diff options
Diffstat (limited to 'arch/arm/mm/cache-v7.S')
| -rw-r--r-- | arch/arm/mm/cache-v7.S | 264 |
1 files changed, 138 insertions, 126 deletions
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 515b00064da8..726681fb7d4d 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -1,23 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm/mm/cache-v7.S * * Copyright (C) 2001 Deep Blue Solutions Ltd. * Copyright (C) 2005 ARM Ltd. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * This is the "shell" of the ARMv7 processor support. */ #include <linux/linkage.h> #include <linux/init.h> +#include <linux/cfi_types.h> #include <asm/assembler.h> #include <asm/errno.h> #include <asm/unwind.h> +#include <asm/hardware/cache-b15-rac.h> #include "proc-macros.S" +.arch armv7-a + +#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND +.globl icache_size + .data + .align 2 +icache_size: + .long 64 + .text +#endif /* * The secondary kernel init calls v7_flush_dcache_all before it enables * the L1; however, the L1 comes out of reset in an undefined state, so @@ -27,41 +36,41 @@ * processor. We fix this by performing an invalidate, rather than a * clean + invalidate, before jumping into the kernel. * - * This function is cloned from arch/arm/mach-tegra/headsmp.S, and needs - * to be called for both secondary cores startup and primary core resume - * procedures. + * This function needs to be called for both secondary cores startup and + * primary core resume procedures. */ ENTRY(v7_invalidate_l1) - mov r0, #0 - mcr p15, 2, r0, c0, c0, 0 - mrc p15, 1, r0, c0, c0, 0 - - ldr r1, =0x7fff - and r2, r1, r0, lsr #13 + mov r0, #0 + mcr p15, 2, r0, c0, c0, 0 @ select L1 data cache in CSSELR + isb + mrc p15, 1, r0, c0, c0, 0 @ read cache geometry from CCSIDR - ldr r1, =0x3ff + movw r3, #0x3ff + and r3, r3, r0, lsr #3 @ 'Associativity' in CCSIDR[12:3] + clz r1, r3 @ WayShift + mov r2, #1 + mov r3, r3, lsl r1 @ NumWays-1 shifted into bits [31:...] + movs r1, r2, lsl r1 @ #1 shifted left by same amount + moveq r1, #1 @ r1 needs value > 0 even if only 1 way - and r3, r1, r0, lsr #3 @ NumWays - 1 - add r2, r2, #1 @ NumSets + and r2, r0, #0x7 + add r2, r2, #4 @ SetShift - and r0, r0, #0x7 - add r0, r0, #4 @ SetShift +1: movw ip, #0x7fff + and r0, ip, r0, lsr #13 @ 'NumSets' in CCSIDR[27:13] - clz r1, r3 @ WayShift - add r4, r3, #1 @ NumWays -1: sub r2, r2, #1 @ NumSets-- - mov r3, r4 @ Temp = NumWays -2: subs r3, r3, #1 @ Temp-- - mov r5, r3, lsl r1 - mov r6, r2, lsl r0 - orr r5, r5, r6 @ Reg = (Temp<<WayShift)|(NumSets<<SetShift) - mcr p15, 0, r5, c7, c6, 2 - bgt 2b - cmp r2, #0 - bgt 1b - dsb - isb - mov pc, lr +2: mov ip, r0, lsl r2 @ NumSet << SetShift + orr ip, ip, r3 @ Reg = (Temp<<WayShift)|(NumSets<<SetShift) + mcr p15, 0, ip, c7, c6, 2 + subs r0, r0, #1 @ Set-- + bpl 2b + subs r3, r3, r1 @ Way-- + bcc 3f + mrc p15, 1, r0, c0, c0, 0 @ re-read cache geometry from CCSIDR + b 1b +3: dsb st + isb + ret lr ENDPROC(v7_invalidate_l1) /* @@ -72,39 +81,38 @@ ENDPROC(v7_invalidate_l1) * Registers: * r0 - set to 0 */ -ENTRY(v7_flush_icache_all) +SYM_TYPED_FUNC_START(v7_flush_icache_all) mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate - mov pc, lr -ENDPROC(v7_flush_icache_all) + ret lr +SYM_FUNC_END(v7_flush_icache_all) /* * v7_flush_dcache_louis() * * Flush the D-cache up to the Level of Unification Inner Shareable * - * Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode) + * Corrupted registers: r0-r6, r9-r10 */ ENTRY(v7_flush_dcache_louis) dmb @ ensure ordering with previous memory accesses mrc p15, 1, r0, c0, c0, 1 @ read clidr, r0 = clidr - ALT_SMP(ands r3, r0, #(7 << 21)) @ extract LoUIS from clidr - ALT_UP(ands r3, r0, #(7 << 27)) @ extract LoUU from clidr +ALT_SMP(mov r3, r0, lsr #20) @ move LoUIS into position +ALT_UP( mov r3, r0, lsr #26) @ move LoUU into position + ands r3, r3, #7 << 1 @ extract LoU*2 field from clidr + bne start_flush_levels @ LoU != 0, start flushing #ifdef CONFIG_ARM_ERRATA_643719 - ALT_SMP(mrceq p15, 0, r2, c0, c0, 0) @ read main ID register - ALT_UP(moveq pc, lr) @ LoUU is zero, so nothing to do - ldreq r1, =0x410fc090 @ ID of ARM Cortex A9 r0p? - biceq r2, r2, #0x0000000f @ clear minor revision number - teqeq r2, r1 @ test for errata affected core and if so... - orreqs r3, #(1 << 21) @ fix LoUIS value (and set flags state to 'ne') +ALT_SMP(mrc p15, 0, r2, c0, c0, 0) @ read main ID register +ALT_UP( ret lr) @ LoUU is zero, so nothing to do + movw r1, #:lower16:(0x410fc090 >> 4) @ ID of ARM Cortex A9 r0p? + movt r1, #:upper16:(0x410fc090 >> 4) + teq r1, r2, lsr #4 @ test for errata affected core and if so... + moveq r3, #1 << 1 @ fix LoUIS value + beq start_flush_levels @ start flushing cache levels #endif - ALT_SMP(mov r3, r3, lsr #20) @ r3 = LoUIS * 2 - ALT_UP(mov r3, r3, lsr #26) @ r3 = LoUU * 2 - moveq pc, lr @ return if level == 0 - mov r10, #0 @ r10 (starting level) = 0 - b flush_levels @ start flushing cache levels + ret lr ENDPROC(v7_flush_dcache_louis) /* @@ -112,16 +120,17 @@ ENDPROC(v7_flush_dcache_louis) * * Flush the whole D-cache. * - * Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode) + * Corrupted registers: r0-r6, r9-r10 * * - mm - mm_struct describing address space */ ENTRY(v7_flush_dcache_all) dmb @ ensure ordering with previous memory accesses mrc p15, 1, r0, c0, c0, 1 @ read clidr - ands r3, r0, #0x7000000 @ extract loc from clidr - mov r3, r3, lsr #23 @ left align loc bit field + mov r3, r0, lsr #23 @ move LoC into position + ands r3, r3, #7 << 1 @ extract LoC*2 from clidr beq finished @ if loc is 0, then no need to clean +start_flush_levels: mov r10, #0 @ start clean at cache level 0 flush_levels: add r2, r10, r10, lsr #1 @ work out 3x current cache level @@ -129,46 +138,49 @@ flush_levels: and r1, r1, #7 @ mask of the bits for current cache only cmp r1, #2 @ see what cache we have at this level blt skip @ skip if no cache, or just i-cache -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION save_and_disable_irqs_notrace r9 @ make cssr&csidr read atomic #endif mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr isb @ isb to sych the new cssr&csidr mrc p15, 1, r1, c0, c0, 0 @ read the new csidr -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION restore_irqs_notrace r9 #endif and r2, r1, #7 @ extract the length of the cache lines add r2, r2, #4 @ add 4 (line length offset) - ldr r4, =0x3ff + movw r4, #0x3ff ands r4, r4, r1, lsr #3 @ find maximum number on the way size clz r5, r4 @ find bit position of way size increment - ldr r7, =0x7fff - ands r7, r7, r1, lsr #13 @ extract max number of the index size + movw r6, #0x7fff + and r1, r6, r1, lsr #13 @ extract max number of the index size + mov r6, #1 + movne r4, r4, lsl r5 @ # of ways shifted into bits [31:...] + movne r6, r6, lsl r5 @ 1 shifted left by same amount loop1: - mov r9, r4 @ create working copy of max way size + mov r9, r1 @ create working copy of max index loop2: - ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11 - THUMB( lsl r6, r9, r5 ) - THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11 - ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11 - THUMB( lsl r6, r7, r2 ) - THUMB( orr r11, r11, r6 ) @ factor index number into r11 - mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way - subs r9, r9, #1 @ decrement the way + mov r5, r9, lsl r2 @ factor set number into r5 + orr r5, r5, r4 @ factor way number into r5 + orr r5, r5, r10 @ factor cache level into r5 + mcr p15, 0, r5, c7, c14, 2 @ clean & invalidate by set/way + subs r9, r9, #1 @ decrement the index bge loop2 - subs r7, r7, #1 @ decrement the index - bge loop1 + subs r4, r4, r6 @ decrement the way + bcs loop1 skip: add r10, r10, #2 @ increment cache number cmp r3, r10 +#ifdef CONFIG_ARM_ERRATA_814220 + dsb +#endif bgt flush_levels finished: - mov r10, #0 @ swith back to cache level 0 + mov r10, #0 @ switch back to cache level 0 mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr - dsb + dsb st isb - mov pc, lr + ret lr ENDPROC(v7_flush_dcache_all) /* @@ -182,17 +194,15 @@ ENDPROC(v7_flush_dcache_all) * unification in a single instruction. * */ -ENTRY(v7_flush_kern_cache_all) - ARM( stmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( stmfd sp!, {r4-r7, r9-r11, lr} ) +SYM_TYPED_FUNC_START(v7_flush_kern_cache_all) + stmfd sp!, {r4-r6, r9-r10, lr} bl v7_flush_dcache_all mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate - ARM( ldmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( ldmfd sp!, {r4-r7, r9-r11, lr} ) - mov pc, lr -ENDPROC(v7_flush_kern_cache_all) + ldmfd sp!, {r4-r6, r9-r10, lr} + ret lr +SYM_FUNC_END(v7_flush_kern_cache_all) /* * v7_flush_kern_cache_louis(void) @@ -200,17 +210,15 @@ ENDPROC(v7_flush_kern_cache_all) * Flush the data cache up to Level of Unification Inner Shareable. * Invalidate the I-cache to the point of unification. */ -ENTRY(v7_flush_kern_cache_louis) - ARM( stmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( stmfd sp!, {r4-r7, r9-r11, lr} ) +SYM_TYPED_FUNC_START(v7_flush_kern_cache_louis) + stmfd sp!, {r4-r6, r9-r10, lr} bl v7_flush_dcache_louis mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 0) @ invalidate I-cache inner shareable ALT_UP(mcr p15, 0, r0, c7, c5, 0) @ I+BTB cache invalidate - ARM( ldmfd sp!, {r4-r5, r7, r9-r11, lr} ) - THUMB( ldmfd sp!, {r4-r7, r9-r11, lr} ) - mov pc, lr -ENDPROC(v7_flush_kern_cache_louis) + ldmfd sp!, {r4-r6, r9-r10, lr} + ret lr +SYM_FUNC_END(v7_flush_kern_cache_louis) /* * v7_flush_cache_all() @@ -219,8 +227,9 @@ ENDPROC(v7_flush_kern_cache_louis) * * - mm - mm_struct describing address space */ -ENTRY(v7_flush_user_cache_all) - /*FALLTHROUGH*/ +SYM_TYPED_FUNC_START(v7_flush_user_cache_all) + ret lr +SYM_FUNC_END(v7_flush_user_cache_all) /* * v7_flush_cache_range(start, end, flags) @@ -234,10 +243,9 @@ ENTRY(v7_flush_user_cache_all) * It is assumed that: * - we have a VIPT cache. */ -ENTRY(v7_flush_user_cache_range) - mov pc, lr -ENDPROC(v7_flush_user_cache_all) -ENDPROC(v7_flush_user_cache_range) +SYM_TYPED_FUNC_START(v7_flush_user_cache_range) + ret lr +SYM_FUNC_END(v7_flush_user_cache_range) /* * v7_coherent_kern_range(start,end) @@ -252,8 +260,11 @@ ENDPROC(v7_flush_user_cache_range) * It is assumed that: * - the Icache does not read data from the write buffer */ -ENTRY(v7_coherent_kern_range) - /* FALLTHROUGH */ +SYM_TYPED_FUNC_START(v7_coherent_kern_range) +#ifdef CONFIG_CFI /* Fallthrough if !CFI */ + b v7_coherent_user_range +#endif +SYM_FUNC_END(v7_coherent_kern_range) /* * v7_coherent_user_range(start,end) @@ -268,7 +279,7 @@ ENTRY(v7_coherent_kern_range) * It is assumed that: * - the Icache does not read data from the write buffer */ -ENTRY(v7_coherent_user_range) +SYM_TYPED_FUNC_START(v7_coherent_user_range) UNWIND(.fnstart ) dcache_line_size r2, r3 sub r3, r2, #1 @@ -282,8 +293,13 @@ ENTRY(v7_coherent_user_range) add r12, r12, r2 cmp r12, r1 blo 1b - dsb + dsb ishst +#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND + ldr r3, =icache_size + ldr r2, [r3, #0] +#else icache_line_size r2, r3 +#endif sub r3, r2, #1 bic r12, r0, r3 2: @@ -294,9 +310,9 @@ ENTRY(v7_coherent_user_range) mov r0, #0 ALT_SMP(mcr p15, 0, r0, c7, c1, 6) @ invalidate BTB Inner Shareable ALT_UP(mcr p15, 0, r0, c7, c5, 6) @ invalidate BTB - dsb + dsb ishst isb - mov pc, lr + ret lr /* * Fault handling for the cache operation above. If the virtual address in r0 @@ -307,10 +323,9 @@ ENTRY(v7_coherent_user_range) dsb #endif mov r0, #-EFAULT - mov pc, lr + ret lr UNWIND(.fnend ) -ENDPROC(v7_coherent_kern_range) -ENDPROC(v7_coherent_user_range) +SYM_FUNC_END(v7_coherent_user_range) /* * v7_flush_kern_dcache_area(void *addr, size_t size) @@ -321,7 +336,7 @@ ENDPROC(v7_coherent_user_range) * - addr - kernel address * - size - region size */ -ENTRY(v7_flush_kern_dcache_area) +SYM_TYPED_FUNC_START(v7_flush_kern_dcache_area) dcache_line_size r2, r3 add r1, r0, r1 sub r3, r2, #1 @@ -335,9 +350,9 @@ ENTRY(v7_flush_kern_dcache_area) add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr -ENDPROC(v7_flush_kern_dcache_area) + dsb st + ret lr +SYM_FUNC_END(v7_flush_kern_dcache_area) /* * v7_dma_inv_range(start,end) @@ -359,17 +374,19 @@ v7_dma_inv_range: ALT_UP(W(nop)) #endif mcrne p15, 0, r0, c7, c14, 1 @ clean & invalidate D / U line + addne r0, r0, r2 tst r1, r3 bic r1, r1, r3 mcrne p15, 0, r1, c7, c14, 1 @ clean & invalidate D / U line -1: - mcr p15, 0, r0, c7, c6, 1 @ invalidate D / U line - add r0, r0, r2 cmp r0, r1 +1: + mcrlo p15, 0, r0, c7, c6, 1 @ invalidate D / U line + addlo r0, r0, r2 + cmplo r0, r1 blo 1b - dsb - mov pc, lr + dsb st + ret lr ENDPROC(v7_dma_inv_range) /* @@ -390,8 +407,8 @@ v7_dma_clean_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr + dsb st + ret lr ENDPROC(v7_dma_clean_range) /* @@ -399,7 +416,7 @@ ENDPROC(v7_dma_clean_range) * - start - virtual start address of region * - end - virtual end address of region */ -ENTRY(v7_dma_flush_range) +SYM_TYPED_FUNC_START(v7_dma_flush_range) dcache_line_size r2, r3 sub r3, r2, #1 bic r0, r0, r3 @@ -412,9 +429,9 @@ ENTRY(v7_dma_flush_range) add r0, r0, r2 cmp r0, r1 blo 1b - dsb - mov pc, lr -ENDPROC(v7_dma_flush_range) + dsb st + ret lr +SYM_FUNC_END(v7_dma_flush_range) /* * dma_map_area(start, size, dir) @@ -422,12 +439,12 @@ ENDPROC(v7_dma_flush_range) * - size - size of region * - dir - DMA direction */ -ENTRY(v7_dma_map_area) +SYM_TYPED_FUNC_START(v7_dma_map_area) add r1, r1, r0 teq r2, #DMA_FROM_DEVICE beq v7_dma_inv_range b v7_dma_clean_range -ENDPROC(v7_dma_map_area) +SYM_FUNC_END(v7_dma_map_area) /* * dma_unmap_area(start, size, dir) @@ -435,14 +452,9 @@ ENDPROC(v7_dma_map_area) * - size - size of region * - dir - DMA direction */ -ENTRY(v7_dma_unmap_area) +SYM_TYPED_FUNC_START(v7_dma_unmap_area) add r1, r1, r0 teq r2, #DMA_TO_DEVICE bne v7_dma_inv_range - mov pc, lr -ENDPROC(v7_dma_unmap_area) - - __INITDATA - - @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) - define_cache_functions v7 + ret lr +SYM_FUNC_END(v7_dma_unmap_area) |