diff options
Diffstat (limited to 'arch/arm/lib/copy_template.S')
| -rw-r--r-- | arch/arm/lib/copy_template.S | 72 |
1 files changed, 42 insertions, 30 deletions
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S index cab355c0c1f..3bc8eb811a7 100644 --- a/arch/arm/lib/copy_template.S +++ b/arch/arm/lib/copy_template.S @@ -13,14 +13,6 @@ */ /* - * This can be used to enable code to cacheline align the source pointer. - * Experiments on tested architectures (StrongARM and XScale) didn't show - * this a worthwhile thing to do. That might be different in the future. - */ -//#define CALGN(code...) code -#define CALGN(code...) - -/* * Theory of operation * ------------------- * @@ -65,6 +57,13 @@ * * Restore registers with the values previously saved with the * 'preserv' macro. Called upon code termination. + * + * LDR1W_SHIFT + * STR1W_SHIFT + * + * Correction to be applied to the "ip" register when branching into + * the ldr1w or str1w instructions (some of these macros may expand to + * than one 32bit instruction in Thumb-2) */ @@ -82,7 +81,7 @@ stmfd sp!, {r5 - r8} blt 5f - CALGN( ands ip, r1, #31 ) + CALGN( ands ip, r0, #31 ) CALGN( rsb r3, ip, #32 ) CALGN( sbcnes r4, r3, r2 ) @ C is always set here CALGN( bcs 2f ) @@ -107,9 +106,15 @@ 5: ands ip, r2, #28 rsb ip, ip, #32 +#if LDR1W_SHIFT > 0 + lsl ip, ip, #LDR1W_SHIFT +#endif addne pc, pc, ip @ C is always clear here b 7f -6: nop +6: + .rept (1 << LDR1W_SHIFT) + W(nop) + .endr ldr1w r1, r3, abort=20f ldr1w r1, r4, abort=20f ldr1w r1, r5, abort=20f @@ -118,9 +123,16 @@ ldr1w r1, r8, abort=20f ldr1w r1, lr, abort=20f +#if LDR1W_SHIFT < STR1W_SHIFT + lsl ip, ip, #STR1W_SHIFT - LDR1W_SHIFT +#elif LDR1W_SHIFT > STR1W_SHIFT + lsr ip, ip, #LDR1W_SHIFT - STR1W_SHIFT +#endif add pc, pc, ip nop - nop + .rept (1 << STR1W_SHIFT) + W(nop) + .endr str1w r0, r3, abort=20f str1w r0, r4, abort=20f str1w r0, r5, abort=20f @@ -168,7 +180,7 @@ subs r2, r2, #28 blt 14f - CALGN( ands ip, r1, #31 ) + CALGN( ands ip, r0, #31 ) CALGN( rsb ip, ip, #32 ) CALGN( sbcnes r4, ip, r2 ) @ C is always set here CALGN( subcc r2, r2, ip ) @@ -185,24 +197,24 @@ 12: PLD( pld [r1, #124] ) 13: ldr4w r1, r4, r5, r6, r7, abort=19f - mov r3, lr, pull #\pull + mov r3, lr, lspull #\pull subs r2, r2, #32 ldr4w r1, r8, r9, ip, lr, abort=19f - orr r3, r3, r4, push #\push - mov r4, r4, pull #\pull - orr r4, r4, r5, push #\push - mov r5, r5, pull #\pull - orr r5, r5, r6, push #\push - mov r6, r6, pull #\pull - orr r6, r6, r7, push #\push - mov r7, r7, pull #\pull - orr r7, r7, r8, push #\push - mov r8, r8, pull #\pull - orr r8, r8, r9, push #\push - mov r9, r9, pull #\pull - orr r9, r9, ip, push #\push - mov ip, ip, pull #\pull - orr ip, ip, lr, push #\push + orr r3, r3, r4, lspush #\push + mov r4, r4, lspull #\pull + orr r4, r4, r5, lspush #\push + mov r5, r5, lspull #\pull + orr r5, r5, r6, lspush #\push + mov r6, r6, lspull #\pull + orr r6, r6, r7, lspush #\push + mov r7, r7, lspull #\pull + orr r7, r7, r8, lspush #\push + mov r8, r8, lspull #\pull + orr r8, r8, r9, lspush #\push + mov r9, r9, lspull #\pull + orr r9, r9, ip, lspush #\push + mov ip, ip, lspull #\pull + orr ip, ip, lr, lspush #\push str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f bge 12b PLD( cmn r2, #96 ) @@ -213,10 +225,10 @@ 14: ands ip, r2, #28 beq 16f -15: mov r3, lr, pull #\pull +15: mov r3, lr, lspull #\pull ldr1w r1, lr, abort=21f subs ip, ip, #4 - orr r3, r3, lr, push #\push + orr r3, r3, lr, lspush #\push str1w r0, r3, abort=21f bgt 15b CALGN( cmp r2, #0 ) |