From 4af9027d3f4061992c0b065102a0a666b72f073b Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 30 Jul 2019 17:02:26 +0800 Subject: csky/dma: Fixup cache_op failed when cross memory ZONEs If the paddr and size are cross between NORMAL_ZONE and HIGHMEM_ZONE memory range, cache_op will panic in do_page_fault with bad_area. Optimize the code to support the range which cross memory ZONEs. Changes for V2: - Revert back to postcore_initcall Signed-off-by: Guo Ren Cc: Christoph Hellwig Cc: Arnd Bergmann --- arch/csky/mm/dma-mapping.c | 71 +++++++++++++++++----------------------------- 1 file changed, 26 insertions(+), 45 deletions(-) (limited to 'arch/csky/mm/dma-mapping.c') diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c index 80783bb71c5c..65f531d54814 100644 --- a/arch/csky/mm/dma-mapping.c +++ b/arch/csky/mm/dma-mapping.c @@ -20,69 +20,50 @@ static int __init atomic_pool_init(void) } postcore_initcall(atomic_pool_init); -void arch_dma_prep_coherent(struct page *page, size_t size) -{ - if (PageHighMem(page)) { - unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; - - do { - void *ptr = kmap_atomic(page); - size_t _size = (size < PAGE_SIZE) ? size : PAGE_SIZE; - - memset(ptr, 0, _size); - dma_wbinv_range((unsigned long)ptr, - (unsigned long)ptr + _size); - - kunmap_atomic(ptr); - - page++; - size -= PAGE_SIZE; - count--; - } while (count); - } else { - void *ptr = page_address(page); - - memset(ptr, 0, size); - dma_wbinv_range((unsigned long)ptr, (unsigned long)ptr + size); - } -} - static inline void cache_op(phys_addr_t paddr, size_t size, void (*fn)(unsigned long start, unsigned long end)) { - struct page *page = pfn_to_page(paddr >> PAGE_SHIFT); - unsigned int offset = paddr & ~PAGE_MASK; - size_t left = size; - unsigned long start; + struct page *page = phys_to_page(paddr); + void *start = __va(page_to_phys(page)); + unsigned long offset = offset_in_page(paddr); + size_t left = size; do { size_t len = left; + if (offset + len > PAGE_SIZE) + len = PAGE_SIZE - offset; + if (PageHighMem(page)) { - void *addr; + start = kmap_atomic(page); - if (offset + len > PAGE_SIZE) { - if (offset >= PAGE_SIZE) { - page += offset >> PAGE_SHIFT; - offset &= ~PAGE_MASK; - } - len = PAGE_SIZE - offset; - } + fn((unsigned long)start + offset, + (unsigned long)start + offset + len); - addr = kmap_atomic(page); - start = (unsigned long)(addr + offset); - fn(start, start + len); - kunmap_atomic(addr); + kunmap_atomic(start); } else { - start = (unsigned long)phys_to_virt(paddr); - fn(start, start + size); + fn((unsigned long)start + offset, + (unsigned long)start + offset + len); } offset = 0; + page++; + start += PAGE_SIZE; left -= len; } while (left); } +static void dma_wbinv_set_zero_range(unsigned long start, unsigned long end) +{ + memset((void *)start, 0, end - start); + dma_wbinv_range(start, end); +} + +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range); +} + void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { -- cgit v1.2.1 From ae76f635d4e1cffa6870cc5472567ca9d6940a22 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 30 Jul 2019 17:16:28 +0800 Subject: csky: Optimize arch_sync_dma_for_cpu/device with dma_inv_range DMA_FROM_DEVICE only need to read dma data of memory into CPU cache, so there is no need to clear cache before. Also clear + inv for DMA_FROM_DEVICE won't cause problem, because the memory range for dma won't be touched by software during dma working. Changes for V2: - Remove clr cache and ignore the DMA_TO_DEVICE in _for_cpu. - Change inv to wbinv cache with DMA_FROM_DEVICE in _for_device. Signed-off-by: Guo Ren Cc: Arnd Bergmann --- arch/csky/mm/dma-mapping.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch/csky/mm/dma-mapping.c') diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c index 65f531d54814..106ef02a8f89 100644 --- a/arch/csky/mm/dma-mapping.c +++ b/arch/csky/mm/dma-mapping.c @@ -85,11 +85,10 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, { switch (dir) { case DMA_TO_DEVICE: - cache_op(paddr, size, dma_wb_range); - break; + return; case DMA_FROM_DEVICE: case DMA_BIDIRECTIONAL: - cache_op(paddr, size, dma_wbinv_range); + cache_op(paddr, size, dma_inv_range); break; default: BUG(); -- cgit v1.2.1