[PATCH v2] spi: cadence-xspi: Support 32bit and 64bit slave dma interface

[Jisheng Zhang]

The cdns xspi controller slave dma interface may support wider data
width. Wider I/O width can benefit performance. We can know the width
by checking the CTRL_FEATURES_REG's DMA_DATA_WIDTH bit, 0 means 32bit
1 means 64bit.

A simple test with QSPI nor flash on one arm64 platform:

Use 8bit slave dma data width (now):
 # 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

Use 32bit slave dma data 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%!

Use 64bit slave dma data 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, 0.831104 seconds, 9.4MB/s

Improved by 64.9%!

Signed-off-by: Jisheng Zhang <jszhang@xxxxxxxxxx>
---

Since v1:
 - the hw capability(slave dma data width) can be found by checking the
   CTRL_FEATURES_REG's DMA_DATA_WIDTH, so no need dt property any more.

 drivers/spi/spi-cadence-xspi.c | 53 +++++++++++++++++++++++++++++++---
 1 file changed, 49 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index 895b4b3276a5..ab6f1c68a2eb 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -369,6 +369,8 @@ struct cdns_xspi_dev {
 
 	void *in_buffer;
 	const void *out_buffer;
+	/* Slave DMA data width in bytes (4 or 8). */
+	u8 dma_data_width;
 
 	u8 hw_num_banks;
 
@@ -573,11 +575,56 @@ static int cdns_xspi_controller_init(struct cdns_xspi_dev *cdns_xspi)
 
 	ctrl_features = readl(cdns_xspi->iobase + CDNS_XSPI_CTRL_FEATURES_REG);
 	cdns_xspi->hw_num_banks = FIELD_GET(CDNS_XSPI_NUM_BANKS, ctrl_features);
+	cdns_xspi->dma_data_width = (ctrl_features & CDNS_XSPI_DMA_DATA_WIDTH) ? 8 : 4;
 	cdns_xspi->set_interrupts_handler(cdns_xspi, false);
 
 	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->dma_data_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;
+		}
+	} else {
+		if (IS_ALIGNED((uintptr_t)src, 8) && IS_ALIGNED((uintptr_t)buf, 8)) {
+			ioread64_rep(src, buf, len >> 3);
+			offset = len & ~0x7;
+			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->dma_data_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;
+		}
+	} else {
+		if (IS_ALIGNED((uintptr_t)dst, 8) && IS_ALIGNED((uintptr_t)buf, 8)) {
+			iowrite64_rep(dst, buf, len >> 3);
+			offset = len & ~0x7;
+			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 +636,11 @@ 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;
 	}
 }
-- 
2.53.0