Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Message-Id: <5ca6639b7c1c21ee4b4138b7cfb31d6245c4195c.1570684298.git.christophe.leroy@c-s.fr>
In-Reply-To: <f12fb9a6cc52d83ee9ddf15a36ee12ac77e6379f.1570684298.git.christophe.leroy@c-s.fr>
References: <f12fb9a6cc52d83ee9ddf15a36ee12ac77e6379f.1570684298.git.christophe.leroy@c-s.fr>
From:   Christophe Leroy <christophe.leroy@c-s.fr>
Subject: [PATCH v4 2/2] powerpc/irq: inline call_do_irq() and
 call_do_softirq()
To:     Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        Michael Ellerman <mpe@ellerman.id.au>,
        segher@kernel.crashing.org
Cc:     linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org
Date:   Thu, 10 Oct 2019 05:36:33 +0000 (UTC)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

call_do_irq() and call_do_softirq() are quite similar on PPC32 and
PPC64 and 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@c-s.fr>
Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org>

---
v2: no change.
v3: no change.
v4:
- comment reminding the purpose of the inline asm block.
- added r2 as clobbered reg
---
 arch/powerpc/include/asm/irq.h |  2 --
 arch/powerpc/kernel/irq.c      | 32 ++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/misc_32.S  | 25 -------------------------
 arch/powerpc/kernel/misc_64.S  | 22 ----------------------
 4 files changed, 32 insertions(+), 49 deletions(-)

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 0c6469983c66..10476d5283dc 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -57,8 +57,6 @@ 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);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 04204be49577..d62fe18405a0 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -642,6 +642,22 @@ void __do_irq(struct pt_regs *regs)
 	irq_exit();
 }
 
+static 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"	1, %2(%1);\n"
+		"	mr		1, %1;\n"
+		"	bl		%3;\n"
+		"	"PPC_LL"	1, 0(1);\n" :
+		"+r"(r3) :
+		"b"(sp), "i"(THREAD_SIZE - STACK_FRAME_OVERHEAD), "i"(__do_irq) :
+		"lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", "cr7",
+		"r0", "r2", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12");
+}
+
 void do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
@@ -686,6 +702,22 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly;
 void *softirq_ctx[NR_CPUS] __read_mostly;
 void *hardirq_ctx[NR_CPUS] __read_mostly;
 
+static inline void call_do_softirq(const void *sp)
+{
+	register unsigned long ret asm("r3");
+
+	/* Temporarily switch r1 to sp, call __do_softirq() then restore r1 */
+	asm volatile(
+		"	"PPC_STLU"	1, %2(%1);\n"
+		"	mr		1, %1;\n"
+		"	bl		%3;\n"
+		"	"PPC_LL"	1, 0(1);\n" :
+		"=r"(ret) :
+		"b"(sp), "i"(THREAD_SIZE - STACK_FRAME_OVERHEAD), "i"(__do_softirq) :
+		"lr", "xer", "ctr", "memory", "cr0", "cr1", "cr5", "cr6", "cr7",
+		"r0", "r2", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12");
+}
+
 void do_softirq_own_stack(void)
 {
 	void *irqsp = softirq_ctx[smp_processor_id()];
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index a5422f7782b3..307307b57743 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -33,31 +33,6 @@
 
 	.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.
  */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index b55a7b4cb543..69fd714a5236 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/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
-
 	.section	".toc","aw"
 PPC64_CACHES:
 	.tc		ppc64_caches[TC],ppc64_caches
-- 
2.13.3