Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md: (97 commits)
  md: raid-1/10: fix RW bits manipulation
  md: remove unnecessary memset from multipath.
  md: report device as congested when suspended
  md: Improve name of threads created by md_register_thread
  md: remove sparse warnings about lock context.
  md: remove sparse waring "symbol xxx shadows an earlier one"
  async_tx/raid6: add missing dma_unmap calls to the async fail case
  ioat3: fix uninitialized var warnings
  drivers/dma/ioat/dma_v2.c: fix warnings
  raid6test: fix stack overflow
  ioat2: clarify ring size limits
  md/raid6: cleanup ops_run_compute6_2
  md/raid6: eliminate BUG_ON with side effect
  dca: module load should not be an error message
  ioat: driver version 4.0
  dca: registering requesters in multiple dca domains
  async_tx: remove HIGHMEM64G restriction
  dmaengine: sh: Add Support SuperH DMA Engine driver
  dmaengine: Move all map_sg/unmap_sg for slave channel to its client
  fsldma: Add DMA_SLAVE support
  ...

46 files changed, 7223 insertions, 3026 deletions

diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c
index 25b743abfb5..52e6bb70a49 100644
--- a/drivers/dca/dca-core.c
+++ b/drivers/dca/dca-core.c
@@ -28,7 +28,7 @@
 #include <linux/device.h>
 #include <linux/dca.h>
 
-#define DCA_VERSION "1.8"
+#define DCA_VERSION "1.12.1"
 
 MODULE_VERSION(DCA_VERSION);
 MODULE_LICENSE("GPL");
@@ -36,20 +36,92 @@ MODULE_AUTHOR("Intel Corporation");
 
 static DEFINE_SPINLOCK(dca_lock);
 
-static LIST_HEAD(dca_providers);
+static LIST_HEAD(dca_domains);
 
-static struct dca_provider *dca_find_provider_by_dev(struct device *dev)
+static struct pci_bus *dca_pci_rc_from_dev(struct device *dev)
 {
-	struct dca_provider *dca, *ret = NULL;
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct pci_bus *bus = pdev->bus;
 
-	list_for_each_entry(dca, &dca_providers, node) {
-		if ((!dev) || (dca->ops->dev_managed(dca, dev))) {
-			ret = dca;
-			break;
-		}
+	while (bus->parent)
+		bus = bus->parent;
+
+	return bus;
+}
+
+static struct dca_domain *dca_allocate_domain(struct pci_bus *rc)
+{
+	struct dca_domain *domain;
+
+	domain = kzalloc(sizeof(*domain), GFP_NOWAIT);
+	if (!domain)
+		return NULL;
+
+	INIT_LIST_HEAD(&domain->dca_providers);
+	domain->pci_rc = rc;
+
+	return domain;
+}
+
+static void dca_free_domain(struct dca_domain *domain)
+{
+	list_del(&domain->node);
+	kfree(domain);
+}
+
+static struct dca_domain *dca_find_domain(struct pci_bus *rc)
+{
+	struct dca_domain *domain;
+
+	list_for_each_entry(domain, &dca_domains, node)
+		if (domain->pci_rc == rc)
+			return domain;
+
+	return NULL;
+}
+
+static struct dca_domain *dca_get_domain(struct device *dev)
+{
+	struct pci_bus *rc;
+	struct dca_domain *domain;
+
+	rc = dca_pci_rc_from_dev(dev);
+	domain = dca_find_domain(rc);
+
+	if (!domain) {
+		domain = dca_allocate_domain(rc);
+		if (domain)
+			list_add(&domain->node, &dca_domains);
+	}
+
+	return domain;
+}
+
+static struct dca_provider *dca_find_provider_by_dev(struct device *dev)
+{
+	struct dca_provider *dca;
+	struct pci_bus *rc;
+	struct dca_domain *domain;
+
+	if (dev) {
+		rc = dca_pci_rc_from_dev(dev);
+		domain = dca_find_domain(rc);
+		if (!domain)
+			return NULL;
+	} else {
+		if (!list_empty(&dca_domains))
+			domain = list_first_entry(&dca_domains,
+						  struct dca_domain,
+						  node);
+		else
+			return NULL;
 	}
 
-	return ret;
+	list_for_each_entry(dca, &domain->dca_providers, node)
+		if ((!dev) || (dca->ops->dev_managed(dca, dev)))
+			return dca;
+
+	return NULL;
 }
 
 /**
@@ -61,6 +133,8 @@ int dca_add_requester(struct device *dev)
 	struct dca_provider *dca;
 	int err, slot = -ENODEV;
 	unsigned long flags;
+	struct pci_bus *pci_rc;
+	struct dca_domain *domain;
 
 	if (!dev)
 		return -EFAULT;
@@ -74,7 +148,14 @@ int dca_add_requester(struct device *dev)
 		return -EEXIST;
 	}
 
-	list_for_each_entry(dca, &dca_providers, node) {
+	pci_rc = dca_pci_rc_from_dev(dev);
+	domain = dca_find_domain(pci_rc);
+	if (!domain) {
+		spin_unlock_irqrestore(&dca_lock, flags);
+		return -ENODEV;
+	}
+
+	list_for_each_entry(dca, &domain->dca_providers, node) {
 		slot = dca->ops->add_requester(dca, dev);
 		if (slot >= 0)
 			break;
@@ -222,13 +303,19 @@ int register_dca_provider(struct dca_provider *dca, struct device *dev)
 {
 	int err;
 	unsigned long flags;
+	struct dca_domain *domain;
 
 	err = dca_sysfs_add_provider(dca, dev);
 	if (err)
 		return err;
 
 	spin_lock_irqsave(&dca_lock, flags);
-	list_add(&dca->node, &dca_providers);
+	domain = dca_get_domain(dev);
+	if (!domain) {
+		spin_unlock_irqrestore(&dca_lock, flags);
+		return -ENODEV;
+	}
+	list_add(&dca->node, &domain->dca_providers);
 	spin_unlock_irqrestore(&dca_lock, flags);
 
 	blocking_notifier_call_chain(&dca_provider_chain,
@@ -241,15 +328,24 @@ EXPORT_SYMBOL_GPL(register_dca_provider);
  * unregister_dca_provider - remove a dca provider
  * @dca - struct created by alloc_dca_provider()
  */
-void unregister_dca_provider(struct dca_provider *dca)
+void unregister_dca_provider(struct dca_provider *dca, struct device *dev)
 {
 	unsigned long flags;
+	struct pci_bus *pci_rc;
+	struct dca_domain *domain;
 
 	blocking_notifier_call_chain(&dca_provider_chain,
 				     DCA_PROVIDER_REMOVE, NULL);
 
 	spin_lock_irqsave(&dca_lock, flags);
+
 	list_del(&dca->node);
+
+	pci_rc = dca_pci_rc_from_dev(dev);
+	domain = dca_find_domain(pci_rc);
+	if (list_empty(&domain->dca_providers))
+		dca_free_domain(domain);
+
 	spin_unlock_irqrestore(&dca_lock, flags);
 
 	dca_sysfs_remove_provider(dca);
@@ -276,7 +372,7 @@ EXPORT_SYMBOL_GPL(dca_unregister_notify);
 
 static int __init dca_init(void)
 {
-	printk(KERN_ERR "dca service started, version %s\n", DCA_VERSION);
+	pr_info("dca service started, version %s\n", DCA_VERSION);
 	return dca_sysfs_init();
 }
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 81e1020fb51..5903a88351b 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -17,11 +17,15 @@ if DMADEVICES
 
 comment "DMA Devices"
 
+config ASYNC_TX_DISABLE_CHANNEL_SWITCH
+	bool
+
 config INTEL_IOATDMA
 	tristate "Intel I/OAT DMA support"
 	depends on PCI && X86
 	select DMA_ENGINE
 	select DCA
+	select ASYNC_TX_DISABLE_CHANNEL_SWITCH
 	help
 	  Enable support for the Intel(R) I/OAT DMA engine present
 	  in recent Intel Xeon chipsets.
@@ -97,6 +101,14 @@ config TXX9_DMAC
 	  Support the TXx9 SoC internal DMA controller.  This can be
 	  integrated in chips such as the Toshiba TX4927/38/39.
 
+config SH_DMAE
+	tristate "Renesas SuperH DMAC support"
+	depends on SUPERH && SH_DMA
+	depends on !SH_DMA_API
+	select DMA_ENGINE
+	help
+	  Enable support for the Renesas SuperH DMA controllers.
+
 config DMA_ENGINE
 	bool
 
@@ -116,7 +128,7 @@ config NET_DMA
 
 config ASYNC_TX_DMA
 	bool "Async_tx: Offload support for the async_tx api"
-	depends on DMA_ENGINE && !HIGHMEM64G
+	depends on DMA_ENGINE
 	help
 	  This allows the async_tx api to take advantage of offload engines for
 	  memcpy, memset, xor, and raid6 p+q operations.  If your platform has
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 40e1e008357..eca71ba78ae 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -1,8 +1,7 @@
 obj-$(CONFIG_DMA_ENGINE) += dmaengine.o
 obj-$(CONFIG_NET_DMA) += iovlock.o
 obj-$(CONFIG_DMATEST) += dmatest.o
-obj-$(CONFIG_INTEL_IOATDMA) += ioatdma.o
-ioatdma-objs := ioat.o ioat_dma.o ioat_dca.o
+obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-$(CONFIG_INTEL_IOP_ADMA) += iop-adma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_MV_XOR) += mv_xor.o
@@ -10,3 +9,4 @@ obj-$(CONFIG_DW_DMAC) += dw_dmac.o
 obj-$(CONFIG_AT_HDMAC) += at_hdmac.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
+obj-$(CONFIG_SH_DMAE) += shdma.o
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index c8522e6f1ad..7585c4164bd 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -87,6 +87,7 @@ static struct at_desc *atc_alloc_descriptor(struct dma_chan *chan,
 	desc = dma_pool_alloc(atdma->dma_desc_pool, gfp_flags, &phys);
 	if (desc) {
 		memset(desc, 0, sizeof(struct at_desc));
+		INIT_LIST_HEAD(&desc->tx_list);
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		/* txd.flags will be overwritten in prep functions */
 		desc->txd.flags = DMA_CTRL_ACK;
@@ -150,11 +151,11 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
 		struct at_desc *child;
 
 		spin_lock_bh(&atchan->lock);
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&atchan->chan_common),
 					"moving child desc %p to freelist\n",
 					child);
-		list_splice_init(&desc->txd.tx_list, &atchan->free_list);
+		list_splice_init(&desc->tx_list, &atchan->free_list);
 		dev_vdbg(chan2dev(&atchan->chan_common),
 			 "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &atchan->free_list);
@@ -247,30 +248,33 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	param = txd->callback_param;
 
 	/* move children to free_list */
-	list_splice_init(&txd->tx_list, &atchan->free_list);
+	list_splice_init(&desc->tx_list, &atchan->free_list);
 	/* move myself to free_list */
 	list_move(&desc->desc_node, &atchan->free_list);
 
 	/* unmap dma addresses */
-	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
-		if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
-			dma_unmap_single(chan2parent(&atchan->chan_common),
-					desc->lli.daddr,
-					desc->len, DMA_FROM_DEVICE);
-		else
-			dma_unmap_page(chan2parent(&atchan->chan_common),
-					desc->lli.daddr,
-					desc->len, DMA_FROM_DEVICE);
-	}
-	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
-		if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
-			dma_unmap_single(chan2parent(&atchan->chan_common),
-					desc->lli.saddr,
-					desc->len, DMA_TO_DEVICE);
-		else
-			dma_unmap_page(chan2parent(&atchan->chan_common),
-					desc->lli.saddr,
-					desc->len, DMA_TO_DEVICE);
+	if (!atchan->chan_common.private) {
+		struct device *parent = chan2parent(&atchan->chan_common);
+		if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP)) {
+			if (txd->flags & DMA_COMPL_DEST_UNMAP_SINGLE)
+				dma_unmap_single(parent,
+						desc->lli.daddr,
+						desc->len, DMA_FROM_DEVICE);
+			else
+				dma_unmap_page(parent,
+						desc->lli.daddr,
+						desc->len, DMA_FROM_DEVICE);
+		}
+		if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP)) {
+			if (txd->flags & DMA_COMPL_SRC_UNMAP_SINGLE)
+				dma_unmap_single(parent,
+						desc->lli.saddr,
+						desc->len, DMA_TO_DEVICE);
+			else
+				dma_unmap_page(parent,
+						desc->lli.saddr,
+						desc->len, DMA_TO_DEVICE);
+		}
 	}
 
 	/*
@@ -334,7 +338,7 @@ static void atc_cleanup_descriptors(struct at_dma_chan *atchan)
 			/* This one is currently in progress */
 			return;
 
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			if (!(child->lli.ctrla & ATC_DONE))
 				/* Currently in progress */
 				return;
@@ -407,7 +411,7 @@ static void atc_handle_error(struct at_dma_chan *atchan)
 	dev_crit(chan2dev(&atchan->chan_common),
 			"  cookie: %d\n", bad_desc->txd.cookie);
 	atc_dump_lli(atchan, &bad_desc->lli);
-	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &bad_desc->tx_list, desc_node)
 		atc_dump_lli(atchan, &child->lli);
 
 	/* Pretend the descriptor completed successfully */
@@ -587,7 +591,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			prev->lli.dscr = desc->txd.phys;
 			/* insert the link descriptor to the LD ring */
 			list_add_tail(&desc->desc_node,
-					&first->txd.tx_list);
+					&first->tx_list);
 		}
 		prev = desc;
 	}
@@ -646,8 +650,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 	reg_width = atslave->reg_width;
 
-	sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
-
 	ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
 	ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN;
 
@@ -687,7 +689,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				prev->lli.dscr = desc->txd.phys;
 				/* insert the link descriptor to the LD ring */
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
@@ -729,7 +731,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				prev->lli.dscr = desc->txd.phys;
 				/* insert the link descriptor to the LD ring */
 				list_add_tail(&desc->desc_node,
-						&first->txd.tx_list);
+						&first->tx_list);
 			}
 			prev = desc;
 			total_len += len;
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 4c972afc49e..495457e3dc4 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -165,6 +165,7 @@ struct at_desc {
 	struct at_lli			lli;
 
 	/* THEN values for driver housekeeping */
+	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	struct list_head		desc_node;
 	size_t				len;
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 5a87384ea4f..bd0b248de2c 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -608,6 +608,40 @@ void dmaengine_put(void)
 }
 EXPORT_SYMBOL(dmaengine_put);
 
+static bool device_has_all_tx_types(struct dma_device *device)
+{
+	/* A device that satisfies this test has channels that will never cause
+	 * an async_tx channel switch event as all possible operation types can
+	 * be handled.
+	 */
+	#ifdef CONFIG_ASYNC_TX_DMA
+	if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE)
+	if (!dma_has_cap(DMA_MEMCPY, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_MEMSET) || defined(CONFIG_ASYNC_MEMSET_MODULE)
+	if (!dma_has_cap(DMA_MEMSET, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE)
+	if (!dma_has_cap(DMA_XOR, device->cap_mask))
+		return false;
+	#endif
+
+	#if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE)
+	if (!dma_has_cap(DMA_PQ, device->cap_mask))
+		return false;
+	#endif
+
+	return true;
+}
+
 static int get_dma_id(struct dma_device *device)
 {
 	int rc;
@@ -644,8 +678,12 @@ 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) &&
@@ -661,6 +699,12 @@ int dma_async_device_register(struct dma_device *device)
 	BUG_ON(!device->device_issue_pending);
 	BUG_ON(!device->dev);
 
+	/* note: this only matters in the
+	 * CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH=y case
+	 */
+	if (device_has_all_tx_types(device))
+		dma_cap_set(DMA_ASYNC_TX, device->cap_mask);
+
 	idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
 	if (!idr_ref)
 		return -ENOMEM;
@@ -933,55 +977,29 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 {
 	tx->chan = chan;
 	spin_lock_init(&tx->lock);
-	INIT_LIST_HEAD(&tx->tx_list);
 }
 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 d93017fc787..a32a4cf7b1e 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -48,6 +48,11 @@ 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.
@@ -232,6 +237,7 @@ 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;
@@ -248,6 +254,11 @@ 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;
 
@@ -283,6 +294,7 @@ static int dmatest_func(void *data)
 		dma_addr_t dma_dsts[dst_cnt];
 		struct completion cmp;
 		unsigned long tmo = msecs_to_jiffies(3000);
+		u8 align = 0;
 
 		total_tests++;
 
@@ -290,6 +302,18 @@ static int dmatest_func(void *data)
 		src_off = dmatest_random() % (test_buf_size - len + 1);
 		dst_off = dmatest_random() % (test_buf_size - len + 1);
 
+		/* honor alignment restrictions */
+		if (thread->type == DMA_MEMCPY)
+			align = dev->copy_align;
+		else if (thread->type == DMA_XOR)
+			align = dev->xor_align;
+		else if (thread->type == DMA_PQ)
+			align = dev->pq_align;
+
+		len = (len >> align) << align;
+		src_off = (src_off >> align) << align;
+		dst_off = (dst_off >> align) << align;
+
 		dmatest_init_srcs(thread->srcs, src_off, len);
 		dmatest_init_dsts(thread->dsts, dst_off, len);
 
@@ -306,6 +330,7 @@ static int dmatest_func(void *data)
 						     DMA_BIDIRECTIONAL);
 		}
 
+
 		if (thread->type == DMA_MEMCPY)
 			tx = dev->device_prep_dma_memcpy(chan,
 							 dma_dsts[0] + dst_off,
@@ -316,6 +341,15 @@ 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++)
@@ -459,6 +493,8 @@ 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;
 
@@ -514,6 +550,10 @@ static int dmatest_add_channel(struct dma_chan *chan)
 		cnt = dmatest_add_threads(dtc, DMA_XOR);
 		thread_count += cnt > 0 ? cnt : 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/dw_dmac.c b/drivers/dma/dw_dmac.c
index 933c143b6a7..2eea823516a 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -116,7 +116,7 @@ static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
 	struct dw_desc	*child;
 
-	list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+	list_for_each_entry(child, &desc->tx_list, desc_node)
 		dma_sync_single_for_cpu(chan2parent(&dwc->chan),
 				child->txd.phys, sizeof(child->lli),
 				DMA_TO_DEVICE);
@@ -137,11 +137,11 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 		dwc_sync_desc_for_cpu(dwc, desc);
 
 		spin_lock_bh(&dwc->lock);
-		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
+		list_for_each_entry(child, &desc->tx_list, desc_node)
 			dev_vdbg(chan2dev(&dwc->chan),
 					"moving child desc %p to freelist\n",
 					child);
-		list_splice_init(&desc->txd.tx_list, &dwc->free_list);
+		list_splice_init(&desc->tx_list, &dwc->free_list);
 		dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
 		list_add(&desc->desc_node, &dwc->free_list);
 		spin_unlock_bh(&dwc->lock);
@@ -209,19 +209,28 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	param = txd->callback_param;
 
 	dwc_sync_desc_for_cpu(dwc, desc);
-	list_splice_init(&txd->tx_list, &dwc->free_list);
+	list_splice_init(&desc->tx_list, &dwc->free_list);
 	list_move(&desc->desc_node, &dwc->free_list);
 
-	/*
-	 * We use dma_unmap_page() regardless of how the buffers were
-	 * mapped before they were submitted...
-	 */
-	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.dar,
-			       desc->len, DMA_FROM_DEVICE);