On 07/18/16 13:42, Russell King - ARM Linux wrote:

On Thu, Jul 14, 2016 at 03:42:42PM +0300, Peter Ujfalusi wrote:

quoted

 struct omap_desc {
+	struct omap_chan *c;
 	struct virt_dma_desc vd;

No need for this.  to_omap_dma_chan(foo->vd.tx.chan) will give you the
omap_chan for the descriptor.  In any case, I question whether you
actually need this (see below.)

I don't know how I missed that. Works and looks better!

quoted

+	bool using_ll;
 	enum dma_transfer_direction dir;
 	dma_addr_t dev_addr;
 

@@ -81,6 +109,9 @@ struct omap_desc {
 };
 
 enum {
+	CAPS_0_SUPPORT_LL123	= BIT(20),	/* Linked List type1/2/3 */
+	CAPS_0_SUPPORT_LL4	= BIT(21),	/* Linked List type4 */
+
 	CCR_FS			= BIT(5),
 	CCR_READ_PRIORITY	= BIT(6),
 	CCR_ENABLE		= BIT(7),

@@ -151,6 +182,19 @@ enum {
 	CICR_SUPER_BLOCK_IE	= BIT(14),	/* OMAP2+ only */
 
 	CLNK_CTRL_ENABLE_LNK	= BIT(15),
+
+	CDP_DST_VALID_INC	= 0 << 0,
+	CDP_DST_VALID_RELOAD	= 1 << 0,
+	CDP_DST_VALID_REUSE	= 2 << 0,
+	CDP_SRC_VALID_INC	= 0 << 2,
+	CDP_SRC_VALID_RELOAD	= 1 << 2,
+	CDP_SRC_VALID_REUSE	= 2 << 2,
+	CDP_NTYPE_TYPE1		= 1 << 4,
+	CDP_NTYPE_TYPE2		= 2 << 4,
+	CDP_NTYPE_TYPE3		= 3 << 4,
+	CDP_TMODE_NORMAL	= 0 << 8,
+	CDP_TMODE_LLIST		= 1 << 8,
+	CDP_FAST		= BIT(10),
 };
 
 static const unsigned es_bytes[] = {

@@ -180,7 +224,64 @@ static inline struct omap_desc *to_omap_dma_desc(struct dma_async_tx_descriptor
 
 static void omap_dma_desc_free(struct virt_dma_desc *vd)
 {
-	kfree(container_of(vd, struct omap_desc, vd));
+	struct omap_desc *d = container_of(vd, struct omap_desc, vd);

	struct omap_desc *d = to_omap_dma_desc(&vd->tx);

works just as well, and looks much nicer, and follows the existing code
pattern.

Yes, I missed this as well.

quoted

+
+	if (d->using_ll) {
+		struct omap_chan *c = d->c;
+		int i;
+
+		for (i = 0; i < d->sglen; i++) {
+			if (d->sg[i].t2_desc)
+				dma_pool_free(c->desc_pool, d->sg[i].t2_desc,
+					      d->sg[i].t2_desc_paddr);

Why do you need a per-channel pool of descriptors?  Won't a per-device
descriptor pool be much better, and simplify the code here?

I was planning to try per-device pool after this series. I think I went with
per-channel pool as for example bcm2835-dma was doing the same.
In code wise I don't think it is going to simplify much as we still need to
free here what we have allocated. I can test this out.

-- 
P?ter