dmaengine: bcm2835: Avoid accessing memory when copying zeroes

The BCM2835 DMA controller is capable of synthesizing zeroes instead of
copying them from a source address. The feature is enabled by setting
the SRC_IGNORE bit in the Transfer Information field of a Control Block:

"Do not perform source reads.
 In addition, destination writes will zero all the write strobes.
 This is used for fast cache fill operations."
https://www.raspberrypi.org/app/uploads/2012/02/BCM2835-ARM-Peripherals.pdf

The feature is only available on 8 of the 16 channels. The others are
so-called "lite" channels with a limited feature set and performance.

Make use of the feature if a cyclic transaction copies from the zero
page. This reduces traffic on the memory bus.

A forthcoming use case is the BCM2835 SPI driver, which will cyclically
copy from the zero page to the TX FIFO. The idea to use SRC_IGNORE was
taken from an ancient GitHub conversation between Martin and Noralf:
msperl/spi-bcm2835#13 (comment)

Signed-off-by: Lukas Wunner <[email protected]>
Cc: Martin Sperl <[email protected]>
Cc: Noralf Trønnes <[email protected]>
Cc: Florian Kauer <[email protected]>

Author: l1k

drivers/dma/bcm2835-dma.c

@@ -53,11 +53,14 @@
  * @ddev: DMA device
  * @base: base address of register map
  * @dma_parms: DMA parameters (to convey 1 GByte max segment size to clients)
+ * @zero_page: bus address of zero page (to detect transactions copying from
+ *	zero page and avoid accessing memory if so)
  */
 struct bcm2835_dmadev {
 	struct dma_device ddev;
 	void __iomem *base;
 	struct device_dma_parameters dma_parms;
+	dma_addr_t zero_page;
 };
 
 struct bcm2835_dma_cb {
@@ -705,6 +708,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic(
 	size_t period_len, enum dma_transfer_direction direction,
 	unsigned long flags)
 {
+	struct bcm2835_dmadev *od = to_bcm2835_dma_dev(chan->device);
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
 	struct bcm2835_desc *d;
 	dma_addr_t src, dst;
@@ -755,6 +759,10 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic(
 		dst = c->cfg.dst_addr;
 		src = buf_addr;
 		info |= BCM2835_DMA_D_DREQ | BCM2835_DMA_S_INC;
+
+		/* non-lite channels can write zeroes w/o accessing memory */
+		if (buf_addr == od->zero_page && !c->is_lite_channel)
+			info |= BCM2835_DMA_S_IGNORE;
 	}
 
 	/* calculate number of frames */
@@ -857,6 +865,9 @@ static void bcm2835_dma_free(struct bcm2835_dmadev *od)
 		list_del(&c->vc.chan.device_node);
 		tasklet_kill(&c->vc.task);
 	}
+
+	dma_unmap_page_attrs(od->ddev.dev, od->zero_page, PAGE_SIZE,
+			     DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 }
 
 static const struct of_device_id bcm2835_dma_of_match[] = {
@@ -943,6 +954,14 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, od);
 
+	od->zero_page = dma_map_page_attrs(od->ddev.dev, ZERO_PAGE(0), 0,
+					   PAGE_SIZE, DMA_TO_DEVICE,
+					   DMA_ATTR_SKIP_CPU_SYNC);
+	if (dma_mapping_error(od->ddev.dev, od->zero_page)) {
+		dev_err(&pdev->dev, "Failed to map zero page\n");
+		return -ENOMEM;
+	}
+
 	/* Request DMA channel mask from device tree */
 	if (of_property_read_u32(pdev->dev.of_node,
 			"brcm,dma-channel-mask",