[PATCH 0/2] spi: cadence-xspi: support 4bytes sdma-io-width

[PATCH 0/2] spi: cadence-xspi: support 4bytes sdma-io-width

[Jisheng Zhang]

The cdns xspi controller SDMA data port may support wider I/O width.
Wider I/O width can benefit performance. A simple test with QSPI nor
flash on one arm64 platform:

1 byte io width (default):
 # dd if=/dev/mtdblock0 of=/dev/null bs=8192 count=1000
 1000+0 records in
 1000+0 records out
 8192000 bytes (7.8MB) copied, 1.368735 seconds, 5.7MB/s

4 bytes io width:
 # dd if=/dev/mtdblock0 of=/dev/null bs=8192 count=1000
 1000+0 records in
 1000+0 records out
 8192000 bytes (7.8MB) copied, 1.088787 seconds, 7.2MB/s

Improved by 26.3%!


Jisheng Zhang (2):
  spi: dt-bindings: cdns,xspi: add sdma-io-width
  spi: cadence-xspi: support 4bytes sdma-io-width

 .../devicetree/bindings/spi/cdns,xspi.yaml    |  6 +++
 drivers/spi/spi-cadence-xspi.c                | 43 +++++++++++++++++--
 2 files changed, 45 insertions(+), 4 deletions(-)

-- 
2.53.0

[PATCH 1/2] spi: dt-bindings: cdns,xspi: add sdma-io-width

[Jisheng Zhang]

The cdns xspi controller SDMA data port may support wider I/O width.
Wider I/O width can benefit performance. A simple test with QSPI nor
flash on one arm64 platform:

1 byte io width (default):
 # dd if=/dev/mtdblock0 of=/dev/null bs=8192 count=1000
 1000+0 records in
 1000+0 records out
 8192000 bytes (7.8MB) copied, 1.368735 seconds, 5.7MB/s

4 bytes io width:
 # dd if=/dev/mtdblock0 of=/dev/null bs=8192 count=1000
 1000+0 records in
 1000+0 records out
 8192000 bytes (7.8MB) copied, 1.088787 seconds, 7.2MB/s

Improved by 26.3%!

Add dt binding for sdma-io-width.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
---
 Documentation/devicetree/bindings/spi/cdns,xspi.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/spi/cdns,xspi.yaml b/Documentation/devicetree/bindings/spi/cdns,xspi.yaml
index 38a5795589de..1fd4b6dfd417 100644
--- a/Documentation/devicetree/bindings/spi/cdns,xspi.yaml
+++ b/Documentation/devicetree/bindings/spi/cdns,xspi.yaml
@@ -40,6 +40,12 @@ properties:
   interrupts:
     maxItems: 1
 
+  sdma-io-width:
+    description: Slave DMA data port I/O width (in bytes)
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 1
+    enum: [ 1, 4 ]
+
 required:
   - compatible
   - reg
-- 
2.53.0

[PATCH 2/2] spi: cadence-xspi: support 4bytes sdma-io-width

[Jisheng Zhang]

The cdns xspi controller SDMA data port may support wider I/O width.
Wider I/O width can benefit performance. A simple test with QSPI nor
flash on one arm64 platform:

1 byte io width (default):
 # dd if=/dev/mtdblock0 of=/dev/null bs=8192 count=1000
 1000+0 records in
 1000+0 records out
 8192000 bytes (7.8MB) copied, 1.368735 seconds, 5.7MB/s

4 bytes io width:
 # dd if=/dev/mtdblock0 of=/dev/null bs=8192 count=1000
 1000+0 records in
 1000+0 records out
 8192000 bytes (7.8MB) copied, 1.088787 seconds, 7.2MB/s

Improved by 26.3%!

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
---
 drivers/spi/spi-cadence-xspi.c | 43 ++++++++++++++++++++++++++++++----
 1 file changed, 39 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index 895b4b3276a5..c1fb749540e7 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -369,6 +369,7 @@ struct cdns_xspi_dev {
 
 	void *in_buffer;
 	const void *out_buffer;
+	u32 sdma_io_width;
 
 	u8 hw_num_banks;
 
@@ -578,6 +579,38 @@ static int cdns_xspi_controller_init(struct cdns_xspi_dev *cdns_xspi)
 	return 0;
 }
 
+static inline void cdns_xspi_sdma_read(struct cdns_xspi_dev *cdns_xspi, size_t len)
+{
+	void __iomem *src = cdns_xspi->sdmabase;
+	void *buf = cdns_xspi->in_buffer;
+	size_t offset = 0;
+
+	if (cdns_xspi->sdma_io_width == 4) {
+		if (IS_ALIGNED((uintptr_t)src, 4) && IS_ALIGNED((uintptr_t)buf, 4)) {
+			ioread32_rep(src, buf, len >> 2);
+			offset = len & ~0x3;
+			len -= offset;
+		}
+	}
+	ioread8_rep(src, (u8 *)buf + offset, len);
+}
+
+static inline void cdns_xspi_sdma_write(struct cdns_xspi_dev *cdns_xspi, size_t len)
+{
+	void __iomem *dst = cdns_xspi->sdmabase;
+	const void *buf = cdns_xspi->out_buffer;
+	size_t offset = 0;
+
+	if (cdns_xspi->sdma_io_width == 4) {
+		if (IS_ALIGNED((uintptr_t)dst, 4) && IS_ALIGNED((uintptr_t)buf, 4)) {
+			iowrite32_rep(dst, buf, len >> 2);
+			offset = len & ~0x3;
+			len -= offset;
+		}
+	}
+	iowrite8_rep(dst, (const u8 *)buf + offset, len);
+}
+
 static void cdns_xspi_sdma_handle(struct cdns_xspi_dev *cdns_xspi)
 {
 	u32 sdma_size, sdma_trd_info;
@@ -589,13 +622,11 @@ static void cdns_xspi_sdma_handle(struct cdns_xspi_dev *cdns_xspi)
 
 	switch (sdma_dir) {
 	case CDNS_XSPI_SDMA_DIR_READ:
-		ioread8_rep(cdns_xspi->sdmabase,
-			    cdns_xspi->in_buffer, sdma_size);
+		cdns_xspi_sdma_read(cdns_xspi, sdma_size);
 		break;
 
 	case CDNS_XSPI_SDMA_DIR_WRITE:
-		iowrite8_rep(cdns_xspi->sdmabase,
-			     cdns_xspi->out_buffer, sdma_size);
+		cdns_xspi_sdma_write(cdns_xspi, sdma_size);
 		break;
 	}
 }
@@ -1215,6 +1246,10 @@ static int cdns_xspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (device_property_read_u32(&pdev->dev, "sdma-io-width",
+				     &cdns_xspi->sdma_io_width))
+		cdns_xspi->sdma_io_width = 1;
+
 	cdns_xspi->irq = platform_get_irq(pdev, 0);
 	if (cdns_xspi->irq < 0)
 		return -ENXIO;
-- 
2.53.0