Thread (20 messages) 20 messages, 4 authors, 2015-05-23

Re: [PATCH v3 06/11] scatterlist: support "page-less" (__pfn_t only) entries

From: Dan Williams <hidden>
Date: 2015-05-20 16:03:04
Also in: linux-fsdevel, lkml, nvdimm

On Mon, May 18, 2015 at 9:10 PM, Vinod Koul [off-list ref] wrote:
On Wed, May 13, 2015 at 06:35:55PM +0000, Williams, Dan J wrote:
quoted
[ adding willy (yes, need to fix my scripts), and dmaengine folks]

Jens, Christoph,

I've rebased this patch series block/for-next.  With commit 84be456f883c
"remove <asm/scatterlist.h>" I think we can take the next step of
removing all references to page_link and just use __pfn_t by default.
v4 patch below.

Jens, I'm wondering if you want to take this series(.) as patches or
prepare a git branch to pull?
quoted
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 4d63e0d4da9a..21736afd3320 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -582,7 +582,7 @@ static int omap_sham_xmit_dma(struct omap_sham_dev *dd, dma_addr_t dma_addr,
               * the dmaengine may try to DMA the incorrect amount of data.
               */
              sg_init_table(&ctx->sgl, 1);
-             ctx->sgl.page_link = ctx->sg->page_link;
+             ctx->sgl.pfn = ctx->sg->pfn;
Do you want drivers to tinker with internals of sg, I think driver should be
agnostic here, perhpas a helper to get pfn, sg_get_pfn()
Hmm, we have sg_page() seems like we also need an sg_pfn().  Thanks, will fix.
quoted
              ctx->sgl.offset = ctx->sg->offset;
              sg_dma_len(&ctx->sgl) = len32;
              sg_dma_address(&ctx->sgl) = sg_dma_address(ctx->sg);
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index eed405976ea9..a767727bcfef 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -886,7 +886,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
      sg_init_table(imxdmac->sg_list, periods);

      for (i = 0; i < periods; i++) {
-             imxdmac->sg_list[i].page_link = 0;
+             imxdmac->sg_list[i].pfn.page = NULL;
same here, sg_set_pfn_page() ?
sg_set_page() would work here.
quoted
              imxdmac->sg_list[i].offset = 0;
              imxdmac->sg_list[i].dma_address = dma_addr;
              sg_dma_len(&imxdmac->sg_list[i]) = period_len;
@@ -894,10 +894,7 @@ static struct dma_async_tx_descriptor *imxdma_prep_dma_cyclic(
      }

      /* close the loop */
-     imxdmac->sg_list[periods].offset = 0;
-     sg_dma_len(&imxdmac->sg_list[periods]) = 0;
-     imxdmac->sg_list[periods].page_link =
-             ((unsigned long)imxdmac->sg_list | 0x01) & ~0x02;
+     sg_chain(imxdmac->sg_list, periods + 1, imxdmac->sg_list);
This looks right...
Cool, thanks for taking a look.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help