Merge branch 'linux-3.10.33' into dev-kernel-3.10

Bug 1456092

Change-Id: I3021247ec68a3c2dddd9e98cde13d70a45191d53
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>

6 files changed, 58 insertions, 14 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e9924898043a..0ba5a95199d3 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -333,6 +333,7 @@ config NET_DMA
 	bool "Network: TCP receive copy offload"
 	depends on DMA_ENGINE && NET
 	default (INTEL_IOATDMA || FSL_DMA)
+	depends on BROKEN
 	help
 	  This enables the use of DMA engines in the network stack to
 	  offload receive copy-to-user operations, freeing CPU cycles.
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 17a2393b3e25..533e1874e1d6 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);
 }
 
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 54fb7b9ff9aa..a1d78847e5a5 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -370,6 +370,7 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
 void ioat_kobject_del(struct ioatdma_device *device);
 int ioat_dma_setup_interrupts(struct ioatdma_device *device);
+void ioat_stop(struct ioat_chan_common *chan);
 extern const struct sysfs_ops ioat_sysfs_ops;
 extern struct ioat_sysfs_entry ioat_version_attr;
 extern struct ioat_sysfs_entry ioat_cap_attr;
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index b925e1b1d139..1cd761026d84 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -190,8 +190,11 @@ static void ioat2_cleanup(struct ioat2_dma_chan *ioat)
 void ioat2_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat2_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
@@ -553,10 +556,10 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	ioat->issued = 0;
 	ioat->tail = 0;
 	ioat->alloc_order = order;
+	set_bit(IOAT_RUN, &chan->state);
 	spin_unlock_bh(&ioat->prep_lock);
 	spin_unlock_bh(&chan->cleanup_lock);
 
-	tasklet_enable(&chan->cleanup_task);
 	ioat2_start_null_desc(ioat);
 
 	/* check that we got off the ground */
@@ -566,7 +569,6 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
 
 	if (is_ioat_active(status) || is_ioat_idle(status)) {
-		set_bit(IOAT_RUN, &chan->state);
 		return 1 << ioat->alloc_order;
 	} else {
 		u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -809,11 +811,8 @@ void ioat2_free_chan_resources(struct dma_chan *c)
 	if (!ioat->ring)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	device->cleanup_fn((unsigned long) c);
+	ioat_stop(chan);
 	device->reset_hw(chan);
-	clear_bit(IOAT_RUN, &chan->state);
 
 	spin_lock_bh(&chan->cleanup_lock);
 	spin_lock_bh(&ioat->prep_lock);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index fa43a42ccc86..38b94b393c6c 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -635,8 +635,11 @@ static void ioat3_cleanup(struct ioat2_dma_chan *ioat)
 static void ioat3_cleanup_event(unsigned long data)
 {
 	struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat3_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 71bf4ec300ea..ca78044df4b5 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1587,6 +1587,7 @@ static void dma_tasklet(unsigned long data)
 	struct d40_chan *d40c = (struct d40_chan *) data;
 	struct d40_desc *d40d;
 	unsigned long flags;
+	bool callback_active;
 	dma_async_tx_callback callback;
 	void *callback_param;
 
@@ -1614,6 +1615,7 @@ static void dma_tasklet(unsigned long data)
 	}
 
 	/* Callback to client */
+	callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
 	callback = d40d->txd.callback;
 	callback_param = d40d->txd.callback_param;
 
@@ -1636,7 +1638,7 @@ static void dma_tasklet(unsigned long data)
 
 	spin_unlock_irqrestore(&d40c->lock, flags);
 
-	if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT))
+	if (callback_active && callback)
 		callback(callback_param);
 
 	return;