diff options
Diffstat (limited to 'arch/powerpc/lib/copyuser_power7.S')
| -rw-r--r-- | arch/powerpc/lib/copyuser_power7.S | 86 |
1 files changed, 47 insertions, 39 deletions
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index d1f11795a7a..c46c876ac96 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -19,6 +19,14 @@ */ #include <asm/ppc_asm.h> +#ifdef __BIG_ENDIAN__ +#define LVS(VRT,RA,RB) lvsl VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRA,VRB,VRC +#else +#define LVS(VRT,RA,RB) lvsr VRT,RA,RB +#define VPERM(VRT,VRA,VRB,VRC) vperm VRT,VRB,VRA,VRC +#endif + .macro err1 100: .section __ex_table,"a" @@ -58,7 +66,7 @@ ld r15,STK_REG(R15)(r1) ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl .exit_vmx_usercopy + bl exit_vmx_usercopy ld r0,STACKFRAMESIZE+16(r1) mtlr r0 b .Lexit @@ -77,9 +85,9 @@ .Lexit: addi r1,r1,STACKFRAMESIZE .Ldo_err1: - ld r3,48(r1) - ld r4,56(r1) - ld r5,64(r1) + ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + ld r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + ld r5,-STACKFRAMESIZE+STK_REG(R29)(r1) b __copy_tofrom_user_base @@ -88,18 +96,18 @@ _GLOBAL(__copy_tofrom_user_power7) cmpldi r5,16 cmpldi cr1,r5,4096 - std r3,48(r1) - std r4,56(r1) - std r5,64(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy bgt cr1,.Lvmx_copy #else cmpldi r5,16 - std r3,48(r1) - std r4,56(r1) - std r5,64(r1) + std r3,-STACKFRAMESIZE+STK_REG(R31)(r1) + std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) + std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) blt .Lshort_copy #endif @@ -287,12 +295,12 @@ err1; stb r0,0(r3) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_usercopy + bl enter_vmx_usercopy cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) - ld r3,STACKFRAMESIZE+48(r1) - ld r4,STACKFRAMESIZE+56(r1) - ld r5,STACKFRAMESIZE+64(r1) + ld r3,STK_REG(R31)(r1) + ld r4,STK_REG(R30)(r1) + ld r5,STK_REG(R29)(r1) mtlr r0 /* @@ -506,7 +514,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_usercopy /* tail call optimise */ + b exit_vmx_usercopy /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -552,13 +560,13 @@ err3; stw r7,4(r3) li r10,32 li r11,48 - lvsl vr16,0,r4 /* Setup permute control vector */ + LVS(vr16,0,r4) /* Setup permute control vector */ err3; lvx vr0,0,r4 addi r4,r4,16 bf cr7*4+3,5f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 err3; stvx vr8,r0,r3 addi r3,r3,16 @@ -566,9 +574,9 @@ err3; stvx vr8,r0,r3 5: bf cr7*4+2,6f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) err3; lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -576,13 +584,13 @@ err3; stvx vr9,r3,r9 6: bf cr7*4+1,7f err3; lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) err3; lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) err3; lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) err3; lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -611,21 +619,21 @@ err3; stvx vr11,r3,r11 .align 5 8: err4; lvx vr7,r0,r4 - vperm vr8,vr0,vr7,vr16 + VPERM(vr8,vr0,vr7,vr16) err4; lvx vr6,r4,r9 - vperm vr9,vr7,vr6,vr16 + VPERM(vr9,vr7,vr6,vr16) err4; lvx vr5,r4,r10 - vperm vr10,vr6,vr5,vr16 + VPERM(vr10,vr6,vr5,vr16) err4; lvx vr4,r4,r11 - vperm vr11,vr5,vr4,vr16 + VPERM(vr11,vr5,vr4,vr16) err4; lvx vr3,r4,r12 - vperm vr12,vr4,vr3,vr16 + VPERM(vr12,vr4,vr3,vr16) err4; lvx vr2,r4,r14 - vperm vr13,vr3,vr2,vr16 + VPERM(vr13,vr3,vr2,vr16) err4; lvx vr1,r4,r15 - vperm vr14,vr2,vr1,vr16 + VPERM(vr14,vr2,vr1,vr16) err4; lvx vr0,r4,r16 - vperm vr15,vr1,vr0,vr16 + VPERM(vr15,vr1,vr0,vr16) addi r4,r4,128 err4; stvx vr8,r0,r3 err4; stvx vr9,r3,r9 @@ -649,13 +657,13 @@ err4; stvx vr15,r3,r16 bf cr7*4+1,9f err3; lvx vr3,r0,r4 - vperm vr8,vr0,vr3,vr16 + VPERM(vr8,vr0,vr3,vr16) err3; lvx vr2,r4,r9 - vperm vr9,vr3,vr2,vr16 + VPERM(vr9,vr3,vr2,vr16) err3; lvx vr1,r4,r10 - vperm vr10,vr2,vr1,vr16 + VPERM(vr10,vr2,vr1,vr16) err3; lvx vr0,r4,r11 - vperm vr11,vr1,vr0,vr16 + VPERM(vr11,vr1,vr0,vr16) addi r4,r4,64 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -665,9 +673,9 @@ err3; stvx vr11,r3,r11 9: bf cr7*4+2,10f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) err3; lvx vr0,r4,r9 - vperm vr9,vr1,vr0,vr16 + VPERM(vr9,vr1,vr0,vr16) addi r4,r4,32 err3; stvx vr8,r0,r3 err3; stvx vr9,r3,r9 @@ -675,7 +683,7 @@ err3; stvx vr9,r3,r9 10: bf cr7*4+3,11f err3; lvx vr1,r0,r4 - vperm vr8,vr0,vr1,vr16 + VPERM(vr8,vr0,vr1,vr16) addi r4,r4,16 err3; stvx vr8,r0,r3 addi r3,r3,16 @@ -709,5 +717,5 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_usercopy /* tail call optimise */ + b exit_vmx_usercopy /* tail call optimise */ #endif /* CONFiG_ALTIVEC */ |