--- zzzz-none-000/linux-3.10.107/arch/arm64/mm/cache.S 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/arm64/mm/cache.S 2021-02-04 17:41:59.000000000 +0000 @@ -17,86 +17,16 @@ * along with this program. If not, see . */ +#include #include #include #include +#include +#include #include "proc-macros.S" /* - * __flush_dcache_all() - * - * Flush the whole D-cache. - * - * Corrupted registers: x0-x7, x9-x11 - */ -ENTRY(__flush_dcache_all) - dsb sy // ensure ordering with previous memory accesses - mrs x0, clidr_el1 // read clidr - and x3, x0, #0x7000000 // extract loc from clidr - lsr x3, x3, #23 // left align loc bit field - cbz x3, finished // if loc is 0, then no need to clean - mov x10, #0 // start clean at cache level 0 -loop1: - add x2, x10, x10, lsr #1 // work out 3x current cache level - lsr x1, x0, x2 // extract cache type bits from clidr - and x1, x1, #7 // mask of the bits for current cache only - cmp x1, #2 // see what cache we have at this level - b.lt skip // skip if no cache, or just i-cache - save_and_disable_irqs x9 // make CSSELR and CCSIDR access atomic - msr csselr_el1, x10 // select current cache level in csselr - isb // isb to sych the new cssr&csidr - mrs x1, ccsidr_el1 // read the new ccsidr - restore_irqs x9 - and x2, x1, #7 // extract the length of the cache lines - add x2, x2, #4 // add 4 (line length offset) - mov x4, #0x3ff - and x4, x4, x1, lsr #3 // find maximum number on the way size - clz w5, w4 // find bit position of way size increment - mov x7, #0x7fff - and x7, x7, x1, lsr #13 // extract max number of the index size -loop2: - mov x9, x4 // create working copy of max way size -loop3: - lsl x6, x9, x5 - orr x11, x10, x6 // factor way and cache number into x11 - lsl x6, x7, x2 - orr x11, x11, x6 // factor index number into x11 - dc cisw, x11 // clean & invalidate by set/way - subs x9, x9, #1 // decrement the way - b.ge loop3 - subs x7, x7, #1 // decrement the index - b.ge loop2 -skip: - add x10, x10, #2 // increment cache number - cmp x3, x10 - b.gt loop1 -finished: - mov x10, #0 // swith back to cache level 0 - msr csselr_el1, x10 // select current cache level in csselr - dsb sy - isb - ret -ENDPROC(__flush_dcache_all) - -/* - * flush_cache_all() - * - * Flush the entire cache system. The data cache flush is now achieved - * using atomic clean / invalidates working outwards from L1 cache. This - * is done using Set/Way based cache maintainance instructions. The - * instruction cache can still be invalidated back to the point of - * unification in a single instruction. - */ -ENTRY(flush_cache_all) - mov x12, lr - bl __flush_dcache_all - mov x0, #0 - ic ialluis // I+BTB cache invalidate - ret x12 -ENDPROC(flush_cache_all) - -/* * flush_icache_range(start,end) * * Ensure that the I and D caches are coherent within specified region. @@ -128,7 +58,7 @@ add x4, x4, x2 cmp x4, x1 b.lo 1b - dsb sy + dsb ish icache_line_size x2, x3 sub x3, x2, #1 @@ -138,15 +68,18 @@ add x4, x4, x2 cmp x4, x1 b.lo 1b -9: // ignore any faulting cache operation - dsb sy + dsb ish isb + mov x0, #0 + ret +9: + mov x0, #-EFAULT ret ENDPROC(flush_icache_range) ENDPROC(__flush_cache_user_range) /* - * __flush_kern_dcache_page(kaddr) + * __flush_dcache_area(kaddr, size) * * Ensure that the data held in the page kaddr is written back to the * page in question. @@ -165,4 +98,103 @@ b.lo 1b dsb sy ret -ENDPROC(__flush_dcache_area) +ENDPIPROC(__flush_dcache_area) + +/* + * __inval_cache_range(start, end) + * - start - start address of region + * - end - end address of region + */ +ENTRY(__inval_cache_range) + /* FALLTHROUGH */ + +/* + * __dma_inv_range(start, end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(__dma_inv_range) + dcache_line_size x2, x3 + sub x3, x2, #1 + tst x1, x3 // end cache line aligned? + bic x1, x1, x3 + b.eq 1f + dc civac, x1 // clean & invalidate D / U line +1: tst x0, x3 // start cache line aligned? + bic x0, x0, x3 + b.eq 2f + dc civac, x0 // clean & invalidate D / U line + b 3f +2: dc ivac, x0 // invalidate D / U line +3: add x0, x0, x2 + cmp x0, x1 + b.lo 2b + dsb sy + ret +ENDPIPROC(__inval_cache_range) +ENDPROC(__dma_inv_range) + +/* + * __dma_clean_range(start, end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(__dma_clean_range) + dcache_line_size x2, x3 + sub x3, x2, #1 + bic x0, x0, x3 +1: +alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE + dc cvac, x0 +alternative_else + dc civac, x0 +alternative_endif + add x0, x0, x2 + cmp x0, x1 + b.lo 1b + dsb sy + ret +ENDPROC(__dma_clean_range) + +/* + * __dma_flush_range(start, end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(__dma_flush_range) + dcache_line_size x2, x3 + sub x3, x2, #1 + bic x0, x0, x3 +1: dc civac, x0 // clean & invalidate D / U line + add x0, x0, x2 + cmp x0, x1 + b.lo 1b + dsb sy + ret +ENDPIPROC(__dma_flush_range) + +/* + * __dma_map_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(__dma_map_area) + add x1, x1, x0 + cmp w2, #DMA_FROM_DEVICE + b.eq __dma_inv_range + b __dma_clean_range +ENDPIPROC(__dma_map_area) + +/* + * __dma_unmap_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(__dma_unmap_area) + add x1, x1, x0 + cmp w2, #DMA_TO_DEVICE + b.ne __dma_inv_range + ret +ENDPIPROC(__dma_unmap_area)