dmaengine: remove dependency on async_tx

async_tx.ko is a consumer of dma channels.  A circular dependency arises
if modules in drivers/dma rely on common code in async_tx.ko.  It
prevents either module from being unloaded.

Move dma_wait_for_async_tx and async_tx_run_dependencies to dmaeninge.o
where they should have been from the beginning.

Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

4 files changed, 86 insertions, 6 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 904e57558bb..e34b0642081 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -33,7 +33,6 @@ config INTEL_IOATDMA
 config INTEL_IOP_ADMA
 	tristate "Intel IOP ADMA support"
 	depends on ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX
-	select ASYNC_CORE
 	select DMA_ENGINE
 	help
 	  Enable support for the Intel(R) IOP Series RAID engines.
@@ -59,7 +58,6 @@ config FSL_DMA
 config MV_XOR
 	bool "Marvell XOR engine support"
 	depends on PLAT_ORION
-	select ASYNC_CORE
 	select DMA_ENGINE
 	---help---
 	  Enable support for the Marvell XOR engine.
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 65799651737..b9008932a8f 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -626,6 +626,90 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 }
 EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 
+/* dma_wait_for_async_tx - spin wait for a transaction to complete
+ * @tx: in-flight transaction to wait on
+ *
+ * This routine assumes that tx was obtained from a call to async_memcpy,
+ * async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped
+ * and submitted).  Walking the parent chain is only meant to cover for DMA
+ * drivers that do not implement the DMA_INTERRUPT capability and may race with
+ * the driver's descriptor cleanup routine.
+ */
+enum dma_status
+dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
+{
+	enum dma_status status;
+	struct dma_async_tx_descriptor *iter;
+	struct dma_async_tx_descriptor *parent;
+
+	if (!tx)
+		return DMA_SUCCESS;
+
+	WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for"
+		  " %s\n", __func__, dev_name(&tx->chan->dev));
+
+	/* poll through the dependency chain, return when tx is complete */
+	do {
+		iter = tx;
+
+		/* find the root of the unsubmitted dependency chain */
+		do {
+			parent = iter->parent;
+			if (!parent)
+				break;
+			else
+				iter = parent;
+		} while (parent);
+
+		/* there is a small window for ->parent == NULL and
+		 * ->cookie == -EBUSY
+		 */
+		while (iter->cookie == -EBUSY)
+			cpu_relax();
+
+		status = dma_sync_wait(iter->chan, iter->cookie);
+	} while (status == DMA_IN_PROGRESS || (iter != tx));
+
+	return status;
+}
+EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
+
+/* dma_run_dependencies - helper routine for dma drivers to process
+ *	(start) dependent operations on their target channel
+ * @tx: transaction with dependencies
+ */
+void dma_run_dependencies(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_async_tx_descriptor *dep = tx->next;
+	struct dma_async_tx_descriptor *dep_next;
+	struct dma_chan *chan;
+
+	if (!dep)
+		return;
+
+	chan = dep->chan;
+
+	/* keep submitting up until a channel switch is detected
+	 * in that case we will be called again as a result of
+	 * processing the interrupt from async_tx_channel_switch
+	 */
+	for (; dep; dep = dep_next) {
+		spin_lock_bh(&dep->lock);
+		dep->parent = NULL;
+		dep_next = dep->next;
+		if (dep_next && dep_next->chan == chan)
+			dep->next = NULL; /* ->next will be submitted */
+		else
+			dep_next = NULL; /* submit current dep and terminate */
+		spin_unlock_bh(&dep->lock);
+
+		dep->tx_submit(dep);
+	}
+
+	chan->device->device_issue_pending(chan);
+}
+EXPORT_SYMBOL_GPL(dma_run_dependencies);
+
 static int __init dma_bus_init(void)
 {
 	mutex_init(&dma_list_mutex);
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 6be31726220..be9ea9f8880 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -24,7 +24,6 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/async_tx.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/spinlock.h>
@@ -116,7 +115,7 @@ iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
 	}
 
 	/* run dependent operations */
-	async_tx_run_dependencies(&desc->async_tx);
+	dma_run_dependencies(&desc->async_tx);
 
 	return cookie;
 }
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index bcda1742641..3f46df3390c 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -18,7 +18,6 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/async_tx.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/spinlock.h>
@@ -340,7 +339,7 @@ mv_xor_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
 	}
 
 	/* run dependent operations */
-	async_tx_run_dependencies(&desc->async_tx);
+	dma_run_dependencies(&desc->async_tx);
 
 	return cookie;
 }