Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: (22 commits)
  ioat: fix self test for multi-channel case
  dmaengine: bump initcall level to arch_initcall
  dmaengine: advertise all channels on a device to dma_filter_fn
  dmaengine: use idr for registering dma device numbers
  dmaengine: add a release for dma class devices and dependent infrastructure
  ioat: do not perform removal actions at shutdown
  iop-adma: enable module removal
  iop-adma: kill debug BUG_ON
  iop-adma: let devm do its job, don't duplicate free
  dmaengine: kill enum dma_state_client
  dmaengine: remove 'bigref' infrastructure
  dmaengine: kill struct dma_client and supporting infrastructure
  dmaengine: replace dma_async_client_register with dmaengine_get
  atmel-mci: convert to dma_request_channel and down-level dma_slave
  dmatest: convert to dma_request_channel
  dmaengine: introduce dma_request_channel and private channels
  net_dma: convert to dma_find_channel
  dmaengine: provide a common 'issue_pending_all' implementation
  dmaengine: centralize channel allocation, introduce dma_find_channel
  dmaengine: up-level reference counting to the module level
  ...

26 files changed, 900 insertions, 1260 deletions

diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt
index c1e9545..9f59fcb 100644
--- a/Documentation/crypto/async-tx-api.txt
+++ b/Documentation/crypto/async-tx-api.txt
@@ -13,9 +13,9 @@
 3.6 Constraints
 3.7 Example
 
-4 DRIVER DEVELOPER NOTES
+4 DMAENGINE DRIVER DEVELOPER NOTES
 4.1 Conformance points
-4.2 "My application needs finer control of hardware channels"
+4.2 "My application needs exclusive control of hardware channels"
 
 5 SOURCE
 
@@ -150,6 +150,7 @@ ops_run_* and ops_complete_* routines in drivers/md/raid5.c for more
 implementation examples.
 
 4 DRIVER DEVELOPMENT NOTES
+
 4.1 Conformance points:
 There are a few conformance points required in dmaengine drivers to
 accommodate assumptions made by applications using the async_tx API:
@@ -158,58 +159,49 @@ accommodate assumptions made by applications using the async_tx API:
 3/ Use async_tx_run_dependencies() in the descriptor clean up path to
    handle submission of dependent operations
 
-4.2 "My application needs finer control of hardware channels"
-This requirement seems to arise from cases where a DMA engine driver is
-trying to support device-to-memory DMA.  The dmaengine and async_tx
-implementations were designed for offloading memory-to-memory
-operations; however, there are some capabilities of the dmaengine layer
-that can be used for platform-specific channel management.
-Platform-specific constraints can be handled by registering the
-application as a 'dma_client' and implementing a 'dma_event_callback' to
-apply a filter to the available channels in the system.  Before showing
-how to implement a custom dma_event callback some background of
-dmaengine's client support is required.
-
-The following routines in dmaengine support multiple clients requesting
-use of a channel:
-- dma_async_client_register(struct dma_client *client)
-- dma_async_client_chan_request(struct dma_client *client)
-
-dma_async_client_register takes a pointer to an initialized dma_client
-structure.  It expects that the 'event_callback' and 'cap_mask' fields
-are already initialized.
-
-dma_async_client_chan_request triggers dmaengine to notify the client of
-all channels that satisfy the capability mask.  It is up to the client's
-event_callback routine to track how many channels the client needs and
-how many it is currently using.  The dma_event_callback routine returns a
-dma_state_client code to let dmaengine know the status of the
-allocation.
-
-Below is the example of how to extend this functionality for
-platform-specific filtering of the available channels beyond the
-standard capability mask:
-
-static enum dma_state_client
-my_dma_client_callback(struct dma_client *client,
-			struct dma_chan *chan, enum dma_state state)
-{
-	struct dma_device *dma_dev;
-	struct my_platform_specific_dma *plat_dma_dev;
-	
-	dma_dev = chan->device;
-	plat_dma_dev = container_of(dma_dev,
-				    struct my_platform_specific_dma,
-				    dma_dev);
-
-	if (!plat_dma_dev->platform_specific_capability)
-		return DMA_DUP;
-
-	. . .
-}
+4.2 "My application needs exclusive control of hardware channels"
+Primarily this requirement arises from cases where a DMA engine driver
+is being used to support device-to-memory operations.  A channel that is
+performing these operations cannot, for many platform specific reasons,
+be shared.  For these cases the dma_request_channel() interface is
+provided.
+
+The interface is:
+struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+				     dma_filter_fn filter_fn,
+				     void *filter_param);
+
+Where dma_filter_fn is defined as:
+typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+When the optional 'filter_fn' parameter is set to NULL
+dma_request_channel simply returns the first channel that satisfies the
+capability mask.  Otherwise, when the mask parameter is insufficient for
+specifying the necessary channel, the filter_fn routine can be used to
+disposition the available channels in the system. The filter_fn routine
+is called once for each free channel in the system.  Upon seeing a
+suitable channel filter_fn returns DMA_ACK which flags that channel to
+be the return value from dma_request_channel.  A channel allocated via
+this interface is exclusive to the caller, until dma_release_channel()
+is called.
+
+The DMA_PRIVATE capability flag is used to tag dma devices that should
+not be used by the general-purpose allocator.  It can be set at
+initialization time if it is known that a channel will always be
+private.  Alternatively, it is set when dma_request_channel() finds an
+unused "public" channel.
+
+A couple caveats to note when implementing a driver and consumer:
+1/ Once a channel has been privately allocated it will no longer be
+   considered by the general-purpose allocator even after a call to
+   dma_release_channel().
+2/ Since capabilities are specified at the device level a dma_device
+   with multiple channels will either have all channels public, or all
+   channels private.
 
 5 SOURCE
-include/linux/dmaengine.h: core header file for DMA drivers and clients
+
+include/linux/dmaengine.h: core header file for DMA drivers and api users
 drivers/dma/dmaengine.c: offload engine channel management routines
 drivers/dma/: location for offload engine drivers
 include/linux/async_tx.h: core header file for the async_tx api
diff --git a/Documentation/dmaengine.txt b/Documentation/dmaengine.txt
new file mode 100644
index 0000000..0c1c2f6
--- /dev/null
+++ b/Documentation/dmaengine.txt
@@ -0,0 +1 @@
+See Documentation/crypto/async-tx-api.txt
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index ea7bc1e..3fbfd1e 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -1305,7 +1305,7 @@ struct platform_device *__init
 at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 {
 	struct platform_device		*pdev;
-	struct dw_dma_slave		*dws;
+	struct dw_dma_slave		*dws = &data->dma_slave;
 	u32				pioa_mask;
 	u32				piob_mask;
 
@@ -1324,22 +1324,13 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 				ARRAY_SIZE(atmel_mci0_resource)))
 		goto fail;
 
-	if (data->dma_slave)
-		dws = kmemdup(to_dw_dma_slave(data->dma_slave),
-				sizeof(struct dw_dma_slave), GFP_KERNEL);
-	else
-		dws = kzalloc(sizeof(struct dw_dma_slave), GFP_KERNEL);
-
-	dws->slave.dev = &pdev->dev;
-	dws->slave.dma_dev = &dw_dmac0_device.dev;
-	dws->slave.reg_width = DMA_SLAVE_WIDTH_32BIT;
+	dws->dma_dev = &dw_dmac0_device.dev;
+	dws->reg_width = DW_DMA_SLAVE_WIDTH_32BIT;
 	dws->cfg_hi = (DWC_CFGH_SRC_PER(0)
 				| DWC_CFGH_DST_PER(1));
 	dws->cfg_lo &= ~(DWC_CFGL_HS_DST_POL
 				| DWC_CFGL_HS_SRC_POL);
 
-	data->dma_slave = &dws->slave;
-
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct mci_platform_data)))
 		goto fail;
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index dcbf1be..f21147f 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -28,351 +28,18 @@
 #include <linux/async_tx.h>
 
 #ifdef CONFIG_DMA_ENGINE
-static enum dma_state_client
-dma_channel_add_remove(struct dma_client *client,
-	struct dma_chan *chan, enum dma_state state);
-
-static struct dma_client async_tx_dma = {
-	.event_callback = dma_channel_add_remove,
-	/* .cap_mask == 0 defaults to all channels */
-};
-
-/**
- * dma_cap_mask_all - enable iteration over all operation types
- */
-static dma_cap_mask_t dma_cap_mask_all;
-
-/**
- * chan_ref_percpu - tracks channel allocations per core/opertion
- */
-struct chan_ref_percpu {
-	struct dma_chan_ref *ref;
-};
-
-static int channel_table_initialized;
-static struct chan_ref_percpu *channel_table[DMA_TX_TYPE_END];
-
-/**
- * async_tx_lock - protect modification of async_tx_master_list and serialize
- *	rebalance operations
- */
-static spinlock_t async_tx_lock;
-
-static LIST_HEAD(async_tx_master_list);
-
-/* async_tx_issue_pending_all - start all transactions on all channels */
-void async_tx_issue_pending_all(void)
-{
-	struct dma_chan_ref *ref;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ref, &async_tx_master_list, node)
-		ref->chan->device->device_issue_pending(ref->chan);
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(async_tx_issue_pending_all);
-
-/* dma_wait_for_async_tx - spin wait for a transcation to complete
- * @tx: transaction to wait on
- */
-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;
-
-	if (!tx)
-		return DMA_SUCCESS;
-
-	/* 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;
-}
-EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
-
-/* async_tx_run_dependencies - helper routine for dma drivers to process
- *	(start) dependent operations on their target channel
- * @tx: transaction with dependencies
- */
-void async_tx_run_dependencies(struct dma_async_tx_descriptor *tx)
-{
-	struct dma_async_tx_descriptor *dep = tx->next;
-	struct dma_async_tx_descriptor *dep_next;
-	struct dma_chan *chan;
-
-	if (!dep)
-		return;
-
-	chan = dep->chan;
-
-	/* keep submitting up until a channel switch is detected
-	 * in that case we will be called again as a result of
-	 * processing the interrupt from async_tx_channel_switch
-	 */
-	for (; dep; dep = dep_next) {
-		spin_lock_bh(&dep->lock);
-		dep->parent = NULL;
-		dep_next = dep->next;
-		if (dep_next && dep_next->chan == chan)
-			dep->next = NULL; /* ->next will be submitted */
-		else
-			dep_next = NULL; /* submit current dep and terminate */
-		spin_unlock_bh(&dep->lock);
-
-		dep->tx_submit(dep);
-	}
-
-	chan->device->device_issue_pending(chan);
-}
-EXPORT_SYMBOL_GPL(async_tx_run_dependencies);
-
-static void
-free_dma_chan_ref(struct rcu_head *rcu)
-{
-	struct dma_chan_ref *ref;
-	ref = container_of(rcu, struct dma_chan_ref, rcu);
-	kfree(ref);
-}
-
-static void
-init_dma_chan_ref(struct dma_chan_ref *ref, struct dma_chan *chan)
-{
-	INIT_LIST_HEAD(&ref->node);
-	INIT_RCU_HEAD(&ref->rcu);
-	ref->chan = chan;
-	atomic_set(&ref->count, 0);
-}
-
-/**
- * get_chan_ref_by_cap - returns the nth channel of the given capability
- * 	defaults to returning the channel with the desired capability and the
- * 	lowest reference count if the index can not be satisfied
- * @cap: capability to match
- * @index: nth channel desired, passing -1 has the effect of forcing the
- *  default return value
- */
-static struct dma_chan_ref *
-get_chan_ref_by_cap(enum dma_transaction_type cap, int index)
-{
-	struct dma_chan_ref *ret_ref = NULL, *min_ref = NULL, *ref;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ref, &async_tx_master_list, node)
-		if (dma_has_cap(cap, ref->chan->device->cap_mask)) {
-			if (!min_ref)
-				min_ref = ref;
-			else if (atomic_read(&ref->count) <
-				atomic_read(&min_ref->count))
-				min_ref = ref;
-
-			if (index-- == 0) {
-				ret_ref = ref;
-				break;
-			}
-		}
-	rcu_read_unlock();
-
-	if (!ret_ref)
-		ret_ref = min_ref;
-
-	if (ret_ref)
-		atomic_inc(&ret_ref->count);
-
-	return ret_ref;
-}
-
-/**
- * async_tx_rebalance - redistribute the available channels, optimize
- * for cpu isolation in the SMP case, and opertaion isolation in the
- * uniprocessor case
- */
-static void async_tx_rebalance(void)
-{
-	int cpu, cap, cpu_idx = 0;
-	unsigned long flags;
-
-	if (!channel_table_initialized)
-		return;
-
-	spin_lock_irqsave(&async_tx_lock, flags);
-
-	/* undo the last distribution */
-	for_each_dma_cap_mask(cap, dma_cap_mask_all)
-		for_each_possible_cpu(cpu) {
-			struct dma_chan_ref *ref =
-				per_cpu_ptr(channel_table[cap], cpu)->ref;
-			if (ref) {
-				atomic_set(&ref->count, 0);
-				per_cpu_ptr(channel_table[cap], cpu)->ref =
-									NULL;
-			}
-		}
-
-	for_each_dma_cap_mask(cap, dma_cap_mask_all)
-		for_each_online_cpu(cpu) {
-			struct dma_chan_ref *new;
-			if (NR_CPUS > 1)
-				new = get_chan_ref_by_cap(cap, cpu_idx++);
-			else
-				new = get_chan_ref_by_cap(cap, -1);
-
-			per_cpu_ptr(channel_table[cap], cpu)->ref = new;
-		}
-
-	spin_unlock_irqrestore(&async_tx_lock, flags);
-}
-
-static enum dma_state_client
-dma_channel_add_remove(struct dma_client *client,
-	struct dma_chan *chan, enum dma_state state)
-{
-	unsigned long found, flags;
-	struct dma_chan_ref *master_ref, *ref;
-	enum dma_state_client ack = DMA_DUP; /* default: take no action */
-
-	switch (state) {
-	case DMA_RESOURCE_AVAILABLE:
-		found = 0;
-		rcu_read_lock();
-		list_for_each_entry_rcu(ref, &async_tx_master_list, node)
-			if (ref->chan == chan) {
-				found = 1;
-				break;
-			}
-		rcu_read_unlock();
-
-		pr_debug("async_tx: dma resource available [%s]\n",
-			found ? "old" : "new");
-
-		if (!found)
-			ack = DMA_ACK;
-		else
-			break;
-
-		/* add the channel to the generic management list */
-		master_ref = kmalloc(sizeof(*master_ref), GFP_KERNEL);
-		if (master_ref) {
-			/* keep a reference until async_tx is unloaded */
-			dma_chan_get(chan);
-			init_dma_chan_ref(master_ref, chan);
-			spin_lock_irqsave(&async_tx_lock, flags);
-			list_add_tail_rcu(&master_ref->node,
-				&async_tx_master_list);
-			spin_unlock_irqrestore(&async_tx_lock,
-				flags);
-		} else {
-			printk(KERN_WARNING "async_tx: unable to create"
-				" new master entry in response to"
-				" a DMA_RESOURCE_ADDED event"
-				" (-ENOMEM)\n");
-			return 0;
-		}
-
-		async_tx_rebalance();
-		break;
-	case DMA_RESOURCE_REMOVED:
-		found = 0;
-		spin_lock_irqsave(&async_tx_lock, flags);
-		list_for_each_entry(ref, &async_tx_master_list, node)
-			if (ref->chan == chan) {
-				/* permit backing devices to go away */
-				dma_chan_put(ref->chan);
-				list_del_rcu(&ref->node);
-				call_rcu(&ref->rcu, free_dma_chan_ref);
-				found = 1;
-				break;
-			}
-		spin_unlock_irqrestore(&async_tx_lock, flags);
-
-		pr_debug("async_tx: dma resource removed [%s]\n",
-			found ? "ours" : "not ours");
-
-		if (found)
-			ack = DMA_ACK;
-		else
-			break;
-
-		async_tx_rebalance();
-		break;
-	case DMA_RESOURCE_SUSPEND:
-	case DMA_RESOURCE_RESUME:
-		printk(KERN_WARNING "async_tx: does not support dma channel"
-			" suspend/resume\n");
-		break;
-	default:
-		BUG();
-	}
-
-	return ack;
-}
-
-static int __init
-async_tx_init(void)
+static int __init async_tx_init(void)
 {
-	enum dma_transaction_type cap;
-
-	spin_lock_init(&async_tx_lock);
-	bitmap_fill(dma_cap_mask_all.bits, DMA_TX_TYPE_END);
-
-	/* an interrupt will never be an explicit operation type.
-	 * clearing this bit prevents allocation to a slot in 'channel_table'
-	 */
-	clear_bit(DMA_INTERRUPT, dma_cap_mask_all.bits);
-
-	for_each_dma_cap_mask(cap, dma_cap_mask_all) {
-		channel_table[cap] = alloc_percpu(struct chan_ref_percpu);
-		if (!channel_table[cap])
-			goto err;
-	}
-
-	channel_table_initialized = 1;
-	dma_async_client_register(&async_tx_dma);
-	dma_async_client_chan_request(&async_tx_dma);
+	dmaengine_get();
 
 	printk(KERN_INFO "async_tx: api initialized (async)\n");
 
 	return 0;
-err:
-	printk(KERN_ERR "async_tx: initialization failure\n");
-
-	while (--cap >= 0)
-		free_percpu(channel_table[cap]);
-
-	return 1;
 }
 
 static void __exit async_tx_exit(void)
 {
-	enum dma_transaction_type cap;
-
-	channel_table_initialized = 0;
-
-	for_each_dma_cap_mask(cap, dma_cap_mask_all)
-		if (channel_table[cap])
-			free_percpu(channel_table[cap]);
-
-	dma_async_client_unregister(&async_tx_dma);
+	dmaengine_put();
 }
 
 /**
@@ -387,16 +54,9 @@ __async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
 {
 	/* see if we can keep the chain on one channel */
 	if (depend_tx &&
-		dma_has_cap(tx_type, depend_tx->chan->device->cap_mask))
+	    dma_has_cap(tx_type, depend_tx->chan->device->cap_mask))
 		return depend_tx->chan;
-	else if (likely(channel_table_initialized)) {
-		struct dma_chan_ref *ref;
-		int cpu = get_cpu();
-		ref = per_cpu_ptr(channel_table[tx_type], cpu)->ref;
-		put_cpu();
-		return ref ? ref->chan : NULL;
-	} else
-		return NULL;
+	return dma_find_channel(tx_type);
 }
 EXPORT_SYMBOL_GPL(__async_tx_find_channel);
 #else
diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c
index d883e1b..5543384 100644
--- a/drivers/dca/dca-core.c
+++ b/drivers/dca/dca-core.c
@@ -270,6 +270,6 @@ static void __exit dca_exit(void)
 	dca_sysfs_exit();
 }
 
-subsys_initcall(dca_init);
+arch_initcall(dca_init);
 module_exit(dca_exit);
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 904e575..e34b064 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -33,7 +33,6 @@ config INTEL_IOATDMA
 config INTEL_IOP_ADMA
 	tristate "Intel IOP ADMA support"
 	depends on ARCH_IOP32X || ARCH_IOP33X || ARCH_IOP13XX
-	select ASYNC_CORE
 	select DMA_ENGINE
 	help
 	  Enable support for the Intel(R) IOP Series RAID engines.
@@ -59,7 +58,6 @@ config FSL_DMA
 config MV_XOR
 	bool "Marvell XOR engine support"
 	depends on PLAT_ORION
-	select ASYNC_CORE
 	select DMA_ENGINE
 	---help---
 	  Enable support for the Marvell XOR engine.
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 6579965..403dbe7 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -31,32 +31,18 @@
  *
  * LOCKING:
  *
- * The subsystem keeps two global lists, dma_device_list and dma_client_list.
- * Both of these are protected by a mutex, dma_list_mutex.
+ * The subsystem keeps a global list of dma_device structs it is protected by a
+ * mutex, dma_list_mutex.
+ *
+ * A subsystem can get access to a channel by calling dmaengine_get() followed
+ * by dma_find_channel(), or if it has need for an exclusive channel it can call
+ * dma_request_channel().  Once a channel is allocated a reference is taken
+ * against its corresponding driver to disable removal.
  *
  * Each device has a channels list, which runs unlocked but is never modified
  * once the device is registered, it's just setup by the driver.
  *
- * Each client is responsible for keeping track of the channels it uses.  See
- * the definition of dma_event_callback in dmaengine.h.
- *
- * Each device has a kref, which is initialized to 1 when the device is
- * registered. A kref_get is done for each device registered.  When the
- * device is released, the corresponding kref_put is done in the release
- * method. Every time one of the device's channels is allocated to a client,
- * a kref_get occurs.  When the channel is freed, the corresponding kref_put
- * happens. The device's release function does a completion, so
- * unregister_device does a remove event, device_unregister, a kref_put
- * for the first reference, then waits on the completion for all other
- * references to finish.
- *
- * Each channel has an open-coded implementation of Rusty Russell's "bigref,"
- * with a kref and a per_cpu local_t.  A dma_chan_get is called when a client
- * signals that it wants to use a channel, and dma_chan_put is called when
- * a channel is removed or a client using it is unregistered.  A client can
- * take extra references per outstanding transaction, as is the case with
- * the NET DMA client.  The release function does a kref_put on the device.
- *	-ChrisL, DanW
+ * See Documentation/dmaengine.txt for more details
  */
 
 #include <linux/init.h>
@@ -70,54 +56,85 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 #include <linux/jiffies.h>
+#include <linux/rculist.h>
+#include <linux/idr.h>
 
 static DEFINE_MUTEX(dma_list_mutex);
 static LIST_HEAD(dma_device_list);
-static LIST_HEAD(dma_client_list);
+static long dmaengine_ref_count;
+static struct idr dma_idr;
 
 /* --- sysfs implementation --- */
 
+/**
+ * dev_to_dma_chan - convert a device pointer to the its sysfs container object
+ * @dev - device node
+ *
+ * Must be called under dma_list_mutex
+ */
+static struct dma_chan *dev_to_dma_chan(struct device *dev)
+{
+	struct dma_chan_dev *chan_dev;
+
+	chan_dev = container_of(dev, typeof(*chan_dev), device);
+	return chan_dev->chan;
+}
+
 static ssize_t show_memcpy_count(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct dma_chan *chan = to_dma_chan(dev);
+	struct dma_chan *chan;
 	unsigned long count = 0;
 	int i;
+	int err;
 
-	for_each_possible_cpu(i)
-		count += per_cpu_ptr(chan->local, i)->memcpy_count;
+	mutex_lock(&dma_list_mutex);
+	chan = dev_to_dma_chan(dev);
+	if (chan) {
+		for_each_possible_cpu(i)
+			count += per_cpu_ptr(chan->local, i)->memcpy_count;
+		err = sprintf(buf, "%lu\n", count);
+	} else
+		err = -ENODEV;
+	mutex_unlock(&dma_list_mutex);
 
-	return sprintf(buf, "%lu\n", count);
+	return err;
 }
 
 static ssize_t show_bytes_transferred(struct device *dev, struct device_attribute *attr,
 				      char *buf)
 {
-	struct dma_chan *chan = to_dma_chan(dev);
+	struct dma_chan *chan;
 	unsigned long count = 0;
 	int i;
+	int err;
 
-	for_each_possible_cpu(i)
-		count += per_cpu_ptr(chan->local, i)->bytes_transferred;
+	mutex_lock(&dma_list_mutex);
+	chan = dev_to_dma_chan(dev);
+	if (chan) {
+		for_each_possible_cpu(i)
+			count += per_cpu_ptr(chan->local, i)->bytes_transferred;
+		err = sprintf(buf, "%lu\n", count);
+	} else
+		err = -ENODEV;
+	mutex_unlock(&dma_list_mutex);
 
-	return sprintf(buf, "%lu\n", count);
+	return err;
 }
 
 static ssize_t show_in_use(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	struct dma_chan *chan = to_dma_chan(dev);
-	int in_use = 0;
-
-	if (unlikely(chan->slow_ref) &&
-		atomic_read(&chan->refcount.refcount) > 1)
-		in_use = 1;
-	else {
-		if (local_read(&(per_cpu_ptr(chan->local,
-			get_cpu())->refcount)) > 0)
-			in_use = 1;
-		put_cpu();
-	}
+	struct dma_chan *chan;
+	int err;
 
-	return sprintf(buf, "%d\n", in_use);
+	mutex_lock(&dma_list_mutex);
+	chan = dev_to_dma_chan(dev);
+	if (chan)
+		err = sprintf(buf, "%d\n", chan->client_count);
+	else
+		err = -ENODEV;
+	mutex_unlock(&dma_list_mutex);
+
+	return err;
 }
 
 static struct device_attribute dma_attrs[] = {
@@ -127,76 +144,110 @@ static struct device_attribute dma_attrs[] = {
 	__ATTR_NULL
 };
 
-static void dma_async_device_cleanup(struct kref *kref);
-
-static void dma_dev_release(struct device *dev)
+static void chan_dev_release(struct device *dev)
 {
-	struct dma_chan *chan = to_dma_chan(dev);
-	kref_put(&chan->device->refcount, dma_async_device_cleanup);
+	struct dma_chan_dev *chan_dev;
+
+	chan_dev = container_of(dev, typeof(*chan_dev), device);
+	if (atomic_dec_and_test(chan_dev->idr_ref)) {
+		mutex_lock(&dma_list_mutex);
+		idr_remove(&dma_idr, chan_dev->dev_id);
+		mutex_unlock(&dma_list_mutex);
+		kfree(chan_dev->idr_ref);
+	}
+	kfree(chan_dev);
 }
 
 static struct class dma_devclass = {
 	.name		= "dma",
 	.dev_attrs	= dma_attrs,
-	.dev_release	= dma_dev_release,
+	.dev_release	= chan_dev_release,
 };
 
 /* --- client and device registration --- */
 
-#define dma_chan_satisfies_mask(chan, mask) \
-	__dma_chan_satisfies_mask((chan), &(mask))
+#define dma_device_satisfies_mask(device, mask) \
+	__dma_device_satisfies_mask((device), &(mask))
 static int
-__dma_chan_satisfies_mask(struct dma_chan *chan, dma_cap_mask_t *want)
+__dma_device_satisfies_mask(struct dma_device *device, dma_cap_mask_t *want)
 {
 	dma_cap_mask_t has;
 
-	bitmap_and(has.bits, want->bits, chan->device->cap_mask.bits,
+	bitmap_and(has.bits, want->bits, device->cap_mask.bits,
 		DMA_TX_TYPE_END);
 	return bitmap_equal(want->bits, has.bits, DMA_TX_TYPE_END);
 }
 
+static struct module *dma_chan_to_owner(struct dma_chan *chan)
+{
+	return chan->device->dev->driver->owner;
+}
+
 /**
- * dma_client_chan_alloc - try to allocate channels to a client
- * @client: &dma_client
+ * balance_ref_count - catch up the channel reference count
+ * @chan - channel to balance ->client_count versus dmaengine_ref_count
  *
- * Called with dma_list_mutex held.
+ * balance_ref_count must be called under dma_list_mutex
  */
-static void dma_client_chan_alloc(struct dma_client *client)
+static void balance_ref_count(struct dma_chan *chan)
 {
-	struct dma_device *device;
-	struct dma_chan *chan;
-	int desc;	/* allocated descriptor count */
-	enum dma_state_client ack;
+	struct module *owner = dma_chan_to_owner(chan);
 
-	/* Find a channel */
-	list_for_each_entry(device, &dma_device_list, global_node) {
-		/* Does the client require a specific DMA controller? */
-		if (client->slave && client->slave->dma_dev
-				&& client->slave->dma_dev != device->dev)
-			continue;
+	while (chan->client_count < dmaengine_ref_count) {
+		__module_get(owner);
+		chan->client_count++;
+	}
+}
 
-		list_for_each_entry(chan, &device->channels, device_node) {
-			if (!dma_chan_satisfies_mask(chan, client->cap_mask))
-				continue;
+/**
+ * dma_chan_get - try to grab a dma channel's parent driver module
+ * @chan - channel to grab
+ *
+ * Must be called under dma_list_mutex
+ */
+static int dma_chan_get(struct dma_chan *chan)
+{
+	int err = -ENODEV;
+	struct module *owner = dma_chan_to_owner(chan);
+
+	if (chan->client_count) {
+		__module_get(owner);
+		err = 0;
+	} else if (try_module_get(owner))
+		err = 0;
+
+	if (err == 0)
+		chan->client_count++;
+
+	/* allocate upon first client reference */
+	if (chan->client_count == 1 && err == 0) {
+		int desc_cnt = chan->device->device_alloc_chan_resources(chan);
+
+		if (desc_cnt < 0) {
+			err = desc_cnt;
+			chan->client_count = 0;
+			module_put(owner);
+		} else if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask))
+			balance_ref_count(chan);
+	}
 
-			desc = chan->device->device_alloc_chan_resources(
-					chan, client);
-			if (desc >= 0) {
-				ack = client->event_callback(client,
-						chan,
-						DMA_RESOURCE_AVAILABLE);
+	return err;
+}
 
-				/* we are done once this client rejects
-				 * an available resource
-				 */
-				if (ack == DMA_ACK) {
-					dma_chan_get(chan);
-					chan->client_count++;
-				} else if (ack == DMA_NAK)
-					return;
-			}
-		}
-	}
+/**
+ * dma_chan_put - drop a reference to a dma channel's parent driver module
+ * @chan - channel to release
+ *
+ * Must be called under dma_list_mutex
+ */
+static void dma_chan_put(struct dma_chan *chan)
+{
+	if (!chan->client_count)
+		return; /* this channel failed alloc_chan_resources */
+	chan->client_count--;
+	module_put(dma_chan_to_owner(chan));
+	if (chan->client_count == 0)
+		chan->device->device_free_chan_resources(chan);
 }
 
 enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
@@ -218,138 +269,342 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
 EXPORT_SYMBOL(dma_sync_wait);
 
 /**
- * dma_chan_cleanup - release a DMA channel's resources
- * @kref: kernel reference structure that contains the DMA channel device
+ * dma_cap_mask_all - enable iteration over all operation types
+ */
+static dma_cap_mask_t dma_cap_mask_all;
+
+/**
+ * dma_chan_tbl_ent - tracks channel allocations per core/operation
+ * @chan - associated channel for this entry
+ */
+struct dma_chan_tbl_ent {
+	struct dma_chan *chan;
+};
+
+/**
+ * channel_table - percpu lookup table for memory-to-memory offload providers
  */
-void dma_chan_cleanup(struct kref *kref)
+static struct dma_chan_tbl_ent *channel_table[DMA_TX_TYPE_END];
+
+static int __init dma_channel_table_init(void)
 {
-	struct dma_chan *chan = container_of(kref, struct dma_chan, refcount);
-	chan->device->device_free_chan_resources(chan);
-	kref_put(&chan->device->refcount, dma_async_device_cleanup);
+	enum dma_transaction_type cap;
+	int err = 0;
+
+	bitmap_fill(dma_cap_mask_all.bits, DMA_TX_TYPE_END);
+
+	/* 'interrupt', 'private', and 'slave' are channel capabilities,
+	 * but are not associated with an operation so they do not need
+	 * an entry in the channel_table
+	 */
+	clear_bit(DMA_INTERRUPT, dma_cap_mask_all.bits);
+	clear_bit(DMA_PRIVATE, dma_cap_mask_all.bits);
+	clear_bit(DMA_SLAVE, dma_cap_mask_all.bits);
+
+	for_each_dma_cap_mask(cap, dma_cap_mask_all) {
+		channel_table[cap] = alloc_percpu(struct dma_chan_tbl_ent);
+		if (!channel_table[cap]) {
+			err = -ENOMEM;
+			break;
+		}
+	}
+
+	if (err) {
+		pr_err("dmaengine: initialization failure\n");
+		for_each_dma_cap_mask(cap, dma_cap_mask_all)
+			if (channel_table[cap])
+				free_percpu(channel_table[cap]);
+	}
+
+	return err;
 }
-EXPORT_SYMBOL(dma_chan_cleanup);
+arch_initcall(dma_channel_table_init);
 
-static void dma_chan_free_rcu(struct rcu_head *rcu)
+/**
+ * dma_find_channel - find a channel to carry out the operation
+ * @tx_type: transaction type
+ */
+struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
 {
-	struct dma_chan *chan = container_of(rcu, struct dma_chan, rcu);
-	int bias = 0x7FFFFFFF;
-	int i;
-	for_each_possible_cpu(i)
-		bias -= local_read(&per_cpu_ptr(chan->local, i)->refcount);
-	atomic_sub(bias, &chan->refcount.refcount);
-	kref_put(&chan->refcount, dma_chan_cleanup);
+	struct dma_chan *chan;
+	int cpu;
+
+	WARN_ONCE(dmaengine_ref_count == 0,
+		  "client called %s without a reference", __func__);
+
+	cpu = get_cpu();
+	chan = per_cpu_ptr(channel_table[tx_type], cpu)->chan;
+	put_cpu();
+
+	return chan;
 }
+EXPORT_SYMBOL(dma_find_channel);
 
-static void dma_chan_release(struct dma_chan *chan)
+/**
+ * dma_issue_pending_all - flush all pending operations across all channels
+ */
+void dma_issue_pending_all(void)
 {
-	atomic_add(0x7FFFFFFF, &chan->refcount.refcount);
-	chan->slow_ref = 1;
-	call_rcu(&chan->rcu, dma_chan_free_rcu);
+	struct dma_device *device;
+	struct dma_chan *chan;
+
+	WARN_ONCE(dmaengine_ref_count == 0,
+		  "client called %s without a reference", __func__);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(device, &dma_device_list, global_node) {
+		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node)
+			if (chan->client_count)
+				device->device_issue_pending(chan);
+	}
+	rcu_read_unlock();
 }
+EXPORT_SYMBOL(dma_issue_pending_all);
 
 /**
- * dma_chans_notify_available - broadcast available channels to the clients
+ * nth_chan - returns the nth channel of the given capability
+ * @cap: capability to match
+ * @n: nth channel desired
+ *
+ * Defaults to returning the channel with the desired capability and the
+ * lowest reference count when 'n' cannot be satisfied.  Must be called
+ * under dma_list_mutex.
  */
-static void dma_clients_notify_available(void)
+static struct dma_chan *nth_chan(enum dma_transaction_type cap, int n)
 {
-	struct dma_client *client;
+	struct dma_device *device;
+	struct dma_chan *chan;
+	struct dma_chan *ret = NULL;
+	struct dma_chan *min = NULL;
 
-	mutex_lock(&dma_list_mutex);
+	list_for_each_entry(device, &dma_device_list, global_node) {
+		if (!dma_has_cap(cap, device->cap_mask) ||
+		    dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node) {
+			if (!chan->client_count)
+				continue;
+			if (!min)
+				min = chan;
+			else if (chan->table_count < min->table_count)
+				min = chan;
+
+			if (n-- == 0) {
+				ret = chan;
+				break; /* done */
+			}
+		}
+		if (ret)
+			break; /* done */
+	}
 
-	list_for_each_entry(client, &dma_client_list, global_node)
-		dma_client_chan_alloc(client);
+	if (!ret)
+		ret = min;
 
-	mutex_unlock(&dma_list_mutex);
+	if (ret)
+		ret->table_count++;
+
+	return ret;
 }
 
 /**
- * dma_chans_notify_available - tell the clients that a channel is going away
- * @chan: channel on its way out
+ * dma_channel_rebalance - redistribute the available channels
+ *
+ * Optimize for cpu isolation (each cpu gets a dedicated channel for an
+ * operation type) in the SMP case,  and operation isolation (avoid
+ * multi-tasking channels) in the non-SMP case.  Must be called under
+ * dma_list_mutex.
  */
-static void dma_clients_notify_removed(struct dma_chan *chan)
+static void dma_channel_rebalance(void)
 {
-	struct dma_client *client;
-	enum dma_state_client ack;
+	struct dma_chan *chan;
+	struct dma_device *device;
+	int cpu;
+	int cap;
+	int n;
 
-	mutex_lock(&dma_list_mutex);
+	/* undo the last distribution */
+	for_each_dma_cap_mask(cap, dma_cap_mask_all)
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(channel_table[cap], cpu)->chan = NULL;
+
+	list_for_each_entry(device, &dma_device_list, global_node) {
+		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node)
+			chan->table_count = 0;
+	}
 
-	list_for_each_entry(client, &dma_client_list, global_node) {
-		ack = client->event_callback(client, chan,
-				DMA_RESOURCE_REMOVED);
+	/* don't populate the channel_table if no clients are available */
+	if (!dmaengine_ref_count)
+		return;
 
-		/* client was holding resources for this channel so
-		 * free it
-		 */
-		if (ack == DMA_ACK) {
-			dma_chan_put(chan);
-			chan->client_count--;
+	/* redistribute available channels */
+	n = 0;
+	for_each_dma_cap_mask(cap, dma_cap_mask_all)
+		for_each_online_cpu(cpu) {
+			if (num_possible_cpus() > 1)
+				chan = nth_chan(cap, n++);
+			else
+				chan = nth_chan(cap, -1);
+
+			per_cpu_ptr(channel_table[cap], cpu)->chan = chan;
+		}
+}
+
+static struct dma_chan *private_candidate(dma_cap_mask_t *mask, struct dma_device *dev,
+					  dma_filter_fn fn, void *fn_param)
+{
+	struct dma_chan *chan;
+
+	if (!__dma_device_satisfies_mask(dev, mask)) {
+		pr_debug("%s: wrong capabilities\n", __func__);
+		return NULL;
+	}
+	/* devices with multiple channels need special handling as we need to
+	 * ensure that all channels are either private or public.
+	 */
+	if (dev->chancnt > 1 && !dma_has_cap(DMA_PRIVATE, dev->cap_mask))
+		list_for_each_entry(chan, &dev->channels, device_node) {
+			/* some channels are already publicly allocated */
+			if (chan->client_count)
+				return NULL;
 		}
+
+	list_for_each_entry(chan, &dev->channels, device_node) {
+		if (chan->client_count) {
+			pr_debug("%s: %s busy\n",
+				 __func__, dma_chan_name(chan));
+			continue;
+		}
+		if (fn && !fn(chan, fn_param)) {
+			pr_debug("%s: %s filter said false\n",
+				 __func__, dma_chan_name(chan));
+			continue;
+		}
+		return chan;
 	}
 
-	mutex_unlock(&dma_list_mutex);
+	return NULL;
 }
 
 /**
- * dma_async_client_register - register a &dma_client
- * @client: ptr to a client structure with valid 'event_callback' and 'cap_mask'
+ * dma_request_channel - try to allocate an exclusive channel
+ * @mask: capabilities that the channel must satisfy
+ * @fn: optional callback to disposition available channels
+ * @fn_param: opaque parameter to pass to dma_filter_fn
  */
-void dma_async_client_register(struct dma_client *client)
+struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param)
 {
-	/* validate client data */
-	BUG_ON(dma_has_cap(DMA_SLAVE, client->cap_mask) &&
-		!client->slave);
+	struct dma_device *device, *_d;
+	struct dma_chan *chan = NULL;
+	int err;
 
+	/* Find a channel */
+	mutex_lock(&dma_list_mutex);
+	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
+		chan = private_candidate(mask, device, fn, fn_param);
+		if (chan) {
+			/* Found a suitable channel, try to grab, prep, and
+			 * return it.  We first set DMA_PRIVATE to disable
+			 * balance_ref_count as this channel will not be
+			 * published in the general-purpose allocator
+			 */
+			dma_cap_set(DMA_PRIVATE, device->cap_mask);
+			err = dma_chan_get(chan);
+
+			if (err == -ENODEV) {
+				pr_debug("%s: %s module removed\n", __func__,
+					 dma_chan_name(chan));
+				list_del_rcu(&device->global_node);
+			} else if (err)
+				pr_err("dmaengine: failed to get %s: (%d)\n",
+				       dma_chan_name(chan), err);
+			else
+				break;
+			chan = NULL;
+		}
+	}
+	mutex_unlock(&dma_list_mutex);
+
+	pr_debug("%s: %s (%s)\n", __func__, chan ? "success" : "fail",
+		 chan ? dma_chan_name(chan) : NULL);
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(__dma_request_channel);
+
+void dma_release_channel(struct dma_chan *chan)
+{
 	mutex_lock(&dma_list_mutex);
-	list_add_tail(&client->global_node, &dma_client_list);
+	WARN_ONCE(chan->client_count != 1,
+		  "chan reference count %d != 1\n", chan->client_count);
+	dma_chan_put(chan);
 	mutex_unlock(&dma_list_mutex);
 }
-EXPORT_SYMBOL(dma_async_client_register);
+EXPORT_SYMBOL_GPL(dma_release_channel);
 
 /**
- * dma_async_client_unregister - unregister a client and free the &dma_client
- * @client: &dma_client to free
- *
- * Force frees any allocated DMA channels, frees the &dma_client memory
+ * dmaengine_get - register interest in dma_channels
  */
-void dma_async_client_unregister(struct dma_client *client)
+void dmaengine_get(void)
 {
-	struct dma_device *device;
+	struct dma_device *device, *_d;
 	struct dma_chan *chan;
-	enum dma_state_client ack;
-
-	if (!client)
-		return;
+	int err;
 
 	mutex_lock(&dma_list_mutex);
-	/* free all channels the client is holding */
-	list_for_each_entry(device, &dma_device_list, global_node)
-		list_for_each_entry(chan, &device->channels, device_node) {
-			ack = client->event_callback(client, chan,
-				DMA_RESOURCE_REMOVED);
+	dmaengine_ref_count++;
 
-			if (ack == DMA_ACK) {
-				dma_chan_put(chan);
-				chan->client_count--;
-			}
+	/* try to grab channels */
+	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
+		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node) {
+			err = dma_chan_get(chan);
+			if (err == -ENODEV) {
+				/* module removed before we could use it */
+				list_del_rcu(&device->global_node);
+				break;
+			} else if (err)
+				pr_err("dmaengine: failed to get %s: (%d)\n",
+				       dma_chan_name(chan), err);
 		}
+	}
 
-	list_del(&client->global_node);
+	/* if this is the first reference and there were channels
+	 * waiting we need to rebalance to get those channels
+	 * incorporated into the channel table
+	 */
+	if (dmaengine_ref_count == 1)
+		dma_channel_rebalance();
 	mutex_unlock(&dma_list_mutex);
 }
-EXPORT_SYMBOL(dma_async_client_unregister);
+EXPORT_SYMBOL(dmaengine_get);
 
 /**
- * dma_async_client_chan_request - send all available channels to the
- * client that satisfy the capability mask
- * @client - requester
+ * dmaengine_put - let dma drivers be removed when ref_count == 0
  */
-void dma_async_client_chan_request(struct dma_client *client)
+void dmaengine_put(void)
 {
+	struct dma_device *device;
+	struct dma_chan *chan;
+
 	mutex_lock(&dma_list_mutex);
-	dma_client_chan_alloc(client);
+	dmaengine_ref_count--;
+	BUG_ON(dmaengine_ref_count < 0);
+	/* drop channel references */
+	list_for_each_entry(device, &dma_device_list, global_node) {
+		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
+			continue;
+		list_for_each_entry(chan, &device->channels, device_node)
+			dma_chan_put(chan);
+	}
 	mutex_unlock(&dma_list_mutex);
 }
-EXPORT_SYMBOL(dma_async_client_chan_request);
+EXPORT_SYMBOL(dmaengine_put);
 
 /**
  * dma_async_device_register - registers DMA devices found
@@ -357,9 +612,9 @@ EXPORT_SYMBOL(dma_async_client_chan_request);
  */
 int dma_async_device_register(struct dma_device *device)
 {
-	static int id;
 	int chancnt = 0, rc;
 	struct dma_chan* chan;
+	atomic_t *idr_ref;
 
 	if (!device)
 		return -ENODEV;
@@ -386,57 +641,83 @@ int dma_async_device_register(struct dma_device *device)
 	BUG_ON(!device->device_issue_pending);
 	BUG_ON(!device->dev);
 
-	init_completion(&device->done);
-	kref_init(&device->refcount);
-
+	idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
+	if (!idr_ref)
+		return -ENOMEM;
+	atomic_set(idr_ref, 0);
+ idr_retry:
+	if (!idr_pre_get(&dma_idr, GFP_KERNEL))
+		return -ENOMEM;
 	mutex_lock(&dma_list_mutex);
-	device->dev_id = id++;
+	rc = idr_get_new(&dma_idr, NULL, &device->dev_id);
 	mutex_unlock(&dma_list_mutex);
+	if (rc == -EAGAIN)
+		goto idr_retry;
+	else if (rc != 0)
+		return rc;
 
 	/* represent channels in sysfs. Probably want devs too */
 	list_for_each_entry(chan, &device->channels, device_node) {
 		chan->local = alloc_percpu(typeof(*chan->local));
 		if (chan->local == NULL)
 			continue;
+		chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL);
+		if (chan->dev == NULL) {
+			free_percpu(chan->local);
+			continue;
+		}
 
 		chan->chan_id = chancnt++;
-		chan->dev.class = &dma_devclass;
-		chan->dev.parent = device->dev;
-		dev_set_name(&chan->dev, "dma%dchan%d",
+		chan->dev->device.class = &dma_devclass;
+		chan->dev->device.parent = device->dev;
+		chan->dev->chan = chan;
+		chan->dev->idr_ref = idr_ref;
+		chan->dev->dev_id = device->dev_id;
+		atomic_inc(idr_ref);
+		dev_set_name(&chan->dev->device, "dma%dchan%d",
 			     device->dev_id, chan->chan_id);
 
-		rc = device_register(&chan->dev);
+		rc = device_register(&chan->dev->device);
 		if (rc) {
-			chancnt--;
 			free_percpu(chan->local);
 			chan->local = NULL;
 			goto err_out;
 		}
-
-		/* One for the channel, one of the class device */
-		kref_get(&device->refcount);
-		kref_get(&device->refcount);
-		kref_init(&chan->refcount);
 		chan->client_count = 0;
-		chan->slow_ref = 0;
-		INIT_RCU_HEAD(&chan->rcu);
 	}
+	device->chancnt = chancnt;
 
 	mutex_lock(&dma_list_mutex);
-	list_add_tail(&device->global_node, &dma_device_list);
+	/* take references on public channels */
+	if (dmaengine_ref_count && !dma_has_cap(DMA_PRIVATE, device->cap_mask))
+		list_for_each_entry(chan, &device->channels, device_node) {
+			/* if clients are already waiting for channels we need
+			 * to take references on their behalf
+			 */
+			if (dma_chan_get(chan) == -ENODEV) {
+				/* note we can only get here for the first
+				 * channel as the remaining channels are
+				 * guaranteed to get a reference
+				 */
+				rc = -ENODEV;
+				mutex_unlock(&dma_list_mutex);
+				goto err_out;
+			}
+		}
+	list_add_tail_rcu(&device->global_node, &dma_device_list);
+	dma_channel_rebalance();
 	mutex_unlock(&dma_list_mutex);
 
-	dma_clients_notify_available();
-
 	return 0;
 
 err_out:
 	list_for_each_entry(chan, &device->channels, device_node) {
 		if (chan->local == NULL)
 			continue;
-		kref_put(&device->refcount, dma_async_device_cleanup);
-		device_unregister(&chan->dev);
-		chancnt--;
+		mutex_lock(&dma_list_mutex);
+		chan->dev->chan = NULL;
+		mutex_unlock(&dma_list_mutex);
+		device_unregister(&chan->dev->device);
 		free_percpu(chan->local);
 	}
 	return rc;
@@ -444,37 +725,30 @@ err_out:
 EXPORT_SYMBOL(dma_async_device_register);
 
 /**
- * dma_async_device_cleanup - function called when all references are released
- * @kref: kernel reference object
- */
-static void dma_async_device_cleanup(struct kref *kref)
-{
-	struct dma_device *device;
-
-	device = container_of(kref, struct dma_device, refcount);
-	complete(&device->done);
-}
-
-/**
- * dma_async_device_unregister - unregisters DMA devices
+ * dma_async_device_unregister - unregister a DMA device
  * @device: &dma_device
+ *
+ * This routine is called by dma driver exit routines, dmaengine holds module
+ * references to prevent it being called while channels are in use.
  */
 void dma_async_device_unregister(struct dma_device *device)
 {
 	struct dma_chan *chan;
 
 	mutex_lock(&dma_list_mutex);
-	list_del(&device->global_node);
+	list_del_rcu(&device->global_node);
+	dma_channel_rebalance();
 	mutex_unlock(&dma_list_mutex);
 
 	list_for_each_entry(chan, &device->channels, device_node) {
-		dma_clients_notify_removed(chan);
-		device_unregister(&chan->dev);
-		dma_chan_release(chan);
+		WARN_ONCE(chan->client_count,
+			  "%s called while %d clients hold a reference\n",
+			  __func__, chan->client_count);
+		mutex_lock(&dma_list_mutex);
+		chan->dev->chan = NULL;
+		mutex_unlock(&dma_list_mutex);
+		device_unregister(&chan->dev->device);
 	}
-
-	kref_put(&device->refcount, dma_async_device_cleanup);
-	wait_for_completion(&device->done);
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
@@ -626,10 +900,96 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 }
 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;
+
+	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;
+}
+EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);
+
+/* dma_run_dependencies - helper routine for dma drivers to process
+ *	(start) dependent operations on their target channel
+ * @tx: transaction with dependencies
+ */
+void dma_run_dependencies(struct dma_async_tx_descriptor *tx)
+{
+	struct dma_async_tx_descriptor *dep = tx->next;
+	struct dma_async_tx_descriptor *dep_next;
+	struct dma_chan *chan;
+
+	if (!dep)
+		return;
+
+	chan = dep->chan;
+
+	/* keep submitting up until a channel switch is detected
+	 * in that case we will be called again as a result of
+	 * processing the interrupt from async_tx_channel_switch
+	 */
+	for (; dep; dep = dep_next) {
+		spin_lock_bh(&dep->lock);
+		dep->parent = NULL;
+		dep_next = dep->next;
+		if (dep_next && dep_next->chan == chan)
+			dep->next = NULL; /* ->next will be submitted */
+		else
+			dep_next = NULL; /* submit current dep and terminate */
+		spin_unlock_bh(&dep->lock);
+
+		dep->tx_submit(dep);
+	}
+
+	chan->device->device_issue_pending(chan);
+}
+EXPORT_SYMBOL_GPL(dma_run_dependencies);
+
 static int __init dma_bus_init(void)
 {
+	idr_init(&dma_idr);
 	mutex_init(&dma_list_mutex);
 	return class_register(&dma_devclass);
 }
-subsys_initcall(dma_bus_init);
+arch_initcall(dma_bus_init);
+
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index ed9636b..3603f1e 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -35,7 +35,7 @@ MODULE_PARM_DESC(threads_per_chan,
 
 static unsigned int max_channels;
 module_param(max_channels, uint, S_IRUGO);
-MODULE_PARM_DESC(nr_channels,
+MODULE_PARM_DESC(max_channels,
 		"Maximum number of channels to use (default: all)");
 
 /*
@@ -71,7 +71,7 @@ struct dmatest_chan {
 
 /*
  * These are protected by dma_list_mutex since they're only used by
- * the DMA client event callback
+ * the DMA filter function callback
  */
 static LIST_HEAD(dmatest_channels);
 static unsigned int nr_channels;
@@ -80,7 +80,7 @@ static bool dmatest_match_channel(struct dma_chan *chan)
 {
 	if (test_channel[0] == '\0')
 		return true;
-	return strcmp(dev_name(&chan->dev), test_channel) == 0;
+	return strcmp(dma_chan_name(chan), test_channel) == 0;
 }
 
 static bool dmatest_match_device(struct dma_device *device)
@@ -215,7 +215,6 @@ static int dmatest_func(void *data)
 
 	smp_rmb();
 	chan = thread->chan;
-	dma_chan_get(chan);
 
 	while (!kthread_should_stop()) {
 		total_tests++;
@@ -293,7 +292,6 @@ static int dmatest_func(void *data)
 	}
 
 	ret = 0;
-	dma_chan_put(chan);
 	kfree(thread->dstbuf);
 err_dstbuf:
 	kfree(thread->srcbuf);
@@ -319,21 +317,16 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
 	kfree(dtc);
 }
 
-static enum dma_state_client dmatest_add_channel(struct dma_chan *chan)
+static int dmatest_add_channel(struct dma_chan *chan)
 {
 	struct dmatest_chan	*dtc;
 	struct dmatest_thread	*thread;
 	unsigned int		i;
 
-	/* Have we already been told about this channel? */
-	list_for_each_entry(dtc, &dmatest_channels, node)
-		if (dtc->chan == chan)
-			return DMA_DUP;
-
 	dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL);
 	if (!dtc) {
-		pr_warning("dmatest: No memory for %s\n", dev_name(&chan->dev));
-		return DMA_NAK;
+		pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan));
+		return -ENOMEM;
 	}
 
 	dtc->chan = chan;
@@ -343,16 +336,16 @@ static enum dma_state_client dmatest_add_channel(struct dma_chan *chan)
 		thread = kzalloc(sizeof(struct dmatest_thread), GFP_KERNEL);
 		if (!thread) {
 			pr_warning("dmatest: No memory for %s-test%u\n",
-				   dev_name(&chan->dev), i);
+				   dma_chan_name(chan), i);
 			break;
 		}
 		thread->chan = dtc->chan;
 		smp_wmb();
 		thread->task = kthread_run(dmatest_func, thread, "%s-test%u",
-				dev_name(&chan->dev), i);
+				dma_chan_name(chan), i);
 		if (IS_ERR(thread->task)) {
 			pr_warning("dmatest: Failed to run thread %s-test%u\n",
-					dev_name(&chan->dev), i);
+					dma_chan_name(chan), i);
 			kfree(thread);
 			break;
 		}
@@ -362,86 +355,62 @@ static enum dma_state_client dmatest_add_channel(struct dma_chan *chan)
 		list_add_tail(&thread->node, &dtc->threads);
 	}
 
-	pr_info("dmatest: Started %u threads using %s\n", i, dev_name(&chan->dev));
+	pr_info("dmatest: Started %u threads using %s\n", i, dma_chan_name(chan));
 
 	list_add_tail(&dtc->node, &dmatest_channels);
 	nr_channels++;
 
-	return DMA_ACK;
-}
-
-static enum dma_state_client dmatest_remove_channel(struct dma_chan *chan)
-{
-	struct dmatest_chan	*dtc, *_dtc;
-
-	list_for_each_entry_safe(dtc, _dtc, &dmatest_channels, node) {
-		if (dtc->chan == chan) {
-			list_del(&dtc->node);
-			dmatest_cleanup_channel(dtc);
-			pr_debug("dmatest: lost channel %s\n",
-					dev_name(&chan->dev));
-			return DMA_ACK;
-		}
-	}
-
-	return DMA_DUP;
+	return 0;
 }
 
-/*
- * Start testing threads as new channels are assigned to us, and kill
- * them when the channels go away.
- *
- * When we unregister the client, all channels are removed so this
- * will also take care of cleaning things up when the module is
- * unloaded.
- */
-static enum dma_state_client
-dmatest_event(struct dma_client *client, struct dma_chan *chan,
-		enum dma_state state)
+static bool filter(struct dma_chan *chan, void *param)
 {
-	enum dma_state_client	ack = DMA_NAK;
-
-	switch (state) {
-	case DMA_RESOURCE_AVAILABLE:
-		if (!dmatest_match_channel(chan)
-				|| !dmatest_match_device(chan->device))
-			ack = DMA_DUP;
-		else if (max_channels && nr_channels >= max_channels)
-			ack = DMA_NAK;
-		else
-			ack = dmatest_add_channel(chan);
-		break;
-
-	case DMA_RESOURCE_REMOVED:
-		ack = dmatest_remove_channel(chan);
-		break;
-
-	default:
-		pr_info("dmatest: Unhandled event %u (%s)\n",
-				state, dev_name(&chan->dev));
-		break;
-	}
-
-	return ack;
+	if (!dmatest_match_channel(chan) || !dmatest_match_device(chan->device))
+		return false;
+	else
+		return true;
 }
 
-static struct dma_client dmatest_client = {
-	.event_callback	= dmatest_event,
-};
-
 static int __init dmatest_init(void)
 {
-	dma_cap_set(DMA_MEMCPY, dmatest_client.cap_mask);
-	dma_async_client_register(&dmatest_client);
-	dma_async_client_chan_request(&dmatest_client);
+	dma_cap_mask_t mask;
+	struct dma_chan *chan;
+	int err = 0;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_MEMCPY, mask);
+	for (;;) {
+		chan = dma_request_channel(mask, filter, NULL);
+		if (chan) {
+			err = dmatest_add_channel(chan);
+			if (err == 0)
+				continue;
+			else {
+				dma_release_channel(chan);
+				break; /* add_channel failed, punt */
+			}
+		} else
+			break; /* no more channels available */
+		if (max_channels && nr_channels >= max_channels)
+			break; /* we have all we need */
+	}
 
-	return 0;
+	return err;
 }
-module_init(dmatest_init);
+/* when compiled-in wait for drivers to load first */
+late_initcall(dmatest_init);
 
 static void __exit dmatest_exit(void)
 {
-	dma_async_client_unregister(&dmatest_client);
+	struct dmatest_chan *dtc, *_dtc;
+
+	list_for_each_entry_safe(dtc, _dtc, &dmatest_channels, node) {
+		list_del(&dtc->node);
+		dmatest_cleanup_channel(dtc);
+		pr_debug("dmatest: dropped channel %s\n",
+			 dma_chan_name(dtc->chan));
+		dma_release_channel(dtc->chan);
+	}
 }
 module_exit(dmatest_exit);
 
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 0778d99..6b702cc 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -70,6 +70,15 @@
  * the controller, though.
  */
 
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+static struct device *chan2parent(struct dma_chan *chan)
+{
+	return chan->dev->device.parent;
+}
+
 static struct dw_desc *dwc_first_active(struct dw_dma_chan *dwc)
 {
 	return list_entry(dwc->active_list.next, struct dw_desc, desc_node);
@@ -93,12 +102,12 @@ static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
 			ret = desc;
 			break;
 		}
-		dev_dbg(&dwc->chan.dev, "desc %p not ACKed\n", desc);
+		dev_dbg(chan2dev(&dwc->chan), "desc %p not ACKed\n", desc);
 		i++;
 	}
 	spin_unlock_bh(&dwc->lock);
 
-	dev_vdbg(&dwc->chan.dev, "scanned %u descriptors on freelist\n", i);
+	dev_vdbg(chan2dev(&dwc->chan), "scanned %u descriptors on freelist\n", i);
 
 	return ret;
 }
@@ -108,10 +117,10 @@ 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)
-		dma_sync_single_for_cpu(dwc->chan.dev.parent,
+		dma_sync_single_for_cpu(chan2parent(&dwc->chan),
 				child->txd.phys, sizeof(child->lli),
 				DMA_TO_DEVICE);
-	dma_sync_single_for_cpu(dwc->chan.dev.parent,
+	dma_sync_single_for_cpu(chan2parent(&dwc->chan),
 			desc->txd.phys, sizeof(desc->lli),
 			DMA_TO_DEVICE);
 }
@@ -129,11 +138,11 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 
 		spin_lock_bh(&dwc->lock);
 		list_for_each_entry(child, &desc->txd.tx_list, desc_node)
-			dev_vdbg(&dwc->chan.dev,
+			dev_vdbg(chan2dev(&dwc->chan),
 					"moving child desc %p to freelist\n",
 					child);
 		list_splice_init(&desc->txd.tx_list, &dwc->free_list);
-		dev_vdbg(&dwc->chan.dev, "moving desc %p to freelist\n", desc);
+		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);
 	}
@@ -163,9 +172,9 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 
 	/* ASSERT:  channel is idle */
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
-		dev_err(&dwc->chan.dev,
+		dev_err(chan2dev(&dwc->chan),
 			"BUG: Attempted to start non-idle channel\n");
-		dev_err(&dwc->chan.dev,
+		dev_err(chan2dev(&dwc->chan),
 			"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
 			channel_readl(dwc, SAR),
 			channel_readl(dwc, DAR),
@@ -193,7 +202,7 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	void				*param;
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
 
-	dev_vdbg(&dwc->chan.dev, "descriptor %u complete\n", txd->cookie);
+	dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
 	dwc->completed = txd->cookie;
 	callback = txd->callback;
@@ -208,11 +217,11 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	 * mapped before they were submitted...
 	 */
 	if (!(txd->flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		dma_unmap_page(dwc->chan.dev.parent, desc->lli.dar, desc->len,
-				DMA_FROM_DEVICE);
+		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.dar,
+			       desc->len, DMA_FROM_DEVICE);
 	if (!(txd->flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		dma_unmap_page(dwc->chan.dev.parent, desc->lli.sar, desc->len,
-				DMA_TO_DEVICE);
+		dma_unmap_page(chan2parent(&dwc->chan), desc->lli.sar,
+			       desc->len, DMA_TO_DEVICE);
 
 	/*
 	 * The API requires that no submissions are done from a
@@ -228,7 +237,7 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	LIST_HEAD(list);
 
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
-		dev_err(&dwc->chan.dev,
+		dev_err(chan2dev(&dwc->chan),
 			"BUG: XFER bit set, but channel not idle!\n");
 
 		/* Try to continue after resetting the channel... */
@@ -273,7 +282,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		return;
 	}
 
-	dev_vdbg(&dwc->chan.dev, "scan_descriptors: llp=0x%x\n", llp);
+	dev_vdbg(chan2dev(&dwc->chan), "scan_descriptors: llp=0x%x\n", llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
 		if (desc->lli.llp == llp)
@@ -292,7 +301,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		dwc_descriptor_complete(dwc, desc);
 	}
 
-	dev_err(&dwc->chan.dev,
+	dev_err(chan2dev(&dwc->chan),
 		"BUG: All descriptors done, but channel not idle!\n");
 
 	/* Try to continue after resetting the channel... */
@@ -308,7 +317,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 
 static void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli)
 {
-	dev_printk(KERN_CRIT, &dwc->chan.dev,
+	dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
 			"  desc: s0x%x d0x%x l0x%x c0x%x:%x\n",
 			lli->sar, lli->dar, lli->llp,
 			lli->ctlhi, lli->ctllo);
@@ -342,9 +351,9 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	 * controller flagged an error instead of scribbling over
 	 * random memory locations.
 	 */
-	dev_printk(KERN_CRIT, &dwc->chan.dev,
+	dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
 			"Bad descriptor submitted for DMA!\n");
-	dev_printk(KERN_CRIT, &dwc->chan.dev,
+	dev_printk(KERN_CRIT, chan2dev(&dwc->chan),
 			"  cookie: %d\n", bad_desc->txd.cookie);
 	dwc_dump_lli(dwc, &bad_desc->lli);
 	list_for_each_entry(child, &bad_desc->txd.tx_list, desc_node)
@@ -442,12 +451,12 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
 	 * for DMA. But this is hard to do in a race-free manner.
 	 */
 	if (list_empty(&dwc->active_list)) {
-		dev_vdbg(&tx->chan->dev, "tx_submit: started %u\n",
+		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
 				desc->txd.cookie);
 		dwc_dostart(dwc, desc);
 		list_add_tail(&desc->desc_node, &dwc->active_list);
 	} else {
-		dev_vdbg(&tx->chan->dev, "tx_submit: queued %u\n",
+		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
 				desc->txd.cookie);
 
 		list_add_tail(&desc->desc_node, &dwc->queue);
@@ -472,11 +481,11 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	unsigned int		dst_width;
 	u32			ctllo;
 
-	dev_vdbg(&chan->dev, "prep_dma_memcpy d0x%x s0x%x l0x%zx f0x%lx\n",
+	dev_vdbg(chan2dev(chan), "prep_dma_memcpy d0x%x s0x%x l0x%zx f0x%lx\n",
 			dest, src, len, flags);
 
 	if (unlikely(!len)) {
-		dev_dbg(&chan->dev, "prep_dma_memcpy: length is zero!\n");
+		dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n");
 		return NULL;
 	}
 
@@ -516,7 +525,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			first = desc;
 		} else {
 			prev->lli.llp = desc->txd.phys;
-			dma_sync_single_for_device(chan->dev.parent,
+			dma_sync_single_for_device(chan2parent(chan),
 					prev->txd.phys, sizeof(prev->lli),
 					DMA_TO_DEVICE);
 			list_add_tail(&desc->desc_node,
@@ -531,7 +540,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		prev->lli.ctllo |= DWC_CTLL_INT_EN;
 
 	prev->lli.llp = 0;
-	dma_sync_single_for_device(chan->dev.parent,
+	dma_sync_single_for_device(chan2parent(chan),
 			prev->txd.phys, sizeof(prev->lli),
 			DMA_TO_DEVICE);
 
@@ -562,15 +571,15 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	struct scatterlist	*sg;
 	size_t			total_len = 0;
 
-	dev_vdbg(&chan->dev, "prep_dma_slave\n");
+	dev_vdbg(chan2dev(chan), "prep_dma_slave\n");
 
 	if (unlikely(!dws || !sg_len))
 		return NULL;
 
-	reg_width = dws->slave.reg_width;
+	reg_width = dws->reg_width;
 	prev = first = NULL;
 
-	sg_len = dma_map_sg(chan->dev.parent, sgl, sg_len, direction);
+	sg_len = dma_map_sg(chan2parent(chan), sgl, sg_len, direction);
 
 	switch (direction) {
 	case DMA_TO_DEVICE:
@@ -579,7 +588,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				| DWC_CTLL_DST_FIX
 				| DWC_CTLL_SRC_INC
 				| DWC_CTLL_FC_M2P);
-		reg = dws->slave.tx_reg;
+		reg = dws->tx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len;
@@ -587,7 +596,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 			desc = dwc_desc_get(dwc);
 			if (!desc) {
-				dev_err(&chan->dev,
+				dev_err(chan2dev(chan),
 					"not enough descriptors available\n");
 				goto err_desc_get;
 			}
@@ -607,7 +616,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				first = desc;
 			} else {
 				prev->lli.llp = desc->txd.phys;
-				dma_sync_single_for_device(chan->dev.parent,
+				dma_sync_single_for_device(chan2parent(chan),
 						prev->txd.phys,
 						sizeof(prev->lli),
 						DMA_TO_DEVICE);
@@ -625,7 +634,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				| DWC_CTLL_SRC_FIX
 				| DWC_CTLL_FC_P2M);
 
-		reg = dws->slave.rx_reg;
+		reg = dws->rx_reg;
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
 			u32		len;
@@ -633,7 +642,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 			desc = dwc_desc_get(dwc);
 			if (!desc) {
-				dev_err(&chan->dev,
+				dev_err(chan2dev(chan),
 					"not enough descriptors available\n");
 				goto err_desc_get;
 			}
@@ -653,7 +662,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 				first = desc;
 			} else {
 				prev->lli.llp = desc->txd.phys;
-				dma_sync_single_for_device(chan->dev.parent,
+				dma_sync_single_for_device(chan2parent(chan),
 						prev->txd.phys,
 						sizeof(prev->lli),
 						DMA_TO_DEVICE);
@@ -673,7 +682,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		prev->lli.ctllo |= DWC_CTLL_INT_EN;
 
 	prev->lli.llp = 0;
-	dma_sync_single_for_device(chan->dev.parent,
+	dma_sync_single_for_device(chan2parent(chan),
 			prev->txd.phys, sizeof(prev->lli),
 			DMA_TO_DEVICE);
 
@@ -758,29 +767,21 @@ static void dwc_issue_pending(struct dma_chan *chan)
 	spin_unlock_bh(&dwc->lock);
 }
 
-static int dwc_alloc_chan_resources(struct dma_chan *chan,
-		struct dma_client *client)
+static int dwc_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
 	struct dw_dma		*dw = to_dw_dma(chan->device);
 	struct dw_desc		*desc;
-	struct dma_slave	*slave;
 	struct dw_dma_slave	*dws;
 	int			i;
 	u32			cfghi;
 	u32			cfglo;
 
-	dev_vdbg(&chan->dev, "alloc_chan_resources\n");
-
-	/* Channels doing slave DMA can only handle one client. */
-	if (dwc->dws || client->slave) {
-		if (chan->client_count)
-			return -EBUSY;
-	}
+	dev_vdbg(chan2dev(chan), "alloc_chan_resources\n");
 
 	/* ASSERT:  channel is idle */
 	if (dma_readl(dw, CH_EN) & dwc->mask) {
-		dev_dbg(&chan->dev, "DMA channel not idle?\n");
+		dev_dbg(chan2dev(chan), "DMA channel not idle?\n");
 		return -EIO;
 	}
 
@@ -789,23 +790,17 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan,
 	cfghi = DWC_CFGH_FIFO_MODE;
 	cfglo = 0;
 
-	slave = client->slave;
-	if (slave) {
+	dws = dwc->dws;
+	if (dws) {
 		/*
 		 * We need controller-specific data to set up slave
 		 * transfers.
 		 */
-		BUG_ON(!slave->dma_dev || slave->dma_dev != dw->dma.dev);
-
-		dws = container_of(slave, struct dw_dma_slave, slave);
+		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
 
-		dwc->dws = dws;
 		cfghi = dws->cfg_hi;
 		cfglo = dws->cfg_lo;
-	} else {
-		dwc->dws = NULL;
 	}
-
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
 
@@ -822,7 +817,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan,
 
 		desc = kzalloc(sizeof(struct dw_desc), GFP_KERNEL);
 		if (!desc) {
-			dev_info(&chan->dev,
+			dev_info(chan2dev(chan),
 				"only allocated %d descriptors\n", i);
 			spin_lock_bh(&dwc->lock);
 			break;
@@ -832,7 +827,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan,
 		desc->txd.tx_submit = dwc_tx_submit;
 		desc->txd.flags = DMA_CTRL_ACK;
 		INIT_LIST_HEAD(&desc->txd.tx_list);
-		desc->txd.phys = dma_map_single(chan->dev.parent, &desc->lli,
+		desc->txd.phys = dma_map_single(chan2parent(chan), &desc->lli,
 				sizeof(desc->lli), DMA_TO_DEVICE);
 		dwc_desc_put(dwc, desc);
 
@@ -847,7 +842,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan,
 
 	spin_unlock_bh(&dwc->lock);
 
-	dev_dbg(&chan->dev,
+	dev_dbg(chan2dev(chan),
 		"alloc_chan_resources allocated %d descriptors\n", i);
 
 	return i;
@@ -860,7 +855,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	struct dw_desc		*desc, *_desc;
 	LIST_HEAD(list);
 
-	dev_dbg(&chan->dev, "free_chan_resources (descs allocated=%u)\n",
+	dev_dbg(chan2dev(chan), "free_chan_resources (descs allocated=%u)\n",
 			dwc->descs_allocated);
 
 	/* ASSERT:  channel is idle */
@@ -881,13 +876,13 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	spin_unlock_bh(&dwc->lock);
 
 	list_for_each_entry_safe(desc, _desc, &list, desc_node) {
-		dev_vdbg(&chan->dev, "  freeing descriptor %p\n", desc);
-		dma_unmap_single(chan->dev.parent, desc->txd.phys,
+		dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
+		dma_unmap_single(chan2parent(chan), desc->txd.phys,
 				sizeof(desc->lli), DMA_TO_DEVICE);
 		kfree(desc);
 	}
 
-	dev_vdbg(&chan->dev, "free_chan_resources done\n");
+	dev_vdbg(chan2dev(chan), "free_chan_resources done\n");
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 0b95dcc..ca70a21 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -366,8 +366,7 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
  *
  * Return - The number of descriptors allocated.
  */
-static int fsl_dma_alloc_chan_resources(struct dma_chan *chan,
-					struct dma_client *client)
+static int fsl_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct fsl_dma_chan *fsl_chan = to_fsl_chan(chan);
 
@@ -823,7 +822,7 @@ static int __devinit fsl_dma_chan_probe(struct fsl_dma_device *fdev,
 	 */
 	WARN_ON(fdev->feature != new_fsl_chan->feature);
 
-	new_fsl_chan->dev = &new_fsl_chan->common.dev;
+	new_fsl_chan->dev = &new_fsl_chan->common.dev->device;
 	new_fsl_chan->reg_base = ioremap(new_fsl_chan->reg.start,
 			new_fsl_chan->reg.end - new_fsl_chan->reg.start + 1);
 
diff --git a/drivers/dma/ioat.c b/drivers/dma/ioat.c
index 9b16a3a..4105d65 100644
--- a/drivers/dma/ioat.c
+++ b/drivers/dma/ioat.c
@@ -75,60 +75,10 @@ static int ioat_dca_enabled = 1;
 module_param(ioat_dca_enabled, int, 0644);
 MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
 
-static int ioat_setup_functionality(struct pci_dev *pdev, void __iomem *iobase)
-{
-	struct ioat_device *device = pci_get_drvdata(pdev);
-	u8 version;
-	int err = 0;
-
-	version = readb(iobase + IOAT_VER_OFFSET);
-	switch (version) {
-	case IOAT_VER_1_2:
-		device->dma = ioat_dma_probe(pdev, iobase);
-		if (device->dma && ioat_dca_enabled)
-			device->dca = ioat_dca_init(pdev, iobase);
-		break;
-	case IOAT_VER_2_0:
-		device->dma = ioat_dma_probe(pdev, iobase);
-		if (device->dma && ioat_dca_enabled)
-			device->dca = ioat2_dca_init(pdev, iobase);
-		break;
-	case IOAT_VER_3_0:
-		device->dma = ioat_dma_probe(pdev, iobase);
-		if (device->dma && ioat_dca_enabled)
-			device->dca = ioat3_dca_init(pdev, iobase);
-		break;
-	default:
-		err = -ENODEV;
-		break;
-	}
-	if (!device->dma)
-		err = -ENODEV;
-	return err;
-}
-
-static void ioat_shutdown_functionality(struct pci_dev *pdev)
-{
-	struct ioat_device *device = pci_get_drvdata(pdev);
-
-	dev_err(&pdev->dev, "Removing dma and dca services\n");
-	if (device->dca) {
-		unregister_dca_provider(device->dca);
-		free_dca_provider(device->dca);
-		device->dca = NULL;
-	}
-
-	if (device->dma) {
-		ioat_dma_remove(device->dma);
-		device->dma = NULL;
-	}
-}
-
 static struct pci_driver ioat_pci_driver = {
 	.name		= "ioatdma",
 	.id_table	= ioat_pci_tbl,
 	.probe		= ioat_probe,
-	.shutdown	= ioat_shutdown_functionality,
 	.remove		= __devexit_p(ioat_remove),
 };
 
@@ -179,7 +129,29 @@ static int __devinit ioat_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	err = ioat_setup_functionality(pdev, iobase);
+	switch (readb(iobase + IOAT_VER_OFFSET)) {
+	case IOAT_VER_1_2:
+		device->dma = ioat_dma_probe(pdev, iobase);
+		if (device->dma && ioat_dca_enabled)
+			device->dca = ioat_dca_init(pdev, iobase);
+		break;
+	case IOAT_VER_2_0:
+		device->dma = ioat_dma_probe(pdev, iobase);
+		if (device->dma && ioat_dca_enabled)
+			device->dca = ioat2_dca_init(pdev, iobase);
+		break;
+	case IOAT_VER_3_0:
+		device->dma = ioat_dma_probe(pdev, iobase);
+		if (device->dma && ioat_dca_enabled)
+			device->dca = ioat3_dca_init(pdev, iobase);
+		break;
+	default:
+		err = -ENODEV;
+		break;
+	}
+	if (!device->dma)
+		err = -ENODEV;
+
 	if (err)
 		goto err_version;
 
@@ -198,17 +170,21 @@ err_enable_device:
 	return err;
 }
 
-/*
- * It is unsafe to remove this module: if removed while a requested
- * dma is outstanding, esp. from tcp, it is possible to hang while
- * waiting for something that will never finish.  However, if you're
- * feeling lucky, this usually works just fine.
- */
 static void __devexit ioat_remove(struct pci_dev *pdev)
 {
 	struct ioat_device *device = pci_get_drvdata(pdev);
 
-	ioat_shutdown_functionality(pdev);
+	dev_err(&pdev->dev, "Removing dma and dca services\n");
+	if (device->dca) {
+		unregister_dca_provider(device->dca);
+		free_dca_provider(device->dca);
+		device->dca = NULL;
+	}
+
+	if (device->dma) {
+		ioat_dma_remove(device->dma);
+		device->dma = NULL;
+	}
 
 	kfree(device);
 }
diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c
index 6607fdd..b3759c4 100644
--- a/drivers/dma/ioat_dma.c
+++ b/drivers/dma/ioat_dma.c
@@ -734,8 +734,7 @@ static void ioat2_dma_massage_chan_desc(struct ioat_dma_chan *ioat_chan)
  * ioat_dma_alloc_chan_resources - returns the number of allocated descriptors
  * @chan: the channel to be filled out
  */
-static int ioat_dma_alloc_chan_resources(struct dma_chan *chan,
-					 struct dma_client *client)
+static int ioat_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
 	struct ioat_desc_sw *desc;
@@ -1341,12 +1340,11 @@ static void ioat_dma_start_null_desc(struct ioat_dma_chan *ioat_chan)
  */
 #define IOAT_TEST_SIZE 2000
 
-DECLARE_COMPLETION(test_completion);
 static void ioat_dma_test_callback(void *dma_async_param)
 {
-	printk(KERN_ERR "ioatdma: ioat_dma_test_callback(%p)\n",
-		dma_async_param);
-	complete(&test_completion);
+	struct completion *cmp = dma_async_param;
+
+	complete(cmp);
 }
 
 /**
@@ -1363,6 +1361,7 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	dma_addr_t dma_dest, dma_src;
 	dma_cookie_t cookie;
 	int err = 0;
+	struct completion cmp;
 
 	src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
 	if (!src)
@@ -1381,7 +1380,7 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	dma_chan = container_of(device->common.channels.next,
 				struct dma_chan,
 				device_node);
-	if (device->common.device_alloc_chan_resources(dma_chan, NULL) < 1) {
+	if (device->common.device_alloc_chan_resources(dma_chan) < 1) {
 		dev_err(&device->pdev->dev,
 			"selftest cannot allocate chan resource\n");
 		err = -ENODEV;
@@ -1402,8 +1401,9 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	}
 
 	async_tx_ack(tx);
+	init_completion(&cmp);
 	tx->callback = ioat_dma_test_callback;
-	tx->callback_param = (void *)0x8086;
+	tx->callback_param = &cmp;
 	cookie = tx->tx_submit(tx);
 	if (cookie < 0) {
 		dev_err(&device->pdev->dev,
@@ -1413,7 +1413,7 @@ static int ioat_dma_self_test(struct ioatdma_device *device)
 	}
 	device->common.device_issue_pending(dma_chan);
 
-	wait_for_completion_timeout(&test_completion, msecs_to_jiffies(3000));
+	wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
 
 	if (device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL)
 					!= DMA_SUCCESS) {
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 6be3172..ea5440d 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -24,7 +24,6 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/async_tx.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/spinlock.h>
@@ -116,7 +115,7 @@ iop_adma_run_tx_complete_actions(struct iop_adma_desc_slot *desc,
 	}
 
 	/* run dependent operations */
-	async_tx_run_dependencies(&desc->async_tx);
+	dma_run_dependencies(&desc->async_tx);
 
 	return cookie;
 }
@@ -270,8 +269,6 @@ static void __iop_adma_slot_cleanup(struct iop_adma_chan *iop_chan)
 			break;
 	}
 
-	BUG_ON(!seen_current);
-
 	if (cookie > 0) {
 		iop_chan->completed_cookie = cookie;
 		pr_debug("\tcompleted cookie %d\n", cookie);
@@ -471,8 +468,7 @@ static void iop_chan_start_null_xor(struct iop_adma_chan *iop_chan);
  * greater than 2x the number slots needed to satisfy a device->max_xor
  * request.
  * */
-static int iop_adma_alloc_chan_resources(struct dma_chan *chan,
-					 struct dma_client *client)
+static int iop_adma_alloc_chan_resources(struct dma_chan *chan)
 {
 	char *hw_desc;
 	int idx;
@@ -866,7 +862,7 @@ static int __devinit iop_adma_memcpy_self_test(struct iop_adma_device *device)
 	dma_chan = container_of(device->common.channels.next,
 				struct dma_chan,
 				device_node);
-	if (iop_adma_alloc_chan_resources(dma_chan, NULL) < 1) {
+	if (iop_adma_alloc_chan_resources(dma_chan) < 1) {
 		err = -ENODEV;
 		goto out;
 	}
@@ -964,7 +960,7 @@ iop_adma_xor_zero_sum_self_test(struct iop_adma_device *device)
 	dma_chan = container_of(device->common.channels.next,
 				struct dma_chan,
 				device_node);
-	if (iop_adma_alloc_chan_resources(dma_chan, NULL) < 1) {
+	if (iop_adma_alloc_chan_resources(dma_chan) < 1) {
 		err = -ENODEV;
 		goto out;
 	}
@@ -1115,26 +1111,13 @@ static int __devexit iop_adma_remove(struct platform_device *dev)
 	struct iop_adma_device *device = platform_get_drvdata(dev);
 	struct dma_chan *chan, *_chan;
 	struct iop_adma_chan *iop_chan;
-	int i;
 	struct iop_adma_platform_data *plat_data = dev->dev.platform_data;
 
 	dma_async_device_unregister(&device->common);
 
-	for (i = 0; i < 3; i++) {
-		unsigned int irq;
-		irq = platform_get_irq(dev, i);
-		free_irq(irq, device);
-	}
-
 	dma_free_coherent(&dev->dev, plat_data->pool_size,
 			device->dma_desc_pool_virt, device->dma_desc_pool);
 
-	do {
-		struct resource *res;
-		res = platform_get_resource(dev, IORESOURCE_MEM, 0);
-		release_mem_region(res->start, res->end - res->start);
-	} while (0);
-
 	list_for_each_entry_safe(chan, _chan, &device->common.channels,
 				device_node) {
 		iop_chan = to_iop_adma_chan(chan);
@@ -1255,7 +1238,6 @@ static int __devinit iop_adma_probe(struct platform_device *pdev)
 	spin_lock_init(&iop_chan->lock);
 	INIT_LIST_HEAD(&iop_chan->chain);
 	INIT_LIST_HEAD(&iop_chan->all_slots);
-	INIT_RCU_HEAD(&iop_chan->common.rcu);
 	iop_chan->common.device = dma_dev;
 	list_add_tail(&iop_chan->common.device_node, &dma_dev->channels);
 
@@ -1431,16 +1413,12 @@ static int __init iop_adma_init (void)
 	return platform_driver_register(&iop_adma_driver);
 }
 
-/* it's currently unsafe to unload this module */
-#if 0
 static void __exit iop_adma_exit (void)
 {
 	platform_driver_unregister(&iop_adma_driver);
 	return;
 }
 module_exit(iop_adma_exit);
-#endif
-
 module_init(iop_adma_init);
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index bcda174..d35cbd1 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -18,7 +18,6 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/async_tx.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/spinlock.h>
@@ -340,7 +339,7 @@ mv_xor_run_tx_complete_actions(struct mv_xor_desc_slot *desc,
 	}
 
 	/* run dependent operations */
-	async_tx_run_dependencies(&desc->async_tx);
+	dma_run_dependencies(&desc->async_tx);
 
 	return cookie;
 }
@@ -607,8 +606,7 @@ submit_done:
 }
 
 /* returns the number of allocated descriptors */
-static int mv_xor_alloc_chan_resources(struct dma_chan *chan,
-				       struct dma_client *client)
+static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 {
 	char *hw_desc;
 	int idx;
@@ -958,7 +956,7 @@ static int __devinit mv_xor_memcpy_self_test(struct mv_xor_device *device)
 	dma_chan = container_of(device->common.channels.next,
 				struct dma_chan,
 				device_node);
-	if (mv_xor_alloc_chan_resources(dma_chan, NULL) < 1) {
+	if (mv_xor_alloc_chan_resources(dma_chan) < 1) {
 		err = -ENODEV;
 		goto out;
 	}
@@ -1053,7 +1051,7 @@ mv_xor_xor_self_test(struct mv_xor_device *device)
 	dma_chan = container_of(device->common.channels.next,
 				struct dma_chan,
 				device_node);
-	if (mv_xor_alloc_chan_resources(dma_chan, NULL) < 1) {
+	if (mv_xor_alloc_chan_resources(dma_chan) < 1) {
 		err = -ENODEV;
 		goto out;
 	}
@@ -1221,7 +1219,6 @@ static int __devinit mv_xor_probe(struct platform_device *pdev)
 	INIT_LIST_HEAD(&mv_chan->chain);
 	INIT_LIST_HEAD(&mv_chan->completed_slots);
 	INIT_LIST_HEAD(&mv_chan->all_slots);
-	INIT_RCU_HEAD(&mv_chan->common.rcu);
 	mv_chan->common.device = dma_dev;
 
 	list_add_tail(&mv_chan->common.device_node, &dma_dev->channels);
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 1e97916..76bfe16 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -55,7 +55,6 @@ enum atmel_mci_state {
 
 struct atmel_mci_dma {
 #ifdef CONFIG_MMC_ATMELMCI_DMA
-	struct dma_client		client;
 	struct dma_chan			*chan;
 	struct dma_async_tx_descriptor	*data_desc;
 #endif
@@ -593,10 +592,8 @@ atmci_submit_data_dma(struct atmel_mci *host, struct mmc_data *data)
 
 	/* If we don't have a channel, we can't do DMA */
 	chan = host->dma.chan;
-	if (chan) {
-		dma_chan_get(chan);
+	if (chan)
 		host->data_chan = chan;
-	}
 
 	if (!chan)
 		return -ENODEV;
@@ -1443,60 +1440,6 @@ static irqreturn_t atmci_detect_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-#ifdef CONFIG_MMC_ATMELMCI_DMA
-
-static inline struct atmel_mci *
-dma_client_to_atmel_mci(struct dma_client *client)
-{
-	return container_of(client, struct atmel_mci, dma.client);
-}
-
-static enum dma_state_client atmci_dma_event(struct dma_client *client,
-		struct dma_chan *chan, enum dma_state state)
-{
-	struct atmel_mci	*host;
-	enum dma_state_client	ret = DMA_NAK;
-
-	host = dma_client_to_atmel_mci(client);
-
-	switch (state) {
-	case DMA_RESOURCE_AVAILABLE:
-		spin_lock_bh(&host->lock);
-		if (!host->dma.chan) {
-			host->dma.chan = chan;
-			ret = DMA_ACK;
-		}
-		spin_unlock_bh(&host->lock);
-
-		if (ret == DMA_ACK)
-			dev_info(&host->pdev->dev,
-					"Using %s for DMA transfers\n",
-					chan->dev.bus_id);
-		break;
-
-	case DMA_RESOURCE_REMOVED:
-		spin_lock_bh(&host->lock);
-		if (host->dma.chan == chan) {
-			host->dma.chan = NULL;
-			ret = DMA_ACK;
-		}
-		spin_unlock_bh(&host->lock);
-
-		if (ret == DMA_ACK)
-			dev_info(&host->pdev->dev,
-					"Lost %s, falling back to PIO\n",
-					chan->dev.bus_id);
-		break;
-
-	default:
-		break;
-	}
-
-
-	return ret;
-}
-#endif /* CONFIG_MMC_ATMELMCI_DMA */
-
 static int __init atmci_init_slot(struct atmel_mci *host,
 		struct mci_slot_pdata *slot_data, unsigned int id,
 		u32 sdc_reg)
@@ -1600,6 +1543,18 @@ static void __exit atmci_cleanup_slot(struct atmel_mci_slot *slot,
 	mmc_free_host(slot->mmc);
 }
 
+#ifdef CONFIG_MMC_ATMELMCI_DMA
+static bool filter(struct dma_chan *chan, void *slave)
+{
+	struct dw_dma_slave *dws = slave;
+
+	if (dws->dma_dev == chan->device->dev)
+		return true;
+	else
+		return false;
+}
+#endif
+
 static int __init atmci_probe(struct platform_device *pdev)
 {
 	struct mci_platform_data	*pdata;
@@ -1652,22 +1607,20 @@ static int __init atmci_probe(struct platform_device *pdev)
 		goto err_request_irq;
 
 #ifdef CONFIG_MMC_ATMELMCI_DMA
-	if (pdata->dma_slave) {
-		struct dma_slave *slave = pdata->dma_slave;
+	if (pdata->dma_slave.dma_dev) {
+		struct dw_dma_slave *dws = &pdata->dma_slave;
+		dma_cap_mask_t mask;
 
-		slave->tx_reg = regs->start + MCI_TDR;
-		slave->rx_reg = regs->start + MCI_RDR;
+		dws->tx_reg = regs->start + MCI_TDR;
+		dws->rx_reg = regs->start + MCI_RDR;
 
 		/* Try to grab a DMA channel */
-		host->dma.client.event_callback = atmci_dma_event;
-		dma_cap_set(DMA_SLAVE, host->dma.client.cap_mask);
-		host->dma.client.slave = slave;
-
-		dma_async_client_register(&host->dma.client);
-		dma_async_client_chan_request(&host->dma.client);
-	} else {
-		dev_notice(&pdev->dev, "DMA not available, using PIO\n");
+		dma_cap_zero(mask);
+		dma_cap_set(DMA_SLAVE, mask);
+		host->dma.chan = dma_request_channel(mask, filter, dws);
 	}
+	if (!host->dma.chan)
+		dev_notice(&pdev->dev, "DMA not available, using PIO\n");
 #endif /* CONFIG_MMC_ATMELMCI_DMA */
 
 	platform_set_drvdata(pdev, host);
@@ -1699,8 +1652,8 @@ static int __init atmci_probe(struct platform_device *pdev)
 
 err_init_slot:
 #ifdef CONFIG_MMC_ATMELMCI_DMA
-	if (pdata->dma_slave)
-		dma_async_client_unregister(&host->dma.client);
+	if (host->dma.chan)
+		dma_release_channel(host->dma.chan);
 #endif
 	free_irq(irq, host);
 err_request_irq:
@@ -1731,8 +1684,8 @@ static int __exit atmci_remove(struct platform_device *pdev)
 	clk_disable(host->mck);
 
 #ifdef CONFIG_MMC_ATMELMCI_DMA
-	if (host->dma.client.slave)
-		dma_async_client_unregister(&host->dma.client);
+	if (host->dma.chan)
+		dma_release_channel(host->dma.chan);
 #endif
 
 	free_irq(platform_get_irq(pdev, 0), host);
@@ -1761,7 +1714,7 @@ static void __exit atmci_exit(void)
 	platform_driver_unregister(&atmci_driver);
 }
 
-module_init(atmci_init);
+late_initcall(atmci_init); /* try to load after dma driver when built-in */
 module_exit(atmci_exit);
 
 MODULE_DESCRIPTION("Atmel Multimedia Card Interface driver");
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 0f50d4c..45f6297 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -59,9 +59,7 @@ enum async_tx_flags {
 };
 
 #ifdef CONFIG_DMA_ENGINE
-void async_tx_issue_pending_all(void);
-enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx);
-void async_tx_run_dependencies(struct dma_async_tx_descriptor *tx);
+#define async_tx_issue_pending_all dma_issue_pending_all
 #ifdef CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL
 #include <asm/async_tx.h>
 #else
@@ -77,19 +75,6 @@ static inline void async_tx_issue_pending_all(void)
 	do { } while (0);
 }
 
-static inline enum dma_status
-dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
-{
-	return DMA_SUCCESS;
-}
-
-static inline void
-async_tx_run_dependencies(struct dma_async_tx_descriptor *tx,
-	struct dma_chan *host_chan)
-{
-	do { } while (0);
-}
-
 static inline struct dma_chan *
 async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
 	enum dma_transaction_type tx_type, struct page **dst, int dst_count,
diff --git a/include/linux/atmel-mci.h b/include/linux/atmel-mci.h
index 2a2213e..2f1f957 100644
--- a/include/linux/atmel-mci.h
+++ b/include/linux/atmel-mci.h
@@ -3,7 +3,7 @@
 
 #define ATMEL_MCI_MAX_NR_SLOTS	2
 
-struct dma_slave;
+#include <linux/dw_dmac.h>
 
 /**
  * struct mci_slot_pdata - board-specific per-slot configuration
@@ -28,11 +28,11 @@ struct mci_slot_pdata {
 
 /**
  * struct mci_platform_data - board-specific MMC/SDcard configuration
- * @dma_slave: DMA slave interface to use in data transfers, or NULL.
+ * @dma_slave: DMA slave interface to use in data transfers.
  * @slot: Per-slot configuration data.
  */
 struct mci_platform_data {
-	struct dma_slave	*dma_slave;
+	struct dw_dma_slave	dma_slave;
 	struct mci_slot_pdata	slot[ATMEL_MCI_MAX_NR_SLOTS];
 };
 
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index adb0b08..64dea2a 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -29,32 +29,6 @@
 #include <linux/dma-mapping.h>
 
 /**
- * enum dma_state - resource PNP/power management state
- * @DMA_RESOURCE_SUSPEND: DMA device going into low power state
- * @DMA_RESOURCE_RESUME: DMA device returning to full power
- * @DMA_RESOURCE_AVAILABLE: DMA device available to the system
- * @DMA_RESOURCE_REMOVED: DMA device removed from the system
- */
-enum dma_state {
-	DMA_RESOURCE_SUSPEND,
-	DMA_RESOURCE_RESUME,
-	DMA_RESOURCE_AVAILABLE,
-	DMA_RESOURCE_REMOVED,
-};
-
-/**
- * enum dma_state_client - state of the channel in the client
- * @DMA_ACK: client would like to use, or was using this channel
- * @DMA_DUP: client has already seen this channel, or is not using this channel
- * @DMA_NAK: client does not want to see any more channels
- */
-enum dma_state_client {
-	DMA_ACK,
-	DMA_DUP,
-	DMA_NAK,
-};
-
-/**
  * typedef dma_cookie_t - an opaque DMA cookie
  *
  * if dma_cookie_t is >0 it's a DMA request cookie, <0 it's an error code
@@ -89,23 +63,13 @@ enum dma_transaction_type {
 	DMA_MEMSET,
 	DMA_MEMCPY_CRC32C,
 	DMA_INTERRUPT,
+	DMA_PRIVATE,
 	DMA_SLAVE,
 };
 
 /* last transaction type for creation of the capabilities mask */
 #define DMA_TX_TYPE_END (DMA_SLAVE + 1)
 
-/**
- * enum dma_slave_width - DMA slave register access width.
- * @DMA_SLAVE_WIDTH_8BIT: Do 8-bit slave register accesses
- * @DMA_SLAVE_WIDTH_16BIT: Do 16-bit slave register accesses
- * @DMA_SLAVE_WIDTH_32BIT: Do 32-bit slave register accesses
- */
-enum dma_slave_width {
-	DMA_SLAVE_WIDTH_8BIT,
-	DMA_SLAVE_WIDTH_16BIT,
-	DMA_SLAVE_WIDTH_32BIT,
-};
 
 /**
  * enum dma_ctrl_flags - DMA flags to augment operation preparation,
@@ -132,32 +96,6 @@ enum dma_ctrl_flags {
 typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t;
 
 /**
- * struct dma_slave - Information about a DMA slave
- * @dev: device acting as DMA slave
- * @dma_dev: required DMA master device. If non-NULL, the client can not be
- *	bound to other masters than this.
- * @tx_reg: physical address of data register used for
- *	memory-to-peripheral transfers
- * @rx_reg: physical address of data register used for
- *	peripheral-to-memory transfers
- * @reg_width: peripheral register width
- *
- * If dma_dev is non-NULL, the client can not be bound to other DMA
- * masters than the one corresponding to this device. The DMA master
- * driver may use this to determine if there is controller-specific
- * data wrapped around this struct. Drivers of platform code that sets
- * the dma_dev field must therefore make sure to use an appropriate
- * controller-specific dma slave structure wrapping this struct.
- */
-struct dma_slave {
-	struct device		*dev;
-	struct device		*dma_dev;
-	dma_addr_t		tx_reg;
-	dma_addr_t		rx_reg;
-	enum dma_slave_width	reg_width;
-};
-
-/**
  * struct dma_chan_percpu - the per-CPU part of struct dma_chan
  * @refcount: local_t used for open-coded "bigref" counting
  * @memcpy_count: transaction counter
@@ -165,7 +103,6 @@ struct dma_slave {
  */
 
 struct dma_chan_percpu {
-	local_t refcount;
 	/* stats */
 	unsigned long memcpy_count;
 	unsigned long bytes_transferred;
@@ -176,13 +113,14 @@ struct dma_chan_percpu {
  * @device: ptr to the dma device who supplies this channel, always !%NULL
  * @cookie: last cookie value returned to client
  * @chan_id: channel ID for sysfs
- * @class_dev: class device for sysfs
+ * @dev: class device for sysfs
  * @refcount: kref, used in "bigref" slow-mode
  * @slow_ref: indicates that the DMA channel is free
  * @rcu: the DMA channel's RCU head
  * @device_node: used to add this to the device chan list
  * @local: per-cpu pointer to a struct dma_chan_percpu
  * @client-count: how many clients are using this channel
+ * @table_count: number of appearances in the mem-to-mem allocation table
  */
 struct dma_chan {
 	struct dma_device *device;
@@ -190,73 +128,47 @@ struct dma_chan {
 
 	/* sysfs */
 	int chan_id;
-	struct device dev;
-
-	struct kref refcount;
-	int slow_ref;
-	struct rcu_head rcu;
+	struct dma_chan_dev *dev;
 
 	struct list_head device_node;
 	struct dma_chan_percpu *local;
 	int client_count;
+	int table_count;
 };
 
-#define to_dma_chan(p) container_of(p, struct dma_chan, dev)
-
-void dma_chan_cleanup(struct kref *kref);
-
-static inline void dma_chan_get(struct dma_chan *chan)
-{
-	if (unlikely(chan->slow_ref))
-		kref_get(&chan->refcount);
-	else {
-		local_inc(&(per_cpu_ptr(chan->local, get_cpu())->refcount));
-		put_cpu();
-	}
-}
+/**
+ * struct dma_chan_dev - relate sysfs device node to backing channel device
+ * @chan - driver channel device
+ * @device - sysfs device
+ * @dev_id - parent dma_device dev_id
+ * @idr_ref - reference count to gate release of dma_device dev_id
+ */
+struct dma_chan_dev {
+	struct dma_chan *chan;
+	struct device device;
+	int dev_id;
+	atomic_t *idr_ref;
+};
 
-static inline void dma_chan_put(struct dma_chan *chan)
+static inline const char *dma_chan_name(struct dma_chan *chan)
 {
-	if (unlikely(chan->slow_ref))
-		kref_put(&chan->refcount, dma_chan_cleanup);
-	else {
-		local_dec(&(per_cpu_ptr(chan->local, get_cpu())->refcount));
-		put_cpu();
-	}
+	return dev_name(&chan->dev->device);
 }
 
-/*
- * typedef dma_event_callback - function pointer to a DMA event callback
- * For each channel added to the system this routine is called for each client.
- * If the client would like to use the channel it returns '1' to signal (ack)
- * the dmaengine core to take out a reference on the channel and its
- * corresponding device.  A client must not 'ack' an available channel more
- * than once.  When a channel is removed all clients are notified.  If a client
- * is using the channel it must 'ack' the removal.  A client must not 'ack' a
- * removed channel more than once.
- * @client - 'this' pointer for the client context
- * @chan - channel to be acted upon
- * @state - available or removed
- */
-struct dma_client;
-typedef enum dma_state_client (*dma_event_callback) (struct dma_client *client,
-		struct dma_chan *chan, enum dma_state state);
+void dma_chan_cleanup(struct kref *kref);
 
 /**
- * struct dma_client - info on the entity making use of DMA services
- * @event_callback: func ptr to call when something happens
- * @cap_mask: only return channels that satisfy the requested capabilities
- *  a value of zero corresponds to any capability
- * @slave: data for preparing slave transfer. Must be non-NULL iff the
- *  DMA_SLAVE capability is requested.
- * @global_node: list_head for global dma_client_list
+ * typedef dma_filter_fn - callback filter for dma_request_channel
+ * @chan: channel to be reviewed
+ * @filter_param: opaque parameter passed through dma_request_channel
+ *
+ * When this optional parameter is specified in a call to dma_request_channel a
+ * suitable channel is passed to this routine for further dispositioning before
+ * being returned.  Where 'suitable' indicates a non-busy channel that
+ * satisfies the given capability mask.  It returns 'true' to indicate that the
+ * channel is suitable.
  */
-struct dma_client {
-	dma_event_callback	event_callback;
-	dma_cap_mask_t		cap_mask;
-	struct dma_slave	*slave;
-	struct list_head	global_node;
-};
+typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
 
 typedef void (*dma_async_tx_callback)(void *dma_async_param);
 /**
@@ -323,14 +235,10 @@ struct dma_device {
 	dma_cap_mask_t  cap_mask;
 	int max_xor;
 
-	struct kref refcount;
-	struct completion done;
-
 	int dev_id;
 	struct device *dev;
 
-	int (*device_alloc_chan_resources)(struct dma_chan *chan,
-			struct dma_client *client);
+	int (*device_alloc_chan_resources)(struct dma_chan *chan);
 	void (*device_free_chan_resources)(struct dma_chan *chan);
 
 	struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)(
@@ -362,9 +270,8 @@ struct dma_device {
 
 /* --- public DMA engine API --- */
 
-void dma_async_client_register(struct dma_client *client);
-void dma_async_client_unregister(struct dma_client *client);
-void dma_async_client_chan_request(struct dma_client *client);
+void dmaengine_get(void);
+void dmaengine_put(void);
 dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
 	void *dest, void *src, size_t len);
 dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan,
@@ -406,6 +313,12 @@ __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
 	set_bit(tx_type, dstp->bits);
 }
 
+#define dma_cap_zero(mask) __dma_cap_zero(&(mask))
+static inline void __dma_cap_zero(dma_cap_mask_t *dstp)
+{
+	bitmap_zero(dstp->bits, DMA_TX_TYPE_END);
+}
+
 #define dma_has_cap(tx, mask) __dma_has_cap((tx), &(mask))
 static inline int
 __dma_has_cap(enum dma_transaction_type tx_type, dma_cap_mask_t *srcp)
@@ -475,11 +388,25 @@ static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie,
 }
 
 enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie);
+#ifdef CONFIG_DMA_ENGINE
+enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx);
+#else
+static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
+{
+	return DMA_SUCCESS;
+}
+#endif
 
 /* --- DMA device --- */
 
 int dma_async_device_register(struct dma_device *device);
 void dma_async_device_unregister(struct dma_device *device);
+void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
+struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type);
+void dma_issue_pending_all(void);
+#define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y)
+struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param);
+void dma_release_channel(struct dma_chan *chan);
 
 /* --- Helper iov-locking functions --- */
 
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index 04d217b..d797dde 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -22,14 +22,34 @@ struct dw_dma_platform_data {
 };
 
 /**
+ * enum dw_dma_slave_width - DMA slave register access width.
+ * @DMA_SLAVE_WIDTH_8BIT: Do 8-bit slave register accesses
+ * @DMA_SLAVE_WIDTH_16BIT: Do 16-bit slave register accesses
+ * @DMA_SLAVE_WIDTH_32BIT: Do 32-bit slave register accesses
+ */
+enum dw_dma_slave_width {
+	DW_DMA_SLAVE_WIDTH_8BIT,
+	DW_DMA_SLAVE_WIDTH_16BIT,
+	DW_DMA_SLAVE_WIDTH_32BIT,
+};
+
+/**
  * struct dw_dma_slave - Controller-specific information about a slave
- * @slave: Generic information about the slave
- * @ctl_lo: Platform-specific initializer for the CTL_LO register
+ *
+ * @dma_dev: required DMA master device
+ * @tx_reg: physical address of data register used for
+ *	memory-to-peripheral transfers
+ * @rx_reg: physical address of data register used for
+ *	peripheral-to-memory transfers
+ * @reg_width: peripheral register width
  * @cfg_hi: Platform-specific initializer for the CFG_HI register
  * @cfg_lo: Platform-specific initializer for the CFG_LO register
  */
 struct dw_dma_slave {
-	struct dma_slave	slave;
+	struct device		*dma_dev;
+	dma_addr_t		tx_reg;
+	dma_addr_t		rx_reg;
+	enum dw_dma_slave_width	reg_width;
 	u32			cfg_hi;
 	u32			cfg_lo;
 };
@@ -54,9 +74,4 @@ struct dw_dma_slave {
 #define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
 #define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
 
-static inline struct dw_dma_slave *to_dw_dma_slave(struct dma_slave *slave)
-{
-	return container_of(slave, struct dw_dma_slave, slave);
-}
-
 #endif /* DW_DMAC_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 114091b..f245568 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1125,9 +1125,6 @@ struct softnet_data
 	struct sk_buff		*completion_queue;
 
 	struct napi_struct	backlog;
-#ifdef CONFIG_NET_DMA
-	struct dma_chan		*net_dma;
-#endif
 };
 
 DECLARE_PER_CPU(struct softnet_data,softnet_data);
diff --git a/include/net/netdma.h b/include/net/netdma.h
index f28c6e0..8ba8ce2 100644
--- a/include/net/netdma.h
+++ b/include/net/netdma.h
@@ -24,17 +24,6 @@
 #include <linux/dmaengine.h>
 #include <linux/skbuff.h>
 
-static inline struct dma_chan *get_softnet_dma(void)
-{
-	struct dma_chan *chan;
-	rcu_read_lock();
-	chan = rcu_dereference(__get_cpu_var(softnet_data).net_dma);
-	if (chan)
-		dma_chan_get(chan);
-	rcu_read_unlock();
-	return chan;
-}
-
 int dma_skb_copy_datagram_iovec(struct dma_chan* chan,
 		struct sk_buff *skb, int offset, struct iovec *to,
 		size_t len, struct dma_pinned_list *pinned_list);
diff --git a/net/core/dev.c b/net/core/dev.c
index bab8bce..5f736f1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -170,25 +170,6 @@ static DEFINE_SPINLOCK(ptype_lock);
 static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 static struct list_head ptype_all __read_mostly;	/* Taps */
 
-#ifdef CONFIG_NET_DMA
-struct net_dma {
-	struct dma_client client;
-	spinlock_t lock;
-	cpumask_t channel_mask;
-	struct dma_chan **channels;
-};
-
-static enum dma_state_client
-netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
-	enum dma_state state);
-
-static struct net_dma net_dma = {
-	.client = {
-		.event_callback = netdev_dma_event,
-	},
-};
-#endif
-
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
  * semaphore.
@@ -2754,14 +2735,7 @@ out:
 	 * There may not be any more sk_buffs coming right now, so push
 	 * any pending DMA copies to hardware
 	 */
-	if (!cpus_empty(net_dma.channel_mask)) {
-		int chan_idx;
-		for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) {
-			struct dma_chan *chan = net_dma.channels[chan_idx];
-			if (chan)
-				dma_async_memcpy_issue_pending(chan);
-		}
-	}
+	dma_issue_pending_all();
 #endif
 
 	return;
@@ -4952,122 +4926,6 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 	return NOTIFY_OK;
 }
 
-#ifdef CONFIG_NET_DMA
-/**
- * net_dma_rebalance - try to maintain one DMA channel per CPU
- * @net_dma: DMA client and associated data (lock, channels, channel_mask)
- *
- * This is called when the number of channels allocated to the net_dma client
- * changes.  The net_dma client tries to have one DMA channel per CPU.
- */
-
-static void net_dma_rebalance(struct net_dma *net_dma)
-{
-	unsigned int cpu, i, n, chan_idx;
-	struct dma_chan *chan;
-
-	if (cpus_empty(net_dma->channel_mask)) {
-		for_each_online_cpu(cpu)
-			rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL);
-		return;
-	}
-
-	i = 0;
-	cpu = first_cpu(cpu_online_map);
-
-	for_each_cpu_mask_nr(chan_idx, net_dma->channel_mask) {
-		chan = net_dma->channels[chan_idx];
-
-		n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask))
-		   + (i < (num_online_cpus() %
-			cpus_weight(net_dma->channel_mask)) ? 1 : 0));
-
-		while(n) {
-			per_cpu(softnet_data, cpu).net_dma = chan;
-			cpu = next_cpu(cpu, cpu_online_map);
-			n--;
-		}
-		i++;
-	}
-}
-
-/**
- * netdev_dma_event - event callback for the net_dma_client
- * @client: should always be net_dma_client
- * @chan: DMA channel for the event
- * @state: DMA state to be handled
- */
-static enum dma_state_client
-netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
-	enum dma_state state)
-{
-	int i, found = 0, pos = -1;
-	struct net_dma *net_dma =
-		container_of(client, struct net_dma, client);
-	enum dma_state_client ack = DMA_DUP; /* default: take no action */
-
-	spin_lock(&net_dma->lock);
-	switch (state) {
-	case DMA_RESOURCE_AVAILABLE:
-		for (i = 0; i < nr_cpu_ids; i++)
-			if (net_dma->channels[i] == chan) {
-				found = 1;
-				break;
-			} else if (net_dma->channels[i] == NULL && pos < 0)
-				pos = i;
-
-		if (!found && pos >= 0) {
-			ack = DMA_ACK;
-			net_dma->channels[pos] = chan;
-			cpu_set(pos, net_dma->channel_mask);
-			net_dma_rebalance(net_dma);
-		}
-		break;
-	case DMA_RESOURCE_REMOVED:
-		for (i = 0; i < nr_cpu_ids; i++)
-			if (net_dma->channels[i] == chan) {
-				found = 1;
-				pos = i;
-				break;
-			}
-
-		if (found) {
-			ack = DMA_ACK;
-			cpu_clear(pos, net_dma->channel_mask);
-			net_dma->channels[i] = NULL;
-			net_dma_rebalance(net_dma);
-		}
-		break;
-	default:
-		break;
-	}
-	spin_unlock(&net_dma->lock);
-
-	return ack;
-}
-
-/**
- * netdev_dma_register - register the networking subsystem as a DMA client
- */
-static int __init netdev_dma_register(void)
-{
-	net_dma.channels = kzalloc(nr_cpu_ids * sizeof(struct net_dma),
-								GFP_KERNEL);
-	if (unlikely(!net_dma.channels)) {
-		printk(KERN_NOTICE
-				"netdev_dma: no memory for net_dma.channels\n");
-		return -ENOMEM;
-	}
-	spin_lock_init(&net_dma.lock);
-	dma_cap_set(DMA_MEMCPY, net_dma.client.cap_mask);
-	dma_async_client_register(&net_dma.client);
-	dma_async_client_chan_request(&net_dma.client);
-	return 0;
-}
-
-#else
-static int __init netdev_dma_register(void) { return -ENODEV; }
-#endif /* CONFIG_NET_DMA */
 
 /**
  *	netdev_increment_features - increment feature set by one
@@ -5287,14 +5145,15 @@ static int __init net_dev_init(void)
 	if (register_pernet_device(&default_device_ops))
 		goto out;
 
-	netdev_dma_register();
-
 	open_softirq(NET_TX_SOFTIRQ, net_tx_action);
 	open_softirq(NET_RX_SOFTIRQ, net_rx_action);
 
 	hotcpu_notifier(dev_cpu_callback, 0);
 	dst_init();
 	dev_mcast_init();
+	#ifdef CONFIG_NET_DMA
+	dmaengine_get();
+	#endif
 	rc = 0;
 out:
 	return rc;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bd6ff90..ce572f9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1313,7 +1313,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		if ((available < target) &&
 		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
 		    !sysctl_tcp_low_latency &&
-		    __get_cpu_var(softnet_data).net_dma) {
+		    dma_find_channel(DMA_MEMCPY)) {
 			preempt_enable_no_resched();
 			tp->ucopy.pinned_list =
 					dma_pin_iovec_pages(msg->msg_iov, len);
@@ -1523,7 +1523,7 @@ do_prequeue:
 		if (!(flags & MSG_TRUNC)) {
 #ifdef CONFIG_NET_DMA
 			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-				tp->ucopy.dma_chan = get_softnet_dma();
+				tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
 
 			if (tp->ucopy.dma_chan) {
 				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
@@ -1628,7 +1628,6 @@ skip_copy:
 
 		/* Safe to free early-copied skbs now */
 		__skb_queue_purge(&sk->sk_async_wait_queue);
-		dma_chan_put(tp->ucopy.dma_chan);
 		tp->ucopy.dma_chan = NULL;
 	}
 	if (tp->ucopy.pinned_list) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 99b7ecb..a6961d7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5005,7 +5005,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
 		return 0;
 
 	if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-		tp->ucopy.dma_chan = get_softnet_dma();
+		tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
 
 	if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9d839fa..19d7b42 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1594,7 +1594,7 @@ process:
 #ifdef CONFIG_NET_DMA
 		struct tcp_sock *tp = tcp_sk(sk);
 		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = get_softnet_dma();
+			tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
 		if (tp->ucopy.dma_chan)
 			ret = tcp_v4_do_rcv(sk, skb);
 		else
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 1297306..e5b85d4 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1675,7 +1675,7 @@ process:
 #ifdef CONFIG_NET_DMA
 		struct tcp_sock *tp = tcp_sk(sk);
 		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = get_softnet_dma();
+			tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
 		if (tp->ucopy.dma_chan)
 			ret = tcp_v6_do_rcv(sk, skb);
 		else