Hi Robin,

On Wed, Sep 01, 2021 at 09:03:30PM +0100, Robin Murphy wrote:

[...]

...

@@ -600,6 +601,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, { struct etr_flat_buf *flat_buf; struct device *real_dev = drvdata->csdev->dev.parent;

• ssize_t aligned_size; /* We cannot reuse existing pages for flat buf */ if (pages)

@@ -609,11 +611,18 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, if (!flat_buf) return -ENOMEM;

• flat_buf->vaddr = dma_alloc_coherent(real_dev, etr_buf->size,

• 			     &flat_buf->daddr, GFP_KERNEL);
  

• if (!flat_buf->vaddr) {

• kfree(flat_buf);
  

• return -ENOMEM;
  

• aligned_size = PAGE_ALIGN(etr_buf->size);
• flat_buf->pages = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO,

• 			   get_order(aligned_size));
  

• if (!flat_buf->pages)

• goto fail_alloc_pages;
  

• flat_buf->vaddr = page_address(flat_buf->pages);
• flat_buf->daddr = dma_map_page(real_dev, flat_buf->pages, 0,

• 		       aligned_size, DMA_FROM_DEVICE);
  

Use dma_alloc_noncoherent() rather than open-coding this - bare alloc_pages() has no understanding of DMA masks, and you wouldn't want to end up in the worst case of dma_map_page() bounce-buffering your bounce buffer...

Will refine the code with dma_alloc_noncoherent(); it's much reliable than the self writing code.

Thanks a lot for the suggestion!