct regbit *bits, const char *sep)
 {
-	const char *sep = "";
+	const char *s = "";
 
-	printk("<");
 	for (; bits->bit; ++bits)
 		if (val & bits->bit) {
-			printk("%s%s", sep, bits->name);
-			sep = ",";
+			printk("%s%s", s, bits->name);
+			s = sep;
 		}
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static struct regbit msr_tm_bits[] = {
+	{MSR_TS_T,	"T"},
+	{MSR_TS_S,	"S"},
+	{MSR_TM,	"E"},
+	{0,		NULL}
+};
+
+static void print_tm_bits(unsigned long val)
+{
+/*
+ * This only prints something if at least one of the TM bit is set.
+ * Inside the TM[], the output means:
+ *   E: Enabled		(bit 32)
+ *   S: Suspended	(bit 33)
+ *   T: Transactional	(bit 34)
+ */
+	if (val & (MSR_TM | MSR_TS_S | MSR_TS_T)) {
+		printk(",TM[");
+		print_bits(val, msr_tm_bits, "");
+		printk("]");
+	}
+}
+#else
+static void print_tm_bits(unsigned long val) {}
+#endif
+
+static void print_msr_bits(unsigned long val)
+{
+	printk("<");
+	print_bits(val, msr_bits, ",");
+	print_tm_bits(val);
 	printk(">");
 }
 
@@ -1019,7 +1153,7 @@ void show_regs(struct pt_regs * regs)
 	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
 	       regs, regs->trap, print_tainted(), init_utsname()->release);
 	printk("MSR: "REG" ", regs->msr);
-	printbits(regs->msr, msr_bits);
+	print_msr_bits(regs->msr);
 	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
 	trap = TRAP(regs);
 	if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
@@ -1061,13 +1195,10 @@ void show_regs(struct pt_regs * regs)
 
 void exit_thread(void)
 {
-	discard_lazy_cpu_state();
 }
 
 void flush_thread(void)
 {
-	discard_lazy_cpu_state();
-
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	flush_ptrace_hw_breakpoint(current);
 #else /* CONFIG_HAVE_HW_BREAKPOINT */
@@ -1086,10 +1217,7 @@ release_thread(struct task_struct *t)
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	flush_fp_to_thread(src);
-	flush_altivec_to_thread(src);
-	flush_vsx_to_thread(src);
-	flush_spe_to_thread(src);
+	flush_all_to_thread(src);
 	/*
 	 * Flush TM state out so we can copy it.  __switch_to_tm() does this
 	 * flush but it removes the checkpointed state from the current CPU and
@@ -1212,7 +1340,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #ifdef CONFIG_PPC64 
 	if (cpu_has_feature(CPU_FTR_DSCR)) {
 		p->thread.dscr_inherit = current->thread.dscr_inherit;
-		p->thread.dscr = current->thread.dscr;
+		p->thread.dscr = mfspr(SPRN_DSCR);
 	}
 	if (cpu_has_feature(CPU_FTR_HAS_PPR))
 		p->thread.ppr = INIT_PPR;
@@ -1305,7 +1433,6 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 		regs->msr = MSR_USER32;
 	}
 #endif
-	discard_lazy_cpu_state();
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 92dea8df6b26..da5192590c44 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -389,6 +389,7 @@ static void __init prom_printf(const char *format, ...)
 			break;
 		}
 	}
+	va_end(args);
 }
 
 
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 737c0d0b53ac..30a03c03fe73 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -60,6 +60,7 @@ struct pt_regs_offset {
 #define STR(s)	#s			/* convert to string */
 #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
 #define GPR_OFFSET_NAME(num)	\
+	{.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
 	{.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
 #define REG_OFFSET_END {.name = NULL, .offset = 0}
 
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 5a753fae8265..28736ff27fea 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -44,6 +44,9 @@
 #include <asm/mmu.h>
 #include <asm/topology.h>
 
+/* This is here deliberately so it's only used in this file */
+void enter_rtas(unsigned long);
+
 struct rtas_t rtas = {
 	.lock = __ARCH_SPIN_LOCK_UNLOCKED
 };
@@ -93,21 +96,13 @@ static void unlock_rtas(unsigned long flags)
  */
 static void call_rtas_display_status(unsigned char c)
 {
-	struct rtas_args *args = &rtas.args;
 	unsigned long s;
 
 	if (!rtas.base)
 		return;
-	s = lock_rtas();
-
-	args->token = cpu_to_be32(10);
-	args->nargs = cpu_to_be32(1);
-	args->nret  = cpu_to_be32(1);
-	args->rets  = &(args->args[1]);
-	args->args[0] = cpu_to_be32(c);
-
-	enter_rtas(__pa(args));
 
+	s = lock_rtas();
+	rtas_call_unlocked(&rtas.args, 10, 1, 1, NULL, c);
 	unlock_rtas(s);
 }
 
@@ -418,6 +413,36 @@ static char *__fetch_rtas_last_error(char *altbuf)
 #define get_errorlog_buffer()		NULL
 #endif
 
+
+static void
+va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret,
+		      va_list list)
+{
+	int i;
+
+	args->token = cpu_to_be32(token);
+	args->nargs = cpu_to_be32(nargs);
+	args->nret  = cpu_to_be32(nret);
+	args->rets  = &(args->args[nargs]);
+
+	for (i = 0; i < nargs; ++i)
+		args->args[i] = cpu_to_be32(va_arg(list, __u32));
+
+	for (i = 0; i < nret; ++i)
+		args->rets[i] = 0;
+
+	enter_rtas(__pa(args));
+}
+
+void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...)
+{
+	va_list list;
+
+	va_start(list, nret);
+	va_rtas_call_unlocked(args, token, nargs, nret, list);
+	va_end(list);
+}
+
 int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 {
 	va_list list;
@@ -431,22 +456,14 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 		return -1;
 
 	s = lock_rtas();
+
+	/* We use the global rtas args buffer */
 	rtas_args = &rtas.args;
 
-	rtas_args->token = cpu_to_be32(token);
-	rtas_args->nargs = cpu_to_be32(nargs);
-	rtas_args->nret  = cpu_to_be32(nret);
-	rtas_args->rets  = &(rtas_args->args[nargs]);
 	va_start(list, outputs);
-	for (i = 0; i < nargs; ++i)
-		rtas_args->args[i] = cpu_to_be32(va_arg(list, __u32));
+	va_rtas_call_unlocked(rtas_args, token, nargs, nret, list);
 	va_end(list);
 
-	for (i = 0; i < nret; ++i)
-		rtas_args->rets[i] = 0;
-
-	enter_rtas(__pa(rtas_args));
-
 	/* A -1 return code indicates that the last command couldn't
 	   be completed due to a hardware error. */
 	if (be32_to_cpu(rtas_args->rets[0]) == -1)
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index ef7c24e84a62..b6aa378aff63 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -458,7 +458,7 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 	 * contains valid data
 	 */
 	if (current->thread.used_vsr && ctx_has_vsx_region) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		if (copy_vsx_to_user(&frame->mc_vsregs, current))
 			return 1;
 		msr |= MSR_VSX;
@@ -606,7 +606,7 @@ static int save_tm_user_regs(struct pt_regs *regs,
 	 * contains valid data
 	 */
 	if (current->thread.used_vsr) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		if (copy_vsx_to_user(&frame->mc_vsregs, current))
 			return 1;
 		if (msr & MSR_VSX) {
@@ -687,15 +687,6 @@ static long restore_user_regs(struct pt_regs *regs,
 	if (sig)
 		regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
-	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr/evr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec/SPE, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
 #ifdef CONFIG_ALTIVEC
 	/*
 	 * Force the process to reload the altivec registers from
@@ -798,15 +789,6 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	/* Restore the previous little-endian mode */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
-	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr/evr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec/SPE, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
 #ifdef CONFIG_ALTIVEC
 	regs->msr &= ~MSR_VEC;
 	if (msr & MSR_VEC) {
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c676ecec0869..25520794aa37 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -147,7 +147,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	 * VMX data.
 	 */
 	if (current->thread.used_vsr && ctx_has_vsx_region) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		v_regs += ELF_NVRREG;
 		err |= copy_vsx_to_user(v_regs, current);
 		/* set MSR_VSX in the MSR value in the frame to
@@ -270,7 +270,7 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 	 * VMX data.
 	 */
 	if (current->thread.used_vsr) {
-		__giveup_vsx(current);
+		flush_vsx_to_thread(current);
 		v_regs += ELF_NVRREG;
 		tm_v_regs += ELF_NVRREG;
 
@@ -350,15 +350,6 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 		err |=  __get_user(set->sig[0], &sc->oldmask);
 
 	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
-	/*
 	 * Force reload of FP/VEC.
 	 * This has to be done before copying stuff into current->thread.fpr/vr
 	 * for the reasons explained in the previous comment.
@@ -469,15 +460,6 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 	err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);
 
 	/*
-	 * Do this before updating the thread state in
-	 * current->thread.fpr/vr.  That way, if we get preempted
-	 * and another task grabs the FPU/Altivec, it won't be
-	 * tempted to save the current CPU state into the thread_struct
-	 * and corrupt what we are writing there.
-	 */
-	discard_lazy_cpu_state();
-
-	/*
 	 * Force reload of FP/VEC.
 	 * This has to be done before copying stuff into current->thread.fpr/vr
 	 * for the reasons explained in the previous comment.
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index ea43a347a104..4f24606afc3f 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -61,3 +61,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	save_context_stack(trace, tsk->thread.ksp, tsk, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+void
+save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	save_context_stack(trace, regs->gpr[1], current, 0);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index eae33e10b65f..6669b1752512 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -20,9 +20,7 @@ void save_processor_state(void)
 	 * flush out all the special registers so we don't need
 	 * to save them in the snapshot
 	 */
-	flush_fp_to_thread(current);
-	flush_altivec_to_thread(current);
-	flush_spe_to_thread(current);
+	flush_all_to_thread(current);
 
 #ifdef CONFIG_PPC64
 	hard_irq_disable();
diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c
index 2384129f5893..55323a620cfe 100644
--- a/arch/powerpc/kernel/systbl_chk.c
+++ b/arch/powerpc/kernel/systbl_chk.c
@@ -57,4 +57,4 @@
 
 START_TABLE
 #include <asm/systbl.h>
-END_TABLE __NR_syscalls
+END_TABLE NR_syscalls
diff --git a/arch/powerpc/kernel/systbl_chk.sh b/arch/powerpc/kernel/systbl_chk.sh
index 19415e7674a5..31b6e7c358ca 100644
--- a/arch/powerpc/kernel/systbl_chk.sh
+++ b/arch/powerpc/kernel/systbl_chk.sh
@@ -16,7 +16,7 @@ awk	'BEGIN { num = -1; }	# Ignore the beginning of the file
 	/^START_TABLE/ { num = 0; next; }
 	/^END_TABLE/ {
 		if (num != $2) {
-			printf "__NR_syscalls (%s) is not one more than the last syscall (%s)\n",
+			printf "NR_syscalls (%s) is not one more than the last syscall (%s)\n",
 				$2, num - 1;
 			exit(1);
 		}
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1be1092c7204..81b0900a39ee 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -1002,38 +1002,6 @@ static int month_days[12] = {
 	31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31
 };
 
-/*
- * This only works for the Gregorian calendar - i.e. after 1752 (in the UK)
- */
-void GregorianDay(struct rtc_time * tm)
-{
-	int leapsToDate;
-	int lastYear;
-	int day;
-	int MonthOffset[] = { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 };
-
-	lastYear = tm->tm_year - 1;
-
-	/*
-	 * Number of leap corrections to apply up to end of last year
-	 */
-	leapsToDate = lastYear / 4 - lastYear / 100 + lastYear / 400;
-
-	/*
-	 * This year is a leap year if it is divisible by 4 except when it is
-	 * divisible by 100 unless it is divisible by 400
-	 *
-	 * e.g. 1904 was a leap year, 1900 was not, 1996 is, and 2000 was
-	 */
-	day = tm->tm_mon > 2 && leapyear(tm->tm_year);
-
-	day += lastYear*365 + leapsToDate + MonthOffset[tm->tm_mon-1] +
-		   tm->tm_mday;
-
-	tm->tm_wday = day % 7;
-}
-EXPORT_SYMBOL_GPL(GregorianDay);
-
 void to_tm(int tim, struct rtc_time * tm)
 {
 	register int    i;
@@ -1064,9 +1032,9 @@ void to_tm(int tim, struct rtc_time * tm)
 	tm->tm_mday = day + 1;
 
 	/*
-	 * Determine the day of week
+	 * No-one uses the day of the week.
 	 */
-	GregorianDay(tm);
+	tm->tm_wday = -1;
 }
 EXPORT_SYMBOL(to_tm);
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 37de90f8a845..b6becc795bb5 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1313,13 +1313,6 @@ void nonrecoverable_exception(struct pt_regs *regs)
 	die("nonrecoverable exception", regs, SIGKILL);
 }
 
-void trace_syscall(struct pt_regs *regs)
-{
-	printk("Task: %p(%d), PC: %08lX/%08lX, Syscall: %3ld, Result: %s%ld    %s\n",
-	       current, task_pid_nr(current), regs->nip, regs->link, regs->gpr[0],
-	       regs->ccr&0x10000000?"Error=":"", regs->gpr[3], print_tainted());
-}
-
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index b457bfa28436..def1b8b5e6c1 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -671,7 +671,7 @@ static void __init vdso_setup_syscall_map(void)
 	extern unsigned long sys_ni_syscall;
 
 
-	for (i = 0; i < __NR_syscalls; i++) {
+	for (i = 0; i < NR_syscalls; i++) {
 #ifdef CONFIG_PPC64
 		if (sys_call_table[i*2] != sys_ni_syscall)
 			vdso_data->syscall_map_64[i >> 5] |=
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 59cf5f452879..3745113fcc65 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -61,7 +61,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	addi	r3,r3,CFG_SYSCALL_MAP32
 	cmpli	cr0,r4,0
 	beqlr
-	li	r0,__NR_syscalls
+	li	r0,NR_syscalls
 	stw	r0,0(r4)
 	crclr	cr0*4+so
 	blr
diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S
index 2f01c4a0d8a0..184a6ba7f283 100644
--- a/arch/powerpc/kernel/vdso64/datapage.S
+++ b/arch/powerpc/kernel/vdso64/datapage.S
@@ -62,7 +62,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	cmpli	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
-	li	r0,__NR_syscalls
+	li	r0,NR_syscalls
 	stw	r0,0(r4)
 	blr
   .cfi_endproc
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index f5c80d567d8d..162d0f714941 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -29,24 +29,10 @@ _GLOBAL(do_load_up_transact_altivec)
 	addi	r10,r3,THREAD_TRANSACT_VRSTATE
 	REST_32VRS(0,r4,r10)
 
-	/* Disable VEC again. */
-	MTMSRD(r6)
-	isync
-
 	blr
 #endif
 
 /*
- * Enable use of VMX/Altivec for the caller.
- */
-_GLOBAL(vec_enable)
-	mfmsr	r3
-	oris	r3,r3,MSR_VEC@h
-	MTMSRD(r3)
-	isync
-	blr
-
-/*
  * Load state from memory into VMX registers including VSCR.
  * Assumes the caller has enabled VMX in the MSR.
  */
@@ -84,39 +70,6 @@ _GLOBAL(load_up_altivec)
 	MTMSRD(r5)			/* enable use of AltiVec now */
 	isync
 
-/*
- * For SMP, we don't do lazy VMX switching because it just gets too
- * horrendously complex, especially when a task switches from one CPU
- * to another.  Instead we call giveup_altvec in switch_to.
- * VRSAVE isn't dealt with here, that is done in the normal context
- * switch code. Note that we could rely on vrsave value to eventually
- * avoid saving all of the VREGs here...
- */
-#ifndef CONFIG_SMP
-	LOAD_REG_ADDRBASE(r3, last_task_used_altivec)
-	toreal(r3)
-	PPC_LL	r4,ADDROFF(last_task_used_altivec)(r3)
-	PPC_LCMPI	0,r4,0
-	beq	1f
-
-	/* Save VMX state to last_task_used_altivec's THREAD struct */
-	toreal(r4)
-	addi	r4,r4,THREAD
-	addi	r6,r4,THREAD_VRSTATE
-	SAVE_32VRS(0,r5,r6)
-	mfvscr	v0
-	li	r10,VRSTATE_VSCR
-	stvx	v0,r10,r6
-	/* Disable VMX for last_task_used_altivec */
-	PPC_LL	r5,PT_REGS(r4)
-	toreal(r5)
-	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r10,MSR_VEC@h
-	andc	r4,r4,r10
-	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
-
 	/* Hack: if we get an altivec unavailable trap with VRSAVE
 	 * set to all zeros, we assume this is a broken application
 	 * that fails to set it properly, and thus we switch it to
@@ -145,39 +98,15 @@ _GLOBAL(load_up_altivec)
 	lvx	v0,r10,r6
 	mtvscr	v0
 	REST_32VRS(0,r4,r6)
-#ifndef CONFIG_SMP
-	/* Update last_task_used_altivec to 'current' */
-	subi	r4,r5,THREAD		/* Back to 'current' */
-	fromreal(r4)
-	PPC_STL	r4,ADDROFF(last_task_used_altivec)(r3)
-#endif /* CONFIG_SMP */
 	/* restore registers and return */
 	blr
 
-_GLOBAL(giveup_altivec_notask)
-	mfmsr	r3
-	andis.	r4,r3,MSR_VEC@h
-	bnelr				/* Already enabled? */
-	oris	r3,r3,MSR_VEC@h
-	SYNC
-	MTMSRD(r3)			/* enable use of VMX now */
-	isync
-	blr
-
 /*
- * giveup_altivec(tsk)
+ * __giveup_altivec(tsk)
  * Disable VMX for the task given as the argument,
  * and save the vector registers in its thread_struct.
- * Enables the VMX for use in the kernel on return.
  */
-_GLOBAL(giveup_altivec)
-	mfmsr	r5
-	oris	r5,r5,MSR_VEC@h
-	SYNC
-	MTMSRD(r5)			/* enable use of VMX now */
-	isync
-	PPC_LCMPI	0,r3,0
-	beqlr				/* if no previous owner, done */
+_GLOBAL(__giveup_altivec)
 	addi	r3,r3,THREAD		/* want THREAD of task */
 	PPC_LL	r7,THREAD_VRSAVEAREA(r3)
 	PPC_LL	r5,PT_REGS(r3)
@@ -203,11 +132,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
 	andc	r4,r4,r3		/* disable FP for previous task */
 	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	LOAD_REG_ADDRBASE(r4,last_task_used_altivec)
-	PPC_STL	r5,ADDROFF(last_task_used_altivec)(r4)
-#endif /* CONFIG_SMP */
 	blr
 
 #ifdef CONFIG_VSX
@@ -230,20 +154,6 @@ _GLOBAL(load_up_vsx)
 	andis.	r5,r12,MSR_VEC@h
 	beql+	load_up_altivec		/* skip if already loaded */
 
-#ifndef CONFIG_SMP
-	ld	r3,last_task_used_vsx@got(r2)
-	ld	r4,0(r3)
-	cmpdi	0,r4,0
-	beq	1f
-	/* Disable VSX for last_task_used_vsx */
-	addi	r4,r4,THREAD
-	ld	r5,PT_REGS(r4)
-	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	lis	r6,MSR_VSX@h
-	andc	r6,r4,r6
-	std	r6,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
-#endif /* CONFIG_SMP */
 	ld	r4,PACACURRENT(r13)
 	addi	r4,r4,THREAD		/* Get THREAD */
 	li	r6,1
@@ -251,27 +161,14 @@ _GLOBAL(load_up_vsx)
 	/* enable use of VSX after return */
 	oris	r12,r12,MSR_VSX@h
 	std	r12,_MSR(r1)
-#ifndef CONFIG_SMP
-	/* Update last_task_used_vsx to 'current' */
-	ld	r4,PACACURRENT(r13)
-	std	r4,0(r3)
-#endif /* CONFIG_SMP */
 	b	fast_exception_return
 
 /*
  * __giveup_vsx(tsk)
  * Disable VSX for the task given as the argument.
  * Does NOT save vsx registers.
- * Enables the VSX for use in the kernel on return.
  */
 _GLOBAL(__giveup_vsx)
-	mfmsr	r5
-	oris	r5,r5,MSR_VSX@h
-	mtmsrd	r5			/* enable use of VSX now */
-	isync
-
-	cmpdi	0,r3,0
-	beqlr-				/* if no previous owner, done */
 	addi	r3,r3,THREAD		/* want THREAD of task */
 	ld	r5,PT_REGS(r3)
 	cmpdi	0,r5,0
@@ -281,11 +178,6 @@ _GLOBAL(__giveup_vsx)
 	andc	r4,r4,r3		/* disable VSX for previous task */
 	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
-#ifndef CONFIG_SMP
-	li	r5,0
-	ld	r4,last_task_used_vsx@got(r2)
-	std	r5,0(r4)
-#endif /* CONFIG_SMP */
 	blr
 
 #endif /* CONFIG_VSX */