dmaengine: fsl-edma: integrate v3 support

Significant alterations have been made to the EDMA v3's register layout.
Now, each channel possesses a separate address space, encapsulating all
channel-related controls and statuses, including IRQs. There are changes
in bit position definitions as well. However, the fundamental control flow
remains analogous to the previous versions.

EDMA v3 was utilized in imx8qm, imx93, and will be in forthcoming chips.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20230821161617.2142561-13-Frank.Li@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>

Author: nxpfrankli

drivers/dma/fsl-edma-common.c

@@ -7,6 +7,8 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 
 #include "fsl-edma-common.h"
 
@@ -66,11 +68,46 @@ void fsl_edma_tx_chan_handler(struct fsl_edma_chan *fsl_chan)
 	spin_unlock(&fsl_chan->vchan.lock);
 }
 
+static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan)
+{
+	u32 val, flags;
+
+	flags = fsl_edma_drvflags(fsl_chan);
+	val = edma_readl_chreg(fsl_chan, ch_sbr);
+	/* Remote/local swapped wrongly on iMX8 QM Audio edma */
+	if (flags & FSL_EDMA_DRV_QUIRK_SWAPPED) {
+		if (!fsl_chan->is_rxchan)
+			val |= EDMA_V3_CH_SBR_RD;
+		else
+			val |= EDMA_V3_CH_SBR_WR;
+	} else {
+		if (fsl_chan->is_rxchan)
+			val |= EDMA_V3_CH_SBR_RD;
+		else
+			val |= EDMA_V3_CH_SBR_WR;
+	}
+
+	if (fsl_chan->is_remote)
+		val &= ~(EDMA_V3_CH_SBR_RD | EDMA_V3_CH_SBR_WR);
+
+	edma_writel_chreg(fsl_chan, val, ch_sbr);
+
+	if (flags & FSL_EDMA_DRV_HAS_CHMUX)
+		edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux);
+
+	val = edma_readl_chreg(fsl_chan, ch_csr);
+	val |= EDMA_V3_CH_CSR_ERQ;
+	edma_writel_chreg(fsl_chan, val, ch_csr);
+}
+
 static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan)
 {
 	struct edma_regs *regs = &fsl_chan->edma->regs;
 	u32 ch = fsl_chan->vchan.chan.chan_id;
 
+	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_SPLIT_REG)
+		return fsl_edma3_enable_request(fsl_chan);
+
 	if (fsl_chan->edma->drvdata->flags & FSL_EDMA_DRV_WRAP_IO) {
 		edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), regs->seei);
 		edma_writeb(fsl_chan->edma, ch, regs->serq);
@@ -83,11 +120,28 @@ static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan)
 	}
 }
 
+static void fsl_edma3_disable_request(struct fsl_edma_chan *fsl_chan)
+{
+	u32 val = edma_readl_chreg(fsl_chan, ch_csr);
+	u32 flags;
+
+	flags = fsl_edma_drvflags(fsl_chan);
+
+	if (flags & FSL_EDMA_DRV_HAS_CHMUX)
+		edma_writel_chreg(fsl_chan, 0, ch_mux);
+
+	val &= ~EDMA_V3_CH_CSR_ERQ;
+	edma_writel_chreg(fsl_chan, val, ch_csr);
+}
+
 void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan)
 {
 	struct edma_regs *regs = &fsl_chan->edma->regs;
 	u32 ch = fsl_chan->vchan.chan.chan_id;
 
+	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_SPLIT_REG)
+		return fsl_edma3_disable_request(fsl_chan);
+
 	if (fsl_chan->edma->drvdata->flags & FSL_EDMA_DRV_WRAP_IO) {
 		edma_writeb(fsl_chan->edma, ch, regs->cerq);
 		edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), regs->ceei);
@@ -135,6 +189,9 @@ void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
 	int endian_diff[4] = {3, 1, -1, -3};
 	u32 dmamux_nr = fsl_chan->edma->drvdata->dmamuxs;
 
+	if (!dmamux_nr)
+		return;
+
 	chans_per_mux = fsl_chan->edma->n_chans / dmamux_nr;
 	ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux;
 
@@ -186,6 +243,10 @@ int fsl_edma_terminate_all(struct dma_chan *chan)
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+
+	if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_PD)
+		pm_runtime_allow(fsl_chan->pd_dev);
+
 	return 0;
 }
 
@@ -286,12 +347,16 @@ static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
 	enum dma_transfer_direction dir = edesc->dirn;
 	dma_addr_t cur_addr, dma_addr;
 	size_t len, size;
+	u32 nbytes = 0;
 	int i;
 
 	/* calculate the total size in this desc */
-	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++)
-		len += le32_to_cpu(edesc->tcd[i].vtcd->nbytes)
-			* le16_to_cpu(edesc->tcd[i].vtcd->biter);
+	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++) {
+		nbytes = le32_to_cpu(edesc->tcd[i].vtcd->nbytes);
+		if (nbytes & (EDMA_V3_TCD_NBYTES_DMLOE | EDMA_V3_TCD_NBYTES_SMLOE))
+			nbytes = EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(nbytes);
+		len += nbytes * le16_to_cpu(edesc->tcd[i].vtcd->biter);
+	}
 
 	if (!in_progress)
 		return len;
@@ -303,8 +368,12 @@ static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
 
 	/* figure out the finished and calculate the residue */
 	for (i = 0; i < fsl_chan->edesc->n_tcds; i++) {
-		size = le32_to_cpu(edesc->tcd[i].vtcd->nbytes)
-			* le16_to_cpu(edesc->tcd[i].vtcd->biter);
+		nbytes = le32_to_cpu(edesc->tcd[i].vtcd->nbytes);
+		if (nbytes & (EDMA_V3_TCD_NBYTES_DMLOE | EDMA_V3_TCD_NBYTES_SMLOE))
+			nbytes = EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(nbytes);
+
+		size = nbytes * le16_to_cpu(edesc->tcd[i].vtcd->biter);
+
 		if (dir == DMA_MEM_TO_DEV)
 			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->saddr);
 		else
@@ -389,12 +458,15 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 }
 
 static inline
-void fsl_edma_fill_tcd(struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
+void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
+		       struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
 		       u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer,
 		       u16 biter, u16 doff, u32 dlast_sga, bool major_int,
 		       bool disable_req, bool enable_sg)
 {
+	struct dma_slave_config *cfg = &fsl_chan->cfg;
 	u16 csr = 0;
+	u32 burst;
 
 	/*
 	 * eDMA hardware SGs require the TCDs to be stored in little
@@ -409,6 +481,21 @@ void fsl_edma_fill_tcd(struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
 
 	tcd->soff = cpu_to_le16(soff);
 
+	if (fsl_chan->is_multi_fifo) {
+		/* set mloff to support multiple fifo */
+		burst = cfg->direction == DMA_DEV_TO_MEM ?
+				cfg->src_addr_width : cfg->dst_addr_width;
+		nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4));
+		/* enable DMLOE/SMLOE */
+		if (cfg->direction == DMA_MEM_TO_DEV) {
+			nbytes |= EDMA_V3_TCD_NBYTES_DMLOE;
+			nbytes &= ~EDMA_V3_TCD_NBYTES_SMLOE;
+		} else {
+			nbytes |= EDMA_V3_TCD_NBYTES_SMLOE;
+			nbytes &= ~EDMA_V3_TCD_NBYTES_DMLOE;
+		}
+	}
+
 	tcd->nbytes = cpu_to_le32(nbytes);
 	tcd->slast = cpu_to_le32(slast);
 
@@ -427,6 +514,12 @@ void fsl_edma_fill_tcd(struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
 	if (enable_sg)
 		csr |= EDMA_TCD_CSR_E_SG;
 
+	if (fsl_chan->is_rxchan)
+		csr |= EDMA_TCD_CSR_ACTIVE;
+
+	if (fsl_chan->is_sw)
+		csr |= EDMA_TCD_CSR_START;
+
 	tcd->csr = cpu_to_le16(csr);
 }
 
@@ -466,6 +559,7 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 	struct fsl_edma_desc *fsl_desc;
 	dma_addr_t dma_buf_next;
+	bool major_int = true;
 	int sg_len, i;
 	u32 src_addr, dst_addr, last_sg, nbytes;
 	u16 soff, doff, iter;
@@ -509,17 +603,23 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 			src_addr = dma_buf_next;
 			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
-			doff = 0;
-		} else {
+			doff = fsl_chan->is_multi_fifo ? 4 : 0;
+		} else if (direction == DMA_DEV_TO_MEM) {
 			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = dma_buf_next;
-			soff = 0;
+			soff = fsl_chan->is_multi_fifo ? 4 : 0;
 			doff = fsl_chan->cfg.src_addr_width;
+		} else {
+			/* DMA_DEV_TO_DEV */
+			src_addr = fsl_chan->cfg.src_addr;
+			dst_addr = fsl_chan->cfg.dst_addr;
+			soff = doff = 0;
+			major_int = false;
 		}
 
-		fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr, dst_addr,
+		fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[i].vtcd, src_addr, dst_addr,
 				  fsl_chan->attr, soff, nbytes, 0, iter,
-				  iter, doff, last_sg, true, false, true);
+				  iter, doff, last_sg, major_int, false, true);
 		dma_buf_next += period_len;
 	}
 
@@ -568,23 +668,51 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
 			doff = 0;
-		} else {
+		} else if (direction == DMA_DEV_TO_MEM) {
 			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = sg_dma_address(sg);
 			soff = 0;
 			doff = fsl_chan->cfg.src_addr_width;
+		} else {
+			/* DMA_DEV_TO_DEV */
+			src_addr = fsl_chan->cfg.src_addr;
+			dst_addr = fsl_chan->cfg.dst_addr;
+			soff = 0;
+			doff = 0;
 		}
 
+		/*
+		 * Choose the suitable burst length if sg_dma_len is not
+		 * multiple of burst length so that the whole transfer length is
+		 * multiple of minor loop(burst length).
+		 */
+		if (sg_dma_len(sg) % nbytes) {
+			u32 width = (direction == DMA_DEV_TO_MEM) ? doff : soff;
+			u32 burst = (direction == DMA_DEV_TO_MEM) ?
+						fsl_chan->cfg.src_maxburst :
+						fsl_chan->cfg.dst_maxburst;
+			int j;
+
+			for (j = burst; j > 1; j--) {
+				if (!(sg_dma_len(sg) % (j * width))) {
+					nbytes = j * width;
+					break;
+				}
+			}
+			/* Set burst size as 1 if there's no suitable one */
+			if (j == 1)
+				nbytes = width;
+		}
 		iter = sg_dma_len(sg) / nbytes;
 		if (i < sg_len - 1) {
 			last_sg = fsl_desc->tcd[(i + 1)].ptcd;
-			fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr,
+			fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[i].vtcd, src_addr,
 					  dst_addr, fsl_chan->attr, soff,
 					  nbytes, 0, iter, iter, doff, last_sg,
 					  false, false, true);
 		} else {
 			last_sg = 0;
-			fsl_edma_fill_tcd(fsl_desc->tcd[i].vtcd, src_addr,
+			fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[i].vtcd, src_addr,
 					  dst_addr, fsl_chan->attr, soff,
 					  nbytes, 0, iter, iter, doff, last_sg,
 					  true, true, false);
@@ -609,7 +737,7 @@ struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan,
 	fsl_chan->is_sw = true;
 
 	/* To match with copy_align and max_seg_size so 1 tcd is enough */
-	fsl_edma_fill_tcd(fsl_desc->tcd[0].vtcd, dma_src, dma_dst,
+	fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[0].vtcd, dma_src, dma_dst,
 			fsl_edma_get_tcd_attr(DMA_SLAVE_BUSWIDTH_32_BYTES),
 			32, len, 0, 1, 1, 32, 0, true, true, false);