raid6: fix recovery performance regression

The raid6 recovery code should immediately drop back to the optimized
synchronous path when a p+q dma resource is not available.  Otherwise we
run the non-optimized/multi-pass async code in sync mode.

Verified with raid6test (NDISKS=255)

Applies to kernels >= 2.6.32.

Cc: <stable@kernel.org>
Acked-by: NeilBrown <neilb@suse.de>
Reported-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

crypto/async_tx/async_raid6_recov.c

@@ -324,6 +324,7 @@ struct dma_async_tx_descriptor *
 async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 			struct page **blocks, struct async_submit_ctl *submit)
 {
+	void *scribble = submit->scribble;
 	int non_zero_srcs, i;
 
 	BUG_ON(faila == failb);
@@ -332,11 +333,13 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
-	/* we need to preserve the contents of 'blocks' for the async
-	 * case, so punt to synchronous if a scribble buffer is not available
+	/* if a dma resource is not available or a scribble buffer is not
+	 * available punt to the synchronous path.  In the 'dma not
+	 * available' case be sure to use the scribble buffer to
+	 * preserve the content of 'blocks' as the caller intended.
 	 */
-	if (!submit->scribble) {
-		void **ptrs = (void **) blocks;
+	if (!async_dma_find_channel(DMA_PQ) || !scribble) {
+		void **ptrs = scribble ? scribble : (void **) blocks;
 
 		async_tx_quiesce(&submit->depend_tx);
 		for (i = 0; i < disks; i++)
@@ -406,11 +409,13 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 
 	pr_debug("%s: disks: %d len: %zu\n", __func__, disks, bytes);
 
-	/* we need to preserve the contents of 'blocks' for the async
-	 * case, so punt to synchronous if a scribble buffer is not available
+	/* if a dma resource is not available or a scribble buffer is not
+	 * available punt to the synchronous path.  In the 'dma not
+	 * available' case be sure to use the scribble buffer to
+	 * preserve the content of 'blocks' as the caller intended.
 	 */
-	if (!scribble) {
-		void **ptrs = (void **) blocks;
+	if (!async_dma_find_channel(DMA_PQ) || !scribble) {
+		void **ptrs = scribble ? scribble : (void **) blocks;
 
 		async_tx_quiesce(&submit->depend_tx);
 		for (i = 0; i < disks; i++)