[PATCH v1 0/13] Patches to improve dma transfer efficiency for Rockchip SoCs.

[PATCH v1 0/13] Patches to improve dma transfer efficiency for Rockchip SoCs.

[Sugar Zhang]

Sugar Zhang (13):
  dmaengine: pl330: Remove the burst limit for quirk 'NO-FLUSHP'
  dmaengine: pl330: Add quirk 'arm,pl330-periph-burst'
  dt-bindings: dma: pl330: Document the quirk 'arm,pl330-periph-burst'
  ARM: dts: rk3036: Add 'arm,pl330-periph-burst' for dmac
  ARM: dts: rk322x: Add 'arm,pl330-periph-burst' for dmac
  ARM: dts: rk3288: Add 'arm,pl330-periph-burst' for dmac
  ARM: dts: rk3xxx: Add 'arm,pl330-periph-burst' for dmac
  ARM: dts: rv1108: Add 'arm,pl330-periph-burst' for dmac
  arm64: dts: px30: Add 'arm,pl330-periph-burst' for dmac
  arm64: dts: rk3308: Add 'arm,pl330-periph-burst' for dmac
  arm64: dts: rk3328: Add 'arm,pl330-periph-burst' for dmac
  arm64: dts: rk3368: Add 'arm,pl330-periph-burst' for dmac
  arm64: dts: rk3399: Add 'arm,pl330-periph-burst' for dmac

 .../devicetree/bindings/dma/arm-pl330.txt          |  1 +
 arch/arm/boot/dts/rk3036.dtsi                      |  1 +
 arch/arm/boot/dts/rk322x.dtsi                      |  1 +
 arch/arm/boot/dts/rk3288.dtsi                      |  3 ++
 arch/arm/boot/dts/rk3xxx.dtsi                      |  3 ++
 arch/arm/boot/dts/rv1108.dtsi                      |  1 +
 arch/arm64/boot/dts/rockchip/px30.dtsi             |  1 +
 arch/arm64/boot/dts/rockchip/rk3308.dtsi           |  2 +
 arch/arm64/boot/dts/rockchip/rk3328.dtsi           |  1 +
 arch/arm64/boot/dts/rockchip/rk3368.dtsi           |  2 +
 arch/arm64/boot/dts/rockchip/rk3399.dtsi           |  2 +
 drivers/dma/pl330.c                                | 44 +++++++++++++++-------
 12 files changed, 49 insertions(+), 13 deletions(-)

-- 
2.7.4

[PATCH v1 01/13] dmaengine: pl330: Remove the burst limit for quirk 'NO-FLUSHP'

[Sugar Zhang]

There is no reason to limit the performance on the 'NO-FLUSHP' SoCs,
cuz these platforms are just that the 'FLUSHP' instruction is broken.
so, remove the limit to improve the efficiency.

Signed-off-by: Sugar Zhang <sugar.zhang@rock-chips.com>
---

 drivers/dma/pl330.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 6a158ee..ff0a91f 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1183,9 +1183,6 @@ static inline int _ldst_peripheral(struct pl330_dmac *pl330,
 {
 	int off = 0;
 
-	if (pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP)
-		cond = BURST;
-
 	/*
 	 * do FLUSHP at beginning to clear any stale dma requests before the
 	 * first WFP.
@@ -1231,8 +1228,9 @@ static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 }
 
 /*
- * transfer dregs with single transfers to peripheral, or a reduced size burst
- * for mem-to-mem.
+ * only the unaligned bursts transfers have the dregs.
+ * transfer dregs with a reduced size burst to peripheral,
+ * or a reduced size burst for mem-to-mem.
  */
 static int _dregs(struct pl330_dmac *pl330, unsigned int dry_run, u8 buf[],
 		const struct _xfer_spec *pxs, int transfer_length)
@@ -1247,8 +1245,23 @@ static int _dregs(struct pl330_dmac *pl330, unsigned int dry_run, u8 buf[],
 	case DMA_MEM_TO_DEV:
 		/* fall through */
 	case DMA_DEV_TO_MEM:
-		off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs,
-			transfer_length, SINGLE);
+		/*
+		 * dregs_len = (total bytes - BURST_TO_BYTE(bursts, ccr)) /
+		 *             BRST_SIZE(ccr)
+		 * the dregs len must be smaller than burst len,
+		 * so, for higher efficiency, we can modify CCR
+		 * to use a reduced size burst len for the dregs.
+		 */
+		dregs_ccr = pxs->ccr;
+		dregs_ccr &= ~((0xf << CC_SRCBRSTLEN_SHFT) |
+			(0xf << CC_DSTBRSTLEN_SHFT));
+		dregs_ccr |= (((transfer_length - 1) & 0xf) <<
+			CC_SRCBRSTLEN_SHFT);
+		dregs_ccr |= (((transfer_length - 1) & 0xf) <<
+			CC_DSTBRSTLEN_SHFT);
+		off += _emit_MOV(dry_run, &buf[off], CCR, dregs_ccr);
+		off += _ldst_peripheral(pl330, dry_run, &buf[off], pxs, 1,
+					BURST);
 		break;
 
 	case DMA_MEM_TO_MEM:
@@ -2221,9 +2234,7 @@ static bool pl330_prep_slave_fifo(struct dma_pl330_chan *pch,
 
 static int fixup_burst_len(int max_burst_len, int quirks)
 {
-	if (quirks & PL330_QUIRK_BROKEN_NO_FLUSHP)
-		return 1;
-	else if (max_burst_len > PL330_MAX_BURST)
+	if (max_burst_len > PL330_MAX_BURST)
 		return PL330_MAX_BURST;
 	else if (max_burst_len < 1)
 		return 1;
@@ -3128,8 +3139,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pd->dst_addr_widths = PL330_DMA_BUSWIDTHS;
 	pd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	pd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
-	pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ?
-			 1 : PL330_MAX_BURST);
+	pd->max_burst = PL330_MAX_BURST;
 
 	ret = dma_async_device_register(pd);
 	if (ret) {
-- 
2.7.4

[PATCH v1 02/13] dmaengine: pl330: Add quirk 'arm,pl330-periph-burst'

[Sugar Zhang]

This patch adds the qurik to use busrt transfers only
for pl330 controller, even for request with a length of 1.

Although, the correct way should be: if the peripheral request
length is 1, the peripheral should use SINGLE request, and then
notify the dmac using SINGLE mode by src/dst_maxburst with 1.

For example, on the Rockchip SoCs, all the peripherals can use
SINGLE or BURST request by setting GRF registers. it is possible
that if these peripheral drivers are used only for Rockchip SoCs.
Unfortunately, it's not, such as dw uart, which is used so widely,
and we can't set src/dst_maxburst according to the SoCs' specific
to compatible with all the other SoCs.

So, for convenience, all the peripherals are set as BURST request
by default on the Rockchip SoCs. even for request with a length of 1.
the current pl330 driver will perform SINGLE transfer if the client's
maxburst is 1, which still should be working according to chapter 2.6.6
of datasheet which describe how DMAC performs SINGLE transfers for
a BURST request. unfortunately, it's broken on the Rockchip SoCs,
which support only matching transfers, such as BURST transfer for
BURST request, SINGLE transfer for SINGLE request.

Finaly, we add the quirk to specify pl330 to use burst transfers only.

Signed-off-by: Sugar Zhang <sugar.zhang@rock-chips.com>
---

 drivers/dma/pl330.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index ff0a91f..1941ec6 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -33,7 +33,8 @@
 #define PL330_MAX_PERI		32
 #define PL330_MAX_BURST         16
 
-#define PL330_QUIRK_BROKEN_NO_FLUSHP BIT(0)
+#define PL330_QUIRK_BROKEN_NO_FLUSHP	BIT(0)
+#define PL330_QUIRK_PERIPH_BURST	BIT(1)
 
 enum pl330_cachectrl {
 	CCTRL0,		/* Noncacheable and nonbufferable */
@@ -509,6 +510,10 @@ static struct pl330_of_quirks {
 	{
 		.quirk = "arm,pl330-broken-no-flushp",
 		.id = PL330_QUIRK_BROKEN_NO_FLUSHP,
+	},
+	{
+		.quirk = "arm,pl330-periph-burst",
+		.id = PL330_QUIRK_PERIPH_BURST,
 	}
 };
 
@@ -1206,6 +1211,9 @@ static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 	int off = 0;
 	enum pl330_cond cond = BRST_LEN(pxs->ccr) > 1 ? BURST : SINGLE;
 
+	if (pl330->quirks & PL330_QUIRK_PERIPH_BURST)
+		cond = BURST;
+
 	switch (pxs->desc->rqtype) {
 	case DMA_MEM_TO_DEV:
 		/* fall through */
-- 
2.7.4

[PATCH v1 03/13] dt-bindings: dma: pl330: Document the quirk 'arm,pl330-periph-burst'

[Sugar Zhang]

This patch Adds the quirk 'arm,pl330-periph-burst' for pl330.

Signed-off-by: Sugar Zhang <sugar.zhang@rock-chips.com>
---

 Documentation/devicetree/bindings/dma/arm-pl330.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/dma/arm-pl330.txt b/Documentation/devicetree/bindings/dma/arm-pl330.txt
index 2c7fd19..315e901 100644
--- a/Documentation/devicetree/bindings/dma/arm-pl330.txt
+++ b/Documentation/devicetree/bindings/dma/arm-pl330.txt
@@ -16,6 +16,7 @@ Optional properties:
   - dma-channels: contains the total number of DMA channels supported by the DMAC
   - dma-requests: contains the total number of DMA requests supported by the DMAC
   - arm,pl330-broken-no-flushp: quirk for avoiding to execute DMAFLUSHP
+  - arm,pl330-periph-burst: quirk for performing burst transfer only
   - resets: contains an entry for each entry in reset-names.
 	    See ../reset/reset.txt for details.
   - reset-names: must contain at least "dma", and optional is "dma-ocp".
-- 
2.7.4