diff options
Diffstat (limited to 'arch/powerpc/lib/copyuser_power7.S')
| -rw-r--r-- | arch/powerpc/lib/copyuser_power7.S | 130 |
1 files changed, 79 insertions, 51 deletions
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 497db7b23bb1..0d24ff15f5f6 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -19,9 +19,6 @@ */ #include <asm/ppc_asm.h> -#define STACKFRAMESIZE 256 -#define STK_REG(i) (112 + ((i)-14)*8) - .macro err1 100: .section __ex_table,"a" @@ -57,26 +54,26 @@ .Ldo_err4: - ld r16,STK_REG(r16)(r1) - ld r15,STK_REG(r15)(r1) - ld r14,STK_REG(r14)(r1) + ld r16,STK_REG(R16)(r1) + ld r15,STK_REG(R15)(r1) + ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl .exit_vmx_copy + bl .exit_vmx_usercopy ld r0,STACKFRAMESIZE+16(r1) mtlr r0 b .Lexit #endif /* CONFIG_ALTIVEC */ .Ldo_err2: - ld r22,STK_REG(r22)(r1) - ld r21,STK_REG(r21)(r1) - ld r20,STK_REG(r20)(r1) - ld r19,STK_REG(r19)(r1) - ld r18,STK_REG(r18)(r1) - ld r17,STK_REG(r17)(r1) - ld r16,STK_REG(r16)(r1) - ld r15,STK_REG(r15)(r1) - ld r14,STK_REG(r14)(r1) + ld r22,STK_REG(R22)(r1) + ld r21,STK_REG(R21)(r1) + ld r20,STK_REG(R20)(r1) + ld r19,STK_REG(R19)(r1) + ld r18,STK_REG(R18)(r1) + ld r17,STK_REG(R17)(r1) + ld r16,STK_REG(R16)(r1) + ld r15,STK_REG(R15)(r1) + ld r14,STK_REG(R14)(r1) .Lexit: addi r1,r1,STACKFRAMESIZE .Ldo_err1: @@ -137,15 +134,15 @@ err1; stw r0,0(r3) mflr r0 stdu r1,-STACKFRAMESIZE(r1) - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) - std r17,STK_REG(r17)(r1) - std r18,STK_REG(r18)(r1) - std r19,STK_REG(r19)(r1) - std r20,STK_REG(r20)(r1) - std r21,STK_REG(r21)(r1) - std r22,STK_REG(r22)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) + std r17,STK_REG(R17)(r1) + std r18,STK_REG(R18)(r1) + std r19,STK_REG(R19)(r1) + std r20,STK_REG(R20)(r1) + std r21,STK_REG(R21)(r1) + std r22,STK_REG(R22)(r1) std r0,STACKFRAMESIZE+16(r1) srdi r6,r5,7 @@ -192,15 +189,15 @@ err2; std r21,120(r3) clrldi r5,r5,(64-7) - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) - ld r17,STK_REG(r17)(r1) - ld r18,STK_REG(r18)(r1) - ld r19,STK_REG(r19)(r1) - ld r20,STK_REG(r20)(r1) - ld r21,STK_REG(r21)(r1) - ld r22,STK_REG(r22)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) + ld r17,STK_REG(R17)(r1) + ld r18,STK_REG(R18)(r1) + ld r19,STK_REG(R19)(r1) + ld r20,STK_REG(R20)(r1) + ld r21,STK_REG(R21)(r1) + ld r22,STK_REG(R22)(r1) addi r1,r1,STACKFRAMESIZE /* Up to 127B to go */ @@ -290,15 +287,46 @@ err1; stb r0,0(r3) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl .enter_vmx_copy - cmpwi r3,0 + 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) mtlr r0 - beq .Lunwind_stack_nonvmx_copy + /* + * We prefetch both the source and destination using enhanced touch + * instructions. We use a stream ID of 0 for the load side and + * 1 for the store side. + */ + clrrdi r6,r4,7 + clrrdi r9,r3,7 + ori r9,r9,1 /* stream=1 */ + + srdi r7,r5,7 /* length in cachelines, capped at 0x3FF */ + cmpldi r7,0x3FF + ble 1f + li r7,0x3FF +1: lis r0,0x0E00 /* depth=7 */ + sldi r7,r7,7 + or r7,r7,r0 + ori r10,r7,1 /* stream=1 */ + + lis r8,0x8000 /* GO=1 */ + clrldi r8,r8,32 + +.machine push +.machine "power4" + dcbt r0,r6,0b01000 + dcbt r0,r7,0b01010 + dcbtst r0,r9,0b01000 + dcbtst r0,r10,0b01010 + eieio + dcbt r0,r8,0b01010 /* GO */ +.machine pop + + beq cr1,.Lunwind_stack_nonvmx_copy /* * If source and destination are not relatively aligned we use a @@ -378,9 +406,9 @@ err3; stvx vr0,r3,r11 7: sub r5,r5,r6 srdi r6,r5,7 - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) li r12,64 li r14,80 @@ -415,9 +443,9 @@ err4; stvx vr0,r3,r16 addi r3,r3,128 bdnz 8b - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) /* Up to 127B to go */ clrldi r5,r5,(64-7) @@ -476,7 +504,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_copy /* tail call optimise */ + b .exit_vmx_usercopy /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -563,9 +591,9 @@ err3; stvx vr11,r3,r11 7: sub r5,r5,r6 srdi r6,r5,7 - std r14,STK_REG(r14)(r1) - std r15,STK_REG(r15)(r1) - std r16,STK_REG(r16)(r1) + std r14,STK_REG(R14)(r1) + std r15,STK_REG(R15)(r1) + std r16,STK_REG(R16)(r1) li r12,64 li r14,80 @@ -608,9 +636,9 @@ err4; stvx vr15,r3,r16 addi r3,r3,128 bdnz 8b - ld r14,STK_REG(r14)(r1) - ld r15,STK_REG(r15)(r1) - ld r16,STK_REG(r16)(r1) + ld r14,STK_REG(R14)(r1) + ld r15,STK_REG(R15)(r1) + ld r16,STK_REG(R16)(r1) /* Up to 127B to go */ clrldi r5,r5,(64-7) @@ -679,5 +707,5 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b .exit_vmx_copy /* tail call optimise */ + b .exit_vmx_usercopy /* tail call optimise */ #endif /* CONFiG_ALTIVEC */ |
