Re: [PATCH 13/31] nds32: DMA mapping API
flat view
From: Arnd Bergmann <arnd@arndb.de>
Date: 2017-11-08 09:09:40
Also in:
linux-arch, lkml
On Wed, Nov 8, 2017 at 6:55 AM, Greentime Hu [off-list ref] wrote:
quoted hunk ↗ jump to hunk
+static void consistent_sync(void *vaddr, size_t size, int direction) +{ + unsigned long start = (unsigned long)vaddr; + unsigned long end = start + size; + + switch (direction) { + case DMA_FROM_DEVICE: /* invalidate only */ + cpu_dma_inval_range(start, end); + break; + case DMA_TO_DEVICE: /* writeback only */ + cpu_dma_wb_range(start, end); + break; + case DMA_BIDIRECTIONAL: /* writeback and invalidate */ + cpu_dma_wbinval_range(start, end); + break; + default: + BUG(); + } +}
quoted hunk ↗ jump to hunk
+ +static void +nds32_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) +{ + consistent_sync((void *)dma_to_virt(dev, handle), size, dir); +} + +static void +nds32_dma_sync_single_for_device(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) +{ + consistent_sync((void *)dma_to_virt(dev, handle), size, dir); +}
You do the same cache operations for _to_cpu and _to_device, which
usually works,
but is more expensive than you need. It's better to take the ownership into
account and only do what you need.
Arnd