Merge branch 'md-raid6-accel' into ioat3.2

Conflicts:
	include/linux/dmaengine.h

4 files changed, 63 insertions, 58 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 3b3c01b..912a51b 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -4,7 +4,7 @@
 
 menuconfig DMADEVICES
 	bool "DMA Engine support"
-	depends on !HIGHMEM64G && HAS_DMA
+	depends on HAS_DMA
 	help
 	  DMA engines can do asynchronous data transfers without
 	  involving the host CPU.  Currently, this framework can be
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 5a87384..9659847 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -644,8 +644,12 @@ int dma_async_device_register(struct dma_device *device)
 		!device->device_prep_dma_memcpy);
 	BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) &&
 		!device->device_prep_dma_xor);
-	BUG_ON(dma_has_cap(DMA_ZERO_SUM, device->cap_mask) &&
-		!device->device_prep_dma_zero_sum);
+	BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) &&
+		!device->device_prep_dma_xor_val);
+	BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) &&
+		!device->device_prep_dma_pq);
+	BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) &&
+		!device->device_prep_dma_pq_val);
 	BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) &&
 		!device->device_prep_dma_memset);
 	BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) &&
@@ -939,49 +943,24 @@ EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 
 /* dma_wait_for_async_tx - spin wait for a transaction to complete
  * @tx: in-flight transaction to wait on
- *
- * This routine assumes that tx was obtained from a call to async_memcpy,
- * async_xor, async_memset, etc which ensures that tx is "in-flight" (prepped
- * and submitted).  Walking the parent chain is only meant to cover for DMA
- * drivers that do not implement the DMA_INTERRUPT capability and may race with
- * the driver's descriptor cleanup routine.
  */
 enum dma_status
 dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 {
-	enum dma_status status;
-	struct dma_async_tx_descriptor *iter;
-	struct dma_async_tx_descriptor *parent;
+	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);
 
 	if (!tx)
 		return DMA_SUCCESS;
 
-	WARN_ONCE(tx->parent, "%s: speculatively walking dependency chain for"
-		  " %s\n", __func__, dma_chan_name(tx->chan));
-
-	/* poll through the dependency chain, return when tx is complete */
-	do {
-		iter = tx;
-
-		/* find the root of the unsubmitted dependency chain */
-		do {
-			parent = iter->parent;
-			if (!parent)
-				break;
-			else
-				iter = parent;
-		} while (parent);
-
-		/* there is a small window for ->parent == NULL and
-		 * ->cookie == -EBUSY
-		 */
-		while (iter->cookie == -EBUSY)
-			cpu_relax();
-
-		status = dma_sync_wait(iter->chan, iter->cookie);
-	} while (status == DMA_IN_PROGRESS || (iter != tx));
-
-	return status;
+	while (tx->cookie == -EBUSY) {
+		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
+			pr_err("%s timeout waiting for descriptor submission\n",
+				__func__);
+			return DMA_ERROR;
+		}
+		cpu_relax();
+	}
+	return dma_sync_wait(tx->chan, tx->cookie);
 }
 EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index fb7da51..58e49e4 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -43,6 +43,11 @@ module_param(xor_sources, uint, S_IRUGO);
 MODULE_PARM_DESC(xor_sources,
 		"Number of xor source buffers (default: 3)");
 
+static unsigned int pq_sources = 3;
+module_param(pq_sources, uint, S_IRUGO);
+MODULE_PARM_DESC(pq_sources,
+		"Number of p+q source buffers (default: 3)");
+
 /*
  * Initialization patterns. All bytes in the source buffer has bit 7
  * set, all bytes in the destination buffer has bit 7 cleared.
@@ -227,6 +232,7 @@ static int dmatest_func(void *data)
 	dma_cookie_t		cookie;
 	enum dma_status		status;
 	enum dma_ctrl_flags 	flags;
+	u8			pq_coefs[pq_sources];
 	int			ret;
 	int			src_cnt;
 	int			dst_cnt;
@@ -243,6 +249,11 @@ static int dmatest_func(void *data)
 	else if (thread->type == DMA_XOR) {
 		src_cnt = xor_sources | 1; /* force odd to ensure dst = src */
 		dst_cnt = 1;
+	} else if (thread->type == DMA_PQ) {
+		src_cnt = pq_sources | 1; /* force odd to ensure dst = src */
+		dst_cnt = 2;
+		for (i = 0; i < pq_sources; i++)
+			pq_coefs[i] = 1;
 	} else
 		goto err_srcs;
 
@@ -310,6 +321,15 @@ static int dmatest_func(void *data)
 						      dma_dsts[0] + dst_off,
 						      dma_srcs, xor_sources,
 						      len, flags);
+		else if (thread->type == DMA_PQ) {
+			dma_addr_t dma_pq[dst_cnt];
+
+			for (i = 0; i < dst_cnt; i++)
+				dma_pq[i] = dma_dsts[i] + dst_off;
+			tx = dev->device_prep_dma_pq(chan, dma_pq, dma_srcs,
+						     pq_sources, pq_coefs,
+						     len, flags);
+		}
 
 		if (!tx) {
 			for (i = 0; i < src_cnt; i++)
@@ -446,6 +466,8 @@ static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_ty
 		op = "copy";
 	else if (type == DMA_XOR)
 		op = "xor";
+	else if (type == DMA_PQ)
+		op = "pq";
 	else
 		return -EINVAL;
 
@@ -501,6 +523,10 @@ static int dmatest_add_channel(struct dma_chan *chan)
 		cnt = dmatest_add_threads(dtc, DMA_XOR);
 		thread_count += cnt > 0 ?: 0;
 	}
+	if (dma_has_cap(DMA_PQ, dma_dev->cap_mask)) {
+		cnt = dmatest_add_threads(dtc, DMA_PQ);
+		thread_count += cnt > 0 ?: 0;
+	}
 
 	pr_info("dmatest: Started %u threads using %s\n",
 		thread_count, dma_chan_name(chan));
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 2f05226..4496bc6 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -660,9 +660,9 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 }
 
 static struct dma_async_tx_descriptor *
-iop_adma_prep_dma_zero_sum(struct dma_chan *chan, dma_addr_t *dma_src,
-			   unsigned int src_cnt, size_t len, u32 *result,
-			   unsigned long flags)
+iop_adma_prep_dma_xor_val(struct dma_chan *chan, dma_addr_t *dma_src,
+			  unsigned int src_cnt, size_t len, u32 *result,
+			  unsigned long flags)
 {
 	struct iop_adma_chan *iop_chan = to_iop_adma_chan(chan);
 	struct iop_adma_desc_slot *sw_desc, *grp_start;
@@ -906,7 +906,7 @@ out:
 
 #define IOP_ADMA_NUM_SRC_TEST 4 /* must be <= 15 */
 static int __devinit
-iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
+iop_adma_xor_val_self_test(struct iop_adma_device *device)
 {
 	int i, src_idx;
 	struct page *dest;
@@ -1002,7 +1002,7 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		PAGE_SIZE, DMA_TO_DEVICE);
 
 	/* skip zero sum if the capability is not present */
-	if (!dma_has_cap(DMA_ZERO_SUM, dma_chan->device->cap_mask))
+	if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask))
 		goto free_resources;
 
 	/* zero sum the sources with the destintation page */
@@ -1016,10 +1016,10 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		dma_srcs[i] = dma_map_page(dma_chan->device->dev,
 					   zero_sum_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-	tx = iop_adma_prep_dma_zero_sum(dma_chan, dma_srcs,
-					IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
-					&zero_sum_result,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	tx = iop_adma_prep_dma_xor_val(dma_chan, dma_srcs,
+				       IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
+				       &zero_sum_result,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	cookie = iop_adma_tx_submit(tx);
 	iop_adma_issue_pending(dma_chan);
@@ -1072,10 +1072,10 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 		dma_srcs[i] = dma_map_page(dma_chan->device->dev,
 					   zero_sum_srcs[i], 0, PAGE_SIZE,
 					   DMA_TO_DEVICE);
-	tx = iop_adma_prep_dma_zero_sum(dma_chan, dma_srcs,
-					IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
-					&zero_sum_result,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	tx = iop_adma_prep_dma_xor_val(dma_chan, dma_srcs,
+				       IOP_ADMA_NUM_SRC_TEST + 1, PAGE_SIZE,
+				       &zero_sum_result,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 
 	cookie = iop_adma_tx_submit(tx);
 	iop_adma_issue_pending(dma_chan);
@@ -1192,9 +1192,9 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 		dma_dev->max_xor = iop_adma_get_max_xor();
 		dma_dev->device_prep_dma_xor = iop_adma_prep_dma_xor;
 	}
-	if (dma_has_cap(DMA_ZERO_SUM, dma_dev->cap_mask))
-		dma_dev->device_prep_dma_zero_sum =
-			iop_adma_prep_dma_zero_sum;
+	if (dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask))
+		dma_dev->device_prep_dma_xor_val =
+			iop_adma_prep_dma_xor_val;
 	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
 		dma_dev->device_prep_dma_interrupt =
 			iop_adma_prep_dma_interrupt;
@@ -1249,7 +1249,7 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 
 	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask) ||
 		dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)) {
-		ret = iop_adma_xor_zero_sum_self_test(adev);
+		ret = iop_adma_xor_val_self_test(adev);
 		dev_dbg(&pdev->dev, "xor self test returned %d\n", ret);
 		if (ret)
 			goto err_free_iop_chan;
@@ -1257,12 +1257,12 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 
 	dev_printk(KERN_INFO, &pdev->dev, "Intel(R) IOP: "
 	  "( %s%s%s%s%s%s%s%s%s%s)\n",
-	  dma_has_cap(DMA_PQ_XOR, dma_dev->cap_mask) ? "pq_xor " : "",
+	  dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "",
 	  dma_has_cap(DMA_PQ_UPDATE, dma_dev->cap_mask) ? "pq_update " : "",
-	  dma_has_cap(DMA_PQ_ZERO_SUM, dma_dev->cap_mask) ? "pq_zero_sum " : "",
+	  dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "",
 	  dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
 	  dma_has_cap(DMA_DUAL_XOR, dma_dev->cap_mask) ? "dual_xor " : "",
-	  dma_has_cap(DMA_ZERO_SUM, dma_dev->cap_mask) ? "xor_zero_sum " : "",
+	  dma_has_cap(DMA_XOR_VAL, dma_dev->cap_mask) ? "xor_val " : "",
 	  dma_has_cap(DMA_MEMSET, dma_dev->cap_mask)  ? "fill " : "",
 	  dma_has_cap(DMA_MEMCPY_CRC32C, dma_dev->cap_mask) ? "cpy+crc " : "",
 	  dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",