Merge tag 'powerpc-5.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Slightly late as I had to rebase mid-week to insert a bug fix:

   - A large series from Nick for 64-bit to further rework our exception
     vectors, and rewrite portions of the syscall entry/exit and
     interrupt return in C. The result is much easier to follow code
     that is also faster in general.

   - Cleanup of our ptrace code to split various parts out that had
     become badly intertwined with #ifdefs over the years.

   - Changes to our NUMA setup under the PowerVM hypervisor which should
     hopefully avoid non-sensical topologies which can lead to warnings
     from the workqueue code and other problems.

   - MAINTAINERS updates to remove some of our old orphan entries and
     update the status of others.

   - Quite a few other small changes and fixes all over the map.

  Thanks to: Abdul Haleem, afzal mohammed, Alexey Kardashevskiy, Andrew
  Donnellan, Aneesh Kumar K.V, Balamuruhan S, Cédric Le Goater, Chen
  Zhou, Christophe JAILLET, Christophe Leroy, Christoph Hellwig, Clement
  Courbet, Daniel Axtens, David Gibson, Douglas Miller, Fabiano Rosas,
  Fangrui Song, Ganesh Goudar, Gautham R. Shenoy, Greg Kroah-Hartman,
  Greg Kurz, Gustavo Luiz Duarte, Hari Bathini, Ilie Halip, Jan Kara,
  Joe Lawrence, Joe Perches, Kajol Jain, Larry Finger, Laurentiu Tudor,
  Leonardo Bras, Libor Pechacek, Madhavan Srinivasan, Mahesh Salgaonkar,
  Masahiro Yamada, Masami Hiramatsu, Mauricio Faria de Oliveira, Michael
  Neuling, Michal Suchanek, Mike Rapoport, Nageswara R Sastry, Nathan
  Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Nick
  Desaulniers, Oliver O'Halloran, Po-Hsu Lin, Pratik Rajesh Sampat,
  Rasmus Villemoes, Ravi Bangoria, Roman Bolshakov, Sam Bobroff,
  Sandipan Das, Santosh S, Sedat Dilek, Segher Boessenkool, Shilpasri G
  Bhat, Sourabh Jain, Srikar Dronamraju, Stephen Rothwell, Tyrel
  Datwyler, Vaibhav Jain, YueHaibing"

* tag 'powerpc-5.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (158 commits)
  powerpc: Make setjmp/longjmp signature standard
  powerpc/cputable: Remove unnecessary copy of cpu_spec->oprofile_type
  powerpc: Suppress .eh_frame generation
  powerpc: Drop -fno-dwarf2-cfi-asm
  powerpc/32: drop unused ISA_DMA_THRESHOLD
  powerpc/powernv: Add documentation for the opal sensor_groups sysfs interfaces
  selftests/powerpc: Fix try-run when source tree is not writable
  powerpc/vmlinux.lds: Explicitly retain .gnu.hash
  powerpc/ptrace: move ptrace_triggered() into hw_breakpoint.c
  powerpc/ptrace: create ppc_gethwdinfo()
  powerpc/ptrace: create ptrace_get_debugreg()
  powerpc/ptrace: split out ADV_DEBUG_REGS related functions.
  powerpc/ptrace: move register viewing functions out of ptrace.c
  powerpc/ptrace: split out TRANSACTIONAL_MEM related functions.
  powerpc/ptrace: split out SPE related functions.
  powerpc/ptrace: split out ALTIVEC related functions.
  powerpc/ptrace: split out VSX related functions.
  powerpc/ptrace: drop PARAMETER_SAVE_AREA_OFFSET
  powerpc/ptrace: drop unnecessary #ifdefs CONFIG_PPC64
  powerpc/ptrace: remove unused header includes
  ...

1 files changed, 185 insertions, 710 deletions

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6ba675b0cf7d..63f0a4414618 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -16,6 +16,7 @@
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <asm/cache.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/page.h>
@@ -69,6 +70,7 @@ BEGIN_FTR_SECTION
 	bne	.Ltabort_syscall
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
+_ASM_NOKPROBE_SYMBOL(system_call_common)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
@@ -76,342 +78,122 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
+	std	r2,GPR2(r1)
 #ifdef CONFIG_PPC_FSL_BOOK3E
 START_BTB_FLUSH_SECTION
 	BTB_FLUSH(r10)
 END_BTB_FLUSH_SECTION
 #endif
-	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
-	std	r2,GPR2(r1)
+	ld	r2,PACATOC(r13)
+	mfcr	r12
+	li	r11,0
+	/* Can we avoid saving r3-r8 in common case? */
 	std	r3,GPR3(r1)
-	mfcr	r2
 	std	r4,GPR4(r1)
 	std	r5,GPR5(r1)
 	std	r6,GPR6(r1)
 	std	r7,GPR7(r1)
 	std	r8,GPR8(r1)
-	li	r11,0
+	/* Zero r9-r12, this should only be required when restoring all GPRs */
 	std	r11,GPR9(r1)
 	std	r11,GPR10(r1)
 	std	r11,GPR11(r1)
 	std	r11,GPR12(r1)
+	std	r9,GPR13(r1)
+	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
 	std	r11,_CTR(r1)
-	std	r9,GPR13(r1)
 	mflr	r10
+
 	/*
 	 * This clears CR0.SO (bit 28), which is the error indication on
 	 * return from this system call.
 	 */
-	rldimi	r2,r11,28,(63-28)
-	li	r11,0xc01
+	rldimi	r12,r11,28,(63-28)
+	li	r11,0xc00
 	std	r10,_LINK(r1)
 	std	r11,_TRAP(r1)
+	std	r12,_CCR(r1)
 	std	r3,ORIG_GPR3(r1)
-	std	r2,_CCR(r1)
-	ld	r2,PACATOC(r13)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
+	addi	r10,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
-	std	r11,-16(r9)		/* "regshere" marker */
-
-	kuap_check_amr r10, r11
-
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
-BEGIN_FW_FTR_SECTION
-	/* see if there are any DTL entries to process */
-	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
-	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
-	addi	r10,r10,LPPACA_DTLIDX
-	LDX_BE	r10,0,r10		/* get log write index */
-	cmpd	r11,r10
-	beq+	33f
-	bl	accumulate_stolen_time
-	REST_GPR(0,r1)
-	REST_4GPRS(3,r1)
-	REST_2GPRS(7,r1)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-33:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
-
-	/*
-	 * A syscall should always be called with interrupts enabled
-	 * so we just unconditionally hard-enable here. When some kind
-	 * of irq tracing is used, we additionally check that condition
-	 * is correct
-	 */
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
-	lbz	r10,PACAIRQSOFTMASK(r13)
-1:	tdnei	r10,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
-
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r11,MSR_RI
-	ori	r11,r11,MSR_EE
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-system_call:			/* label this so stack traces look sane */
-	/* We do need to set SOFTE in the stack frame or the return
-	 * from interrupt will be painful
-	 */
-	li	r10,IRQS_ENABLED
-	std	r10,SOFTE(r1)
-
-	ld	r11, PACA_THREAD_INFO(r13)
-	ld	r10,TI_FLAGS(r11)
-	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
-	bne	.Lsyscall_dotrace		/* does not return */
-	cmpldi	0,r0,NR_syscalls
-	bge-	.Lsyscall_enosys
+	std	r11,-16(r10)		/* "regshere" marker */
 
-.Lsyscall:
-/*
- * Need to vector to 32 Bit or default sys_call_table here,
- * based on caller's run-mode / personality.
- */
-	ld	r11,SYS_CALL_TABLE@toc(2)
-	andis.	r10,r10,_TIF_32BIT@h
-	beq	15f
-	ld	r11,COMPAT_SYS_CALL_TABLE@toc(2)
-	clrldi	r3,r3,32
-	clrldi	r4,r4,32
-	clrldi	r5,r5,32
-	clrldi	r6,r6,32
-	clrldi	r7,r7,32
-	clrldi	r8,r8,32
-15:
-	slwi	r0,r0,3
-
-	barrier_nospec_asm
 	/*
-	 * Prevent the load of the handler below (based on the user-passed
-	 * system call number) being speculatively executed until the test
-	 * against NR_syscalls and branch to .Lsyscall_enosys above has
-	 * committed.
+	 * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
+	 * would clobber syscall parameters. Also we always enter with IRQs
+	 * enabled and nothing pending. system_call_exception() will call
+	 * trace_hardirqs_off().
 	 */
+	li	r11,IRQS_ALL_DISABLED
+	li	r12,PACA_IRQ_HARD_DIS
+	stb	r11,PACAIRQSOFTMASK(r13)
+	stb	r12,PACAIRQHAPPENED(r13)
 
-	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
-	mtctr   r12
-	bctrl			/* Call handler */
+	/* Calling convention has r9 = orig r0, r10 = regs */
+	mr	r9,r0
+	bl	system_call_exception
 
-	/* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */
 .Lsyscall_exit:
-	std	r3,RESULT(r1)
-
-#ifdef CONFIG_DEBUG_RSEQ
-	/* Check whether the syscall is issued inside a restartable sequence */
-	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      rseq_syscall
-	ld	r3,RESULT(r1)
-#endif
-
-	ld	r12, PACA_THREAD_INFO(r13)
-
-	ld	r8,_MSR(r1)
-
-/*
- * This is a few instructions into the actual syscall exit path (which actually
- * starts at .Lsyscall_exit) to cater to kprobe blacklisting and to reduce the
- * number of visible symbols for profiling purposes.
- *
- * We can probe from system_call until this point as MSR_RI is set. But once it
- * is cleared below, we won't be able to take a trap.
- *
- * This is blacklisted from kprobes further below with _ASM_NOKPROBE_SYMBOL().
- */
-system_call_exit:
-	/*
-	 * Disable interrupts so current_thread_info()->flags can't change,
-	 * and so that we don't get interrupted after loading SRR0/1.
-	 *
-	 * Leave MSR_RI enabled for now, because with THREAD_INFO_IN_TASK we
-	 * could fault on the load of the TI_FLAGS below.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r11,MSR_RI
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
+	addi    r4,r1,STACK_FRAME_OVERHEAD
+	bl	syscall_exit_prepare
 
-	ld	r9,TI_FLAGS(r12)
-	li	r11,-MAX_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
-	bne-	.Lsyscall_exit_work
+	ld	r2,_CCR(r1)
+	ld	r4,_NIP(r1)
+	ld	r5,_MSR(r1)
+	ld	r6,_LINK(r1)
 
-	andi.	r0,r8,MSR_FP
-	beq 2f
-#ifdef CONFIG_ALTIVEC
-	andis.	r0,r8,MSR_VEC@h
-	bne	3f
-#endif
-2:	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_math
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-
-3:	cmpld	r3,r11
-	ld	r5,_CCR(r1)
-	bge-	.Lsyscall_error
-.Lsyscall_error_cont:
-	ld	r7,_NIP(r1)
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1			/* to clear the reservation */
 END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
-	andi.	r6,r8,MSR_PR
-	ld	r4,_LINK(r1)
 
-	kuap_check_amr r10, r11
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r5
+	mtlr	r6
 
-#ifdef CONFIG_PPC_BOOK3S
-	/*
-	 * Clear MSR_RI, MSR_EE is already and remains disabled. We could do
-	 * this later, but testing shows that doing it here causes less slow
-	 * down than doing it closer to the rfid.
-	 */
+	cmpdi	r3,0
+	bne	.Lsyscall_restore_regs
+	/* Zero volatile regs that may contain sensitive kernel data */
+	li	r0,0
+	li	r4,0
+	li	r5,0
+	li	r6,0
+	li	r7,0
+	li	r8,0
+	li	r9,0
+	li	r10,0
 	li	r11,0
-	mtmsrd	r11,1
-#endif
-
-	beq-	1f
-	ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
+	li	r12,0
+	mtctr	r0
+	mtspr	SPRN_XER,r0
+.Lsyscall_restore_regs_cont:
 
 BEGIN_FTR_SECTION
 	HMT_MEDIUM_LOW
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	std	r8, PACATMSCRATCH(r13)
-#endif
-
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
 	 * The value of AMR only matters while we're in the kernel.
 	 */
-	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	mtcr	r2
 	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r13,GPR13(r1)
 	ld	r1,GPR1(r1)
-	mtlr	r4
-	mtcr	r5
-	mtspr	SPRN_SRR0,r7
-	mtspr	SPRN_SRR1,r8
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 
-1:	/* exit to kernel */
-	kuap_restore_amr r2
-
-	ld	r2,GPR2(r1)
-	ld	r1,GPR1(r1)
-	mtlr	r4
-	mtcr	r5
-	mtspr	SPRN_SRR0,r7
-	mtspr	SPRN_SRR1,r8
-	RFI_TO_KERNEL
-	b	.	/* prevent speculative execution */
-
-.Lsyscall_error:
-	oris	r5,r5,0x1000	/* Set SO bit in CR */
-	neg	r3,r3
-	std	r5,_CCR(r1)
-	b	.Lsyscall_error_cont
-
-/* Traced system call support */
-.Lsyscall_dotrace:
-	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_enter
-
-	/*
-	 * We use the return value of do_syscall_trace_enter() as the syscall
-	 * number. If the syscall was rejected for any reason do_syscall_trace_enter()
-	 * returns an invalid syscall number and the test below against
-	 * NR_syscalls will fail.
-	 */
-	mr	r0,r3
-
-	/* Restore argument registers just clobbered and/or possibly changed. */
-	ld	r3,GPR3(r1)
-	ld	r4,GPR4(r1)
-	ld	r5,GPR5(r1)
-	ld	r6,GPR6(r1)
-	ld	r7,GPR7(r1)
-	ld	r8,GPR8(r1)
-
-	/* Repopulate r9 and r10 for the syscall path */
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-	ld	r10, PACA_THREAD_INFO(r13)
-	ld	r10,TI_FLAGS(r10)
-
-	cmpldi	r0,NR_syscalls
-	blt+	.Lsyscall
-
-	/* Return code is already in r3 thanks to do_syscall_trace_enter() */
-	b	.Lsyscall_exit
-
-
-.Lsyscall_enosys:
-	li	r3,-ENOSYS
-	b	.Lsyscall_exit
-	
-.Lsyscall_exit_work:
-	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
-	 If TIF_NOERROR is set, just save r3 as it is. */
-
-	andi.	r0,r9,_TIF_RESTOREALL
-	beq+	0f
+.Lsyscall_restore_regs:
+	ld	r3,_CTR(r1)
+	ld	r4,_XER(r1)
 	REST_NVGPRS(r1)
-	b	2f
-0:	cmpld	r3,r11		/* r11 is -MAX_ERRNO */
-	blt+	1f
-	andi.	r0,r9,_TIF_NOERROR
-	bne-	1f
-	ld	r5,_CCR(r1)
-	neg	r3,r3
-	oris	r5,r5,0x1000	/* Set SO bit in CR */
-	std	r5,_CCR(r1)
-1:	std	r3,GPR3(r1)
-2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
-	beq	4f
-
-	/* Clear per-syscall TIF flags if any are set.  */
-
-	li	r11,_TIF_PERSYSCALL_MASK
-	addi	r12,r12,TI_FLAGS
-3:	ldarx	r10,0,r12
-	andc	r10,r10,r11
-	stdcx.	r10,0,r12
-	bne-	3b
-	subi	r12,r12,TI_FLAGS
-
-4:	/* Anything else left to do? */
-BEGIN_FTR_SECTION
-	lis	r3,DEFAULT_PPR@highest	/* Set default PPR */
-	sldi	r3,r3,32	/* bits 11-13 are used for ppr */
-	std	r3,_PPR(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
-	beq	ret_from_except_lite
-
-	/* Re-enable interrupts */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r10,MSR_RI
-	ori	r10,r10,MSR_EE
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_leave
-	b	ret_from_except
+	mtctr	r3
+	mtspr	SPRN_XER,r4
+	ld	r0,GPR0(r1)
+	REST_8GPRS(4, r1)
+	ld	r12,GPR12(r1)
+	b	.Lsyscall_restore_regs_cont
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 .Ltabort_syscall:
@@ -439,64 +221,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
-_ASM_NOKPROBE_SYMBOL(system_call_common);
-_ASM_NOKPROBE_SYMBOL(system_call_exit);
-
-/* Save non-volatile GPRs, if not already saved. */
-_GLOBAL(save_nvgprs)
-	ld	r11,_TRAP(r1)
-	andi.	r0,r11,1
-	beqlr-
-	SAVE_NVGPRS(r1)
-	clrrdi	r0,r11,1
-	std	r0,_TRAP(r1)
-	blr
-_ASM_NOKPROBE_SYMBOL(save_nvgprs);
-
-	
-/*
- * The sigsuspend and rt_sigsuspend system calls can call do_signal
- * and thus put the process into the stopped state where we might
- * want to examine its user state with ptrace.  Therefore we need
- * to save all the nonvolatile registers (r14 - r31) before calling
- * the C code.  Similarly, fork, vfork and clone need the full
- * register state on the stack so that it can be copied to the child.
- */
-
-_GLOBAL(ppc_fork)
-	bl	save_nvgprs
-	bl	sys_fork
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_vfork)
-	bl	save_nvgprs
-	bl	sys_vfork
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_clone)
-	bl	save_nvgprs
-	bl	sys_clone
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_clone3)
-       bl      save_nvgprs
-       bl      sys_clone3
-       b       .Lsyscall_exit
-
-_GLOBAL(ppc32_swapcontext)
-	bl	save_nvgprs
-	bl	compat_sys_swapcontext
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc64_swapcontext)
-	bl	save_nvgprs
-	bl	sys_swapcontext
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_switch_endian)
-	bl	save_nvgprs
-	bl	sys_switch_endian
-	b	.Lsyscall_exit
 
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
@@ -516,6 +240,19 @@ _GLOBAL(ret_from_kernel_thread)
 	li	r3,0
 	b	.Lsyscall_exit
 
+#ifdef CONFIG_PPC_BOOK3E
+/* Save non-volatile GPRs, if not already saved. */
+_GLOBAL(save_nvgprs)
+	ld	r11,_TRAP(r1)
+	andi.	r0,r11,1
+	beqlr-
+	SAVE_NVGPRS(r1)
+	clrrdi	r0,r11,1
+	std	r0,_TRAP(r1)
+	blr
+_ASM_NOKPROBE_SYMBOL(save_nvgprs);
+#endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 
 #define FLUSH_COUNT_CACHE	\
@@ -578,7 +315,7 @@ flush_count_cache:
  * state of one is saved on its kernel stack.  Then the state
  * of the other is restored from its kernel stack.  The memory
  * management hardware is updated to the second process's state.
- * Finally, we can return to the second process, via ret_from_except.
+ * Finally, we can return to the second process, via interrupt_return.
  * On entry, r3 points to the THREAD for the current task, r4
  * points to the THREAD for the new task.
  *
@@ -730,408 +467,146 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	addi	r1,r1,SWITCH_FRAME_SIZE
 	blr
 
-	.align	7
-_GLOBAL(ret_from_except)
-	ld	r11,_TRAP(r1)
-	andi.	r0,r11,1
-	bne	ret_from_except_lite
-	REST_NVGPRS(r1)
-
-_GLOBAL(ret_from_except_lite)
-	/*
-	 * Disable interrupts so that current_thread_info()->flags
-	 * can't change between when we test it and when we return
-	 * from the interrupt.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r10,MSR_RI
-	mtmsrd	r10,1		  /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-
-	ld	r9, PACA_THREAD_INFO(r13)
-	ld	r3,_MSR(r1)
-#ifdef CONFIG_PPC_BOOK3E
-	ld	r10,PACACURRENT(r13)
-#endif /* CONFIG_PPC_BOOK3E */
-	ld	r4,TI_FLAGS(r9)
-	andi.	r3,r3,MSR_PR
-	beq	resume_kernel
-#ifdef CONFIG_PPC_BOOK3E
-	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
-#endif /* CONFIG_PPC_BOOK3E */
-
-	/* Check current_thread_info()->flags */
-	andi.	r0,r4,_TIF_USER_WORK_MASK
-	bne	1f
-#ifdef CONFIG_PPC_BOOK3E
+#ifdef CONFIG_PPC_BOOK3S
 	/*
-	 * Check to see if the dbcr0 register is set up to debug.
-	 * Use the internal debug mode bit to do this.
-	 */
-	andis.	r0,r3,DBCR0_IDM@h
-	beq	restore
-	mfmsr	r0
-	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
-	mtmsr	r0
-	mtspr	SPRN_DBCR0,r3
-	li	r10, -1
-	mtspr	SPRN_DBSR,r10
-	b	restore
-#else
+	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
+	 * touched, AMR not set, no exit work created, then this can be used.
+	 */
+	.balign IFETCH_ALIGN_BYTES
+	.globl fast_interrupt_return
+fast_interrupt_return:
+_ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
+	ld	r4,_MSR(r1)
+	andi.	r0,r4,MSR_PR
+	bne	.Lfast_user_interrupt_return
+	andi.	r0,r4,MSR_RI
+	li	r3,0 /* 0 return value, no EMULATE_STACK_STORE */
+	bne+	.Lfast_kernel_interrupt_return
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_math
-	b	restore
-#endif
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	2f
-	bl	restore_interrupts
-	SCHEDULE_USER
-	b	ret_from_except_lite
-2:
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	andi.	r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
-	bne	3f		/* only restore TM if nothing else to do */
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_tm_state
-	b	restore
-3:
-#endif
-	bl	save_nvgprs
-	/*
-	 * Use a non volatile GPR to save and restore our thread_info flags
-	 * across the call to restore_interrupts.
-	 */
-	mr	r30,r4
-	bl	restore_interrupts
-	mr	r4,r30
+	bl	unrecoverable_exception
+	b	. /* should not get here */
+
+	.balign IFETCH_ALIGN_BYTES
+	.globl interrupt_return
+interrupt_return:
+_ASM_NOKPROBE_SYMBOL(interrupt_return)
+	ld	r4,_MSR(r1)
+	andi.	r0,r4,MSR_PR
+	beq	.Lkernel_interrupt_return
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_notify_resume
-	b	ret_from_except
-
-resume_kernel:
-	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
-	andis.	r8,r4,_TIF_EMULATE_STACK_STORE@h
-	beq+	1f
+	bl	interrupt_exit_user_prepare
+	cmpdi	r3,0
+	bne-	.Lrestore_nvgprs
 
-	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
+.Lfast_user_interrupt_return:
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
+BEGIN_FTR_SECTION
+	ld	r10,_PPR(r1)
+	mtspr	SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
 
-	ld	r3,GPR1(r1)
-	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
-	mr	r4,r1			/* src:  current exception frame */
-	mr	r1,r3			/* Reroute the trampoline frame to r1 */
+BEGIN_FTR_SECTION
+	stdcx.	r0,0,r1		/* to clear the reservation */
+FTR_SECTION_ELSE
+	ldarx	r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
-	/* Copy from the original to the trampoline. */
-	li	r5,INT_FRAME_SIZE/8	/* size: INT_FRAME_SIZE */
-	li	r6,0			/* start offset: 0 */
-	mtctr	r5
-2:	ldx	r0,r6,r4
-	stdx	r0,r6,r3
-	addi	r6,r6,8
-	bdnz	2b
-
-	/* Do real store operation to complete stdu */
-	ld	r5,GPR1(r1)
-	std	r8,0(r5)
-
-	/* Clear _TIF_EMULATE_STACK_STORE flag */
-	lis	r11,_TIF_EMULATE_STACK_STORE@h
-	addi	r5,r9,TI_FLAGS
-0:	ldarx	r4,0,r5
-	andc	r4,r4,r11
-	stdcx.	r4,0,r5
-	bne-	0b
-1:
-
-#ifdef CONFIG_PREEMPTION
-	/* Check if we need to preempt */
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq+	restore
-	/* Check that preempt_count() == 0 and interrupts are enabled */
-	lwz	r8,TI_PREEMPT(r9)
-	cmpwi	cr0,r8,0
-	bne	restore
-	ld	r0,SOFTE(r1)
-	andi.	r0,r0,IRQS_DISABLED
-	bne	restore
+	ld	r3,_CCR(r1)
+	ld	r4,_LINK(r1)
+	ld	r5,_CTR(r1)
+	ld	r6,_XER(r1)
+	li	r0,0
 
-	/*
-	 * Here we are preempting the current task. We want to make
-	 * sure we are soft-disabled first and reconcile irq state.
-	 */
-	RECONCILE_IRQ_STATE(r3,r4)
-	bl	preempt_schedule_irq
+	REST_4GPRS(7, r1)
+	REST_2GPRS(11, r1)
+	REST_GPR(13, r1)
 
-	/*
-	 * arch_local_irq_restore() from preempt_schedule_irq above may
-	 * enable hard interrupt but we really should disable interrupts
-	 * when we return from the interrupt, and so that we don't get
-	 * interrupted after loading SRR0/1.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r10,MSR_RI
-	mtmsrd	r10,1		  /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-#endif /* CONFIG_PREEMPTION */
+	mtcr	r3
+	mtlr	r4
+	mtctr	r5
+	mtspr	SPRN_XER,r6
 
-	.globl	fast_exc_return_irq
-fast_exc_return_irq:
-restore:
-	/*
-	 * This is the main kernel exit path. First we check if we
-	 * are about to re-enable interrupts
-	 */
-	ld	r5,SOFTE(r1)
-	lbz	r6,PACAIRQSOFTMASK(r13)
-	andi.	r5,r5,IRQS_DISABLED
-	bne	.Lrestore_irq_off
+	REST_4GPRS(2, r1)
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
 
-	/* We are enabling, were we already enabled ? Yes, just return */
-	andi.	r6,r6,IRQS_DISABLED
-	beq	cr0,.Ldo_restore
+.Lrestore_nvgprs:
+	REST_NVGPRS(r1)
+	b	.Lfast_user_interrupt_return
 
-	/*
-	 * We are about to soft-enable interrupts (we are hard disabled
-	 * at this point). We check if there's anything that needs to
-	 * be replayed first.
-	 */
-	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
-	bne-	.Lrestore_check_irq_replay
+	.balign IFETCH_ALIGN_BYTES
+.Lkernel_interrupt_return:
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	interrupt_exit_kernel_prepare
 
-	/*
-	 * Get here when nothing happened while soft-disabled, just
-	 * soft-enable and move-on. We will hard-enable as a side
-	 * effect of rfi
-	 */
-.Lrestore_no_replay:
-	TRACE_ENABLE_INTS
-	li	r0,IRQS_ENABLED
-	stb	r0,PACAIRQSOFTMASK(r13);
+.Lfast_kernel_interrupt_return:
+	cmpdi	cr1,r3,0
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
 
-	/*
-	 * Final return path. BookE is handled in a different file
-	 */
-.Ldo_restore:
-#ifdef CONFIG_PPC_BOOK3E
-	b	exception_return_book3e
-#else
-	/*
-	 * Clear the reservation. If we know the CPU tracks the address of
-	 * the reservation then we can potentially save some cycles and use
-	 * a larx. On POWER6 and POWER7 this is significantly faster.
-	 */
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */
 FTR_SECTION_ELSE
-	ldarx	r4,0,r1
+	ldarx	r0,0,r1
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
-	/*
-	 * Some code path such as load_up_fpu or altivec return directly
-	 * here. They run entirely hard disabled and do not alter the
-	 * interrupt state. They also don't use lwarx/stwcx. and thus
-	 * are known not to leave dangling reservations.
-	 */
-	.globl	fast_exception_return
-fast_exception_return:
-	ld	r3,_MSR(r1)
+	ld	r3,_LINK(r1)
 	ld	r4,_CTR(r1)
-	ld	r0,_LINK(r1)
-	mtctr	r4
-	mtlr	r0
-	ld	r4,_XER(r1)
-	mtspr	SPRN_XER,r4
-
-	kuap_check_amr r5, r6
-
-	REST_8GPRS(5, r1)
-
-	andi.	r0,r3,MSR_RI
-	beq-	.Lunrecov_restore
-
-	/*
-	 * Clear RI before restoring r13.  If we are returning to
-	 * userspace and we take an exception after restoring r13,
-	 * we end up corrupting the userspace r13 value.
-	 */
-	li	r4,0
-	mtmsrd	r4,1
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	/* TM debug */
-	std	r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
-#endif
-	/*
-	 * r13 is our per cpu area, only restore it if we are returning to
-	 * userspace the value stored in the stack frame may belong to
-	 * another CPU.
-	 */
-	andi.	r0,r3,MSR_PR
-	beq	1f
-BEGIN_FTR_SECTION
-	/* Restore PPR */
-	ld	r2,_PPR(r1)
-	mtspr	SPRN_PPR,r2
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
-	REST_GPR(13, r1)
-
-	/*
-	 * We don't need to restore AMR on the way back to userspace for KUAP.
-	 * The value of AMR only matters while we're in the kernel.
-	 */
-	mtspr	SPRN_SRR1,r3
-
-	ld	r2,_CCR(r1)
-	mtcrf	0xFF,r2
-	ld	r2,_NIP(r1)
-	mtspr	SPRN_SRR0,r2
-
-	ld	r0,GPR0(r1)
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
-	ld	r4,GPR4(r1)
-	ld	r1,GPR1(r1)
-	RFI_TO_USER
-	b	.	/* prevent speculative execution */
+	ld	r5,_XER(r1)
+	ld	r6,_CCR(r1)
+	li	r0,0
 
-1:	mtspr	SPRN_SRR1,r3
+	REST_4GPRS(7, r1)
+	REST_2GPRS(11, r1)
 
-	ld	r2,_CCR(r1)
-	mtcrf	0xFF,r2
-	ld	r2,_NIP(r1)
-	mtspr	SPRN_SRR0,r2
+	mtlr	r3
+	mtctr	r4
+	mtspr	SPRN_XER,r5
 
 	/*
 	 * Leaving a stale exception_marker on the stack can confuse
 	 * the reliable stack unwinder later on. Clear it.
 	 */
-	li	r2,0
-	std	r2,STACK_FRAME_OVERHEAD-16(r1)
-
-	ld	r0,GPR0(r1)
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
+	std	r0,STACK_FRAME_OVERHEAD-16(r1)
 
-	kuap_restore_amr r4
+	REST_4GPRS(2, r1)
 
-	ld	r4,GPR4(r1)
-	ld	r1,GPR1(r1)
+	bne-	cr1,1f /* emulate stack store */
+	mtcr	r6
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
 	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
-#endif /* CONFIG_PPC_BOOK3E */
-
-	/*
-	 * We are returning to a context with interrupts soft disabled.
-	 *
-	 * However, we may also about to hard enable, so we need to
-	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
-	 * or that bit can get out of sync and bad things will happen
-	 */
-.Lrestore_irq_off:
-	ld	r3,_MSR(r1)
-	lbz	r7,PACAIRQHAPPENED(r13)
-	andi.	r0,r3,MSR_EE
-	beq	1f
-	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
-	stb	r7,PACAIRQHAPPENED(r13)
-1:
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
-	/* The interrupt should not have soft enabled. */
-	lbz	r7,PACAIRQSOFTMASK(r13)
-1:	tdeqi	r7,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
-	b	.Ldo_restore
-
-	/*
-	 * Something did happen, check if a re-emit is needed
-	 * (this also clears paca->irq_happened)
-	 */
-.Lrestore_check_irq_replay:
-	/* XXX: We could implement a fast path here where we check
-	 * for irq_happened being just 0x01, in which case we can
-	 * clear it and return. That means that we would potentially
-	 * miss a decrementer having wrapped all the way around.
-	 *
-	 * Still, this might be useful for things like hash_page
-	 */
-	bl	__check_irq_replay
-	cmpwi	cr0,r3,0
-	beq	.Lrestore_no_replay
- 
-	/*
-	 * We need to re-emit an interrupt. We do so by re-using our
-	 * existing exception frame. We first change the trap value,
-	 * but we need to ensure we preserve the low nibble of it
-	 */
-	ld	r4,_TRAP(r1)
-	clrldi	r4,r4,60
-	or	r4,r4,r3
-	std	r4,_TRAP(r1)
-
-	/*
-	 * PACA_IRQ_HARD_DIS won't always be set here, so set it now
-	 * to reconcile the IRQ state. Tracing is already accounted for.
-	 */
-	lbz	r4,PACAIRQHAPPENED(r13)
-	ori	r4,r4,PACA_IRQ_HARD_DIS
-	stb	r4,PACAIRQHAPPENED(r13)
-
-	/*
-	 * Then find the right handler and call it. Interrupts are
-	 * still soft-disabled and we keep them that way.
-	*/
-	cmpwi	cr0,r3,0x500
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
- 	bl	do_IRQ
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0xf00
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	performance_monitor_exception
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0xe60
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	handle_hmi_exception
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0x900
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	timer_interrupt
-	b	ret_from_except
-#ifdef CONFIG_PPC_DOORBELL
-1:
-#ifdef CONFIG_PPC_BOOK3E
-	cmpwi	cr0,r3,0x280
-#else
-	cmpwi	cr0,r3,0xa00
-#endif /* CONFIG_PPC_BOOK3E */
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	doorbell_exception
-#endif /* CONFIG_PPC_DOORBELL */
-1:	b	ret_from_except /* What else to do here ? */
- 
-.Lunrecov_restore:
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	unrecoverable_exception
-	b	.Lunrecov_restore
-
-_ASM_NOKPROBE_SYMBOL(ret_from_except);
-_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
-_ASM_NOKPROBE_SYMBOL(resume_kernel);
-_ASM_NOKPROBE_SYMBOL(fast_exc_return_irq);
-_ASM_NOKPROBE_SYMBOL(restore);
-_ASM_NOKPROBE_SYMBOL(fast_exception_return);
+1:	/*
+	 * Emulate stack store with update. New r1 value was already calculated
+	 * and updated in our interrupt regs by emulate_loadstore, but we can't
+	 * store the previous value of r1 to the stack before re-loading our
+	 * registers from it, otherwise they could be clobbered.  Use
+	 * PACA_EXGEN as temporary storage to hold the store data, as
+	 * interrupts are disabled here so it won't be clobbered.
+	 */
+	mtcr	r6
+	std	r9,PACA_EXGEN+0(r13)
+	addi	r9,r1,INT_FRAME_SIZE /* get original r1 */
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
+	std	r9,0(r1) /* perform store component of stdu */
+	ld	r9,PACA_EXGEN+0(r13)
 
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+#endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_RTAS
 /*