powerpc/irq: Inline call_do_irq() and call_do_softirq()

call_do_irq() and call_do_softirq() are simple enough to be
worth inlining.

Inlining them avoids an mflr/mtlr pair plus a save/reload on stack.

This is inspired from S390 arch. Several other arches do more or
less the same. The way sparc arch does seems odd thought.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210320122227.345427-1-mpe@ellerman.id.au

arch/powerpc/include/asm/irq.h

@@ -53,8 +53,6 @@ extern void *mcheckirq_ctx[NR_CPUS];
 extern void *hardirq_ctx[NR_CPUS];
 extern void *softirq_ctx[NR_CPUS];
 
-void call_do_softirq(void *sp);
-void call_do_irq(struct pt_regs *regs, void *sp);
 extern void do_IRQ(struct pt_regs *regs);
 extern void __init init_IRQ(void);
 extern void __do_irq(struct pt_regs *regs);

arch/powerpc/kernel/irq.c

@@ -667,6 +667,47 @@ static inline void check_stack_overflow(void)
 	}
 }
 
+static __always_inline void call_do_softirq(const void *sp)
+{
+	/* Temporarily switch r1 to sp, call __do_softirq() then restore r1. */
+	asm volatile (
+		 PPC_STLU "	%%r1, %[offset](%[sp])	;"
+		"mr		%%r1, %[sp]		;"
+		"bl		%[callee]		;"
+		 PPC_LL "	%%r1, 0(%%r1)		;"
+		 : // Outputs
+		 : // Inputs
+		   [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD),
+		   [callee] "i" (__do_softirq)
+		 : // Clobbers
+		   "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
+		   "cr7", "r0", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
+		   "r11", "r12"
+	);
+}
+
+static __always_inline void call_do_irq(struct pt_regs *regs, void *sp)
+{
+	register unsigned long r3 asm("r3") = (unsigned long)regs;
+
+	/* Temporarily switch r1 to sp, call __do_irq() then restore r1. */
+	asm volatile (
+		 PPC_STLU "	%%r1, %[offset](%[sp])	;"
+		"mr		%%r1, %[sp]		;"
+		"bl		%[callee]		;"
+		 PPC_LL "	%%r1, 0(%%r1)		;"
+		 : // Outputs
+		   "+r" (r3)
+		 : // Inputs
+		   [sp] "b" (sp), [offset] "i" (THREAD_SIZE - STACK_FRAME_OVERHEAD),
+		   [callee] "i" (__do_irq)
+		 : // Clobbers
+		   "lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6",
+		   "cr7", "r0", "r4", "r5", "r6", "r7", "r8", "r9", "r10",
+		   "r11", "r12"
+	);
+}
+
 void __do_irq(struct pt_regs *regs)
 {
 	unsigned int irq;

arch/powerpc/kernel/misc_32.S

@@ -27,31 +27,6 @@
 
 	.text
 
-_GLOBAL(call_do_softirq)
-	mflr	r0
-	stw	r0,4(r1)
-	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
-	mr	r1,r3
-	bl	__do_softirq
-	lwz	r1,0(r1)
-	lwz	r0,4(r1)
-	mtlr	r0
-	blr
-
-/*
- * void call_do_irq(struct pt_regs *regs, void *sp);
- */
-_GLOBAL(call_do_irq)
-	mflr	r0
-	stw	r0,4(r1)
-	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
-	mr	r1,r4
-	bl	__do_irq
-	lwz	r1,0(r1)
-	lwz	r0,4(r1)
-	mtlr	r0
-	blr
-
 /*
  * This returns the high 64 bits of the product of two 64-bit numbers.
  */

arch/powerpc/kernel/misc_64.S

@@ -27,28 +27,6 @@
 
 	.text
 
-_GLOBAL(call_do_softirq)
-	mflr	r0
-	std	r0,16(r1)
-	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
-	mr	r1,r3
-	bl	__do_softirq
-	ld	r1,0(r1)
-	ld	r0,16(r1)
-	mtlr	r0
-	blr
-
-_GLOBAL(call_do_irq)
-	mflr	r0
-	std	r0,16(r1)
-	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
-	mr	r1,r4
-	bl	__do_irq
-	ld	r1,0(r1)
-	ld	r0,16(r1)
-	mtlr	r0
-	blr
-
 _GLOBAL(__bswapdi2)
 EXPORT_SYMBOL(__bswapdi2)
 	srdi	r8,r3,32