[PATCH v3 3/4] dmaengine: dw: Prevent tx-status calling DMA-desc callback

[James Hilliard <james.hilliard1@gmail.com>]

From: Serge Semin <fancer.lancer@gmail.com>

The DMA transfer status getter can invoke a completion callback from
dwc_scan_descriptors(). An 8250 RX timeout queries that status while
holding the UART port lock, and its DMA callback takes the same lock:

  serial8250_handle_irq()
    uart_port_lock_irqsave(port)
    serial8250_rx_dma_flush()
      dmaengine_tx_status()
        dwc_scan_descriptors()
          dwc_descriptor_complete()
            dma_rx_complete()
              uart_port_lock_irqsave(port)

Separate cookie completion from client notification. Under the channel
lock, move completed descriptors onto a completion list and advance their
cookies before starting queued work. The controller tasklet takes ownership
of that list and invokes callbacks outside the lock. Termination discards
notifications still on the shared list; the tasklet retains ownership of
descriptors it has already detached.

Keep handling raw completion events from tx_status(). Clients such as
catpt poll transfers without DMA_PREP_INTERRUPT and can mask the controller
interrupt externally. Polling must still advance software-emulated LLP
blocks and complete cookies without waiting for tasklet execution. Schedule
the tasklet for deferred notifications and calculate residue separately
for active and queued transfers.

Serialize cookie updates with termination so a delayed callback cannot
move completed_cookie back behind a canceled transfer. On channel release,
wait for an executing tasklet and discard queued notifications before
clearing channel configuration. A pending tasklet run can then return
without accessing a controller whose last channel has been released.

Fixes: 3bfb1d20b547 ("dmaengine: Driver for the Synopsys DesignWare DMA controller")
Cc: stable@vger.kernel.org
Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
[james: defer notifications while preserving polled completion and cleanup]
Signed-off-by: James Hilliard <james.hilliard1@gmail.com>

---

Changelog RFC:
- Instead of just dropping the dwc_scan_descriptors() method invocation
  calculate the residue in the Tx-status getter.
---
 drivers/dma/dw/core.c | 275 ++++++++++++++++++++++++++------------------------
 drivers/dma/dw/regs.h |   1 +
 2 files changed, 142 insertions(+), 134 deletions(-)

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 51c5460b4670..6d27af3c0f2d 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -236,18 +236,17 @@ static void dwc_dostart_first_queued(struct dw_dma_chan *dwc)
 /*----------------------------------------------------------------------*/
 
 static void
-dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
-		bool callback_required)
+dwc_descriptor_free(struct dw_dma_chan *dwc, struct dw_desc *desc,
+		    bool callback_required)
 {
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
 	struct dw_desc			*child;
 	unsigned long			flags;
 	struct dmaengine_desc_callback	cb;
 
-	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
+	dev_vdbg(chan2dev(&dwc->chan), "freeing descriptor %p\n", desc);
 
 	spin_lock_irqsave(&dwc->lock, flags);
-	dma_cookie_complete(txd);
 	if (callback_required)
 		dmaengine_desc_get_callback(txd, &cb);
 	else
@@ -263,6 +262,22 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
 	dmaengine_desc_callback_invoke(&cb, NULL);
 }
 
+static void dwc_complete(struct dw_dma_chan *dwc)
+{
+	struct dw_desc *desc, *_desc;
+	unsigned long flags;
+	LIST_HEAD(list);
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	list_splice_tail_init(&dwc->completed, &list);
+	spin_unlock_irqrestore(&dwc->lock, flags);
+
+	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
+		list_del_init(&desc->desc_node);
+		dwc_descriptor_free(dwc, desc, true);
+	}
+}
+
 /* Returns how many bytes were already received from source */
 static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
 {
@@ -275,121 +290,51 @@ static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
 
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
-	dma_addr_t llp;
-	struct dw_desc *desc, *_desc;
+	struct dw_desc *desc;
 	struct dw_desc *child;
-	u32 status_xfer;
-	unsigned long flags;
-	LIST_HEAD(list);
-
-	spin_lock_irqsave(&dwc->lock, flags);
-	llp = channel_readl(dwc, LLP);
-	status_xfer = dma_readl(dw, RAW.XFER);
-
-	if (status_xfer & dwc->mask) {
-		/* Everything we've submitted is done */
-		dma_writel(dw, CLEAR.XFER, dwc->mask);
-		if (list_empty(&dwc->active_list)) {
-			spin_unlock_irqrestore(&dwc->lock, flags);
-			return;
-		}
-
-		if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
-			struct list_head *head, *active = dwc->tx_node_active;
-
-			/*
-			 * We are inside first active descriptor.
-			 * Otherwise something is really wrong.
-			 */
-			desc = dwc_first_active(dwc);
-
-			head = &desc->tx_list;
-			if (active != head) {
-				/* Update residue to reflect last sent descriptor */
-				if (active == head->next)
-					desc->residue -= desc->len;
-				else
-					desc->residue -= to_dw_desc(active->prev)->len;
-
-				child = to_dw_desc(active);
-
-				/* Submit next block */
-				dwc_do_single_block(dwc, child);
 
-				spin_unlock_irqrestore(&dwc->lock, flags);
-				return;
-			}
-
-			/* We are done here */
-			clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
-		}
-
-		if (dma_readl(dw, CH_EN) & dwc->mask) {
-			dev_err(chan2dev(&dwc->chan),
-				"BUG: XFER bit set, but channel not idle!\n");
-
-			/* Try to continue after resetting the channel... */
-			dwc_chan_disable(dw, dwc);
-		}
+	lockdep_assert_held(&dwc->lock);
 
-		/* Detach the completed transfer before starting queued work. */
-		list_splice_init(&dwc->active_list, &list);
-		dwc_dostart_first_queued(dwc);
-		spin_unlock_irqrestore(&dwc->lock, flags);
-
-		list_for_each_entry_safe(desc, _desc, &list, desc_node) {
-			list_del_init(&desc->desc_node);
-			dwc_descriptor_complete(dwc, desc, true);
-		}
+	if (!(dma_readl(dw, RAW.XFER) & dwc->mask))
 		return;
-	}
 
-	if (list_empty(&dwc->active_list)) {
-		spin_unlock_irqrestore(&dwc->lock, flags);
+	dma_writel(dw, CLEAR.XFER, dwc->mask);
+	if (list_empty(&dwc->active_list))
 		return;
-	}
 
+	desc = dwc_first_active(dwc);
 	if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
-		dev_vdbg(chan2dev(&dwc->chan), "%s: soft LLP mode\n", __func__);
-		spin_unlock_irqrestore(&dwc->lock, flags);
-		return;
-	}
+		struct list_head *head = &desc->tx_list;
+		struct list_head *active = dwc->tx_node_active;
 
-	dev_vdbg(chan2dev(&dwc->chan), "%s: llp=%pad\n", __func__, &llp);
+		if (active != head) {
+			/* Update residue to reflect last sent descriptor. */
+			if (active == head->next)
+				desc->residue -= desc->len;
+			else
+				desc->residue -= to_dw_desc(active->prev)->len;
 
-	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
-		/* Initial residue value */
-		desc->residue = desc->total_len;
+			child = to_dw_desc(active);
 
-		/* Check first descriptors addr */
-		if (desc->txd.phys == DWC_LLP_LOC(llp)) {
-			spin_unlock_irqrestore(&dwc->lock, flags);
+			/* Submit next block, including for polled transfers. */
+			dwc_do_single_block(dwc, child);
 			return;
 		}
 
-		/* Check first descriptors llp */
-		if (lli_read(desc, llp) == llp) {
-			/* This one is currently in progress */
-			desc->residue -= dwc_get_sent(dwc);
-			spin_unlock_irqrestore(&dwc->lock, flags);
-			return;
-		}
+		clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
+	}
 
-		desc->residue -= desc->len;
-		list_for_each_entry(child, &desc->tx_list, desc_node) {
-			if (lli_read(child, llp) == llp) {
-				/* Currently in progress */
-				desc->residue -= dwc_get_sent(dwc);
-				spin_unlock_irqrestore(&dwc->lock, flags);
-				return;
-			}
-			desc->residue -= child->len;
-		}
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_err(chan2dev(&dwc->chan),
+			"BUG: XFER bit set, but channel not idle!\n");
 
+		/* Try to continue after resetting the channel... */
+		dwc_chan_disable(dw, dwc);
 	}
 
-	/* Residue describes source reads; only RAW.XFER completes a transfer. */
-	spin_unlock_irqrestore(&dwc->lock, flags);
+	dma_cookie_complete(&desc->txd);
+	list_move_tail(&desc->desc_node, &dwc->completed);
+	dwc_dostart_first_queued(dwc);
 }
 
 static inline void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_desc *desc)
@@ -406,18 +351,17 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
 	struct dw_desc *bad_desc;
 	struct dw_desc *child;
-	unsigned long flags;
 
-	spin_lock_irqsave(&dwc->lock, flags);
+	lockdep_assert_held(&dwc->lock);
 
 	/* Termination may have cleared the error since the tasklet sampled it. */
 	if (!(dma_readl(dw, RAW.ERROR) & dwc->mask))
-		goto unlock;
+		return;
 
 	dwc_chan_disable(dw, dwc);
 	clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
 	if (list_empty(&dwc->active_list))
-		goto unlock;
+		return;
 
 	/*
 	 * The descriptor currently at the head of the active list is
@@ -441,37 +385,43 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		dwc_dump_lli(dwc, child);
 
-	spin_unlock_irqrestore(&dwc->lock, flags);
-
 	/* Pretend the descriptor completed successfully */
-	dwc_descriptor_complete(dwc, bad_desc, true);
-	return;
+	dma_cookie_complete(&bad_desc->txd);
+	list_add_tail(&bad_desc->desc_node, &dwc->completed);
+}
 
-unlock:
-	spin_unlock_irqrestore(&dwc->lock, flags);
+static void dwc_handle_channel(struct dw_dma *dw, struct dw_dma_chan *dwc)
+{
+	lockdep_assert_held(&dwc->lock);
+
+	if (dma_readl(dw, RAW.ERROR) & dwc->mask)
+		dwc_handle_error(dw, dwc);
+	else
+		dwc_scan_descriptors(dw, dwc);
 }
 
 static void dw_dma_tasklet(struct tasklet_struct *t)
 {
 	struct dw_dma *dw = from_tasklet(dw, t, tasklet);
 	struct dw_dma_chan *dwc;
-	u32 status_xfer;
-	u32 status_err;
+	unsigned long flags;
 	unsigned int i;
+	u32 status;
 
-	status_xfer = dma_readl(dw, RAW.XFER);
-	status_err = dma_readl(dw, RAW.ERROR);
+	/* Channel release may have drained a polled completion before this run. */
+	if (!dw->in_use)
+		return;
 
-	dev_vdbg(dw->dma.dev, "%s: status_err=%x\n", __func__, status_err);
+	status = dma_readl(dw, RAW.XFER) | dma_readl(dw, RAW.ERROR);
 
 	for (i = 0; i < dw->dma.chancnt; i++) {
 		dwc = &dw->chan[i];
-		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
-			dev_vdbg(dw->dma.dev, "Cyclic xfer is not implemented\n");
-		else if (status_err & (1 << i))
-			dwc_handle_error(dw, dwc);
-		else if (status_xfer & (1 << i))
-			dwc_scan_descriptors(dw, dwc);
+		spin_lock_irqsave(&dwc->lock, flags);
+		/* The snapshot selects work; recheck events under the channel lock. */
+		if (status & dwc->mask)
+			dwc_handle_channel(dw, dwc);
+		spin_unlock_irqrestore(&dwc->lock, flags);
+		dwc_complete(dwc);
 	}
 
 	/* Re-enable interrupts */
@@ -945,12 +895,17 @@ static int dwc_terminate_all(struct dma_chan *chan)
 	/* active_list entries will end up before queued entries */
 	list_splice_init(&dwc->queue, &list);
 	list_splice_init(&dwc->active_list, &list);
+	list_for_each_entry(desc, &list, desc_node)
+		dma_cookie_complete(&desc->txd);
+	list_splice_init(&dwc->completed, &list);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	/* Flush all pending and queued descriptors */
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		dwc_descriptor_complete(dwc, desc, false);
+	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
+		list_del_init(&desc->desc_node);
+		dwc_descriptor_free(dwc, desc, false);
+	}
 
 	return 0;
 }
@@ -963,24 +918,56 @@ static struct dw_desc *dwc_find_desc(struct dw_dma_chan *dwc, dma_cookie_t c)
 		if (desc->txd.cookie == c)
 			return desc;
 
+	list_for_each_entry(desc, &dwc->queue, desc_node)
+		if (desc->txd.cookie == c)
+			return desc;
+
 	return NULL;
 }
 
+static u32 dwc_get_hard_llp_desc_residue(struct dw_dma_chan *dwc, struct dw_desc *desc)
+{
+	u32 residue = desc->total_len;
+	struct dw_desc *child;
+	dma_addr_t llp;
+
+	llp = channel_readl(dwc, LLP);
+
+	/* The first descriptor may still be waiting to be fetched. */
+	if (desc->txd.phys == DWC_LLP_LOC(llp))
+		return residue;
+
+	if (lli_read(desc, llp) == llp)
+		return residue - dwc_get_sent(dwc);
+
+	residue -= desc->len;
+	list_for_each_entry(child, &desc->tx_list, desc_node) {
+		if (lli_read(child, llp) == llp)
+			return residue - dwc_get_sent(dwc);
+
+		residue -= child->len;
+	}
+
+	return residue;
+}
+
 static u32 dwc_get_residue_and_status(struct dw_dma_chan *dwc, dma_cookie_t cookie,
 				      enum dma_status *status)
 {
 	struct dw_desc *desc;
-	unsigned long flags;
 	u32 residue;
 
-	spin_lock_irqsave(&dwc->lock, flags);
+	lockdep_assert_held(&dwc->lock);
 
 	desc = dwc_find_desc(dwc, cookie);
 	if (desc) {
 		if (desc == dwc_first_active(dwc)) {
-			residue = desc->residue;
-			if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags) && residue)
+			if (test_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags)) {
+				residue = desc->residue;
 				residue -= dwc_get_sent(dwc);
+			} else {
+				residue = dwc_get_hard_llp_desc_residue(dwc, desc);
+			}
 			if (test_bit(DW_DMA_IS_PAUSED, &dwc->flags))
 				*status = DMA_PAUSED;
 		} else {
@@ -990,7 +977,6 @@ static u32 dwc_get_residue_and_status(struct dw_dma_chan *dwc, dma_cookie_t cook
 		residue = 0;
 	}
 
-	spin_unlock_irqrestore(&dwc->lock, flags);
 	return residue;
 }
 
@@ -1000,19 +986,26 @@ dwc_tx_status(struct dma_chan *chan,
 	      struct dma_tx_state *txstate)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(chan->device);
 	enum dma_status		ret;
+	unsigned long		flags;
 
+	spin_lock_irqsave(&dwc->lock, flags);
 	ret = dma_cookie_status(chan, cookie, txstate);
 	if (ret == DMA_COMPLETE)
-		return ret;
+		goto unlock;
 
-	dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
+	/* Poll completion even when the client has masked the controller IRQ. */
+	dwc_handle_channel(dw, dwc);
+	if (!list_empty(&dwc->completed))
+		tasklet_schedule(&dw->tasklet);
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_COMPLETE)
-		return ret;
+	if (ret != DMA_COMPLETE)
+		dma_set_residue(txstate, dwc_get_residue_and_status(dwc, cookie, &ret));
 
-	dma_set_residue(txstate, dwc_get_residue_and_status(dwc, cookie, &ret));
+unlock:
+	spin_unlock_irqrestore(&dwc->lock, flags);
 	return ret;
 }
 
@@ -1089,7 +1082,12 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
+	struct dw_desc		*desc, *_desc;
 	unsigned long		flags;
+	LIST_HEAD(list);
+
+	/* Polled completion can leave descriptors waiting for the tasklet. */
+	tasklet_disable(&dw->tasklet);
 
 	dev_dbg(chan2dev(chan), "%s: descs allocated=%u\n", __func__,
 			dwc->descs_allocated);
@@ -1100,6 +1098,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	BUG_ON(dma_readl(to_dw_dma(chan->device), CH_EN) & dwc->mask);
 
 	spin_lock_irqsave(&dwc->lock, flags);
+	list_splice_init(&dwc->completed, &list);
 
 	/* Clear custom channel configuration */
 	memset(&dwc->dws, 0, sizeof(struct dw_dma_slave));
@@ -1111,11 +1110,18 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
+	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
+		list_del_init(&desc->desc_node);
+		dwc_descriptor_free(dwc, desc, false);
+	}
+
 	/* Disable controller in case it was a last user */
 	dw->in_use &= ~dwc->mask;
 	if (!dw->in_use)
 		do_dw_dma_off(dw);
 
+	tasklet_enable(&dw->tasklet);
+
 	dev_vdbg(chan2dev(chan), "%s: done\n", __func__);
 }
 
@@ -1246,6 +1252,7 @@ int do_dma_probe(struct dw_dma_chip *chip)
 
 		INIT_LIST_HEAD(&dwc->active_list);
 		INIT_LIST_HEAD(&dwc->queue);
+		INIT_LIST_HEAD(&dwc->completed);
 
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 5969d9cc8d7a..c41f18281efe 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -279,6 +279,7 @@ struct dw_dma_chan {
 	unsigned long		flags;
 	struct list_head	active_list;
 	struct list_head	queue;
+	struct list_head	completed;
 
 	unsigned int		descs_allocated;
 

-- 
2.53.0