[PATCH v6 10/10] dmaengine: dw-edma: Remove struct dw_edma_chunk

From: Frank Li <[email protected]>

The current descriptor layout is:

  struct dw_edma_desc *desc
   └─ chunk list
        └─ burst[]

Creating a DMA descriptor requires at least two kzalloc() calls because
each chunk is allocated as a linked-list node. Since the number of bursts
is already known when the descriptor is created, this linked-list layer is
unnecessary.

Move the burst array directly into struct dw_edma_desc and remove the
struct dw_edma_chunk layer entirely.

Use start_burst and done_burst to track the current bursts, which current
are in the DMA link list.

Tested-by: Koichiro Den <[email protected]>
Signed-off-by: Frank Li <[email protected]>
---
change in v6
- use size_t for nburst, start_burst, done_burst, to fix sashiko report
integer overflow problem.

change in v5
- fix double substract and done_burst -1, found by sashiko AI
- remove unused field chuck_list, xfer_sz and chucks_alloc, found by sashiko

change in v4
- fix loop condition check in dw_edma_core_start(), found by sashiko AI.
- collect Koichiro tag

change in v2
- remove debug code
- move "residue = desc->alloc_sz;"  in if(desc) check
- keep inline to avoid build warning
---
 drivers/dma/dw-edma/dw-edma-core.c | 147 ++++++++++++-------------------------
 drivers/dma/dw-edma/dw-edma-core.h |  28 +++----
 2 files changed, 63 insertions(+), 112 deletions(-)

diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 202862a828b4d..30eeb7bffad80 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -40,82 +40,54 @@ u64 dw_edma_get_pci_address(struct dw_edma_chan *chan, phys_addr_t cpu_addr)
 	return cpu_addr;
 }
 
-static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc, u32 nburst)
-{
-	struct dw_edma_chan *chan = desc->chan;
-	struct dw_edma_chunk *chunk;
-
-	chunk = kzalloc_flex(*chunk, burst, nburst, GFP_NOWAIT);
-	if (unlikely(!chunk))
-		return NULL;
-
-	chunk->chan = chan;
-	/* Toggling change bit (CB) in each chunk, this is a mechanism to
-	 * inform the eDMA HW block that this is a new linked list ready
-	 * to be consumed.
-	 *  - Odd chunks originate CB equal to 0
-	 *  - Even chunks originate CB equal to 1
-	 */
-	chunk->cb = !(desc->chunks_alloc % 2);
-
-	chunk->nburst = nburst;
-
-	list_add_tail(&chunk->list, &desc->chunk_list);
-	desc->chunks_alloc++;
-
-	return chunk;
-}
-
-static struct dw_edma_desc *dw_edma_alloc_desc(struct dw_edma_chan *chan)
+static struct dw_edma_desc *
+dw_edma_alloc_desc(struct dw_edma_chan *chan, size_t nburst)
 {
 	struct dw_edma_desc *desc;
 
-	desc = kzalloc_obj(*desc, GFP_NOWAIT);
+	desc = kzalloc_flex(*desc, burst, nburst, GFP_NOWAIT);
 	if (unlikely(!desc))
 		return NULL;
 
 	desc->chan = chan;
-
-	INIT_LIST_HEAD(&desc->chunk_list);
+	desc->nburst = nburst;
+	desc->cb = true;
 
 	return desc;
 }
 
-static void dw_edma_free_desc(struct dw_edma_desc *desc)
-{
-	struct dw_edma_chunk *child, *_next;
-
-	/* Remove all the list elements */
-	list_for_each_entry_safe(child, _next, &desc->chunk_list, list) {
-		list_del(&child->list);
-		kfree(child);
-		desc->chunks_alloc--;
-	}
-
-	kfree(desc);
-}
-
 static void vchan_free_desc(struct virt_dma_desc *vdesc)
 {
-	dw_edma_free_desc(vd2dw_edma_desc(vdesc));
+	kfree(vd2dw_edma_desc(vdesc));
 }
 
-static void dw_edma_core_start(struct dw_edma_chunk *chunk, bool first)
+static void dw_edma_core_start(struct dw_edma_desc *desc, bool first)
 {
-	struct dw_edma_chan *chan = chunk->chan;
-	u32 i = 0;
+	struct dw_edma_chan *chan = desc->chan;
+	size_t i = 0;
 
 	if (chan->non_ll) {
-		if (chunk->nburst == 1)
-			chan->dw->core->non_ll_start(chunk->chan, &chunk->burst[0]);
+		chan->dw->core->non_ll_start(chan, &desc->burst[desc->start_burst]);
+		desc->done_burst = desc->start_burst;
+		desc->start_burst += 1;
 		return;
 	}
 
-	for (i = 0; i < chunk->nburst; i++)
-		dw_edma_core_ll_data(chan, &chunk->burst[i], i, chunk->cb,
-				     i == chunk->nburst - 1);
+	for (i = 0; i + desc->start_burst < desc->nburst; i++) {
+		u32 idx = i + desc->start_burst;
 
-	dw_edma_core_ll_link(chan, i, chunk->cb, chan->ll_region.paddr);
+		if (i == chan->ll_max)
+			break;
+
+		dw_edma_core_ll_data(chan, &desc->burst[idx],
+				     i, desc->cb,
+				     idx == desc->nburst - 1 || i == chan->ll_max - 1);
+	}
+
+	desc->done_burst = desc->start_burst;
+	desc->start_burst += i;
+
+	dw_edma_core_ll_link(chan, i, desc->cb, chan->ll_region.paddr);
 
 	if (first)
 		dw_edma_core_ch_enable(chan);
@@ -125,7 +97,6 @@ static void dw_edma_core_start(struct dw_edma_chunk *chunk, bool first)
 
 static int dw_edma_start_transfer(struct dw_edma_chan *chan)
 {
-	struct dw_edma_chunk *child;
 	struct dw_edma_desc *desc;
 	struct virt_dma_desc *vd;
 
@@ -137,16 +108,9 @@ static int dw_edma_start_transfer(struct dw_edma_chan *chan)
 	if (!desc)
 		return 0;
 
-	child = list_first_entry_or_null(&desc->chunk_list,
-					 struct dw_edma_chunk, list);
-	if (!child)
-		return 0;
+	dw_edma_core_start(desc, !desc->start_burst);
 
-	dw_edma_core_start(child, !desc->xfer_sz);
-	desc->xfer_sz += child->xfer_sz;
-	list_del(&child->list);
-	kfree(child);
-	desc->chunks_alloc--;
+	desc->cb = !desc->cb;
 
 	return 1;
 }
@@ -337,8 +301,10 @@ dw_edma_device_tx_status(struct dma_chan *dchan, dma_cookie_t cookie,
 	vd = vchan_find_desc(&chan->vc, cookie);
 	if (vd) {
 		desc = vd2dw_edma_desc(vd);
-		if (desc)
-			residue = desc->alloc_sz - desc->xfer_sz;
+
+		residue = desc->alloc_sz;
+		if (desc && desc->done_burst)
+			residue -= desc->burst[desc->done_burst - 1].xfer_sz;
 	}
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
@@ -355,13 +321,11 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer,
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(xfer->dchan);
 	enum dma_transfer_direction dir = xfer->direction;
 	struct scatterlist *sg = NULL;
-	struct dw_edma_chunk *chunk = NULL;
 	struct dw_edma_burst *burst;
 	struct dw_edma_desc *desc;
 	u64 src_addr, dst_addr;
 	size_t fsz = 0;
-	u32 bursts_max;
-	u32 cnt = 0;
+	size_t cnt = 0;
 	u32 i;
 
 	if (!chan->configured)
@@ -418,17 +382,6 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer,
 		return NULL;
 	}
 
-	/*
-	 * For non-LL mode, only a single burst can be handled
-	 * in a single chunk unlike LL mode where multiple bursts
-	 * can be configured in a single chunk.
-	 */
-	bursts_max = chan->non_ll ? 1 : chan->ll_max;
-
-	desc = dw_edma_alloc_desc(chan);
-	if (unlikely(!desc))
-		goto err_alloc;
-
 	if (xfer->type == EDMA_XFER_INTERLEAVED) {
 		src_addr = xfer->xfer.il->src_start;
 		dst_addr = xfer->xfer.il->dst_start;
@@ -452,19 +405,15 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer,
 		fsz = xfer->xfer.il->frame_size;
 	}
 
+	desc = dw_edma_alloc_desc(chan, cnt);
+	if (unlikely(!desc))
+		return NULL;
+
 	for (i = 0; i < cnt; i++) {
 		if (xfer->type == EDMA_XFER_SCATTER_GATHER && !sg)
 			break;
 
-		if (!(i % bursts_max)) {
-			u32 n = min(cnt - i, bursts_max);
-
-			chunk = dw_edma_alloc_chunk(desc, n);
-			if (unlikely(!chunk))
-				goto err_alloc;
-		}
-
-		burst = chunk->burst + (i % chan->ll_max);
+		burst = desc->burst + i;
 
 		if (xfer->type == EDMA_XFER_CYCLIC)
 			burst->sz = xfer->xfer.cyclic.len;
@@ -473,8 +422,8 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer,
 		else if (xfer->type == EDMA_XFER_INTERLEAVED)
 			burst->sz = xfer->xfer.il->sgl[i % fsz].size;
 
-		chunk->xfer_sz += burst->sz;
 		desc->alloc_sz += burst->sz;
+		burst->xfer_sz = desc->alloc_sz;
 
 		if (dir == DMA_DEV_TO_MEM) {
 			burst->sar = src_addr;
@@ -529,12 +478,6 @@ dw_edma_device_transfer(struct dw_edma_transfer *xfer,
 	}
 
 	return vchan_tx_prep(&chan->vc, &desc->vd, xfer->flags);
-
-err_alloc:
-	if (desc)
-		dw_edma_free_desc(desc);
-
-	return NULL;
 }
 
 static struct dma_async_tx_descriptor *
@@ -605,8 +548,14 @@ static void dw_hdma_set_callback_result(struct virt_dma_desc *vd,
 		return;
 
 	desc = vd2dw_edma_desc(vd);
-	if (desc)
-		residue = desc->alloc_sz - desc->xfer_sz;
+	if (desc) {
+		residue = desc->alloc_sz;
+
+		if (result == DMA_TRANS_NOERROR)
+			residue -= desc->burst[desc->start_burst - 1].xfer_sz;
+		else if (desc->done_burst)
+			residue -= desc->burst[desc->done_burst - 1].xfer_sz;
+	}
 
 	res = &vd->tx_result;
 	res->result = result;
@@ -625,7 +574,7 @@ static void dw_edma_done_interrupt(struct dw_edma_chan *chan)
 		switch (chan->request) {
 		case EDMA_REQ_NONE:
 			desc = vd2dw_edma_desc(vd);
-			if (!desc->chunks_alloc) {
+			if (desc->start_burst >= desc->nburst) {
 				dw_hdma_set_callback_result(vd,
 							    DMA_TRANS_NOERROR);
 				list_del(&vd->node);
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 4950c57fca34f..3c958ca05144a 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -46,26 +46,21 @@ struct dw_edma_burst {
 	u64				sar;
 	u64				dar;
 	u32				sz;
-};
-
-struct dw_edma_chunk {
-	struct list_head		list;
-	struct dw_edma_chan		*chan;
-	u8				cb;
+	/* precalulate summary of previous burst total size */
 	u32				xfer_sz;
-	u32                             nburst;
-	struct dw_edma_burst            burst[] __counted_by(nburst);
 };
 
 struct dw_edma_desc {
 	struct virt_dma_desc		vd;
 	struct dw_edma_chan		*chan;
-	struct list_head		chunk_list;
-
-	u32				chunks_alloc;
 
 	u32				alloc_sz;
-	u32				xfer_sz;
+
+	size_t				done_burst;
+	size_t				start_burst;
+	u8				cb;
+	size_t				nburst;
+	struct dw_edma_burst            burst[] __counted_by(nburst);
 };
 
 struct dw_edma_chan {
@@ -128,7 +123,6 @@ struct dw_edma_core_ops {
 	void (*ll_link)(struct dw_edma_chan *chan, u32 idx, bool cb, u64 addr);
 	void (*ch_doorbell)(struct dw_edma_chan *chan);
 	void (*ch_enable)(struct dw_edma_chan *chan);
-
 	void (*ch_config)(struct dw_edma_chan *chan);
 	void (*debugfs_on)(struct dw_edma *dw);
 	void (*ack_emulated_irq)(struct dw_edma *dw);
@@ -170,6 +164,14 @@ struct dw_edma_chan *dchan2dw_edma_chan(struct dma_chan *dchan)
 	return vc2dw_edma_chan(to_virt_chan(dchan));
 }
 
+static inline u64 dw_edma_core_get_ll_paddr(struct dw_edma_chan *chan)
+{
+	if (chan->dir == EDMA_DIR_WRITE)
+		return chan->dw->chip->ll_region_wr[chan->id].paddr;
+
+	return chan->dw->chip->ll_region_rd[chan->id].paddr;
+}
+
 static inline
 void dw_edma_core_off(struct dw_edma *dw)
 {

-- 
2.43.0