powerpc/64s: return more carefully from sreset NMI

System Reset, being an NMI, must return more carefully than other
interrupts. It has traditionally returned via the nromal return
from exception path, but that has a number of problems.

- r13 does not get restored if returning to kernel. This is for
  interrupts which may cause a context switch, which sreset will
  never do. Interrupting OPAL (which uses a different r13) is one
  place where this causes breakage.

- It may cause several other problems returning to kernel with
  preempt or TIF_EMULATE_STACK_STORE if it hits at the wrong time.

It's safer just to have a simple restore and return, like machine
check which is the other NMI.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/kernel/exceptions-64s.S

@@ -139,6 +139,21 @@ EXC_COMMON_BEGIN(system_reset_idle_common)
 	b	pnv_powersave_wakeup
 #endif
 
+/*
+ * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
+ * the right thing. We do not want to reconcile because that goes
+ * through irq tracing which we don't want in NMI.
+ *
+ * Save PACAIRQHAPPENED because some code will do a hard disable
+ * (e.g., xmon). So we want to restore this back to where it was
+ * when we return. DAR is unused in the stack, so save it there.
+ */
+#define ADD_RECONCILE_NMI						\
+	li	r10,IRQS_ALL_DISABLED;					\
+	stb	r10,PACAIRQSOFTMASK(r13);				\
+	lbz	r10,PACAIRQHAPPENED(r13);				\
+	std	r10,_DAR(r1)
+
 EXC_COMMON_BEGIN(system_reset_common)
 	/*
 	 * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
@@ -157,16 +172,56 @@ EXC_COMMON_BEGIN(system_reset_common)
 	subi	r1,r1,INT_FRAME_SIZE
 	EXCEPTION_COMMON_NORET_STACK(PACA_EXNMI, 0x100,
 			system_reset, system_reset_exception,
-			ADD_NVGPRS;ADD_RECONCILE)
+			ADD_NVGPRS;ADD_RECONCILE_NMI)
+
+	/* This (and MCE) can be simplified with mtmsrd L=1 */
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r0,MSR_RI
+	mfmsr	r9
+	andc	r9,r9,r0
+	mtmsrd	r9,1
 
 	/*
-	 * The stack is no longer in use, decrement in_nmi.
+	 * MSR_RI is clear, now we can decrement paca->in_nmi.
 	 */
 	lhz	r10,PACA_IN_NMI(r13)
 	subi	r10,r10,1
 	sth	r10,PACA_IN_NMI(r13)
 
-	b	ret_from_except
+	/*
+	 * Restore soft mask settings.
+	 */
+	ld	r10,_DAR(r1)
+	stb	r10,PACAIRQHAPPENED(r13)
+	ld	r10,SOFTE(r1)
+	stb	r10,PACAIRQSOFTMASK(r13)
+
+	/*
+	 * Keep below code in synch with MACHINE_CHECK_HANDLER_WINDUP.
+	 * Should share common bits...
+	 */
+
+	/* Move original SRR0 and SRR1 into the respective regs */
+	ld	r9,_MSR(r1)
+	mtspr	SPRN_SRR1,r9
+	ld	r3,_NIP(r1)
+	mtspr	SPRN_SRR0,r3
+	ld	r9,_CTR(r1)
+	mtctr	r9
+	ld	r9,_XER(r1)
+	mtxer	r9
+	ld	r9,_LINK(r1)
+	mtlr	r9
+	REST_GPR(0, r1)
+	REST_8GPRS(2, r1)
+	REST_GPR(10, r1)
+	ld	r11,_CCR(r1)
+	mtcr	r11
+	REST_GPR(11, r1)
+	REST_2GPRS(12, r1)
+	/* restore original r1. */
+	ld	r1,GPR1(r1)
+	RFI_TO_USER_OR_KERNEL
 
 #ifdef CONFIG_PPC_PSERIES
 /*