Merge branch 'topic/pl330' into for-linus

5 files changed, 89 insertions, 30 deletions

diff --git a/Documentation/devicetree/bindings/dma/arm-pl330.txt b/Documentation/devicetree/bindings/dma/arm-pl330.txt
index 267565894db9..db7e2260f9c5 100644
--- a/Documentation/devicetree/bindings/dma/arm-pl330.txt
+++ b/Documentation/devicetree/bindings/dma/arm-pl330.txt
@@ -15,6 +15,7 @@ Optional properties:
     cells in the dmas property of client device.
   - 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
 
 Example:
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index c50a247be2e0..0cb259c59916 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -496,6 +496,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->src_addr_widths = device->src_addr_widths;
 	caps->dst_addr_widths = device->dst_addr_widths;
 	caps->directions = device->directions;
+	caps->max_burst = device->max_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 17ee758b419f..372b4359da97 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -33,6 +33,9 @@
 #define PL330_MAX_CHAN		8
 #define PL330_MAX_IRQS		32
 #define PL330_MAX_PERI		32
+#define PL330_MAX_BURST         16
+
+#define PL330_QUIRK_BROKEN_NO_FLUSHP BIT(0)
 
 enum pl330_cachectrl {
 	CCTRL0,		/* Noncacheable and nonbufferable */
@@ -488,6 +491,17 @@ struct pl330_dmac {
 	/* Peripheral channels connected to this DMAC */
 	unsigned int num_peripherals;
 	struct dma_pl330_chan *peripherals; /* keep at end */
+	int quirks;
+};
+
+static struct pl330_of_quirks {
+	char *quirk;
+	int id;
+} of_quirks[] = {
+	{
+		.quirk = "arm,pl330-broken-no-flushp",
+		.id = PL330_QUIRK_BROKEN_NO_FLUSHP,
+	}
 };
 
 struct dma_pl330_desc {
@@ -1137,47 +1151,67 @@ static inline int _ldst_memtomem(unsigned dry_run, u8 buf[],
 	return off;
 }
 
-static inline int _ldst_devtomem(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
+static inline int _ldst_devtomem(struct pl330_dmac *pl330, unsigned dry_run,
+				 u8 buf[], const struct _xfer_spec *pxs,
+				 int cyc)
 {
 	int off = 0;
+	enum pl330_cond cond;
+
+	if (pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP)
+		cond = BURST;
+	else
+		cond = SINGLE;
 
 	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
-		off += _emit_LDP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
+		off += _emit_WFP(dry_run, &buf[off], cond, pxs->desc->peri);
+		off += _emit_LDP(dry_run, &buf[off], cond, pxs->desc->peri);
 		off += _emit_ST(dry_run, &buf[off], ALWAYS);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->desc->peri);
+
+		if (!(pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP))
+			off += _emit_FLUSHP(dry_run, &buf[off],
+					    pxs->desc->peri);
 	}
 
 	return off;
 }
 
-static inline int _ldst_memtodev(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs, int cyc)
+static inline int _ldst_memtodev(struct pl330_dmac *pl330,
+				 unsigned dry_run, u8 buf[],
+				 const struct _xfer_spec *pxs, int cyc)
 {
 	int off = 0;
+	enum pl330_cond cond;
+
+	if (pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP)
+		cond = BURST;
+	else
+		cond = SINGLE;
 
 	while (cyc--) {
-		off += _emit_WFP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
+		off += _emit_WFP(dry_run, &buf[off], cond, pxs->desc->peri);
 		off += _emit_LD(dry_run, &buf[off], ALWAYS);
-		off += _emit_STP(dry_run, &buf[off], SINGLE, pxs->desc->peri);
-		off += _emit_FLUSHP(dry_run, &buf[off], pxs->desc->peri);
+		off += _emit_STP(dry_run, &buf[off], cond, pxs->desc->peri);
+
+		if (!(pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP))
+			off += _emit_FLUSHP(dry_run, &buf[off],
+					    pxs->desc->peri);
 	}
 
 	return off;
 }
 
-static int _bursts(unsigned dry_run, u8 buf[],
+static int _bursts(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 		const struct _xfer_spec *pxs, int cyc)
 {
 	int off = 0;
 
 	switch (pxs->desc->rqtype) {
 	case DMA_MEM_TO_DEV:
-		off += _ldst_memtodev(dry_run, &buf[off], pxs, cyc);
+		off += _ldst_memtodev(pl330, dry_run, &buf[off], pxs, cyc);
 		break;
 	case DMA_DEV_TO_MEM:
-		off += _ldst_devtomem(dry_run, &buf[off], pxs, cyc);
+		off += _ldst_devtomem(pl330, dry_run, &buf[off], pxs, cyc);
 		break;
 	case DMA_MEM_TO_MEM:
 		off += _ldst_memtomem(dry_run, &buf[off], pxs, cyc);
@@ -1191,7 +1225,7 @@ static int _bursts(unsigned dry_run, u8 buf[],
 }
 
 /* Returns bytes consumed and updates bursts */
-static inline int _loop(unsigned dry_run, u8 buf[],
+static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[],
 		unsigned long *bursts, const struct _xfer_spec *pxs)
 {
 	int cyc, cycmax, szlp, szlpend, szbrst, off;
@@ -1199,7 +1233,7 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	struct _arg_LPEND lpend;
 
 	if (*bursts == 1)
-		return _bursts(dry_run, buf, pxs, 1);
+		return _bursts(pl330, dry_run, buf, pxs, 1);
 
 	/* Max iterations possible in DMALP is 256 */
 	if (*bursts >= 256*256) {
@@ -1217,7 +1251,7 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	}
 
 	szlp = _emit_LP(1, buf, 0, 0);
-	szbrst = _bursts(1, buf, pxs, 1);
+	szbrst = _bursts(pl330, 1, buf, pxs, 1);
 
 	lpend.cond = ALWAYS;
 	lpend.forever = false;
@@ -1249,7 +1283,7 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	off += _emit_LP(dry_run, &buf[off], 1, lcnt1);
 	ljmp1 = off;
 
-	off += _bursts(dry_run, &buf[off], pxs, cyc);
+	off += _bursts(pl330, dry_run, &buf[off], pxs, cyc);
 
 	lpend.cond = ALWAYS;
 	lpend.forever = false;
@@ -1272,8 +1306,9 @@ static inline int _loop(unsigned dry_run, u8 buf[],
 	return off;
 }
 
-static inline int _setup_loops(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
+static inline int _setup_loops(struct pl330_dmac *pl330,
+			       unsigned dry_run, u8 buf[],
+			       const struct _xfer_spec *pxs)
 {
 	struct pl330_xfer *x = &pxs->desc->px;
 	u32 ccr = pxs->ccr;
@@ -1282,15 +1317,16 @@ static inline int _setup_loops(unsigned dry_run, u8 buf[],
 
 	while (bursts) {
 		c = bursts;
-		off += _loop(dry_run, &buf[off], &c, pxs);
+		off += _loop(pl330, dry_run, &buf[off], &c, pxs);
 		bursts -= c;
 	}
 
 	return off;
 }
 
-static inline int _setup_xfer(unsigned dry_run, u8 buf[],
-		const struct _xfer_spec *pxs)
+static inline int _setup_xfer(struct pl330_dmac *pl330,
+			      unsigned dry_run, u8 buf[],
+			      const struct _xfer_spec *pxs)
 {
 	struct pl330_xfer *x = &pxs->desc->px;
 	int off = 0;
@@ -1301,7 +1337,7 @@ static inline int _setup_xfer(unsigned dry_run, u8 buf[],
 	off += _emit_MOV(dry_run, &buf[off], DAR, x->dst_addr);
 
 	/* Setup Loop(s) */
-	off += _setup_loops(dry_run, &buf[off], pxs);
+	off += _setup_loops(pl330, dry_run, &buf[off], pxs);
 
 	return off;
 }
@@ -1310,8 +1346,9 @@ static inline int _setup_xfer(unsigned dry_run, u8 buf[],
  * A req is a sequence of one or more xfer units.
  * Returns the number of bytes taken to setup the MC for the req.
  */
-static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
-		unsigned index, struct _xfer_spec *pxs)
+static int _setup_req(struct pl330_dmac *pl330, unsigned dry_run,
+		      struct pl330_thread *thrd, unsigned index,
+		      struct _xfer_spec *pxs)
 {
 	struct _pl330_req *req = &thrd->req[index];
 	struct pl330_xfer *x;
@@ -1328,7 +1365,7 @@ static int _setup_req(unsigned dry_run, struct pl330_thread *thrd,
 	if (x->bytes % (BRST_SIZE(pxs->ccr) * BRST_LEN(pxs->ccr)))
 		return -EINVAL;
 
-	off += _setup_xfer(dry_run, &buf[off], pxs);
+	off += _setup_xfer(pl330, dry_run, &buf[off], pxs);
 
 	/* DMASEV peripheral/event */
 	off += _emit_SEV(dry_run, &buf[off], thrd->ev);
@@ -1422,7 +1459,7 @@ static int pl330_submit_req(struct pl330_thread *thrd,
 	xs.desc = desc;
 
 	/* First dry run to check if req is acceptable */
-	ret = _setup_req(1, thrd, idx, &xs);
+	ret = _setup_req(pl330, 1, thrd, idx, &xs);
 	if (ret < 0)
 		goto xfer_exit;
 
@@ -1436,7 +1473,7 @@ static int pl330_submit_req(struct pl330_thread *thrd,
 	/* Hook the request */
 	thrd->lstenq = idx;
 	thrd->req[idx].desc = desc;
-	_setup_req(0, thrd, idx, &xs);
+	_setup_req(pl330, 0, thrd, idx, &xs);
 
 	ret = 0;
 
@@ -2781,6 +2818,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	struct resource *res;
 	int i, ret, irq;
 	int num_chan;
+	struct device_node *np = adev->dev.of_node;
 
 	pdat = dev_get_platdata(&adev->dev);
 
@@ -2800,6 +2838,11 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 
 	pl330->mcbufsz = pdat ? pdat->mcbuf_sz : 0;
 
+	/* get quirk */
+	for (i = 0; i < ARRAY_SIZE(of_quirks); i++)
+		if (of_property_read_bool(np, of_quirks[i].quirk))
+			pl330->quirks |= of_quirks[i].id;
+
 	res = &adev->res;
 	pl330->base = devm_ioremap_resource(&adev->dev, res);
 	if (IS_ERR(pl330->base))
@@ -2895,6 +2938,8 @@ 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_SEGMENT;
+	pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ?
+			 1 : PL330_MAX_BURST);
 
 	ret = dma_async_device_register(pd);
 	if (ret) {
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 79a8bc4f6cec..aa9561f586ab 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -199,6 +199,7 @@ struct rockchip_spi {
 	struct sg_table rx_sg;
 	struct rockchip_spi_dma_data dma_rx;
 	struct rockchip_spi_dma_data dma_tx;
+	struct dma_slave_caps dma_caps;
 };
 
 static inline void spi_enable_chip(struct rockchip_spi *rs, int enable)
@@ -449,7 +450,10 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 		rxconf.direction = rs->dma_rx.direction;
 		rxconf.src_addr = rs->dma_rx.addr;
 		rxconf.src_addr_width = rs->n_bytes;
-		rxconf.src_maxburst = rs->n_bytes;
+		if (rs->dma_caps.max_burst > 4)
+			rxconf.src_maxburst = 4;
+		else
+			rxconf.src_maxburst = 1;
 		dmaengine_slave_config(rs->dma_rx.ch, &rxconf);
 
 		rxdesc = dmaengine_prep_slave_sg(
@@ -466,7 +470,10 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 		txconf.direction = rs->dma_tx.direction;
 		txconf.dst_addr = rs->dma_tx.addr;
 		txconf.dst_addr_width = rs->n_bytes;
-		txconf.dst_maxburst = rs->n_bytes;
+		if (rs->dma_caps.max_burst > 4)
+			txconf.dst_maxburst = 4;
+		else
+			txconf.dst_maxburst = 1;
 		dmaengine_slave_config(rs->dma_tx.ch, &txconf);
 
 		txdesc = dmaengine_prep_slave_sg(
@@ -730,6 +737,7 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	}
 
 	if (rs->dma_tx.ch && rs->dma_rx.ch) {
+		dma_get_slave_caps(rs->dma_rx.ch, &(rs->dma_caps));
 		rs->dma_tx.addr = (dma_addr_t)(mem->start + ROCKCHIP_SPI_TXDR);
 		rs->dma_rx.addr = (dma_addr_t)(mem->start + ROCKCHIP_SPI_RXDR);
 		rs->dma_tx.direction = DMA_MEM_TO_DEV;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index d85ecd20af50..017433712833 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -401,6 +401,7 @@ enum dma_residue_granularity {
  * 	since the enum dma_transfer_direction is not defined as bits for each
  * 	type of direction, the dma controller should fill (1 << <TYPE>) and same
  * 	should be checked by controller as well
+ * @max_burst: max burst capability per-transfer
  * @cmd_pause: true, if pause and thereby resume is supported
  * @cmd_terminate: true, if terminate cmd is supported
  * @residue_granularity: granularity of the reported transfer residue
@@ -411,6 +412,7 @@ struct dma_slave_caps {
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
 	u32 directions;
+	u32 max_burst;
 	bool cmd_pause;
 	bool cmd_terminate;
 	enum dma_residue_granularity residue_granularity;
@@ -654,6 +656,7 @@ struct dma_filter {
  * 	the enum dma_transfer_direction is not defined as bits for
  * 	each type of direction, the dma controller should fill (1 <<
  * 	<TYPE>) and same should be checked by controller as well
+ * @max_burst: max burst capability per-transfer
  * @residue_granularity: granularity of the transfer residue reported
  *	by tx_status
  * @device_alloc_chan_resources: allocate resources and return the
@@ -712,6 +715,7 @@ struct dma_device {
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
 	u32 directions;
+	u32 max_burst;
 	bool descriptor_reuse;
 	enum dma_residue_granularity residue_granularity;