[PATCH v2 2/2] sparc64: Use lzcnt instruction for fls and __fls

[Vijay Kumar]

For T4 and above, patch fls and __fls functions
at the boot time to use lzcnt instruction.

Signed-off-by: Vijay Kumar <vijay.ac.kumar@xxxxxxxxxx>
Reviewed-by: Babu Moger <babu.moger@xxxxxxxxxx>
---
 arch/sparc/Makefile         |    1 +
 arch/sparc/kernel/head_64.S |    2 ++
 arch/sparc/lib/Makefile     |    3 +++
 arch/sparc/lib/NG4fls.S     |   30 ++++++++++++++++++++++++++++++
 arch/sparc/lib/NG4patch.S   |    9 +++++++++
 5 files changed, 45 insertions(+), 0 deletions(-)

diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index 8496a07..0763cd8 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -48,6 +48,7 @@ KBUILD_CFLAGS += -ffixed-g4 -ffixed-g5 -fcall-used-g7 -Wno-sign-compare
 KBUILD_CFLAGS += -Wa,--undeclared-regs
 KBUILD_CFLAGS += $(call cc-option,-mtune=ultrasparc3)
 KBUILD_AFLAGS += -m64 -mcpu=ultrasparc -Wa,--undeclared-regs
+KBUILD_AFLAGS += -Wa,-Asparc4
 
 ifeq ($(CONFIG_MCOUNT),y)
   KBUILD_CFLAGS += -pg
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 78e0211..1165254 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -628,6 +628,8 @@ niagara4_patch:
 	 nop
 	call	niagara4_patch_pageops
 	 nop
+	call	niagara4_patch_fls
+	 nop
 
 	ba,a,pt	%xcc, 80f
 	 nop
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index eefbb9c..72d2d8c 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -46,3 +46,6 @@ lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 obj-$(CONFIG_SPARC64) += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o
 obj-$(CONFIG_SPARC64) += PeeCeeI.o
+
+obj-$(CONFIG_SPARC64) += fls.o
+obj-$(CONFIG_SPARC64) += NG4fls.o
diff --git a/arch/sparc/lib/NG4fls.S b/arch/sparc/lib/NG4fls.S
new file mode 100644
index 0000000..eb239aa
--- /dev/null
+++ b/arch/sparc/lib/NG4fls.S
@@ -0,0 +1,30 @@
+/* NG4fls.S: SPARC optimized fls and __fls for T4 and above.
+ *
+ * Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved.
+ */
+
+	.text
+	.align 32
+
+	.globl NG4fls
+	.globl __NG4fls
+	.type  NG4fls, #function
+	.type  __NG4fls, #function
+
+NG4fls:
+	lzcnt   %o0, %o1
+	mov     64, %o2
+	retl
+	 sub     %o2, %o1, %o0
+	.size   NG4fls, .-NG4fls
+
+__NG4fls:
+	brz,pn  %o0, 1f
+        mov	%o0, %o1
+	lzcnt	%o1, %o0
+	mov     63, %o2
+	sub     %o2, %o0, %o0
+1:
+	retl
+	 nop
+	.size   __NG4fls, .-__NG4fls
diff --git a/arch/sparc/lib/NG4patch.S b/arch/sparc/lib/NG4patch.S
index 3cc0f8c..1010d53 100644
--- a/arch/sparc/lib/NG4patch.S
+++ b/arch/sparc/lib/NG4patch.S
@@ -52,3 +52,12 @@ niagara4_patch_pageops:
 	retl
 	 nop
 	.size	niagara4_patch_pageops,.-niagara4_patch_pageops
+
+	.globl	niagara4_patch_fls
+	.type	niagara4_patch_fls,#function
+niagara4_patch_fls:
+	NG_DO_PATCH(fls, NG4fls)
+	NG_DO_PATCH(__fls, __NG4fls)
+	retl
+	 nop
+	.size	niagara4_patch_fls,.-niagara4_patch_fls
-- 
1.7.1