[PATCH v2 2/2] powerpc: Use scv instruction on clone when available

[Matheus Castanho <msc@linux.ibm.com>]

clone already uses r31 to temporarily save input arguments before doing the
syscall, so we use a different register to read from the TCB. We can also avoid
allocating another stack frame, which is not needed since we can simply extend
the usage of the red zone.
---
 .../unix/sysv/linux/powerpc/powerpc64/clone.S | 33 +++++++++++++++++--
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S b/sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S
index fc496fa671..247e0de68c 100644
--- a/sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S
+++ b/sysdeps/unix/sysv/linux/powerpc/powerpc64/clone.S
@@ -38,9 +38,11 @@ ENTRY (__clone)
 	beq-	cr0,L(badargs)
 
 	/* Save some regs in the "red zone".  */
+	std	r28,-32(r1)
 	std	r29,-24(r1)
 	std	r30,-16(r1)
 	std	r31,-8(r1)
+	cfi_offset(r28,-32)
 	cfi_offset(r29,-24)
 	cfi_offset(r30,-16)
 	cfi_offset(r31,-8)
@@ -69,11 +71,26 @@ ENTRY (__clone)
 
 	/* Do the call.  */
 	li 	r0,SYS_ify(clone)
-	DO_CALL_SC
+	CHECK_SCV_SUPPORT r28 0f
+	/* This is equivalent to DO_CALL_SCV, but we cannot use the macro here
+	because it uses CFI directives and we just called cfi_endproc.  */
+	mflr 	r9
+	std 	r9,FRAME_LR_SAVE(r1)
+	scv 	0
+	ld 	r9,FRAME_LR_SAVE(r1)
+	mtlr 	r9
+
+	/* Check for child process.  */
+	/* When using scv, error is indicated by negative r3.  */
+	cmpdi	cr1,r3,0
+	b 1f
+0:      DO_CALL_SC
 
 	/* Check for child process.  */
+	/* With sc, error is indicated by cr0.SO.  */
 	cmpdi	cr1,r3,0
 	crandc	cr1*4+eq,cr1*4+eq,cr0*4+so
+1:
 	bne-	cr1,L(parent)		/* The '-' is to minimise the race.  */
 
 	std	r2,FRAME_TOC_SAVE(r1)
@@ -95,19 +112,29 @@ L(badargs):
 	TAIL_CALL_SYSCALL_ERROR
 
 L(parent):
+	/* Check if scv is available. */
+	cmpdi cr1,r28,0
+
 	/* Parent.  Restore registers & return.  */
+	cfi_offset(r28,-32)
 	cfi_offset(r29,-24)
 	cfi_offset(r30,-16)
 	cfi_offset(r31,-8)
+	ld	r28,-32(r1)
 	ld	r29,-24(r1)
 	ld	r30,-16(r1)
 	ld	r31,-8(r1)
+	cfi_restore(r28)
 	cfi_restore(r29)
 	cfi_restore(r30)
 	cfi_restore(r31)
 
-	RET_SC
-	TAIL_CALL_SYSCALL_ERROR
+	beq cr1,0f
+	RET_SCV
+	b 1f
+0:	RET_SC
+1:	TAIL_CALL_SYSCALL_ERROR
+
 
 END (__clone)
 
-- 
2.26.2