diff options
Diffstat (limited to 'arch/arm/mm/cache-v7.S')
| -rw-r--r-- | arch/arm/mm/cache-v7.S | 131 |
1 files changed, 113 insertions, 18 deletions
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S index 39e3fb3db80..615c99e38ba 100644 --- a/arch/arm/mm/cache-v7.S +++ b/arch/arm/mm/cache-v7.S @@ -19,6 +19,52 @@ #include "proc-macros.S" /* + * 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 + * the clean + invalidate performed by v7_flush_dcache_all causes a bunch + * of cache lines with uninitialized data and uninitialized tags to get + * written out to memory, which does really unpleasant things to the main + * 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. + */ +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 + + ldr r1, =0x3ff + + and r3, r1, r0, lsr #3 @ NumWays - 1 + add r2, r2, #1 @ NumSets + + and r0, r0, #0x7 + add r0, r0, #4 @ SetShift + + 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 st + isb + mov pc, lr +ENDPROC(v7_invalidate_l1) + +/* * v7_flush_icache_all() * * Flush the whole I-cache. @@ -33,6 +79,34 @@ ENTRY(v7_flush_icache_all) mov pc, lr ENDPROC(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) + */ + +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 +#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') +#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 +ENDPROC(v7_flush_dcache_louis) + /* * v7_flush_dcache_all() * @@ -49,7 +123,7 @@ ENTRY(v7_flush_dcache_all) mov r3, r3, lsr #23 @ left align loc bit field beq finished @ if loc is 0, then no need to clean mov r10, #0 @ start clean at cache level 0 -loop1: +flush_levels: add r2, r10, r10, lsr #1 @ work out 3x current cache level mov r1, r0, lsr r2 @ extract cache type bits from clidr and r1, r1, #7 @ mask of the bits for current cache only @@ -71,28 +145,28 @@ loop1: 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 +loop1: + mov r9, r7 @ create working copy of max index loop2: - mov r9, r4 @ create working copy of max way size -loop3: - ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11 - THUMB( lsl r6, r9, r5 ) + ARM( orr r11, r10, r4, lsl r5 ) @ factor way and cache number into r11 + THUMB( lsl r6, r4, 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 ) + ARM( orr r11, r11, r9, lsl r2 ) @ factor index number into r11 + THUMB( lsl r6, r9, 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 - bge loop3 - subs r7, r7, #1 @ decrement the index + subs r9, r9, #1 @ decrement the index bge loop2 + subs r4, r4, #1 @ decrement the way + bge loop1 skip: add r10, r10, #2 @ increment cache number cmp r3, r10 - bgt loop1 + bgt flush_levels finished: mov r10, #0 @ swith 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 ENDPROC(v7_flush_dcache_all) @@ -120,6 +194,24 @@ ENTRY(v7_flush_kern_cache_all) mov pc, lr ENDPROC(v7_flush_kern_cache_all) + /* + * v7_flush_kern_cache_louis(void) + * + * 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} ) + 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) + /* * v7_flush_cache_all() * @@ -190,7 +282,7 @@ ENTRY(v7_coherent_user_range) add r12, r12, r2 cmp r12, r1 blo 1b - dsb + dsb ishst icache_line_size r2, r3 sub r3, r2, #1 bic r12, r0, r3 @@ -202,7 +294,7 @@ 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 @@ -211,6 +303,9 @@ ENTRY(v7_coherent_user_range) * isn't mapped, fail with -EFAULT. */ 9001: +#ifdef CONFIG_ARM_ERRATA_775420 + dsb +#endif mov r0, #-EFAULT mov pc, lr UNWIND(.fnend ) @@ -240,7 +335,7 @@ ENTRY(v7_flush_kern_dcache_area) add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_flush_kern_dcache_area) @@ -273,7 +368,7 @@ v7_dma_inv_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_inv_range) @@ -295,7 +390,7 @@ v7_dma_clean_range: add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_clean_range) @@ -317,7 +412,7 @@ ENTRY(v7_dma_flush_range) add r0, r0, r2 cmp r0, r1 blo 1b - dsb + dsb st mov pc, lr ENDPROC(v7_dma_flush_range) |