[PATCH v2] dmaengine: tegra-apb: Support per-burst residue granularity

[Dmitry Osipenko]

Tegra's APB DMA engine updates words counter after each transferred burst
of data, hence it can report transfer's residual with more fidelity which
may be required in cases like audio playback. In particular this fixes
audio stuttering during playback in a chromiuim web browser. The patch is
based on the original work that was made by Ben Dooks. It was tested on
Tegra20 and Tegra30 devices.

Link: https://lore.kernel.org/lkml/20190424162348.23692-1-ben.dooks@xxxxxxxxxxxxxxx/
Inspired-by: Ben Dooks <ben.dooks@xxxxxxxxxxxxxxx>
Signed-off-by: Dmitry Osipenko <digetx@xxxxxxxxx>
---

Changelog:

v2:  Addressed review comments made by Jon Hunter to v1. We won't try
     to get words count if dma_desc is on free list as it will result
     in a NULL dereference because this case wasn't handled properly.

     The residual value is now updated properly, avoiding potential
     integer overflow by adding the "bytes" to the "bytes_transferred"
     instead of the subtraction.

 drivers/dma/tegra20-apb-dma.c | 33 ++++++++++++++++++++++++++-------
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 79e9593815f1..fed18bc46479 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -797,6 +797,28 @@ static int tegra_dma_terminate_all(struct dma_chan *dc)
 	return 0;
 }
 
+static unsigned int tegra_dma_sg_bytes_xferred(struct tegra_dma_channel *tdc,
+					       struct tegra_dma_sg_req *sg_req)
+{
+	unsigned long status, wcount = 0;
+
+	if (!list_is_first(&sg_req->node, &tdc->pending_sg_req))
+		return 0;
+
+	if (tdc->tdma->chip_data->support_separate_wcount_reg)
+		wcount = tdc_read(tdc, TEGRA_APBDMA_CHAN_WORD_TRANSFER);
+
+	status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
+
+	if (!tdc->tdma->chip_data->support_separate_wcount_reg)
+		wcount = status;
+
+	if (status & TEGRA_APBDMA_STATUS_ISE_EOC)
+		return sg_req->req_len;
+
+	return get_current_xferred_count(tdc, sg_req, wcount);
+}
+
 static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
@@ -806,6 +828,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	enum dma_status ret;
 	unsigned long flags;
 	unsigned int residual;
+	unsigned int bytes = 0;
 
 	ret = dma_cookie_status(dc, cookie, txstate);
 	if (ret == DMA_COMPLETE)
@@ -825,6 +848,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 	list_for_each_entry(sg_req, &tdc->pending_sg_req, node) {
 		dma_desc = sg_req->dma_desc;
 		if (dma_desc->txd.cookie == cookie) {
+			bytes = tegra_dma_sg_bytes_xferred(tdc, sg_req);
 			ret = dma_desc->dma_status;
 			goto found;
 		}
@@ -836,7 +860,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 found:
 	if (dma_desc && txstate) {
 		residual = dma_desc->bytes_requested -
-			   (dma_desc->bytes_transferred %
+			   ((dma_desc->bytes_transferred + bytes) %
 			    dma_desc->bytes_requested);
 		dma_set_residue(txstate, residual);
 	}
@@ -1441,12 +1465,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) |
 		BIT(DMA_SLAVE_BUSWIDTH_8_BYTES);
 	tdma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
-	/*
-	 * XXX The hardware appears to support
-	 * DMA_RESIDUE_GRANULARITY_BURST-level reporting, but it's
-	 * only used by this driver during tegra_dma_terminate_all()
-	 */
-	tdma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	tdma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	tdma->dma_dev.device_config = tegra_dma_slave_config;
 	tdma->dma_dev.device_terminate_all = tegra_dma_terminate_all;
 	tdma->dma_dev.device_tx_status = tegra_dma_tx_status;
-- 
2.22.0