dmaengine: ptdma: Extend ptdma to support multi-channel and version

To support multi-channel functionality with AE4DMA engine, extend the
PTDMA code with reusable components.

Reviewed-by: Raju Rangoju <[email protected]>
Signed-off-by: Basavaraj Natikar <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Vinod Koul <[email protected]>

Author: basuamd

drivers/dma/amd/ae4dma/ae4dma.h

@@ -34,6 +34,8 @@
 #define AE4_Q_BASE_H_OFF		0x1c
 #define AE4_Q_SZ			0x20
 
+#define AE4_DMA_VERSION			4
+
 struct ae4_msix {
 	int msix_count;
 	struct msix_entry msix_entry[MAX_AE4_HW_QUEUES];

drivers/dma/amd/ptdma/ptdma-dmaengine.c

@@ -93,7 +93,24 @@ static void pt_do_cleanup(struct virt_dma_desc *vd)
 	kmem_cache_free(pt->dma_desc_cache, desc);
 }
 
-static int pt_dma_start_desc(struct pt_dma_desc *desc)
+static struct pt_cmd_queue *pt_get_cmd_queue(struct pt_device *pt, struct pt_dma_chan *chan)
+{
+	struct ae4_cmd_queue *ae4cmd_q;
+	struct pt_cmd_queue *cmd_q;
+	struct ae4_device *ae4;
+
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+		cmd_q = &ae4cmd_q->cmd_q;
+	} else {
+		cmd_q = &pt->cmd_q;
+	}
+
+	return cmd_q;
+}
+
+static int pt_dma_start_desc(struct pt_dma_desc *desc, struct pt_dma_chan *chan)
 {
 	struct pt_passthru_engine *pt_engine;
 	struct pt_device *pt;
@@ -104,7 +121,9 @@ static int pt_dma_start_desc(struct pt_dma_desc *desc)
 
 	pt_cmd = &desc->pt_cmd;
 	pt = pt_cmd->pt;
-	cmd_q = &pt->cmd_q;
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
+
 	pt_engine = &pt_cmd->passthru;
 
 	pt->tdata.cmd = pt_cmd;
@@ -199,7 +218,7 @@ static void pt_cmd_callback(void *data, int err)
 		if (!desc)
 			break;
 
-		ret = pt_dma_start_desc(desc);
+		ret = pt_dma_start_desc(desc, chan);
 		if (!ret)
 			break;
 
@@ -234,15 +253,18 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
 	struct pt_passthru_engine *pt_engine;
+	struct pt_device *pt = chan->pt;
+	struct ae4_cmd_queue *ae4cmd_q;
 	struct pt_dma_desc *desc;
+	struct ae4_device *ae4;
 	struct pt_cmd *pt_cmd;
 
 	desc = pt_alloc_dma_desc(chan, flags);
 	if (!desc)
 		return NULL;
 
 	pt_cmd = &desc->pt_cmd;
-	pt_cmd->pt = chan->pt;
+	pt_cmd->pt = pt;
 	pt_engine = &pt_cmd->passthru;
 	pt_cmd->engine = PT_ENGINE_PASSTHRU;
 	pt_engine->src_dma = src;
@@ -253,6 +275,14 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
 
 	desc->len = len;
 
+	if (pt->ver == AE4_DMA_VERSION) {
+		ae4 = container_of(pt, struct ae4_device, pt);
+		ae4cmd_q = &ae4->ae4cmd_q[chan->id];
+		mutex_lock(&ae4cmd_q->cmd_lock);
+		list_add_tail(&pt_cmd->entry, &ae4cmd_q->cmd);
+		mutex_unlock(&ae4cmd_q->cmd_lock);
+	}
+
 	return desc;
 }
 
@@ -310,8 +340,11 @@ static enum dma_status
 pt_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 		struct dma_tx_state *txstate)
 {
-	struct pt_device *pt = to_pt_chan(c)->pt;
-	struct pt_cmd_queue *cmd_q = &pt->cmd_q;
+	struct pt_dma_chan *chan = to_pt_chan(c);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
+
+	cmd_q = pt_get_cmd_queue(pt, chan);
 
 	pt_check_status_trans(pt, cmd_q);
 	return dma_cookie_status(c, cookie, txstate);
@@ -320,10 +353,13 @@ pt_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 static int pt_pause(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
-	pt_stop_queue(&chan->pt->cmd_q);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	pt_stop_queue(cmd_q);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
 	return 0;
@@ -333,10 +369,13 @@ static int pt_resume(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
 	struct pt_dma_desc *desc = NULL;
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
 	unsigned long flags;
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
-	pt_start_queue(&chan->pt->cmd_q);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	pt_start_queue(cmd_q);
 	desc = pt_next_dma_desc(chan);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
 
@@ -350,11 +389,17 @@ static int pt_resume(struct dma_chan *dma_chan)
 static int pt_terminate_all(struct dma_chan *dma_chan)
 {
 	struct pt_dma_chan *chan = to_pt_chan(dma_chan);
+	struct pt_device *pt = chan->pt;
+	struct pt_cmd_queue *cmd_q;
 	unsigned long flags;
-	struct pt_cmd_queue *cmd_q = &chan->pt->cmd_q;
 	LIST_HEAD(head);
 
-	iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+	cmd_q = pt_get_cmd_queue(pt, chan);
+	if (pt->ver == AE4_DMA_VERSION)
+		pt_stop_queue(cmd_q);
+	else
+		iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010);
+
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vchan_get_all_descriptors(&chan->vc, &head);
 	spin_unlock_irqrestore(&chan->vc.lock, flags);
@@ -367,14 +412,24 @@ static int pt_terminate_all(struct dma_chan *dma_chan)
 
 int pt_dmaengine_register(struct pt_device *pt)
 {
-	struct pt_dma_chan *chan;
 	struct dma_device *dma_dev = &pt->dma_dev;
-	char *cmd_cache_name;
+	struct ae4_cmd_queue *ae4cmd_q = NULL;
+	struct ae4_device *ae4 = NULL;
+	struct pt_dma_chan *chan;
 	char *desc_cache_name;
-	int ret;
+	char *cmd_cache_name;
+	int ret, i;
+
+	if (pt->ver == AE4_DMA_VERSION)
+		ae4 = container_of(pt, struct ae4_device, pt);
+
+	if (ae4)
+		pt->pt_dma_chan = devm_kcalloc(pt->dev, ae4->cmd_q_count,
+					       sizeof(*pt->pt_dma_chan), GFP_KERNEL);
+	else
+		pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan),
+					       GFP_KERNEL);
 
-	pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan),
-				       GFP_KERNEL);
 	if (!pt->pt_dma_chan)
 		return -ENOMEM;
 
@@ -416,9 +471,6 @@ int pt_dmaengine_register(struct pt_device *pt)
 
 	INIT_LIST_HEAD(&dma_dev->channels);
 
-	chan = pt->pt_dma_chan;
-	chan->pt = pt;
-
 	/* Set base and prep routines */
 	dma_dev->device_free_chan_resources = pt_free_chan_resources;
 	dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy;
@@ -430,8 +482,21 @@ int pt_dmaengine_register(struct pt_device *pt)
 	dma_dev->device_terminate_all = pt_terminate_all;
 	dma_dev->device_synchronize = pt_synchronize;
 
-	chan->vc.desc_free = pt_do_cleanup;
-	vchan_init(&chan->vc, dma_dev);
+	if (ae4) {
+		for (i = 0; i < ae4->cmd_q_count; i++) {
+			chan = pt->pt_dma_chan + i;
+			ae4cmd_q = &ae4->ae4cmd_q[i];
+			chan->id = ae4cmd_q->id;
+			chan->pt = pt;
+			chan->vc.desc_free = pt_do_cleanup;
+			vchan_init(&chan->vc, dma_dev);
+		}
+	} else {
+		chan = pt->pt_dma_chan;
+		chan->pt = pt;
+		chan->vc.desc_free = pt_do_cleanup;
+		vchan_init(&chan->vc, dma_dev);
+	}
 
 	ret = dma_async_device_register(dma_dev);
 	if (ret)

drivers/dma/amd/ptdma/ptdma.h

@@ -184,6 +184,7 @@ struct pt_dma_desc {
 struct pt_dma_chan {
 	struct virt_dma_chan vc;
 	struct pt_device *pt;
+	u32 id;
 };
 
 struct pt_cmd_queue {
@@ -262,6 +263,7 @@ struct pt_device {
 	unsigned long total_interrupts;
 
 	struct pt_tasklet_data tdata;
+	int ver;
 };
 
 /*