rapidio/tsi721: fix tasklet termination in dma channel release

This patch is a modification of the patch originally proposed by
Xiaotian Feng <xtfeng@gmail.com>: https://lkml.org/lkml/2012/11/5/413
This new version disables DMA channel interrupts and ensures that the
tasklet wil not be scheduled again before calling tasklet_kill().

Unfortunately the updated patch was not released at that time due to
planned rework of Tsi721 mport driver to use threaded interrupts (which
has yet to happen).  Recently the issue was reported again:
https://lkml.org/lkml/2014/2/19/762.

Description from the original Xiaotian's patch:

 "Some drivers use tasklet_disable in device remove/release process,
  tasklet_disable will inc tasklet->count and return.  If the tasklet is
  not handled yet under some softirq pressure, the tasklet will be
  placed on the tasklet_vec, never have a chance to be excuted.  This
  might lead to a heavy loaded ksoftirqd, wakeup with pending_softirq,
  but tasklet is disabled.  tasklet_kill should be used in this case."

This patch is applicable to kernel versions starting from v3.5.

Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Xiaotian Feng <xtfeng@gmail.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Mike Galbraith <bitbucket@online.de>
Cc: <stable@vger.kernel.org>	[3.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/rapidio/devices/tsi721.h

@@ -678,6 +678,7 @@ struct tsi721_bdma_chan {
 	struct list_head	free_list;
 	dma_cookie_t		completed_cookie;
 	struct tasklet_struct	tasklet;
+	bool			active;
 };
 
 #endif /* CONFIG_RAPIDIO_DMA_ENGINE */

drivers/rapidio/devices/tsi721_dma.c

@@ -206,8 +206,8 @@ void tsi721_bdma_handler(struct tsi721_bdma_chan *bdma_chan)
 {
 	/* Disable BDMA channel interrupts */
 	iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE);
-
-	tasklet_schedule(&bdma_chan->tasklet);
+	if (bdma_chan->active)
+		tasklet_schedule(&bdma_chan->tasklet);
 }
 
 #ifdef CONFIG_PCI_MSI
@@ -562,7 +562,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 	}
 #endif /* CONFIG_PCI_MSI */
 
-	tasklet_enable(&bdma_chan->tasklet);
+	bdma_chan->active = true;
 	tsi721_bdma_interrupt_enable(bdma_chan, 1);
 
 	return bdma_chan->bd_num - 1;
@@ -576,9 +576,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan)
 static void tsi721_free_chan_resources(struct dma_chan *dchan)
 {
 	struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
 	struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
 	LIST_HEAD(list);
 
 	dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
@@ -589,14 +587,25 @@ static void tsi721_free_chan_resources(struct dma_chan *dchan)
 	BUG_ON(!list_empty(&bdma_chan->active_list));
 	BUG_ON(!list_empty(&bdma_chan->queue));
 
-	tasklet_disable(&bdma_chan->tasklet);
+	tsi721_bdma_interrupt_enable(bdma_chan, 0);
+	bdma_chan->active = false;
+
+#ifdef CONFIG_PCI_MSI
+	if (priv->flags & TSI721_USING_MSIX) {
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+					   bdma_chan->id].vector);
+		synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT +
+					   bdma_chan->id].vector);
+	} else
+#endif
+	synchronize_irq(priv->pdev->irq);
+
+	tasklet_kill(&bdma_chan->tasklet);
 
 	spin_lock_bh(&bdma_chan->lock);
 	list_splice_init(&bdma_chan->free_list, &list);
 	spin_unlock_bh(&bdma_chan->lock);
 
-	tsi721_bdma_interrupt_enable(bdma_chan, 0);
-
 #ifdef CONFIG_PCI_MSI
 	if (priv->flags & TSI721_USING_MSIX) {
 		free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
@@ -790,6 +799,7 @@ int tsi721_register_dma(struct tsi721_device *priv)
 		bdma_chan->dchan.cookie = 1;
 		bdma_chan->dchan.chan_id = i;
 		bdma_chan->id = i;
+		bdma_chan->active = false;
 
 		spin_lock_init(&bdma_chan->lock);
 
@@ -799,7 +809,6 @@ int tsi721_register_dma(struct tsi721_device *priv)
 
 		tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet,
 			     (unsigned long)bdma_chan);
-		tasklet_disable(&bdma_chan->tasklet);
 		list_add_tail(&bdma_chan->dchan.device_node,
 			      &mport->dma.channels);
 	}