ASR_BASE
Change-Id: Icf3719cc0afe3eeb3edc7fa80a2eb5199ca9dda1
diff --git a/marvell/linux/arch/sh/lib/udivsi3_i4i-Os.S b/marvell/linux/arch/sh/lib/udivsi3_i4i-Os.S
new file mode 100644
index 0000000..fa4e4df
--- /dev/null
+++ b/marvell/linux/arch/sh/lib/udivsi3_i4i-Os.S
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH GCC-exception-2.0
+ *
+ * Copyright (C) 2006 Free Software Foundation, Inc.
+ */
+
+/* Moderately Space-optimized libgcc routines for the Renesas SH /
+ STMicroelectronics ST40 CPUs.
+ Contributed by J"orn Rennecke joern.rennecke@st.com. */
+
+/* Size: 186 bytes jointly for udivsi3_i4i and sdivsi3_i4i
+ sh4-200 run times:
+ udiv small divisor: 55 cycles
+ udiv large divisor: 52 cycles
+ sdiv small divisor, positive result: 59 cycles
+ sdiv large divisor, positive result: 56 cycles
+ sdiv small divisor, negative result: 65 cycles (*)
+ sdiv large divisor, negative result: 62 cycles (*)
+ (*): r2 is restored in the rts delay slot and has a lingering latency
+ of two more cycles. */
+ .balign 4
+ .global __udivsi3_i4i
+ .global __udivsi3_i4
+ .set __udivsi3_i4, __udivsi3_i4i
+ .type __udivsi3_i4i, @function
+ .type __sdivsi3_i4i, @function
+__udivsi3_i4i:
+ sts pr,r1
+ mov.l r4,@-r15
+ extu.w r5,r0
+ cmp/eq r5,r0
+ swap.w r4,r0
+ shlr16 r4
+ bf/s large_divisor
+ div0u
+ mov.l r5,@-r15
+ shll16 r5
+sdiv_small_divisor:
+ div1 r5,r4
+ bsr div6
+ div1 r5,r4
+ div1 r5,r4
+ bsr div6
+ div1 r5,r4
+ xtrct r4,r0
+ xtrct r0,r4
+ bsr div7
+ swap.w r4,r4
+ div1 r5,r4
+ bsr div7
+ div1 r5,r4
+ xtrct r4,r0
+ mov.l @r15+,r5
+ swap.w r0,r0
+ mov.l @r15+,r4
+ jmp @r1
+ rotcl r0
+div7:
+ div1 r5,r4
+div6:
+ div1 r5,r4; div1 r5,r4; div1 r5,r4
+ div1 r5,r4; div1 r5,r4; rts; div1 r5,r4
+
+divx3:
+ rotcl r0
+ div1 r5,r4
+ rotcl r0
+ div1 r5,r4
+ rotcl r0
+ rts
+ div1 r5,r4
+
+large_divisor:
+ mov.l r5,@-r15
+sdiv_large_divisor:
+ xor r4,r0
+ .rept 4
+ rotcl r0
+ bsr divx3
+ div1 r5,r4
+ .endr
+ mov.l @r15+,r5
+ mov.l @r15+,r4
+ jmp @r1
+ rotcl r0
+
+ .global __sdivsi3_i4i
+ .global __sdivsi3_i4
+ .global __sdivsi3
+ .set __sdivsi3_i4, __sdivsi3_i4i
+ .set __sdivsi3, __sdivsi3_i4i
+__sdivsi3_i4i:
+ mov.l r4,@-r15
+ cmp/pz r5
+ mov.l r5,@-r15
+ bt/s pos_divisor
+ cmp/pz r4
+ neg r5,r5
+ extu.w r5,r0
+ bt/s neg_result
+ cmp/eq r5,r0
+ neg r4,r4
+pos_result:
+ swap.w r4,r0
+ bra sdiv_check_divisor
+ sts pr,r1
+pos_divisor:
+ extu.w r5,r0
+ bt/s pos_result
+ cmp/eq r5,r0
+ neg r4,r4
+neg_result:
+ mova negate_result,r0
+ ;
+ mov r0,r1
+ swap.w r4,r0
+ lds r2,macl
+ sts pr,r2
+sdiv_check_divisor:
+ shlr16 r4
+ bf/s sdiv_large_divisor
+ div0u
+ bra sdiv_small_divisor
+ shll16 r5
+ .balign 4
+negate_result:
+ neg r0,r0
+ jmp @r2
+ sts macl,r2