ioat2: catch and recover from broken vtd configurations v6

On some platforms (MacPro3,1) the BIOS assigns the ioatdma device to the
incorrect iommu causing faults when the driver initializes.  Add a quirk
to catch this misconfiguration and try falling back to untranslated
operation (which works in the MacPro3,1 case).

Assuming there are other platforms with misconfigured iommus teach the
ioatdma driver to treat initialization failures as non-fatal (just fail
the driver load and emit a warning instead of triggering a BUG_ON).

This can be classified as a boot regression since 2.6.32 on affected
platforms since the ioatdma module did not autoload prior to that
kernel.

Cc: <stable@kernel.org>
Acked-by: David Woodhouse <David.Woodhouse@intel.com>
Reported-by: Chris Li <lkml@chrisli.org>
Tested-by: Chris Li <lkml@chrisli.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

3 files changed, 27 insertions, 3 deletions

diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 6d3a73b57e5..5216c8a92a2 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -97,6 +97,7 @@ struct ioat_chan_common {
 	#define IOAT_RESET_PENDING 2
 	#define IOAT_KOBJ_INIT_FAIL 3
 	#define IOAT_RESHAPE_PENDING 4
+	#define IOAT_RUN 5
 	struct timer_list timer;
 	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
 	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 3c8b32a8379..216f9d383b5 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -287,7 +287,10 @@ void ioat2_timer_event(unsigned long data)
 			chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
 			dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
 				__func__, chanerr);
-			BUG_ON(is_ioat_bug(chanerr));
+			if (test_bit(IOAT_RUN, &chan->state))
+				BUG_ON(is_ioat_bug(chanerr));
+			else /* we never got off the ground */
+				return;
 		}
 
 		/* if we haven't made progress and we have already
@@ -492,6 +495,8 @@ static struct ioat_ring_ent **ioat2_alloc_ring(struct dma_chan *c, int order, gf
 	return ring;
 }
 
+void ioat2_free_chan_resources(struct dma_chan *c);
+
 /* ioat2_alloc_chan_resources - allocate/initialize ioat2 descriptor ring
  * @chan: channel to be initialized
  */
@@ -500,6 +505,7 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	struct ioat2_dma_chan *ioat = to_ioat2_chan(c);
 	struct ioat_chan_common *chan = &ioat->base;
 	struct ioat_ring_ent **ring;
+	u64 status;
 	int order;
 
 	/* have we already been set up? */
@@ -540,7 +546,20 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
 	tasklet_enable(&chan->cleanup_task);
 	ioat2_start_null_desc(ioat);
 
-	return 1 << ioat->alloc_order;
+	/* check that we got off the ground */
+	udelay(5);
+	status = ioat_chansts(chan);
+	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);
+
+		dev_WARN(to_dev(chan),
+			"failed to start channel chanerr: %#x\n", chanerr);
+		ioat2_free_chan_resources(c);
+		return -EFAULT;
+	}
 }
 
 bool reshape_ring(struct ioat2_dma_chan *ioat, int order)
@@ -778,6 +797,7 @@ void ioat2_free_chan_resources(struct dma_chan *c)
 	del_timer_sync(&chan->timer);
 	device->cleanup_fn((unsigned long) c);
 	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 1cdd22e1051..d0f49909847 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -361,7 +361,10 @@ static void ioat3_timer_event(unsigned long data)
 			chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
 			dev_err(to_dev(chan), "%s: Channel halted (%x)\n",
 				__func__, chanerr);
-			BUG_ON(is_ioat_bug(chanerr));
+			if (test_bit(IOAT_RUN, &chan->state))
+				BUG_ON(is_ioat_bug(chanerr));
+			else /* we never got off the ground */
+				return;
 		}
 
 		/* if we haven't made progress and we have already