On 07/30/2018 09:26 AM, Eugeniy Paltsev wrote:
> @@ -1263,11 +1254,7 @@ void __init arc_cache_init_master(void)
> if (is_isa_arcv2() && ioc_enable)
> arc_ioc_setup();
>
> - if (is_isa_arcv2() && ioc_enable) {
> - __dma_cache_wback_inv = __dma_cache_wback_inv_ioc;
> - __dma_cache_inv = __dma_cache_inv_ioc;
> - __dma_cache_wback = __dma_cache_wback_ioc;
> - } else if (is_isa_arcv2() && l2_line_sz && slc_enable) {
> + if (is_isa_arcv2() && l2_line_sz && slc_enable) {
> __dma_cache_wback_inv = __dma_cache_wback_inv_slc;
> __dma_cache_inv = __dma_cache_inv_slc;
> __dma_cache_wback = __dma_cache_wback_slc;
> diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
> index cefb776a99ff..4d1466905e48 100644
> --- a/arch/arc/mm/dma.c
> +++ b/arch/arc/mm/dma.c
> @@ -33,19 +33,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
> if (!page)
> return NULL;
>
> - /*
> - * IOC relies on all data (even coherent DMA data) being in cache
> - * Thus allocate normal cached memory
> - *
> - * The gains with IOC are two pronged:
> - * -For streaming data, elides need for cache maintenance, saving
> - * cycles in flush code, and bus bandwidth as all the lines of a
> - * buffer need to be flushed out to memory
> - * -For coherent data, Read/Write to buffers terminate early in cache
> - * (vs. always going to memory - thus are faster)
> - */
> - if ((is_isa_arcv2() && ioc_enable) ||
> - (attrs & DMA_ATTR_NON_CONSISTENT))
> + if (attrs & DMA_ATTR_NON_CONSISTENT)
> need_coh = 0;
>
> /*
> @@ -95,8 +83,7 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
> struct page *page = virt_to_page(paddr);
> int is_non_coh = 1;
>
> - is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) ||
> - (is_isa_arcv2() && ioc_enable);
> + is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT);
>
> if (PageHighMem(page) || !is_non_coh)
> iounmap((void __force __iomem *)vaddr);
> @@ -182,3 +169,20 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
> break;
> }
> }
I think we have some shenanigans with @ioc_enable now.
Do note that it was more of a debug hack using when the hw feature was introduced
to be able to run same kernel on various FPGA bitfiles but just flicking a global
variable via the debugger.
So per code below, if @ioc_enable is NOT set, we still use software assisted cache
maintenance, but dma_{alloc,free} don't do use that variable. Have you tried
testing the combination when @ioc_enable is set to 0 before boot ? And is that works ?
> +
> +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
> + const struct iommu_ops *iommu, bool coherent)
> +{
> + /*
> + * IOC hardware snoops all DMA traffic keeping the caches consistent
> + * with memory - eliding need for any explicit cache maintenance of
> + * DMA buffers - so we can use dma_direct cache ops.
> + */
> + if (is_isa_arcv2() && ioc_enable && coherent) {
> + set_dma_ops(dev, &dma_direct_ops);
> + dev_info(dev, "use dma_direct_ops cache ops\n");
> + } else {
> + set_dma_ops(dev, &dma_noncoherent_ops);
> + dev_info(dev, "use dma_noncoherent_ops cache ops\n");
> + }
> +}
