ioat: fix tasklet tear down

Since commit 77873803363c "net_dma: mark broken" we no longer pin dma
engines active for the network-receive-offload use case.  As a result
the ->free_chan_resources() that occurs after the driver self test no
longer has a NET_DMA induced ->alloc_chan_resources() to back it up.  A
late firing irq can lead to ksoftirqd spinning indefinitely due to the
tasklet_disable() performed by ->free_chan_resources().  Only
->alloc_chan_resources() can clear this condition in affected kernels.

This problem has been present since commit 3e037454bcfa "I/OAT: Add
support for MSI and MSI-X" in 2.6.24, but is now exposed. Given the
NET_DMA use case is deprecated we can revisit moving the driver to use
threaded irqs.  For now, just tear down the irq and tasklet properly by:

1/ Disable the irq from triggering the tasklet

2/ Disable the irq from re-arming

3/ Flush inflight interrupts

4/ Flush the timer

5/ Flush inflight tasklets

References:
https://lkml.org/lkml/2014/1/27/282
https://lkml.org/lkml/2014/2/19/672

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: <stable@vger.kernel.org>
Reported-by: Mike Galbraith <bitbucket@online.de>
Reported-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Tested-by: Mike Galbraith <bitbucket@online.de>
Tested-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 45 insertions, 7 deletions

diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 87529181efcc..4e3549a16132 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -77,7 +77,8 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
 	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
 	for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
 		chan = ioat_chan_by_index(instance, bit);
-		tasklet_schedule(&chan->cleanup_task);
+		if (test_bit(IOAT_RUN, &chan->state))
+			tasklet_schedule(&chan->cleanup_task);
 	}
 
 	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -93,7 +94,8 @@ static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
 {
 	struct ioat_chan_common *chan = data;
 
-	tasklet_schedule(&chan->cleanup_task);
+	if (test_bit(IOAT_RUN, &chan->state))
+		tasklet_schedule(&chan->cleanup_task);
 
 	return IRQ_HANDLED;
 }
@@ -116,7 +118,6 @@ void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *c
 	chan->timer.function = device->timer_fn;
 	chan->timer.data = data;
 	tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
-	tasklet_disable(&chan->cleanup_task);
 }
 
 /**
@@ -354,13 +355,49 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
 	writel(((u64) chan->completion_dma) >> 32,
 	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
-	tasklet_enable(&chan->cleanup_task);
+	set_bit(IOAT_RUN, &chan->state);
 	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
 	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
 		__func__, ioat->desccount);
 	return ioat->desccount;
 }
 
+void ioat_stop(struct ioat_chan_common *chan)
+{
+	struct ioatdma_device *device = chan->device;
+	struct pci_dev *pdev = device->pdev;
+	int chan_id = chan_num(chan);
+	struct msix_entry *msix;
+
+	/* 1/ stop irq from firing tasklets
+	 * 2/ stop the tasklet from re-arming irqs
+	 */
+	clear_bit(IOAT_RUN, &chan->state);
+
+	/* flush inflight interrupts */
+	switch (device->irq_mode) {
+	case IOAT_MSIX:
+		msix = &device->msix_entries[chan_id];
+		synchronize_irq(msix->vector);
+		break;
+	case IOAT_MSI:
+	case IOAT_INTX:
+		synchronize_irq(pdev->irq);
+		break;
+	default:
+		break;
+	}
+
+	/* flush inflight timers */
+	del_timer_sync(&chan->timer);
+
+	/* flush inflight tasklet runs */
+	tasklet_kill(&chan->cleanup_task);
+
+	/* final cleanup now that everything is quiesced and can't re-arm */
+	device->cleanup_fn((unsigned long) &chan->common);
+}
+
 /**
  * ioat1_dma_free_chan_resources - release all the descriptors
  * @chan: the channel to be cleaned
@@ -379,9 +416,7 @@ static void ioat1_dma_free_chan_resources(struct dma_chan *c)
 	if (ioat->desccount == 0)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	ioat1_cleanup(ioat);
+	ioat_stop(chan);
 
 	/* Delay 100ms after reset to allow internal DMA logic to quiesce
 	 * before removing DMA descriptor resources.
@@ -526,8 +561,11 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
 static void ioat1_cleanup_event(unsigned long data)
 {
 	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat1_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }