[PATCH v8 2/2] dmaengine: fsl-edma: Support dynamic scatter/gather chaining

Implement dynamic linking of scatter/gather transfers to enable
chaining multiple DMA descriptors without stopping the channel.
This avoids waiting for the channel to go idle if there is another
transaction already issued.

Add fsl_edma_link_sg() to dynamically link the last TCD of a previously
issued descriptor to the first TCD of a new descriptor by setting the
scatter/gather address and the E_SG flag, and keeping the channel active
by clearing the DREQ bit.

Also in fsl_edma_link_sg(), we assign a non-zero identifier to the new
descriptor that is stored in the EDMA_TCD_CSR_LINKCH field of the CSR
of each TCD, after checking that the descriptors are not using channel
linking. The use of this field (MAJORLINKCH in the datasheet) as an
identifier for dynamic scatter/gather is suggested in the i.MX93 datasheet.

When the last issued descriptor is the one currently active on the
channel and has a single TCD, the scatter/gather address and CSR are
also written directly to the hardware registers to ensure the link
takes effect immediately, unless the DMA controller requires the DONE
bit to be cleared for the CSR change to take effect. Clearing the DONE
bit would disrupt the interrupt handler.

Linking is done in fsl_edma_issue_pending(), which iterates over the
submitted descriptors, links each one to the previously issued
descriptor via fsl_edma_link_sg(), and then moves it to the issued
list. This ensures that transactions are linked in the order they were
issued. Linking of a descriptor is limited to 31 outstanding descriptors
on the issued list so the identifier fits in the LINKCH field of the CSR
register. The value of zero is left to identify non-linked descriptors.

Update fsl_edma_xfer_desc() to avoid re-initializing the hardware when a
transfer is already in progress, allowing seamless chaining of descriptors.

Modify the transfer completion handler to check the DONE flag in the
channel CSR before marking the transfer complete. Since this flag is
only available on SoC with the split registers layout, we only link
transactions for DMA controllers flagged with FSL_EDMA_DRV_SPLIT_REG.

The completion handler also reaps issued descriptors whose link channel ID
(EDMA_TCD_CSR_LINKCH) has already been passed by the hardware, marking
them as completed even if their corresponding interrupt has been missed.

Add trace event for scatter/gather linking operations.

Signed-off-by: Benoît Monin <[email protected]>
---
 drivers/dma/fsl-edma-common.c | 125 +++++++++++++++++++++++++++++++++++++++---
 drivers/dma/fsl-edma-common.h |   3 +
 drivers/dma/fsl-edma-trace.h  |   5 ++
 3 files changed, 126 insertions(+), 7 deletions(-)

diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index c5f5951c988b..189eb9d1269e 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -55,10 +55,37 @@ void fsl_edma_tx_chan_handler(struct fsl_edma_chan *fsl_chan)
 	}
 
 	if (!fsl_chan->edesc->iscyclic) {
-		list_del(&fsl_chan->edesc->vdesc.node);
-		vchan_cookie_complete(&fsl_chan->edesc->vdesc);
+		u16 csr = edma_read_tcdreg(fsl_chan, csr);
+		u8 link_sg_id = FIELD_GET(EDMA_TCD_CSR_LINKCH, csr);
+		bool e_link = FIELD_GET(EDMA_TCD_CSR_E_LINK, csr);
+		struct virt_dma_desc *vdesc, *tmp;
+
+		/* Channel is DONE when a TCD with D_REQ set completes */
+		if (!(fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_SPLIT_REG) ||
+		    (edma_readl_chreg(fsl_chan, ch_csr) & EDMA_V3_CH_CSR_DONE)) {
+			fsl_chan->status = DMA_COMPLETE;
+		}
+
+		list_for_each_entry_safe(vdesc, tmp, &fsl_chan->vchan.desc_issued, node) {
+			struct fsl_edma_desc *fsl_desc = to_fsl_edma_desc(vdesc);
+			bool id_match = (link_sg_id == fsl_desc->link_sg_id);
+
+			/*
+			 * If the transfer is still running,
+			 * don't mark as complete the current descriptor
+			 */
+			if ((e_link || id_match) && fsl_chan->status != DMA_COMPLETE)
+				break;
+
+			list_del(&vdesc->node);
+			vchan_cookie_complete(vdesc);
+
+			if (e_link || id_match)
+				break;
+		}
+
 		fsl_chan->edesc = NULL;
-		fsl_chan->status = DMA_COMPLETE;
+
 	} else {
 		vchan_cyclic_callback(&fsl_chan->edesc->vdesc);
 	}
@@ -931,14 +958,93 @@ void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
 	if (!vdesc)
 		return;
 	fsl_chan->edesc = to_fsl_edma_desc(vdesc);
-	fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
-	fsl_edma_enable_request(fsl_chan);
-	fsl_chan->status = DMA_IN_PROGRESS;
+
+	if (fsl_chan->status != DMA_IN_PROGRESS) {
+		fsl_edma_set_tcd_regs(fsl_chan, fsl_chan->edesc->tcd[0].vtcd);
+		fsl_edma_enable_request(fsl_chan);
+		fsl_chan->status = DMA_IN_PROGRESS;
+	}
+}
+
+static void fsl_edma_link_sg(struct fsl_edma_chan *fsl_chan, struct fsl_edma_desc *fsl_desc)
+{
+	u32 flags = fsl_edma_drvflags(fsl_chan);
+	struct fsl_edma_hw_tcd *last_tcd;
+	struct fsl_edma_desc *prev_desc;
+	struct virt_dma_desc *vdesc;
+	u16 last_csr;
+
+	lockdep_assert_held(&fsl_chan->vchan.lock);
+
+	if (!(flags & FSL_EDMA_DRV_SPLIT_REG) || fsl_desc->iscyclic)
+		return;
+
+	vdesc = list_last_entry_or_null(&fsl_chan->vchan.desc_issued,
+					struct virt_dma_desc, node);
+	if (!vdesc)
+		return;
+
+	prev_desc = to_fsl_edma_desc(vdesc);
+	if (prev_desc->iscyclic)
+		return;
+
+	last_tcd = prev_desc->tcd[prev_desc->n_tcds - 1].vtcd;
+	last_csr = fsl_edma_get_tcd_to_cpu(fsl_chan, last_tcd, csr);
+
+	for (unsigned int i = 0; i < fsl_desc->n_tcds; i++) {
+		struct fsl_edma_hw_tcd *tcd = fsl_desc->tcd[i].vtcd;
+
+		if (fsl_edma_get_tcd_to_cpu(fsl_chan, tcd, csr) & EDMA_TCD_CSR_E_LINK)
+			return;
+	}
+
+	if (!(last_csr & EDMA_TCD_CSR_D_REQ) ||
+	    last_csr & EDMA_TCD_CSR_E_LINK ||
+	    list_count_nodes(&fsl_chan->vchan.desc_issued) >= FIELD_MAX(EDMA_TCD_CSR_LINKCH))
+		return;
+
+	/* Set a non-zero linked SG identifier to all TCD of the new descriptor */
+	fsl_chan->link_sg_id++;
+	if (fsl_chan->link_sg_id > FIELD_MAX(EDMA_TCD_CSR_LINKCH))
+		fsl_chan->link_sg_id = 1;
+
+	fsl_desc->link_sg_id = fsl_chan->link_sg_id;
+
+	for (unsigned int i = 0; i < fsl_desc->n_tcds; i++) {
+		struct fsl_edma_hw_tcd *tcd = fsl_desc->tcd[i].vtcd;
+		u16 csr = fsl_edma_get_tcd_to_cpu(fsl_chan, tcd, csr);
+
+		csr |= FIELD_PREP(EDMA_TCD_CSR_LINKCH, fsl_chan->link_sg_id);
+		fsl_edma_set_tcd_to_le(fsl_chan, tcd, csr, csr);
+	}
+
+	/*
+	 * Set DLAST_SGA before enabling E_SG in CSR: if the DMA engine
+	 * only picks up the former, it updates DADDR at end of transfer,
+	 * which is not reused.
+	 */
+	fsl_edma_set_tcd_to_le(fsl_chan, last_tcd, fsl_desc->tcd[0].ptcd, dlast_sga);
+
+	dma_wmb();
+
+	last_csr &= ~EDMA_TCD_CSR_D_REQ;
+	last_csr |= EDMA_TCD_CSR_E_SG;
+	fsl_edma_set_tcd_to_le(fsl_chan, last_tcd, last_csr, csr);
+
+	if (prev_desc == fsl_chan->edesc &&
+	    prev_desc->n_tcds == 1 &&
+	    !(flags & FSL_EDMA_DRV_CLEAR_DONE_E_SG)) {
+		edma_cp_tcd_to_reg(fsl_chan, last_tcd, dlast_sga);
+		edma_cp_tcd_to_reg(fsl_chan, last_tcd, csr);
+	}
+
+	trace_edma_link_sg(fsl_chan, last_tcd);
 }
 
 void fsl_edma_issue_pending(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct virt_dma_desc *vdesc, *tmp;
 	unsigned long flags;
 
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
@@ -949,7 +1055,12 @@ void fsl_edma_issue_pending(struct dma_chan *chan)
 		return;
 	}
 
-	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
+	list_for_each_entry_safe(vdesc, tmp, &fsl_chan->vchan.desc_submitted, node) {
+		fsl_edma_link_sg(fsl_chan, to_fsl_edma_desc(vdesc));
+		list_move_tail(&vdesc->node, &fsl_chan->vchan.desc_issued);
+	}
+
+	if (!list_empty(&fsl_chan->vchan.desc_issued) && !fsl_chan->edesc)
 		fsl_edma_xfer_desc(fsl_chan);
 
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 0d028048701d..ab7ec43f93cf 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -42,6 +42,7 @@
 #define EDMA_TCD_CSR_E_LINK		BIT(5)
 #define EDMA_TCD_CSR_ACTIVE		BIT(6)
 #define EDMA_TCD_CSR_DONE		BIT(7)
+#define EDMA_TCD_CSR_LINKCH		GENMASK(12, 8)
 
 #define EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(x) ((x) & GENMASK(9, 0))
 #define EDMA_V3_TCD_NBYTES_MLOFF(x)        (x << 10)
@@ -169,6 +170,7 @@ struct fsl_edma_chan {
 	struct dma_slave_config		cfg;
 	u32				attr;
 	bool                            is_sw;
+	u8				link_sg_id;
 	struct dma_pool			*tcd_pool;
 	dma_addr_t			dma_dev_addr;
 	u32				dma_dev_size;
@@ -199,6 +201,7 @@ struct fsl_edma_desc {
 	struct virt_dma_desc		vdesc;
 	struct fsl_edma_chan		*echan;
 	bool				iscyclic;
+	u8				link_sg_id;
 	enum dma_transfer_direction	dirn;
 	unsigned int			n_tcds;
 	struct fsl_edma_sw_tcd		tcd[];
diff --git a/drivers/dma/fsl-edma-trace.h b/drivers/dma/fsl-edma-trace.h
index d3541301a247..ac319d2dbb90 100644
--- a/drivers/dma/fsl-edma-trace.h
+++ b/drivers/dma/fsl-edma-trace.h
@@ -119,6 +119,11 @@ DEFINE_EVENT(edma_log_tcd, edma_fill_tcd,
 	TP_ARGS(chan, tcd)
 );
 
+DEFINE_EVENT(edma_log_tcd, edma_link_sg,
+	     TP_PROTO(struct fsl_edma_chan *chan, void *tcd),
+	     TP_ARGS(chan, tcd)
+);
+
 #endif
 
 /* this part must be outside header guard */

-- 
2.55.0