powerpc/64s: Reimplement power4_idle code in C

This implements the tricky tracing and soft irq handling bits in C,
leaving the low level bit to asm.

A functional difference is that this redirects the interrupt exit to
a return stub to execute blr, rather than the lr address itself. This
is probably barely measurable on real hardware, but it keeps the link
stack balanced.

Tested with QEMU.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Move power4_fixup_nap back into exceptions-64s.S]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190711022404.18132-1-npiggin@gmail.com

arch/powerpc/include/asm/processor.h

@@ -412,6 +412,9 @@ static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
 extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
 extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
+#ifdef CONFIG_PPC_970_NAP
+extern void power4_idle_nap(void);
+#endif
 
 extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};

arch/powerpc/kernel/Makefile

@@ -62,8 +62,7 @@ obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
-obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
-obj-$(CONFIG_PPC_P7_NAP)	+= idle_book3s.o
+obj-$(CONFIG_PPC_BOOK3S_IDLE)	+= idle_book3s.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o

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

@@ -2208,11 +2208,20 @@ __end_interrupts:
 DEFINE_FIXED_SYMBOL(__end_interrupts)
 
 #ifdef CONFIG_PPC_970_NAP
+	/*
+	 * Called by exception entry code if _TLF_NAPPING was set, this clears
+	 * the NAPPING flag, and redirects the exception exit to
+	 * power4_fixup_nap_return.
+	 */
+	.globl power4_fixup_nap
 EXC_COMMON_BEGIN(power4_fixup_nap)
 	andc	r9,r9,r10
 	std	r9,TI_LOCAL_FLAGS(r11)
-	ld	r10,_LINK(r1)		/* make idle task do the */
-	std	r10,_NIP(r1)		/* equivalent of a blr */
+	LOAD_REG_ADDR(r10, power4_idle_nap_return)
+	std	r10,_NIP(r1)
+	blr
+
+power4_idle_nap_return:
 	blr
 #endif
 

arch/powerpc/kernel/idle.c

@@ -77,6 +77,31 @@ void arch_cpu_idle(void)
 
 int powersave_nap;
 
+#ifdef CONFIG_PPC_970_NAP
+void power4_idle(void)
+{
+	if (!cpu_has_feature(CPU_FTR_CAN_NAP))
+		return;
+
+	if (!powersave_nap)
+		return;
+
+	if (!prep_irq_for_idle())
+		return;
+
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		asm volatile("DSSALL ; sync" ::: "memory");
+
+	power4_idle_nap();
+
+	/*
+	 * power4_idle_nap returns with interrupts enabled (soft and hard).
+	 * to our caller with interrupts enabled (soft and hard). Our caller
+	 * can cope with either interrupts disabled or enabled upon return.
+	 */
+}
+#endif
+
 #ifdef CONFIG_SYSCTL
 /*
  * Register the sysctl to set/clear powersave_nap.

arch/powerpc/kernel/idle_book3s.S

@@ -15,7 +15,9 @@
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/thread_info.h> /* TLF_NAPPING */
 
+#ifdef CONFIG_PPC_P7_NAP
 /*
  * Desired PSSCR in r3
  *
@@ -181,4 +183,22 @@ _GLOBAL(isa206_idle_insn_mayloss)
 	bne	2f
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
 2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+#endif
 
+#ifdef CONFIG_PPC_970_NAP
+_GLOBAL(power4_idle_nap)
+	LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
+	ld	r9,PACA_THREAD_INFO(r13)
+	ld	r8,TI_LOCAL_FLAGS(r9)
+	ori	r8,r8,_TLF_NAPPING
+	std	r8,TI_LOCAL_FLAGS(r9)
+	/*
+	 * NAPPING bit is set, from this point onward power4_fixup_nap
+	 * will cause exceptions to return to power4_idle_nap_return.
+	 */
+1:	sync
+	isync
+	mtmsrd	r7
+	isync
+	b	1b
+#endif

arch/powerpc/platforms/Kconfig

@@ -177,6 +177,10 @@ config PPC_970_NAP
 config PPC_P7_NAP
 	bool
 
+config PPC_BOOK3S_IDLE
+	def_bool y
+	depends on (PPC_970_NAP || PPC_P7_NAP)
+
 config PPC_INDIRECT_PIO
 	bool
 	select GENERIC_IOMAP