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_BOOK3S_IDLE)	+= idle_book3s.o
-obj-$(CONFIG_PPC_P7_NAP)	+= idle_book3s.o
 procfs-y			:= proc_powerpc.o
 obj-$(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 */
+	LOAD_REG_ADDR(r10, power4_idle_nap_return)
-	std	r10,_NIP(r1)		/* equivalent of a blr */
+	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/kernel/idle_power4.S

@@ -1,83 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  This file contains the power_save function for 970-family CPUs.
- */
-
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/irqflags.h>
-#include <asm/hw_irq.h>
-#include <asm/feature-fixups.h>
-
-#undef DEBUG
-
-	.text
-
-_GLOBAL(power4_idle)
-BEGIN_FTR_SECTION
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
-	/* Now check if user or arch enabled NAP mode */
-	LOAD_REG_ADDRBASE(r3,powersave_nap)
-	lwz	r4,ADDROFF(powersave_nap)(r3)
-	cmpwi	0,r4,0
-	beqlr
-
-	/* This sequence is similar to prep_irq_for_idle() */
-
-	/* Hard disable interrupts */
-	mfmsr	r7
-	rldicl	r0,r7,48,1
-	rotldi	r0,r0,16
-	mtmsrd	r0,1
-
-	/* Check if something happened while soft-disabled */
-	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
-	bne-	2f
-
-	/*
-	 * Soft-enable interrupts. This will make power4_fixup_nap return
-	 * to our caller with interrupts enabled (soft and hard). The caller
-	 * can cope with either interrupts disabled or enabled upon return.
-	 */
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/* Tell the tracer interrupts are on, because idle responds to them. */
-	mflr	r0
-	std	r0,16(r1)
-	stdu    r1,-128(r1)
-	bl	trace_hardirqs_on
-	addi    r1,r1,128
-	ld	r0,16(r1)
-	mtlr	r0
-	mfmsr	r7
-#endif /* CONFIG_TRACE_IRQFLAGS */
-
-	li	r0,IRQS_ENABLED
-	stb	r0,PACAIRQSOFTMASK(r13)	/* we'll hard-enable shortly */
-BEGIN_FTR_SECTION
-	DSSALL
-	sync
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	ld	r9, PACA_THREAD_INFO(r13)
-	ld	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
-	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
-	std	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
-	ori	r7,r7,MSR_EE
-	oris	r7,r7,MSR_POW@h
-1:	sync
-	isync
-	mtmsrd	r7
-	isync
-	b	1b
-
-2:	/* Return if an interrupt had happened while soft disabled */
-	/* Set the HARD_DIS flag because interrupts are now hard disabled */
-	ori	r0,r0,PACA_IRQ_HARD_DIS
-	stb	r0,PACAIRQHAPPENED(r13)
-	blr

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